GB2619582A

GB2619582A - Monitoring for application AI/ML-based services and operations

Info

Publication number: GB2619582A
Application number: GB2304171.8A
Authority: GB
Inventors: Gutierrez Estevez David
Original assignee: Samsung Electronics Co Ltd
Current assignee: Samsung Electronics Co Ltd
Priority date: 2022-03-29
Filing date: 2023-03-22
Publication date: 2023-12-13
Also published as: GB202204491D0; GB2619104A; GB202212329D0

Abstract

There is disclosed a method for monitoring events in a network. The method comprises: subscribing, by an Application Function (AF), to monitoring the events, wherein the AF supports one or more (Artificial Intelligence/Machine Learning) AIML-based services and/or operations, and the events relate to the performance of the AIML-based services and/or operations; in response to the subscribing, monitoring, by a User Plane Function (UPF), the events; and when an event is detected, reporting, by the UPF to a Network Exposure Function (NEF), the event. The method may comprise reporting, by the NEF to the AF, one or more parameters related to the event. The monitoring events may comprise one or more of: monitoring session inactivity of a PDU session; monitoring traffic volume of a PDU session; monitoring PCF events; per-5QI monitoring; and monitoring of edge resources. The monitoring may comprise QoS monitoring and may be performed for multiple UEs.

Description

Monitoring for Application Al/ML-based Services and Operations BACKGROUND

Field

Certain examples of the present disclosure provide techniques relating to Artificial Intelligence (Al) and/or Machine Leaning (ML), in particular techniques relating to monitoring application Al/ML operation. For example, certain examples of the present disclosure provide methods, apparatus and systems in 3rd Generation Partnership Project (3GPP) 5'h Generation (5G) System (535) for monitoring one or more features (e.g. network resource utilisation and/or Quality of Service (QoS)) for application Al and/or ML operation.

Description of the Related Art

Herein, the following documents are referenced: [1] 33PP IS 22.261 (e.g. V18.5.0) [2] 3GPP IS 23.501 (e.g. V17.3.0) [3] 3GPP IS 23.502 (e.g. V17.3.0) [4] 33PP IS 23.288 (e.g. V17.2.0) Al/ML is being used in a range of application domains across industry sectors. In mobile communications systems, conventional algorithms (e.g. speech recognition, image recognition, video processing) in mobile devices (e.g. smartphones, automotive, robots) are being increasingly replaced with Al/ML models to enable various applications.

The 5G system can support various types of Al/ML operations, in including the following three defined in [1]: * Al/ML operation splitting between AI/ML endpoints The Al/ML operation/model may be split into multiple parts, for example according to the current task and environment. The intention is to offload the computation-intensive, energy-intensive parts to network endpoints, and to 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.

* Al/ML model/data distribution and sharing over 5G system Multi-functional mobile terminals may need to switch an Al/ML model, for example in response to task and environment variations. An assumption of adaptive model selection is that the models to be selected are available for the mobile device. However, since Al/ML models are becoming increasingly diverse, and with the limited storage resource in a UE, not all candidate Al/ML models may be pre-loaded on-board. Online model distribution (i.e. new model downloading) may be needed, in which an Al/ML model can be distributed from a Network (NVV) endpoint to the devices when they need it to adapt to the changed Al/ML tasks and environments. For this purpose, the model performance at the UE may need to be monitored constantly.

* Distributed/Federated Learning over 5G system A cloud server may train a global model by aggregating local models partially-trained by each of a number of end devices e.g. UEs). Within each training iteration, a UE performs the training based on a model downloaded from the Al server using local training data.

Then the UE reports the interim training results to the cloud server, for example 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.

Different levels of interactions are expected between UE and AF as Al/ML endpoints, for example based on [1], to exchange Al/ML models, intermediate data, local training data, inference results and/or model performance as Application Al/ML traffic. However support for the transmission of Application Al/ML traffic, for example over 5GS, between Al/ML endpoints (e.g. UE and AF) as described above is not currently defined in the existing 53C data transfer/traffic routing mechanisms.

3GPP approved a study item for Rel-18 in SA WG2 focused on 5G System Support for Al/MLbased Services. As part of this study, a key issue (i.e. problem statement) was approved with the scope of monitoring the network resource utilization for support of Application Al/ML operations. Another key issue was also approved with the scope of Quality of Service (QoS) and policy enhancements for Al/ML-based services. As part of this key issue, it was agreed to study QoS monitoring aspects to support the operation of the 3d party Al/ML operation.

