Method and apparatus for handling of a PDU session in a wireless communication system

Abstract

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. According to an embodiment, there is provided a first network entity comprising: a transceiver; and at least one processor coupled with the transceiver and configured to: when a serving network of the first entity is a first network of a first network type, identify that a protocol data unit (PDU) session for the first network type is for use in relation to an artificial intelligence (AI) / machine learning (ML) operation; and prevent use of the PDU session in relation to the AI / ML operation for a second network type, wherein the first network supports interworking with a second network of the second network type.

Description

METHOD AND APPARATUS FOR HANDLING OF A PDU SESSION IN A WIRELESS COMMUNICATION SYSTEM

[0001] Embodiments of the disclosure relate to methods, apparatus and / or systems for handling an AI / ML PDU Session. Various examples provide methods and / or apparatus in which one or more network entities handle an AI / ML PDU session during Interworking with EPS.

[0002] Considering the development of wireless communication from generation to generation, the technologies have been developed mainly for services targeting humans, such as voice calls, multimedia services, and data services. Following the commercialization of 5G (5th generation) communication systems, it is expected that the number of connected devices will exponentially grow. Increasingly, these will be connected to communication networks. Examples of connected things may include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machines, and factory equipment. Mobile devices are expected to evolve in various form-factors, such as augmented reality glasses, virtual reality headsets, and hologram devices. In order to provide various services by connecting hundreds of billions of devices and things in the 6G (6th generation) era, there have been ongoing efforts to develop improved 6G communication systems. For these reasons, 6G communication systems are referred to as beyond-5G systems.

[0003] 6G communication systems, which are expected to be commercialized around 2030, will have a peak data rate of tera (1,000 giga)-level bit per second (bps) and a radio latency less than 100μsec, and thus will be 50 times as fast as 5G communication systems and have the 1 / 10 radio latency thereof.

[0004] In order to accomplish such a high data rate and an ultra-low latency, it has been considered to implement 6G communication systems in a terahertz (THz) band (for example, 95 gigahertz (GHz) to 3THz bands). It is expected that, due to severer path loss and atmospheric absorption in the terahertz bands than those in mmWave bands introduced in 5G, technologies capable of securing the signal transmission distance (that is, coverage) will become more crucial. It is necessary to develop, as major technologies for securing the coverage, Radio Frequency (RF) elements, antennas, novel waveforms having a better coverage than Orthogonal Frequency Division Multiplexing (OFDM), beamforming and massive Multiple-input Multiple-Output (MIMO), Full Dimensional MIMO (FD-MIMO), array antennas, and multiantenna transmission technologies such as large-scale antennas. In addition, there has been ongoing discussion on new technologies for improving the coverage of terahertz-band signals, such as metamaterial-based lenses and antennas, Orbital Angular Momentum (OAM), and Reconfigurable Intelligent Surface (RIS).

[0005] Moreover, in order to improve the spectral efficiency and the overall network performances, the following technologies have been developed for 6G communication systems: a full-duplex technology for enabling an uplink transmission and a downlink transmission to simultaneously use the same frequency resource at the same time; a network technology for utilizing satellites, High-Altitude Platform Stations (HAPS), and the like in an integrated manner; an improved network structure for supporting mobile base stations and the like and enabling network operation optimization and automation and the like; a dynamic spectrum sharing technology via collision avoidance based on a prediction of spectrum usage; an use of Artificial Intelligence (AI) in wireless communication for improvement of overall network operation by utilizing AI from a designing phase for developing 6G and internalizing end-to-end AI support functions; and a next-generation distributed computing technology for overcoming the limit of UE computing ability through reachable super-high-performance communication and computing resources (such as Mobile Edge Computing (MEC), clouds, and the like) over the network. In addition, through designing new protocols to be used in 6G communication systems, developing mechanisms for implementing a hardware-based security environment and safe use of data, and developing technologies for maintaining privacy, attempts to strengthen the connectivity between devices, optimize the network, promote softwarization of network entities, and increase the openness of wireless communications are continuing.

[0006] It is expected that research and development of 6G communication systems in hyper-connectivity, including person to machine (P2M) as well as machine to machine (M2M), will allow the next hyper-connected experience. Particularly, it is expected that services such as truly immersive eXtended Reality (XR), high-fidelity mobile hologram, and digital replica could be provided through 6G communication systems. In addition, services such as remote surgery for security and reliability enhancement, industrial automation, and emergency response will be provided through the 6G communication system such that the technologies could be applied in various fields such as industry, medical care, automobiles, and home appliances.

[0007] It is an aim of embodiments of the 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 embodiments of the disclosure to provide at least one advantage over the related art, for example at least one of the advantages described herein.

[0008] According to a first aspect of the disclosure, there is provided a first network entity comprising: a transmitter; a receiver; and at least one processor configured to: when a serving network of the first entity is a first network of a first network type, identify that a protocol data unit (PDU) session for the first network type is for use in relation to an artificial intelligence (AI) / machine learning (ML) operation; and prevent use of the PDU session in relation to the AI / ML operation for a second network type; wherein the first network supports interworking with a second network of the second network type.

[0009] According to various examples, the first network type is a 5thGeneration (5G) System (5GS), and the second network type is a Evolved Packet System (EPS).

[0010] According to various examples, the at least one processor is configured to: establish the PDU session for the first network type; and identify mapped bearer context associated with the PDU session, wherein the mapped bearer context is for transferring the PDU session from the first network type to the second network type.

