WO2019210947A1

WO2019210947A1 - Systems, network functions and methods therein for enabling a determination of information associated with a user plane connection in a communications network

Info

Publication number: WO2019210947A1
Application number: PCT/EP2018/061211
Authority: WO
Inventors: Venkata Sameer Kumar KODUKULA; Peter Hedman; Nipun Sharma; Swarup Kumar Mohalik
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2018-05-02
Filing date: 2018-05-02
Publication date: 2019-11-07

Abstract

A User Plane Function, UPF (201) and method therein for routing user plane data traffic in a system (200) is provided. The UPF (201) receives information indicating that user plane data traffic being routed by the UPF (201) in a user plane connection (131) established for a user equipment, UE (121), is to be additionally routed via a user plane 5 data traffic connection (132) to a Network Data Analysis, NWDA, function (202). Also, the UPF (201) routes user plane data traffic in the user plane connection (131) additionally towards the NWDAF (202) via the user plane data traffic connection (132). Further, a Network Data Analysis, NWDA, function (202) and method therein for determining information associated with a user plane connection (131), a Policy Control 10 Function, PCF (204), and method therein for adapting policy information for a user plane connection (131), and a Session Management Function, SMF (205) and method therein for enabling routing of user plane data traffic are also provided.

Description

SYSTEMS, NETWORK FUNCTIONS AND METHODS THEREIN FOR ENABLING A DETERMINATION OF INFORMATION ASSOCIATED WITH A USER PLANE CONNECTION IN A COMMUNICATIONS NETWORK

TECHNICAL FIELD

Embodiments herein relate to enabling application of machine learning in a system or communications network, such as, for example, a wireless communications network. In particular, embodiments herein relate to network functions and methods therein for enabling routing of user plane data traffic, for routing user plane data traffic in a communications network, for determining information associated with a user plane connection, and for adapting policy information for a user plane connection.

BACKGROUND

A wireless communications network conventionally comprises radio base stations, also referred to as network nodes, providing radio coverage over at least one respective geographical area forming a so-called cell or coverage area. Wireless devices, also referred to herein as User Equipments, UEs, mobile stations, and/or wireless terminals, are served in the cells by the respective radio base station. The wireless devices transmit data over an air or radio interface to the radio base stations in uplink, UL, transmissions and the radio base stations transmit data over an air or radio interface to the wireless devices in downlink, DL, transmissions. In today’s wireless communications networks a number of different technologies are used, such as, for example, 5G/New Radio (NR), Long Term Evolution (LTE), LTE-Advanced, Wideband Code Division Multiple Access (WCDMA), Global System for Mobile communications/Enhanced Data rate for GSM Evolution (GSM/EDGE), Worldwide Interoperability for Microwave Access (WiMax), or Ultra Mobile Broadband (UMB), just to mention a few possible technologies for wireless communication. One of the technologies for a wireless communications network that is currently being worked on is the 5G or New Radio (NR) system architecture.

Fig. 1 shows one example of a proposed system architecture for a 5G wireless communications network 100 comprising a number of defined Network Functions, NFs, and reference points or interfaces connecting the NFs. A User Equipment, UE 121 , is connected to either Radio Access Network or Access Network, (R)AN 110. RAN may, for example, represent a radio base station or network node using new Radio Access Technology, RAT, and evolved LTE, while AN may represent a general base station including non-3GPP access, e.g. Wi-Fi, etc. The UE 121 is also connected to a Access and Mobility Management function, AMF 101 , which is one of the NFs in the core network of the 5G wireless communications network 100. Further NFs in the core network of the 5G wireless communications network 100 may comprise: a Session Management Function, SMF 102, a Policy Control Function, PCF 103, an Application Function, AF 104, an Authentication Server Function, AUSF 105, a User Plane Function, UPF 106, a User Data Management, UDM 107, and Network Slice Selection Function, NSSF 108. A short overview of these NFs and at least some of the functionalities that they support are provided below.

The AMF 101 provides UE-based authentication, authorization, mobility management, etc., and supports e.g. termination of NAS signalling, NAS ciphering & integrity protection, registration management, connection management, mobility management, access authentication and authorization, security context management. The AMF 101 may be view as comprising some of the MME functionality from the legacy EPC system architecture. The SMF 102 is responsible for session management and allocates IP addresses to UEs and supports e.g. session management (session establishment, modification, release), UE IP address allocation & management, DHCP functions, termination of NAS signalling related to session management, DL data notification, traffic steering configuration for UPF for proper traffic routing. The SMF 102 may be view as comprising some of the MME and PGW functionality from the legacy EPC system architecture. The PCF 103 is responsible for policy control in order to support Quality of Service (QoS) and supports e.g. unified policy framework, providing policy rules to CP functions, access subscription information for policy decisions in UDR. The PCF 103 may be view as comprising some of the PCRF functionality from the legacy EPC system architecture. The AF 104 supports e.g. application influence on traffic routing and interaction with policy framework for policy control. The AUSF 105 stores data for authentication of UE 121 and may act as an authentication server, for example, similar to the HSS functionality from the legacy EPC system architecture. The UPF 106 supports e.g. packet routing & forwarding, packet inspection, QoS handling, and acts as external PDU session point of interconnect to a Data Network, DN 109, providing Internet access or operator services. The UPF 106 may also be considered an anchor point for intra- & inter-RAT mobility, and may be view as comprising some of the SGW and PGW functionality from the legacy EPC system architecture. The UDM 107 stores subscription data of the UE 121 and supports, e.g. generation of Authentication and Key Agreement (AKA) credentials, user identification handling, access authorization, subscription management. The UDM 107 may be view as comprising some of the HSS functionality from the legacy EPC system architecture. The NSSF 108 supports, e.g. selecting of the Network Slice instances to serve the UE 121 , determining the allowed NSSAI,