Overview of NWDAF NWDAF represents an (operator-managed) network analytics logical function providing (slice specific) network data analytics to NFs and/or AFs. A NF or AF may subscribe to network analytics provided by NWDAF. NWDAF collects data from NFs, AFs and/or CAM and derives network analytics. NWDAF provides suitable network analytics to subscribed NFs and/or AFs, for example based on triggering events.

The following is stated in 3GPP TS 23.501 V17.2.0, Clause 6.2.18: The Network Data Analytics Function (NWDAF) includes one or more of the ['Mow inglimctionalities: Support data collection from is/Es and AFs: Support data collection from 021M; NWDAF service registration and metadata exposure to NFS and AFS; Support analytics injarmation provisioning to NFs and AFs: Support Machine Learning (115 model training and provisioning to NWDAFs (containing Analytics logicalfunction).

The details of the NWDAF JUnctionah are defined in TS 23.288 [861 The following is stated in 3GPP TS 23.288 V17.2.0, Clause 4.1: lhe N WRAP' (Network Data Analytics Function) is part of the architecture specified iniS 23.501 121 and uses the mechanisms and interfaces specified for 5GC in 178 23,50] [2] and OAM services (See clause 6.2.3.1).

lhe NWDALI interacts with different entities for different purposes: - Data collection based on subscription to events provided by AAIF, SLIP, PCF, EOM, AF (directly or via NEP), and OANE - (Optionally] Analytics and Data collection using the DCCF-(Data Collection Coordination Function); - Retrieval of information from data repositories (e.g. UDR via UM:1pr subscriber-related information); [Optionally] Storage and retrieval of information from ADRF (Analytics Data Repository Function); [Optionally] Analytics and Data collection from MFAF (Messaging Framework Adaptor Function); - Retrieval of information about.N1Fs' (e.g. from ARE for NF-related information); - On demand provision of analytics to consumers, as specified in clause 6.

- Provision of hulked data to consumers, as specified in clause 6.

A single instance or multiple instances-of NWDAP may be deployed in a PLAIN. If multiple NWDAF instances are deployed, the architecture supports deploying the N Wa41-1 as a central NI:, as a collection of distributed Yrs, or as a combination of both. If multiple /VIEW F instances are deployed, an,VWT)./1F can act as an aggregate point (i.e. Aggregator NWDAF) and collect analytics information from other N111),4 Es', which may have different Serving Areas, to produce the aggregated analytics (per Analytics ID,), possibly with Analytics generated by itself MOTE I When multiple MU/DA Es' exist, not all of them need to be able to provide the same type of analytics results; i.e. some of them can be specialized in providing certain tvpes of analytics. An Analytics ID injarmation element is used to identify the type of supported analytics that Mical F can generate.

MOTE 2: IOWA F instance l's) can be collocated with a 505 AR.

The above information is presented as background information only to assist with an understanding of the present disclosure. No determination has been made, and no assertion is made, as to whether any of the above might be applicable as prior art with regard to the present invention.

SUMMARY

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.

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

Embodiments or examples disclosed in the description and/or figures falling outside the scope of the claims are to be understood as examples useful for understanding the present invention.

Other aspects, advantages and salient features of the invention 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

Figure 1 is an example call flow according to an example of the present disclosure; Figure 2 is an example call flow according to another example of the present disclosure; and Figure 3 is a block diagram of an exemplary network entity that may be used in certain examples of the present disclosure.

DETAILED DESCRIPTION

The following description of examples of the present disclosure, with reference to the accompanying drawings, is provided to assist in a comprehensive understanding of the present invention, as defined by the claims. 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.

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

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 invention.

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 invention.

Throughout the description and claims 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 Throughout the description and claims 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.

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

Certain examples of the present disclosure provide techniques relating to Artificial Intelligence (Al) and/or Machine Leaning (ML), in particular techniques relating to monitoring application Al/ML operation. For example, certain examples of the present disclosure provide methods, apparatus and systems in 3' Generation Partnership Project (3GPP) 5th Generation (5G) System (5GS) for monitoring one or more features (e.g. network resource utilisation and/or Quality of Service (QoS)) for application Al and/or ML operation.