[0011] According to various examples, the at least one processor is configured to: delete the identified mapped bearer context to prevent use of the PDU session in relation to the AI / ML operation for the second network type.

[0012] According to various examples, the at least one processor is configured to: delete the identified mapped bearer context by performing a PDU session modification procedure; or delete the identified mapped bearer context locally in the first network entity.

[0013] According to various examples, performing the PDU session modification procedure comprises: sending a PDU session modification request message to the serving network.

[0014] According to various examples, the at least one processor is configured to: maintain the identified mapped bearer context; and when the serving network of the first network entity is changed from the first network to the second network, prevent transfer of the PDU session from the first network type to the second network type to prevent use of the PDU session in relation to the AI / ML operation for the second network type.

[0015] According to various examples, the at least one processor is configured to: when the serving network is changed to the second network, set a state of the mapped bearer context to bearer context inactive.

[0016] According to various examples, the at least one processor is configured to: when the serving network of the first network entity is changed from the first network to the second network, transfer the PDU session from the first network type to the second network type without using the transferred PDU session in relation to the AI / ML operation while the serving network is the second network to prevent use of the PDU session in relation to the AI / ML operation for the second network type; wherein the PDU session is transferred based on the identified mapped bearer context.

[0017] According to various examples, the at least one processor is configured to: use the transferred PDU session in relation to an operation other than the AI / ML operation while the serving network is the second network.

[0018] According to various examples, the at least one processor is configured to: when the serving network of the first network entity is changed from the first network to the second network, suspend the PDU session to prevent use of the PDU session in relation to the AI / ML operation for the second network type.

[0019] According to various examples, the at least one processor is configured to: when the serving network of the first network entity is changed from the second network to the first network, use the PDU session in relation to the AI / ML operation.

[0020] According to various examples, the at least one processor is configured to: when the serving network of the first network entity is changed from the second network to the first network, transmit a first indication that the serving network is the first network and / or a second indication that the PDU session can be used for the AI / ML operation; and / or when the serving network of the first network entity is changed from the first network to the second network, transmit a third indication that the serving network is the second network and / or a fourth indication that the PDU session cannot be used for the AI / ML operation.

[0021] According to various examples, the first indication and / or the second indication is transmitted to an AI / ML server associated with the AI / ML operation; and / or wherein the third indication and / or the fourth indication is transmitted to the AI / ML server associated with the AI / ML operation.

[0022] According to various examples, the at least one processor is configured to: send, to a second network entity, an indication that the PDU session is for the AI / ML operation; and perform session establishment for the PDU session without receiving mapped bearer context for transferring the PDU session from the first network type to the second network type.

[0023] According to various examples, the indication is sent to an access and mobility management function (AMF) in a mobility management non-access stratum (NAS) message or to a session management function (SMF) in a session management message.

[0024] According to various examples, the AI / ML operation is or related to federated learning (FL); and / or the first network entity is a user equipment (UE).

[0025] According to a second aspect of the disclosure, there is provided a second network entity in a first network of a first network type, the second network entity comprising: a transmitter; a receiver; and at least one processor configured to: determine that a protocol data unit (PDU) session, to be established for a first network entity, is for use in an artificial intelligence (AI) / machine learning (ML) operation, wherein a serving network of the first network entity is the first network; and based on the determination, perform session establishment for the PDU session without allocating mapped bearer context for transferring the PDU session from the first network type to a second network type; wherein the first network supports interworking with a second network of the second network type.

[0026] According to various examples, the at least one processor is configured to: determine that the PDU session is for use in the AI / ML operation based on information received from the first network entity; or determine locally that the PDU session is for use in the AI / ML operation based on information stored at the second network entity.

[0027] According to various examples, the information is received from the first network entity, and the at least one processor is configured to transmit, to a third network entity in the first serving network, an indication that the PDU session is for use in the AI / ML operation; or the information is received from a third network entity in the first serving network.

[0028] According to various examples, the second network entity is an access and mobility management function (AMF) and the third network entity is a session management function (SMF).

[0029] According to a third aspect of the disclosure, there is provided a second network entity in a first network of a first network type, the second network entity comprising: a transmitter; a receiver; and at least one processor configured to: subscribe to a network type change event for a first network entity indicating a change in a serving network of the first network entity; receive an indication that the serving network of the first network entity is changed; and based on the change in the serving network, determine whether or not to consider the first network entity for an artificial intelligence (AI) / machine learning (ML) operation.

[0030] According to various examples, the at least one processor is configured to: inform an application function (AF) related to the AI / ML function of the outcome of the determination; and / or update a list of user equipments (UEs) recommended for the AI / ML operation based on identifying the serving network of the first network entity, where the first network entity is a UE.

[0031] According to a fourth aspect of the disclosure, there is provided a method of a first network entity, the method comprising: when a serving network of the first entity is a first network of a first network type, identifying that a protocol data unit (PDU) session for the first network type is to be used in relation to an artificial intelligence (AI) / machine learning (ML) operation; and preventing use of the PDU session in relation to the AI / ML operation for a second network type; wherein the first network supports interworking with a second network of the second network type.