determining the AMF set to be used to serve the UE 121. Further NFs (not shown in Fig.

1 ) may include a Network Exposure function, NEF, and a NF Repository function, NRF. The NEF may orchestrate and manage MTC related control and user plane data traffic and may also support e.g. exposure of capabilities and events, secure provision of information from external application to 3GPP network, translation of internal/external information. The NRF may support e.g. service discovery function, maintains NF profile and available NF instances.

It should be noted that one goal of the system architecture for a 5G wireless communications network 100 in Fig. 1 is to separate the user plane and control plane.

The user plane carries user traffic, while the control plane carries control signalling in the network. In Fig. 1 , the UPF 106 is in the user plane and all other NFs, e.g. AMF 101 , SMF 102, PCF 103, AF 104, AUSF 105, and UDM 107, are in the control plane. Separating the user and control planes enables each plane resource to be scaled independently. It also allows UPFs to be deployed separately from control plane functions in a distributed fashion. In this architecture, UPFs may be deployed very close to UEs to shorten the Round Trip Time, RTT, between a UE 121 and DN 109 for some applications requiring low latency. Hence, the NFs supports the establishment and control of the user plane connection 130 in which data content or payload in transported between the UE 121 and the DN 109 in the 5G wireless communications network 100.

While the NFs exemplified in the 5G wireless communications network 100 are still under development and standardization, it is already seen that this type of new system architecture may advantageously enable, for example, a higher scale of Machine Type Communication, MTC, such as, e.g. loT/M2M/D2D communications, which is expected to grow significantly in coming years. It also evolves the core network and RAN part in the 5G wireless communications network 100 leaving much bandwidth and flexibility, such as, through e.g. mmWave propagation and Cloud RAN part.

SUMMARY

It is an object of embodiments herein to improve the handling of user plane connections in a system.

According to a first aspect of embodiments herein, the object is achieved by a method performed by a User Plane Function, UPF, for routing user plane data traffic in a system. The UPF receives information indicating that user plane data traffic being routed by the UPF in a user plane connection established for a user equipment, UE, is to be additionally routed via a user plane data traffic connection to a Network Data Analysis Function, NWDAF. Also, the UPF routes user plane data traffic in the user plane connection additionally towards the NWDAF via the user plane data traffic connection.

According to a second aspect of embodiments herein, the object is achieved by a UPF for routing user plane data traffic in a system. The UPF is configured to receive information indicating that user plane data traffic being routed by the UPF in a user plane connection established for a UE is to be additionally routed via a user plane data traffic connection to a NWDAF and route user plane data traffic in the user plane connection additionally towards the NWDAF via the user plane data traffic connection.

According to a third aspect of embodiments herein, the object is achieved by a method performed by a NWDAF for determining information associated with a user plane connection established for a UE in a system. The NWDAF receives user plane data traffic associated with a user plane connection established for a UE in the system via a user plane data traffic connection from a UPF. Also, the NWDAF determines at least one user plane data traffic characteristic based on the user plane data traffic. Further, the NWDAF transmits the determined at least one user plane data traffic characteristic to a Policy Control Function, PCF, and/or to a User Data Management/Repository, UDM/UDR, function in the system.

According to a fourth aspect of embodiments herein, the object is achieved by a NWDAF for determining information associated with a user plane connection established for a UE in a system. The NWDAF is configured to receive user plane data traffic associated with a user plane connection established for a UE in the system via a user plane data traffic connection from a UPF. The NWDAF is also configured to determine at least one user plane data traffic characteristic based on the user plane data traffic.

Further, the NWDAF is configured to transmit the determined at least one user plane data traffic characteristic to a PCF and/or to a UDM/UDR function in the system.

According to a fifth aspect of embodiments herein, the object is achieved by a method performed by a PCF for adapting policy information for a user plane connection established for a UE in a system. The PCF receives at least one user plane data traffic characteristic from the NWDAF associated with the user plane connection, the at least one user plane data traffic characteristic is based on the user plane data traffic of the user plane connection that is additionally routed by the UPF via a user plane data traffic connection to the NWDAF. Further, the PCF adapts, if needed, policy information for the user plane connection based on the received at least one user plane data traffic characteristic.