However, the skilled person will appreciate that the present invention is not limited to these examples, 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, including any existing or future releases of the same standards specification, for example 3GPP 5G.

The following examples are applicable to, and use terminology associated with, 3GPP 53.

However, the skilled person will appreciate that the techniques disclosed herein are not limited to 3GPP 5G. 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 or purpose The skilled person will also appreciate that the transmission of information between network entities is not limited to the specific form, type or order of messages described in relation to the examples disclosed herein.

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.

The skilled person will appreciate that the present invention is not limited to the specific examples disclosed herein. For example: * The techniques disclosed herein are not limited to 3GPP 5G.

* 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 entities and/or messages may be added to the examples disclosed herein.

* One or more non-essential 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 and/or the order in which messages are transmitted may be modified, if possible, in alternative examples.

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. Certain examples of the present disclosure may be provided in the form of a system (e.g. network or wireless communication system) comprising one or more such apparatuses/devices/network entities, and/or a method therefor.

In the present disclosure, a UE may refer to one or both of Mobile Termination (MT) and Terminal Equipment (TE). MT may offer common mobile network functions, for example one or more of radio transmission and handover, speech encoding and decoding, error detection and correction, signalling and access to a SIM. An IMEI code, or any other suitable type of identity, may attached to the MT. TE may offer any suitable services to the user via MT functions. However, it may not contain any network functions itself.

Al/ML Application may be part of TE using the services offered by MT in order to support Al/M L operation, whereas Al/ML Application Client may be part of MT. Alternatively, part of Al/ML Application client may be in TE and a part of Al/ML application client may be in MT.

The procedures disclosed herein may refer to various network functions/entities. The functions and definitions of certain network functions/entities, for example those indicated below, are known to the skilled person, and are defined, for example, in at least [2] and [3]: * Al/ML Application Function: Al/ML AF * Network Exposure Function: NEF * Unified Data Repository: UDR * Session Management Function: SMF * User Plane Function: UPF * Access and Mobility management Function AM F * User Equipment: UE However, as noted above, the skilled person will appreciate that the present disclosure is not limited to the definitions given in [2] and [3], and that equivalent functions/entities may be used.

As noted above, as part of the study item for Rel-18 in SA WG2, a key issue was approved with the scope of monitoring the network resource utilization for support of Application Al/ML operations. Another key issue was also approved with the scope of Quality of Service (QoS) and policy enhancements for Al/ML-based services. As part of this key issue, it was agreed to study QoS monitoring aspects to support the operation of the 3d party Al/ML operation.

The following requirements related to the above context has been approved for the 5G system: * Based on operator policy, the 50 system shall be able to provide means to allow an authorized third-party to monitor the resource utilisation of the network service that is associated with the third-party.

NOTE 1: Resource utilization in the preceding requirement refers to measurements relevant to the UE's performance such as the data throughput provided to the US.

* Based on operator policy, the 5G system shall be able to provide an indication about a planned change of bitrate, latency, or reliability for a QoS flow to an authorized 3rd party so that the 314 party Al/ML application is able to adjust the application layer behaviour if time allows. The indication shall provide the anticipated time and location of the change, as well as the target QoS parameters.

* Based on operator policy, 5G system shall be able to provide means to predict and expose predicted network condition changes (i.e. bit rate, latency, reliability) per UE, to an authorized third party.

* Subject to user consent, operator policy and regulatory constraints, the 50 system shall be able to support a mechanism to expose monitoring and status information of an Al-ML session to a 3rd party Al/ML application.

NOTE 2: Such mechanism is needed for Al/ML application to determine an in-time transfer of AWL model.

Certain examples of the present disclosure provide one or more techniques for monitoring features and capabilities to support Al/ML-based services and operations, for example over the 5G System. In certain examples, application Al/ML operations may be understood as including model splitting, model sharing, federated/distributed learning, etc. However, the skilled person will appreciate that the present disclosure is not limited to these examples.

Certain examples of the present disclosure provide a method for monitoring events in a network, the method comprising: subscribing, by an Application Function (AF), to monitoring the events, wherein the AF supports one or more AIML-based services and/or operations, and the events relate to the performance of the AIML-based services and/or operations; in response to the subscribing, monitoring, by a User Plane Function (UPF), the events; and when an event is detected, reporting, by the UPF to a Network Exposure Function (NEF), the event.