[0032] According to various examples, the first network type is a 5thGeneration (5G) System (5GS), and the second network type is a Evolved Packet System (EPS); and / or

[0033] wherein the preventing use of the PDU session in relation to the AI / ML operation for the second network type comprises one of:

[0034] a) deleting mapped bearer context associated with the PDU session;

[0035] b) maintaining mapped bearer context associated with the PDU session, and when the serving network of the first network entity is changed from the first network to the second network, prevent transfer of the PDU session from the first network type to the second network type;

[0036] c) when the serving network of the first network entity is changed from the first network to the second network, transferring, based on mapped bearer context associated with the PDU session, the PDU session from the first network type to the second network type without using the transferred PDU session in relation to the AI / ML operation while the serving network is the second network;

[0037] d) when the serving network of the first network entity is changed from the first network to the second network, suspending the PDU session; or

[0038] e) sending, to a second network entity, an indication that the PDU session is for the AI / ML operation, and performing session establishment for the PDU session without receiving mapped bearer context associated with the PDU session;

[0039] wherein the mapped bearer context is for transferring the PDU session from the first network type to the second network type.

[0040] 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.

[0041] Aspects of the disclosure are to address at least the above-mentioned problems and / or disadvantages and to provide at least the advantages described below. Accordingly, an aspect of the disclosure is to provide efficient communication methods in a wireless communication system.

[0042] Embodiments / examples of the disclosure are further described hereinafter with reference to the accompanying drawings, in which:

[0043] Figure 1 is a block diagram illustrating an example structure of a network entity in accordance with embodiments of the disclosure.

[0044] Figure 2 is a flow diagram illustrating a method in accordance with various examples of the disclosure.

[0045] Figure 3 is a flow diagram illustrating a method in accordance with various examples of the disclosure.

[0046] Figure 4 is a flow diagram illustrating a method in accordance with various examples of the disclosure.

[0047] Figure 5 is a block diagram illustrating an example structure of a network entity in accordance with embodiments of the disclosure.

[0048] Aspects of the disclosure are to address at least the above-mentioned problems and / or disadvantages and to provide at least the advantages described below. Accordingly, an aspect of the disclosure is to provide a terminal and a communication method thereof in a wireless communication system.

[0049] The following description of embodiments of the disclosure, with reference to the accompanying drawings, is provided to assist in a comprehensive understanding of embodiments of the 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 embodiments described herein can be made without departing from the scope of the invention or disclosure.

[0050] The same or similar components may be designated by the same or similar reference numerals, although they may be illustrated in different drawings.

[0051] 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 disclosure.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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 Generation (4G) and Fifth Generation (5G) systems (5GS) are now widely deployed, while beyond 5G (B5G) and 6G systems are being considered.

[0059] 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.

[0060] 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.

[0061] 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. One such new framework is the use of artificial intelligence / machine learning (AI / ML), which may be used for the optimisation of the operation of 5G networks.

[0062] In AI / ML operation, AI / ML models and / or data might be transferred across the AI / ML applications (e.g., application functions (AFs)), 5GC (5G core), UEs (user equipments) etc.). Without limitation, the AI / ML works could be divided into two main phases: model training and inference. During model training and inference, multiple rounds of interaction may be required.

[0063] In various embodiments, Three types of AI / ML operations to be supported are described as follows:

[0064] a)AI / ML operation splitting between AI / ML endpoints

[0065] The AI / ML operation / model is split into multiple parts according to the current task and environment. The intention is to offload the computation-intensive, energy-intensive parts to network endpoints, whereas leave the privacy-sensitive and delay-sensitive parts at the end device. The device executes the operation / model up to a specific part / layer and then sends the intermediate data to the network endpoint. The network endpoint executes the remaining parts / layers and feeds the inference results back to the device.

[0066] b)AI / ML model / data distribution and sharing over 5G system

[0067] Multi-functional mobile terminals might need to switch the AI / ML model in response to task and environment variations. The condition of adaptive model selection is that the models to be selected are available for the mobile device. However, given the fact that the AI / ML models are becoming increasingly diverse, and with the limited storage resource in a UE, it can be determined to not pre-load all candidate AI / ML models on-board. Online model distribution (i.e. new model downloading) is needed, in which an AI / ML model can be distributed from a NW (network) endpoint to the devices when they need it to adapt to the changed AI / ML tasks and environments. For this purpose, the model performance at the UE needs to be monitored constantly.

[0068] c)Distributed / Federated Learning over 5G system

[0069] The cloud server trains a global model by aggregating local models partially-trained by each end devices. Within each training iteration, a UE performs the training based on the model downloaded from the AI server using the local training data. Then the UE reports the interim training results to the cloud server via 5G UL channels. The server aggregates the interim training results from the UEs and updates the global model. The updated global model is then distributed back to the UEs and the UEs can perform the training for the next iteration.

[0070] the AI / ML works can be divided into three main phases: model training, model transfer and inference. More specifically, with the introduction of federated learning, model transfer has become a crucial phase to successfully perform some AI / ML operations. Time spent for model training, inference and transmission of the AI / ML models and for output of the inference depend on computation and / or communication capabilities of participating nodes / components; hence, the time varies among different nodes / components.

[0071] The 5GS supports a set of enablers for AI / ML applications to be run over the system. For example, the 5GS can support member selection for federated learning (FL) where the Network Exposure Function (NEF) of the 5G core network can host UE member selection assistance functionality.

[0072] These enablers or functionalities are expected to be hosted within the 5G core network by specific network functions such as but not limited to the NEF, Network Data Analytics Function (NWDAF), etc.

[0073] A UE can establish a PDU session which it then uses for an AI / ML application where the actual AI / ML data is transparent to the 5GS. There are currently no means by which the network can identify a session as one which is being used for AI / ML applications - e.g. there is no dedicated S-NSSAI, DNN, or other parameter which enables the 5GS to identify a PDU session as a session for AI / ML.

[0074] The 5GS can also support interworking (IWK) with Evolved Packet System (EPS) for UEs which are capable of both N1 mode (i.e. 5GS) and S1 mode (i.e. EPS). For such UEs, and for networks which support the N26 interface (that is used for IWK between EPS and 5GS), a UE with a PDU session in 5GS can transfer the session to EPS after a mobility occurs from 5GS to EPS. In general, unless explicitly stated otherwise, a PDU session is transferable from 5GS to EPS if the UE receives so called mapped EPS bearer context during the session management signaling procedures which are performed in 5GS. If a mapped EPS bearer context does not exist for a PDU session, then the session is deemed to be not transferable from 5GS to EPS.

[0075] Embodiments of the disclosure provide methods, apparatus and / or systems for handling an AI / ML PDU Session. Various embodiments provide methods and / or apparatus in which one or more network entities handle an AI / ML PDU session during Interworking with EPS.

[0076] The following embodiments are applicable to, and use terminology associated with, 3GPP 5G. However, the skilled person will appreciate that the techniques disclosed herein are not limited to these embodiments or to 3GPP 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 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 disclosure also relates.

[0077] 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.

[0078] The skilled person will appreciate that the disclosure is not limited to the specific embodiments disclosed herein. For example:

[0079] ● The techniques disclosed herein are not limited to 3GPP 5G, B5G or 6G.

[0080] ● One or more entities in the embodiments disclosed herein may be replaced with one or more alternative entities performing equivalent or corresponding functions, processes or operations.

[0081] ● One or more of the messages in the embodiments disclosed herein may be replaced with one or more alternative messages, signals or other type of information carriers that communicate equivalent or corresponding information.

[0082] ● One or more further elements, entities and / or messages may be added to the embodiments disclosed herein.

[0083] ● One or more non-essential elements, entities and / or messages may be omitted in embodiments.

[0084] ● 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.

[0085] ● 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.

[0086] ● Information carried by a particular message in one example may be carried by two or more separate messages in an alternative example.

[0087] ● Information carried by two or more separate messages in one example may be carried by a single message in an alternative example.

[0088] ● The order in which operations are performed may be modified, if possible, in alternative embodiments.

[0089] ● 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 embodiments disclosed herein.

[0090] Embodiments of the 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). Embodiments of the 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.

[0091] It will be appreciated that embodiments of the disclosure may be realized in the form of hardware, software or a combination of hardware and software. Embodiments of the 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 disclosure provide a machine-readable storage storing such a program.

[0092] A network according to one or more of the embodiments disclosed herein may include one or more of a Network Data Analytics Function (NWDAF) entity, an Access and Mobility Management Function (AMF) entity, a Session Management Function (SMF) entity, a Network Slice Selection Function (NSSF) entity, a Network Repository Function (NRF) entity, Application Function (AF) entity, and an Operation and Maintenance (OAM) entity. The network may include one or more Service Consumers (including one or more of the entities mentioned above and / or one or more other entities) that receive analytics from NWDAF. The skilled person will appreciate that a network may omit one or more of the entities mentioned above and / or may comprise one or more additional entities

[0093] As described above, there are currently no means by which the network can identify a session as one which is being used for AI / ML applications, and if a mapped EPS bearer context does not exist for a PDU session, then the session is deemed to be not transferable from 5GS to EPS.

[0094] As indicated earlier, the support for AI / ML in 5GS is provided using Network Functions (NF) that are within the 5G core network e.g. member selection for FL is provided by the NEF. A UE in 5GS may have a PDU session for AI / ML and may be participating in FL for a particular AI / ML application. Since the network does not identify a PDU session as one which is exclusive for AI / ML, the network may provide mapped EPS bearer context thereby making the PDU session transferable to EPS. As such, the UE may indeed transfer the session to EPS, however there is no support for member selection in the network functions of EPS. It is also unclear whether the UE should continue using the PDU session in EPS if it was already selected as a member for FL before the inter-system change from 5GS to EPS. If the UE continues to use the session, it therefore may not be possible for EPS to unselect a UE member if the UE was already selected previously, or to select a member UE if the UE was not previously participating in FL.

[0095] Various embodiments, embodiments etc. of the disclosure aim to provide a unified and predictable solution for this identify problem rather than an unpredictable solution which may then lead to interoperability issues and negative user experience.

[0096] Various embodiments of the disclosure relate to (e.g., include, and / or provide features relating to) one or more of the below:

[0097] ● In various embodiments, as the UE is aware of a PDU session which is being used for AI / ML, the UE is configured to delete the mapped EPS bearer context if received. The deletion may be performed with explicit session management signaling, or locally in the UE e.g. without signaling with the network.

[0098] ● In various embodiments, the UE is configured to transfer the PDU session to EPS but does not use it for AI / ML, or does not use it for FL or any other purpose if the AI / ML service was supported by specific NFs in the 5GC e.g. the NEF, where optionally the same support is not provided in EPS.

[0099] ● In various embodiments, the UE is configured to indicate which session is for AI / ML and the network does not allocated mapped bearer context for the indicated session.

[0100] ● In various embodiments, the NEF is informed about the UE’s core network change (e.g. when the UE moves from N1 mode to S1 mode, or vice versa) and the NEF may (or may not) consider the UE for FL (e.g. the NEF considers the UE for FL when the UE is in N1 mode, or the NEF does not consider the UE for FL when the UE is in S1 mode).