In certain examples, the method may further comprise, reporting, by the NEF to the AF, one or more parameters related to the event.

In certain examples, the event may be reported by the UPF to the NEF directly.

In certain examples, reporting, by the UPF to the NEF, the event may comprise: reporting, by the UPF to a Session Management Function (SMF), the event; and reporting, by the SMF to the NEF, the event.

In certain examples, the monitoring events may comprise one or more of: monitoring session inactivity of a PDU session; monitoring traffic volume of a PDU session; monitoring POE events; per-5Q1 monitoring; and monitoring of edge resources.

In certain examples, the monitoring may comprise QoS monitoring and may be performed for multiple UEs.

Certain examples of the present disclosure provide a method for monitoring traffic volume of a PDU session in a network, the method comprising: subscribing, by an Application Function (AF), to monitoring events for traffic volume; in response to the subscribing, monitoring, by a User Plane Function (UPF), traffic volume of the PDU session; when a traffic volume event is detected, reporting, by the UPF to a Network Exposure Function (NEF), a parameter including information on the traffic volume; reporting, by the NEF to the AF, one or more parameters related to the event.

Certain examples of the present disclosure provide a network (or wireless communication system) comprising one or more network entities (e.g. AF, UPF, NEF and/or SMF) configured to operate according to a method of any example, aspect, embodiment and/or claim disclosed herein.

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.

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.

Certain examples of the present disclosure may provide one or more of the following monitoring features and capabilities, for example as part of the 5G System: * Support for monitoring of QoS parameters relevant to the performance of Al/ML-based services at the UE and the application Al/ML operation. Non-limiting examples of such parameters may include one or more of packet delay, traffic/data volume, and any other suitable parameter(s).

* Support for monitoring of N4 session related parameters relevant to the application Al/ML operations. Non-limiting examples of such parameters include one or more of session inactivity timer, and any other suitable parameter(s).

* Support for Application Function (AF) subscription to a series of NWDAF analytics relevant to the application Al/ML operation and performance. Non-limiting examples of such analytics include one or more of DN performance, UE communication, QoS sustainability, for example as defined in 3GPP TS 23.288 (Architecture enhancements for 5G System (5G5) to support network data analytics services), and any other

suitable analytics.

* Support for new Policy Control Function (PCF) events enabling the PCF reporting of the information described above related to Al/ML-based services (e.g. to NEF or AF) and/or Al/ML operation.

* Support for per-501 (5G QoS Identifier) monitoring mechanisms for Al/ML-based services and operations. A non-limiting example includes separate monitoring support of traffic 5QI for collected data for training and traffic 50I for shared models.

* Support for monitoring of edge resources related to the Al/ML-based services and operations.

The skilled person will appreciate that the examples of monitoring features and capabilities described above is not exhaustive. Other monitoring features and capabilities directly or indirectly supporting Al/ML-based services are also possible.

Certain examples of the present disclosure may provide specific capabilities and features enabling monitoring of relevant Al/ML-based services and operations according to one or more of the following examples: - AF monitoring of UL, DL and/or round trip packet delay measurement: the three application Al/ML operations defined in TS 22.281 [1] (model split, model distribution, FL) may benefit from AF packet delay monitoring as the Al/ML application server may schedule training operation at UEs according to application needs, and delay measurements can assist the server in determining what the best strategy for such scheduling is. For example, delay measurements of the UE members of a FL group may assist the application server to decide which UEs need to provide model updates in each iteration. Delay information may also be critical for model split during joint inference, when sharing of inference results may be critical for application performance. Current specifications already detail how the AF monitors this parameter for URLLC services.

AF monitoring of traffic/data volume: AF knowledge on the traffic/data volume may help the application server to decide on the Al/ML operations that may be suitable for the application. For example, it may not be convenient to share or distribute very large models frequently, but smaller size models could be shared frequently. Similarly, there are important implications for model splitting depending on the traffic/data volume that needs to be exchanged between UE and application server, and the application server may need to monitor information on traffic/data volume, for example to decide models' optimal splitting points. In current specifications UPF is already capable of monitoring this parameter and reporting it to SMF. Certain examples of the present disclosure enable the AF to trigger the monitoring procedure and SMF to deliver the report to AF via NEF.