[0101] 1. The UE deletes mapped EPS bearer context if any is received for a PDU session that is used for AI / ML

[0102] The UE is supposed to be aware of which PDU session is being used for AI / ML. For example, the UE may receive indications from the upper layers (e.g. the application layer) that a particular PDU session is for AI / ML. Alternatively the UE may identify an application (e.g. via an application ID) to be one which is for (or related with) an AI / ML application. As such if the request for PDU session is triggered by such an application, then the UE may identify the PDU session which is being used by the application and hence determine that the PDU session is question is one which is being used for AI / ML. For example, the UE's URSP rules may be updated to contain this information, or the UE may be pre-configured with information to determine which application, and hence which PDU session that is used to serve the application, is for AI / ML. Alternatively, the UE may determine that a PDU session is being used for AI / ML using implementation specific methods. The UE may identify a PDU session for AI / ML based on the parameters associated with the PDU session e.g. the slice (or S-NSSAI), the DNN, SSC mode, or any parameter set which may be one or more in any combination.

[0103] According to various embodiments, when the UE determines that a PDU session is for AI / ML, where this determination may be based on any method such as, but not limited to, those listed above, the UE may verify if it received any mapped EPS bearer context for this PDU session. It should be noted that receiving any mapped EPS bearer context may mean that the UE receives the Mapped EPS bearer contexts IE from the network (e.g. from the SMF) or the UE receives other EPS related QoS parameters e.g. EPS bearer identity or Traffic Flow Template, etc, as part of the Authorized QoS flow descriptions IE where this may be received from the network (e.g. from the SMF).

[0104] If yes, then the UE may behave as follows:

[0105] ● The UE may perform a PDU session modification procedure (e.g. the UE sends the PDU Session Modification Request message) to delete any mapped EPS bearer context that may have been received. The UE may include any existing or new 5GSM cause value in the NAS message that it sends to the network, e.g. #83 (Semantic error in the QoS operation), or #84 (Syntactical error in the QoS operation), or #85 (Invalid mapped EPS bearer identity), or any other cause value; and / or

[0106] ● The UE may locally delete any mapped EPS bearer context that is received without any explicit signaling with the network.

[0107] In other embodiments, the UE may maintain any mapped EPS bearer context that is received, however the UE may not transfer the PDU session to EPS. As such, during or upon inter-system change from N1 mode (5GS) to S1 mode (EPS), for any EPS bearer context that is received as part of the PDU session which is used for AI / ML, the UE may set a state of the mapped EPS bearer context to BEARER CONTEXT INACTIVE, (optionally where this may be performed for the default EPS bearer, or for the dedicated EPS bearer, or both).

[0108] 2. UE transfers the session to EPS but does not use it for AI / ML

[0109] According to various embodiments, the UE may transfer the PDU session for AI / ML to EPS, however the UE may (or should) not use the session in EPS for AI / ML. Alternatively, the UE may use the session while in EPS but may not participate in FL - e.g., the UE may use the session while in EPS but not for specific types of AI / ML operations. The UE may inform the AI / ML server via application layer signaling that it is has moved to EPS and as such cannot use the session or cannot perform certain tasks (such as participating in FL) as a result of being in EPS (where some NFs for these AI / ML tasks are not supported).

[0110] For example, the UE may transfer the session back to 5GS (N1 mode) if a subsequent inter-system change is made from S1 mode to N1 mode. In this case, the UE may use the PDU session for AI / ML again including any FL or any other task which was halted previously in EPS. The UE may also use application layer signaling to inform the AI / ML server when it is on 5GS. As such, the UE may use application layer signaling to inform the AI / ML server about its serving core network type (e.g. 5GC or EPC) when the UE moves across these systems.

[0111] In other embodiments, the UE may set the context of the entire PDU session to suspend or to a new state which indicates any form of suspension. As such the UE may not transfer any suspended session to EPS however the UE does not delete the session either. The UE may resume the session when it comes back to 5GS. The UE may send any new or existing NAS message to either indicate the status of a PDU session to be suspended or to resume a PDU session which may be suspended as indicated herein.

[0112] 3. UE indicates that a session is for AI / ML

[0113] According to various embodiments, the UE may determine to establish a session for AI / ML using any of the means described earlier herein.

[0114] When the UE determines to establish a PDU session which is to be used for AI / ML, the UE may provide an indication to the network that the session requested is for AI / ML. This indication may be provided to the AMF in any mobility management NAS message, or to the SMF in any session management message, where the indication may be a new indication that is set in any existing information element or a new information element. If the SMF receives an indication, e.g. from the UE, that the session which is being established is for AI / ML, the SMF may inform the AMF that the session is for AI / ML. If the AMF receives an indication, e.g. from the UE, that the session which is being established is for AI / ML then the AMF may inform the SMF about this and the AMF may be configured to not allocated an mapped EPS bearer context for such a session (this may be alternative to the case of the SMF receiving the indication from the UE). This therefore would make the session not transferable to EPS. The AMF may be configured to behave as described herein when the session is determined to be for AI / ML, where this determination may be local in the AMF (by any means, e.g. based on at least one parameter of the PDU session which may be known to be for AI / ML) or based on an explicit indication from the UE or any other network entity (and this may include subscription information).

[0115] 4. NEF subscribes for CN Type Change Event during assistance with FL

[0116] It will be appreciated that although various embodiments disclosed herein are described with FL as a use case, the proposals are not limited to the use of FL only. As such, all proposals would apply when any NF (e.g. NEF) is involved in any assistance for AI / ML such as, but not limited to, FL for a set of UEs. In other words, the embodiments of the disclosure should not be seen as limited to FL.