AF monitoring of session inactivity time: when a training operation is to be scheduled by an Al/ML application server, either for a single UE or a group of UEs engaged in FL, awareness of session inactivity time as reported by UPF to SMF may be very helpful as it aids the server to determine when a UE or a group of UEs is sharing specific types of Al/ML traffic such as trained models. In particular, the dynamicity of FL groups may greatly benefit from this parameter as UE's may dynamically join or leave the group in a pre-scheduled way (therefore optimizing performance) with assistance of this parameter. In current specifications UPF is already capable of monitoring this parameter and reporting it to SMF. Certain examples of the present disclosure enable the AF to trigger the monitoring procedure and SMF to deliver the report to AF via NEF.

In some examples, if the application has monitoring capabilities to accurately determine traffic volume and session inactivity, then 5G5 monitoring capabilities for traffic/data volume and session inactivity time may not be required.

AF subscription to NVVDAF analytics (e.g. DN performance, UE communication, QoS sustainability), which may assist the Al/ML application operation and is already supported.

Current specifications already detail how the AF subscribes to these analytics.

Figure 1 is an example call flow according to an example of the present disclosure. The procedure in Figure 1 is based on a combination of certain procedures, for example the procedures in clauses 4.15.16.6, 4.16.5, and 4.4.2.2 of TS 23.502 [3]. However, referring to Figure 1, further modifications are described in the following operations.

In operation 1, AF subscribes to NWDAF analytics relevant to the performance of the UE(s) using the Al/ML application over (a) PDU Session(s) (e.g. DN performance, UE communication, QoS sustainability).

In operation 2, the AF utilizes the Nnef AFsessionVVithQoS service to indicate a subscription to notifications of QoS monitoring for UE traffic related to Al/ML-based services, including packet delay measurement parameter, for example as described in clause 5.33.3 of TS 23.501 [2] for the case of URLLC services. Other requested monitored resources may include usage report and inactivity timer.

Operations 2b and 3 may be performed, for example according to Figure 4.15.6.6-1 in TS 23.502 [3], when NEF determines to contact PCF directly. The requested resource monitoring capabilities are forwarded to PCF.

In certain examples, operation 4 may be performed instead of operations 1-3 when the AF is trusted by the operator to interact directly with PCF to request monitoring capabilities for an AF session related to Al/ML-based services.

Operations Sand 6 may be performed, for example according to clause 4.16.5.2 of TS 23.502 [3], for the case when PCF determines that SMF needs updated policy information.

Operations 7-11 may be performed, for example, as steps 4, Sand 6 in Figure 4.15.6.6-1 of TS 23.502 [3] as applied in the case when QoS monitoring is requested for URLLC services without involvement of TSCTSF. In certain examples, operations 9 and 11 may be performed instead of 7, 8 and 10 when the AF is trusted by the operator.

Operations 12-15 may be performed, for example, according to clause 4.4.2.2 of TS 23.502 [3], where the N4 session report may include UL/DL/round trip packet delay measurement, usage report, PDU session inactivity.

Operations 16 and 17 may be performed, for example, according to clause 4.16.5.1 of TS 23.502 [3], providing the event condition(s) that have been met to PCF.

Operations 18-19 may be performed, for example, as steps 7-8 in Figure 4.15.6.6-1 of TS 23.502 [3] with the event information reported by PCF. In certain examples, operation 20 may be performed instead when the AF is trusted by the operator.

In operation 21, the AF analyses the monitored information exposed by the 5GS related to the Al/ML traffic.

In operation 22, if needed, the AF may trigger a modification of the PDU Session after having analysed the monitored data.

The procedure illustrated in Figure 1 may also be applied to QoS monitoring in certain examples as described in the following. The procedure in Figure 1 is based on a combination of certain procedures, for example the procedures in clauses 4.15.6.6, 4.16.5 and 4.4.2.2 of 3GPP TS 23.502 [3]. However, referring to Figure 1, further modifications are described in the following operations.

In operation 1, AF subscribes to NWDAF analytics relevant to the performance of the UE(s) using the Al/ML application (e.g. ON performance, UE communication, QoS sustainability).

In operation 2, the AF uses the Nnef AFsessionWthOoS service to indicate a subscription to notifications of QoS monitoring for delay measurements of UE traffic related to Al/ML-based services. Hence, the AF request may indicate a packet delay measurement parameter (UL, DL, and/or round trip), for example as described in clause 5.33.3 of TS 23.501 [2] and clause 5.2.6.9 of TS 23.502 [3] for the case of URLLC services.