[0117] According to various embodiments, the NEF which is assisting in any AI / ML activity (e.g. FL such as group member selection, etc) may (or should) subscribe to the UDM+HSS node for the CN Type Change event as described in TS 23.501 [2].

[0118] The NEF may (or should) only consider the UE for FL if the UE is determined to be in 5GS. When the NEF receives a CN type change event such that the NEF determines that the current serving CN type is EPC (or that the UE is in EPS), then the NEF should not consider the UE in question for FL. The NEF may inform the AF for AI / ML about this (e.g., the AF to which the AI / ML activity relates).

[0119] For a UE which is considered to be in EPS, if the NEF receives a CN type change event such that the UE is now determined to be in 5GC (or 5GS), then the NEF may reconsider the UE for FL. The NEF may inform the AF (for AI / ML) about this event. In one example, the NEF which becomes aware of a UE being in EPS (e.g. the UE moves from 5GS to EPS, or from 5GC to EPC) may remove any UE which was optionally previously considered or recommended (to the AF) for FL, and may then send an updated recommendation to the AF where the updated recommended list of UEs should exclude any UE that is now in EPS. As such, if a UE moves to EPS, the NEF should not consider the UE. The NEF may then exclude the UE from the list of recommended UEs and the NEF may provide this updated list to the AF.

[0120] In another example, if a UE moves from EPS to 5GS and the NEF is aware that the UE is in 5GS, where optionally the NEF may have considered this UE for FL in a previous time, the NEF may now consider this UE again because of its presence in 5GS. The NEF may include this UE in the list of recommended UEs and provide this updated list to the AF.

[0121] In one example, the consideration of a UE by the NEF, for FL, may be based on the UE's core network type or its presence in a particular system. For example, if the UE is in EPS (or the UE moves from 5GC to EPC) then the NEF may stop recommending this UE and may remove this UE from a list of recommended UEs for FL and may provide this updated list to the AF. For example, if the UE is in 5GS (or the UE moves from EPC to 5GC) then the NEF may now consider this UE as a potential recommended UE for FL. The NEF may include this UE in a list of recommended UEs for FL and may provide this updated list to the AF.

[0122] In other embodiments, the UE may transfer the session to EPS and use it for AI / ML as usual. Moreover, it is proposed that the SCEF should be responsible for or equipped with methods to assist with FL. As such, the assistance should be part of the SCEF which may be standalone or may be combined with an NEF function. Hence the SCEF+NEF may be responsible for assisting with member selection for FL. In one example, the network may inform the UE if the session should be used in EPC or not, where this may be done using any NAS or RRC message.

[0123] Additionally, the AF may indicate if it wants or prefers UE(s) which are in 5GS only, or EPS only, or both (i.e. the AF does not care) when requesting the NEF(+SCEF) function to assist with member selection for FL. Based on this preference (or filtering criteria), the NEF (and optionally the Service Capability Exposure Function (SCEF)) may then consider a UE for FL (e.g. based on its presence in 5GS or EPS) or ignore a UE for FL (e.g. if the UE is in a core network which is indicated as not preferred by the AF for FL). For example, the NEF (+SCEF) may provide notifications to the AF as the UE changes its core network type e.g. as it moves across EPC and 5GC. The NEF may also provide an updated list of recommended UEs as described earlier.

[0124] Figure 1 is a block diagram of an exemplary apparatus, or network entity, that may be used in embodiments of the disclosure. 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.

[0125] The entity 1000 comprises a processor (or controller) 1001, a transmitter 1003 and a receiver 1005. The receiver 1005 is configured for receiving one or more messages from one or more other network entities, for example as described above. The transmitter 1003 is configured for transmitting one or more messages to one or more other network entities, for example as described above. The processor 1001 is configured for performing one or more operations, for example according to the operations as described above.

[0126] Figure 2 is a flow diagram illustrating a method according to various embodiments of the disclosure. The method is performed by a first network entity, e.g. a UE.

[0127] In operation S210, when a serving network of the first entity is a first network of a first network type, the first network entity identifies that a protocol data unit (PDU) session for the first network type is for use in relation to an artificial intelligence (AI) / machine learning (ML) operation.

[0128] In operation S220, the first network entity prevents use of the PDU session in relation to the AI / ML operation for a second network type. The first network supports interworking with a second network of the second network type.

[0129] Figure 3 is a flow diagram illustrating a method according to various embodiments of the disclosure. The method is performed by a second network entity in a first network of a first network type, e.g. the second network entity is an AMF.

[0130] In operation S310, the second network entity determines that a protocol data unit (PDU) session, to be established for a first network entity, is for use in an artificial intelligence (AI) / machine learning (ML) operation, wherein a serving network of the first network entity is the first network.

[0131] In operation S320, based on the determination, the second network entity performs session establishment for the PDU session without allocating mapped bearer context for transferring the PDU session from the first network type to a second network type. The first network supports interworking with a second network of the second network type.

[0132] Figure 4 is a flow diagram illustrating a method according to various embodiments of the disclosure. The method is performed by a second network entity in a first network of a first network type, e.g. the second network entity is an NEF.

[0133] In operation S410, the second network entity subscribes to a network type change event for a first network entity indicating a change in a serving network of the first network entity.

[0134] In operation S420, the second network entity receives an indication that the serving network of the first network entity is changed.