Operations 2b and 3 may be performed, for example according to Figure 4.15.6.6-1 in TS 23.502 [3], when NEF determines to contact PCF directly. The NEF interacts with the PCF by triggering a Npcf_PolicyAuthorizafion_Create request for session management policy control to authorize the AF request and optionally subscribe to PCF events for measurement of packet delay.

In operations 5 and 6, if the PCF determines that the SMF needs updated policy information (for example as is the case for the monitoring parameters in this example), the PCF issues a Npcf_SMPolicyControl_UpdateNotify request with updated policy information, for example as described in the PCF initiated SM Policy Association Modification procedure in clause 4.16.5.2 of TS 23.502 [3]. The SMF then acknowledges the PCF request with a Npcf_SMPolicyControl_UpdateNofify response.

In operations 7-9, the PCF determines whether the request is authorized and notifies the AF if the request is not authorized via NEF or directly by issuing a Npcf_PolicyAuthorizafion_Create response message.

In operations 10 and 11, the NEF or AF may send a Npcf PolicyAuthorization_Subscribe message to the PCF to subscribe to the notification of POE events for measurement of packet delay measurement if not done so previously in operation 3.

In operations 12-15, after receiving the event subscription notification from POE, the SMF issues an N4 Session Modification Request, for example as described in clause 4.4.1.3 of TS 23.502 [3], configuring the triggers for event reporting in UPF. The reporting triggers configured by SMF may entail session reports for packet delay measurement. The UPF may report on these events, for example according to clause 4.4.2.2 of TS 23.502 [3].

Operations 16-17 may be performed, for example according to clause 4.16.5.1 of TS 23.502 [3], with the SMF providing the event condition(s) that have been met to PCF.

Operations 18-19 may be performed, for example, as steps 7-8 in Figure 4.15.6.6-1 of TS 23.502 [3] with the event information reported by PCF to AF via NEF in case of untrusted AF.

In certain examples, operation 20 may be performed instead when the AF is trusted by the operator.

In operation 22, if needed, the AF may trigger a modification of the PDU Session after having analysed the monitored data (for example, see also clause 4.15.6.6a of TS 23.502 [3], without the need for TSCTSF involvement).

Figure 2 is an example call flow according to another example of the present disclosure. In particular, Figure 2 illustrates a procedure for monitoring of session inactivity time and traffic 25 volume.

In operation 1, the AF uses the Nnef EventExposure_Subscribe service operation to indicate a subscription to new NEF monitoring events for traffic volume and/or session inactivity time.

In operation 2, the NEF subscribes to the user plane status information SMF event, for example described in clause 5.2.8.3.1 of TS 23.502 [3], providing the (Al/ML) application ID and the SUPI(s) of the UE(s) being monitored as event filters, for example as described in Table 5.2.8.3.1-1 of TS 23.502 [3].

In operations 3 and 4, after receiving the event subscription notification from NEF, the SMF issues an N4 Session Modification Request, for example as described in clause 4.4.1.3 of TS 23.502 [3], configuring the trigger for event reporting in UPF of PDU session inactivity.

In operation 5, the NEF may subscribe to event exposure from UPF to obtain information on data usage of a PDU session. For example, the Event may be UserDataUsageMeasures. This event provides information of user data usage of the User PDU Session, for example Volume Measurement and Throughput Measurement.

In operation 6, a trigger happens to report events on session inactivity and/or traffic usage by UPF.

In operation 7, when a PDU session inactivity event is detected, UPF reports it to SMF, for example according to clause 4.4.2.2 of TS 23.502 [3].

In operation 8, SMF reports the detection of a user plane status information event to NEF with information on session inactivity time.

In operation 9, UPF reports to the NEF the detection of the event in operation 5 with information on data usage of a PDU session.

In operation 10, NEF reports the monitored session inactivity time and/or traffic volume to AF via Nnef EventExposure_Notify service operation.

In operation 11, the AF analyses the monitored information exposed by the 5G5 related to the Al/ML traffic.

In operation 12, if needed, the AF may trigger a modification of the PDU Session after having analysed the monitored data.

The skilled person will appreciate that the techniques described herein may be used to support both Al/ML-based services (e.g. robotics, computer vision, etc.) and Al/ML model operations that can be done in the network (e.g. Al/ML operation splitting, Al/ML model/data distribution and sharing, and distributed/federated learning). The techniques described herein may improve the performance of such services and operations. The skilled person will also appreciate that certain examples of the present disclosure may also be applied to non-Al/ML related network aspects.

Figure 3 is a block diagram of an exemplary network entity that may be used in examples of the present disclosure, such as the techniques disclosed in relation to Figures 1 and/or 2. For example, the UE, AF, NEF, PCF, SMF, UPF, NWDAF and/or other NFs may be provided in the form of the network entity illustrated in Figure 3. The skilled person will appreciate that a network 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.

The entity 300 comprises a processor (or controller) 301, a transmitter 303 and a receiver 305.

The receiver 305 is configured for receiving one or more messages from one or more other network entities, for example as described above. The transmitter 303 is configured for transmitting one or more messages to one or more other network entities, for example as described above. The processor 301 is configured for performing one or more operations, for example according to the operations as described above.

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, example or claim 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.

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.

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, aspect and/or claim 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.

While the invention has been shown 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 invention, as defined by the appended claims.

Certain examples of the present disclosure provide one or more techniques as disclosed in the accompanying annex to the description. The skilled person will appreciate that any of these techniques may be applied in combination with any of the techniques described above and illustrated in the Figures.

Acronyms and Definitions 3GPP 3rd Generation Partnership Project 5G 51h Generation 5GC 5G Core 5GS 5G System 501 5G QoS Identifier ADRF Analytics Data Repository Function AF Application Function Al Artificial Intelligence AMF Access and Mobility management Function DCCF Data Collection Coordination Function DL Downlink DN Data Network ID Identity/Identifier IM El International Mobile Equipment Identities MFAF Messaging Framework Adaptor Function ML Machine Learning MT Mobile Termination N4 Interface between Control Plane and User Plane NEF Network Exposure Function NF Network Function NRF Network Repository Function NW Network NWDAF Network Data Analytics Function OAM Operations, Administration and Maintenance PDU Protocol Data Unit PLMN Public Land Mobile Network QoS Quality of Service Rel Release SIM Subscriber Identity Module SMF Session Management Function TE Terminal Equipment

TS Technical Specification

TSCTSF Time Sensitive Communication Time Synchronisation Function UDM Unified Data Manager UDR Unified Data Repository UE User Equipment UL Uplink UPF User Plane Function URLLC Ultra-Reliable Low-Latency Communication WG Working Group

Claims

Claims 1. A method for monitoring events in a network, the method comprising: subscribing, by an Application Function (AF), to monitoring the events, wherein the AF supports one or more AIML-based services and/or operations, and the events relate to the performance of the AIM L-based services and/or operations; in response to the subscribing, monitoring, by a User Plane Function (UPF), the events; and when an event is detected, reporting, by the UPF to a Network Exposure Function (NEF), the event.
2. A method according to claim 1, further comprising, reporting, by the NEF to the AF, one or more parameters related to the event.
3. A method according to claim 1 or 2, wherein the event is reported by the UPF to the NEF directly.
4. A method according to claim 1 or 2, wherein reporting, by the UPF to the NEF, the event comprises: reporting, by the UPF to a Session Management Function (SMF), the event; and reporting, by the SMF to the NEF, the event.
5. A method according to any preceding claim, wherein the monitoring events comprises one or more of: monitoring session inactivity of a PDU session; monitoring traffic volume of a PDU session; monitoring POE events; per-501 monitoring; and monitoring of edge resources.
6. A method according to claim 1, wherein the monitoring comprises QoS monitoring and is performed for multiple UEs.
7. A method for monitoring traffic volume of a PDU session in a network, the method 35 comprising: subscribing, by an Application Function (AF), to monitoring events for traffic volume; in response to the subscribing, monitoring, by a User Plane Function (UPF), traffic volume of the PDU session; when a traffic volume event is detected, reporting, by the UPF to a Network Exposure Function (NEF), a parameter including information on the traffic volume; reporting, by the NEF to the AF, one or more parameters related to the event.
8. A network (or wireless communication system) comprising one or more network entities (e.g. AF, UPF, NEF and/or SMF) configured to operate according to a method of any preceding claim.
9 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 of claims 1 to 7.
10. A computer or processor-readable data carrier having stored thereon a computer program according to claim 9.