[0135] In operation S430, based on the change in the serving network, the second network entity determines whether or not to consider the first network entity for an artificial intelligence (AI) / machine learning (ML) operation.

[0136] Figure 5 is a block diagram illustrating an example structure of a network entity in accordance with embodiments of the disclosure.

[0137] Referring to Figure 5, the network entity includes a transceiver (510), a memory (520), and a processor (530). The transceiver (510), the memory (520), and the processor (530) of the network entity may operate according to a communication method of the network entity described above. However, the components of the network entity are not limited thereto. For example, the network entity may include fewer or a greater number of components than those described above. In addition, the processor (530), the transceiver (510), and the memory (520) may be implemented as a single chip. Also, the processor (530) may include at least one processor.

[0138] The network entity includes at least one entity of a core network. For example, the network entity includes an Access and mobility management function (AMF), a session management function (SMF), a policy control function (PCF), a network repository function (NRF), a user plane function (UPF), a network slicing selection function (NSSF), an authentication server function (AUSF), a unified data management (UDM) and a network exposure function (NEF), but the network entity is not limited thereto. For example, the network entity includes a user equipment (UE), a base station (BS). The network entity of Figure 5 corresponds to a network entity of Figure 1.

[0139] The transceiver (510) collectively refers to a network entity receiver and a network entity transmitter, and may transmit / receive a signal to / from a base station. a UE or another network entity. The signal transmitted or received to or from the base station, the UE or the another network entity may include control information and data. In this regard, the transceiver (510) may include an RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and an RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver (510) and components of the transceiver (510) are not limited to the RF transmitter and the RF receiver.

[0140] The transceiver (510) may receive and output, to the processor (530), a signal through a wireless channel, and transmit a signal output from the processor (530) through the wireless channel.

[0141] The memory (520) may store a program and data required for operations of the network entity. Also, the memory (520) may store control information or data included in a signal obtained by the network entity. The memory (520) may be a storage medium, such as a ROM, a RAM, a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0142] The processor (530) may control a series of processes such that the network entity operates as described above. For example, the transceiver (510) may receive a data signal including a control signal, and the processor (530) may determine a result of receiving the data signal.

[0143] 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 / embodiments is found herein, the 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.

[0144] 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.

[0145] It will be appreciated that embodiments of the 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.

[0146] 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 embodiments of the disclosure. Accordingly, embodiments 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.

[0147] While the disclosure has been shown, illustrated and described with reference to embodiments, 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.

[0148] 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 and which are open to public inspection with this specification, and the contents of all such papers and documents are incorporated herein by reference.

[0149] Acronyms and Definitions

[0150] 3GPP 3rd Generation Partnership Project

[0151] 5G 5th Generation

[0152] 5GC 5G Core

[0153] 5QI 5G QoS Identifier

[0154] 5GS 5G System

[0155] 5GSM 5G System Session Management

[0156] 5GMM 5G System Mobility Management

[0157] AF Application Function

[0158] AI Artificial Intelligence

[0159] AIML Artificial Intelligence / Machine Learning

[0160] AM Acknowledged Mode

[0161] AMF Access and Mobility Management Function

[0162] AS Application Server

[0163] ASP Application Service Provider

[0164] ATSSS Access Traffic Steering Switching & Splitting

[0165] AUSF Authentication Server Function

[0166] CDRX Connected Mode Discontinuous Reception

[0167] CSI Channel Status Information

[0168] DCAF Data Collection Application Function

[0169] DNAI Data Network Access Identifier

[0170] DNN Data Network Name

[0171] DNS Domain Name Server

[0172] DRB Data Radio Bearer

[0173] eNB Evolved Node B

[0174] EPS Evolved Packet System

[0175] FQDN Fully Qualified Domain Name

[0176] GBR Guaranteed Bit Rate

[0177] GMLC Gateway Mobile Location Centre

[0178] gNB Next generation Node B

[0179] GPSI Generic Public Subscription Identifier

[0180] IAB Integrated Access and Backhaul

[0181] ID Identity / Identifier

[0182] IIoT Industrial Internet of Things

[0183] IMEI International Mobile Equipment Identities

[0184] IP Internet Protocol

[0185] I-SMF Intermediate SMF

[0186] LMF Location Management Function

[0187] MA-PDU Multiple Access PDU

[0188] ML Machine Learning

[0189] MME Mobility Management Entity

[0190] MN Master Node

[0191] MNO Mobile Network Operator

[0192] MPTCP MultiPath TCP

[0193] MT Mobile Termination

[0194] NAS Non-Access Stratum

[0195] NEF Network Exposure Function

[0196] NRF Network Repository Function

[0197] NG-RAN Next Generation Radio Access Network

[0198] NG-eNB Next Generation eNB

[0199] NSA Non-Standalone

[0200] NSSF Network Slice Selection Function

[0201] NW Network

[0202] NWDAF Network Data Analytics Function

[0203] OS Operating System

[0204] OSAPP OS Application

[0205] PCF Policy Control Function

[0206] PCC Policy and Charging Control

[0207] PCO Protocol Configuration Options

[0208] PDR Packet Detection Rule

[0209] PDU Protocol Data Unit

[0210] PMF Performance Measurement Function

[0211] PSA PDU session anchor

[0212] QFI QoS Flow Identifier (ID)

[0213] QoE Quality of Experience

[0214] QoS Quality of Service

[0215] RACH Random Access Channel

[0216] RAN Radio Access Network

[0217] RAT Radio Access Technology

[0218] RLC-AM Radio Link Control Acknowledge Mode

[0219] RLC-UM Radio Link Control Unacknowledge Mode

[0220] RSD Route Selection Descriptor

[0221] SA Standalone

[0222] SBA Service-Based Architecture

[0223] SBI Service-Based Interface

[0224] SCEF Service Capability Exposure Function

[0225] SCP Service-Based Communication Proxy

[0226] SCTP Stream Control Transmission Protocol

[0227] SDAP Service Data Adaptation Protocol

[0228] SDU Service Data Unit

[0229] SIM Subscriber Identity Module

[0230] SLA Service Level Agreement

[0231] SM Session Management

[0232] SMF Session Management Function

[0233] SN Secondary Node

[0234] S-NSSAI Single Network Slice Selection Assistance Information

[0235] SSB Synchronization Signal Block

[0236] SSC Session and Service Continuity

[0237] SUPI Subscription Permanent Identifier

[0238] TAI Tracking Area Identity

[0239] TE Terminal Equipment

[0240] TM Transparent Mode

[0241] TS Technical Specification

[0242] UDM Unified Data Manager

[0243] UDR Unified Data Repository

[0244] UE User Equipment

[0245] UL Uplink

[0246] UM Unacknowledged Mode

[0247] UP User Plane

[0248] UPF User Plane Function

[0249] URLLC Ultra-Reliable and Low-Latency Communication

[0250] URSP UE Route Selection Policy

[0251] XRM Extended Reality and Media

Claims

1.A first network entity comprising:a transceiver; andat least one processor coupled with the transceiver and configured to:when a serving network of the first entity is a first network of a first network type, identify that a protocol data unit (PDU) session for the first network type is for use in relation to an artificial intelligence (AI) / machine learning (ML) operation; andprevent use of the PDU session in relation to the AI / ML operation for a second network type;wherein the first network supports interworking with a second network of the second network type.2.The first network entity of claim 1, wherein the first network type is a 5thGeneration (5G) System (5GS), and the second network type is a Evolved Packet System (EPS).3.The first network entity of claim 2, wherein the at least one processor is configured to:establish the PDU session for the first network type; andidentify mapped bearer context associated with the PDU session,wherein the mapped bearer context is for transferring the PDU session from the first network type to the second network type.4.The first network entity of claim 3, wherein the at least one processor is configured to:delete the identified mapped bearer context to prevent use of the PDU session in relation to the AI / ML operation for the second network type.5.A second network entity in a first network of a first network type, the second network entity comprising:a transceiver; andat least one processor coupled with the transceiver and configured to:determine that a protocol data unit (PDU) session, to be established for a first network entity, is for use in an artificial intelligence (AI) / machine learning (ML) operation, wherein a serving network of the first network entity is the first network; andbased on the determination, perform session establishment for the PDU session without allocating mapped bearer context for transferring the PDU session from the first network type to a second network type;wherein the first network supports interworking with a second network of the second network type.6.The second network entity of claim 5, wherein the at least one processor is configured to:determine that the PDU session is for use in the AI / ML operation based on information received from the first network entity; ordetermine locally that the PDU session is for use in the AI / ML operation based on information stored at the second network entity or based on at least one parameter associated with the PDU session.7.The second network entity of claim 6, wherein:the information is received from the first network entity, and the at least one processor is configured to transmit, to a third network entity in the first serving network, an indication that the PDU session is for use in the AI / ML operation; orthe information is received from a third network entity in the first serving network.8.The second network entity of claim 7, wherein the second network entity is an access and mobility management function (AMF) and the third network entity is a session management function (SMF).9.A method performed by a first network entity, the method comprising:when a serving network of the first entity is a first network of a first network type, identifying that a protocol data unit (PDU) session for the first network type is to be used in relation to an artificial intelligence (AI) / machine learning (ML) operation; andpreventing use of the PDU session in relation to the AI / ML operation for a second network type;wherein the first network supports interworking with a second network of the second network type.10.The method of claim 9, wherein the first network type is a 5thGeneration (5G) System (5GS), and the second network type is a Evolved Packet System (EPS).11.The method of claim 10, further comprising:establishing the PDU session for the first network type; andidentifying mapped bearer context associated with the PDU session,wherein the mapped bearer context is for transferring the PDU session from the first network type to the second network type.12.The method of claim 11, further comprising:deleting the identified mapped bearer context to prevent use of the PDU session in relation to the AI / ML operation for the second network type.13.A method performed by a second network entity, the method comprising:determining that a protocol data unit (PDU) session, to be established for a first network entity, is for use in an artificial intelligence (AI) / machine learning (ML) operation, wherein a serving network of the first network entity is the first network; andbased on the determination, performing session establishment for the PDU session without allocating mapped bearer context for transferring the PDU session from the first network type to a second network type;wherein the first network supports interworking with a second network of the second network type.14.The method of claim 13, further comprising:determining that the PDU session is for use in the AI / ML operation based on information received from the first network entity; ordetermining locally that the PDU session is for use in the AI / ML operation based on information stored at the second network entity or based on at least one parameter associated with the PDU session.15.The method of claim 14, wherein:the information is received from the first network entity, and the at least one processor is configured to transmit, to a third network entity in the first serving network, an indication that the PDU session is for use in the AI / ML operation; orthe information is received from a third network entity in the first serving network, andwherein the second network entity is an access and mobility management function (AMF) and the third network entity is a session management function (SMF).

Images