According to a sixth aspect of embodiments herein, the object is achieved by a PCF for adapting policy information for a user plane connection established for a UE in a system. The PCF is configured to receive at least one user plane data traffic characteristic from the NWDAF associated with the user plane connection, wherein the at least one user plane data traffic characteristic is based on the user plane data traffic of the user plane connection that is additionally routed by the UPF via a user plane data traffic connection to the NWDAF. Further, the PCF is configured to adapt, if needed, policy information for the user plane connection based on the received at least one user plane data traffic characteristic.

According to a seventh aspect of embodiments herein, the object is achieved by a method performed by Session Management Function, SMF, for enabling routing of user plane data traffic in a system. The SMF obtains subscriber data associated with a user plane connection established for a UE in the system. Also, the SMF determines, based on the received subscriber data, that user plane data traffic of the user plane connection is to be additionally routed via a user plane data traffic connection to a NWDAF. Further, the SMF transmits, to a UPF, information indicating that the user plane data traffic being routed by the UPF in the user plane connection is to be additionally routed via the user plane data traffic connection to the NWDAF.

According to an eight aspect of embodiments herein, the object is achieved by a SMF for enabling routing of user plane data traffic in a system. The SMF is configured to obtain subscriber data associated with a user plane connection established for a UE in the system. The SMF is also configured to determine, based on the received subscriber data, that user plane data traffic of the user plane connection is to be additionally routed via a user plane data traffic connection to a NWDAF. Further, the SMF is configured to transmit, to a UPF, information indicating that the user plane data traffic being routed by the UPF in the user plane connection is to be additionally routed via the user plane data traffic connection to the NWDAF.

According to a ninth aspect of the embodiments herein, the object is achieved by a system comprising one or more of: the UPF, the NWDAF, the PCF, and the SMF; wherein the system comprises at least one processing circuitry and a memory, wherein the memory is containing instructions executable by the at least one processing circuitry.

According to a tenth aspect of the embodiments herein, computer programs configured to perform the methods described above are also provided. Further, according to an eleventh aspect of the embodiments herein, carriers containing the computer programs are also provided.

By additionally routing user plane data traffic via a user plane data traffic connection to a NWDAF from a UPF in a system, that is, by introducing a way to duplicate and divert user plane data traffic of a user plane connection towards a NWDAF in a UPF, the data content of the user plane data traffic is able to be separately classified and analysed without significantly impacting the regular operation of the system. Furthermore, based on, for example, additional machine learning analysis of the data content of the additionally routed user plane data traffic, this also advantageously enables context-based classification and/or context-based policy and charging decisions to be implemented in the system. This means that classification, policy and charging rules or information for a user plane connection in the system may be set based on the communication pattern, the communication type and/or the data content of the data traffic associated with the user plane connection. Hence, the handling of user plane connections in a system improved. Further possible features and benefits of this solution will become apparent from the detailed description below.

BRIEF DESCRIPTION OF THE DRAWINGS

Features and advantages of the embodiments will become readily apparent to those skilled in the art by the following detailed description of exemplary embodiments thereof with reference to the accompanying drawings, wherein:

Fig. 1 is a schematic block diagram illustrating a system architecture of a wireless communications network according to prior art, Fig. 2 is a schematic block diagram illustrating embodiments of a system architecture of a system,

Fig. 3 is a flowchart depicting embodiments of a method in a UPF,

Fig. 4 is another flowchart depicting embodiments of a method in a NWDAF, Fig. 5 is yet another a flowchart depicting embodiments of a method in a PCF, Fig. 6 is a further flowchart depicting embodiments of a method in a SMF, Fig. 7 is a signalling diagram depicting embodiments of a method in a UPF, a

NWDAF, a PCF and a SMF,

Fig. 8 is another signalling diagram depicting a signalling according to the

standard 3GPP TS 23.502, version 2.0.0, 2017-12,

Fig. 9 is another signalling diagram depicting embodiments of a method in a

NWDAF,

Fig. 10 is a block diagram depicting embodiments of a UPF,

Fig. 1 1 is another block diagram depicting embodiments of a NWDAF,

Fig. 12 is yet another block diagram depicting embodiments of a PCF,

Fig. 13 is a further block diagram depicting embodiments of a SMF.

DETAILED DESCRIPTION

The figures are schematic and simplified for clarity, and they merely show details which are essential to the understanding of the embodiments presented herein, while other details have been left out. Throughout, the same reference numerals are used for identical or corresponding parts or steps.

Fig. 2 depicts a system 200 in which the embodiments described herein may operate. In some embodiments, the system 200 may be wireless or radio communications network, such as, 5G/New Radio/Next Generation (NR/NG) network. The system 200 depicted in Fig. 2 is identical to the wireless communications network 100 in Fig. 1 , except in that it may further comprise embodiments of a UPF 201 , a NWDAF 202, a MLaaS 203, a PCF 204, a SMF 205 (denoted by the dashed lined blocks in Fig. 2) as described herein, and some additional interfaces or reference points connected thereto. It should be noted that each of the embodiments of the UPF 201 , the NWDAF 202, the MLaaS 203, the PCF 204, and the SMF 205 may have both functional behaviour and interface. The UPF 201 , NWDAF 202, MLaaS 203, PCF 204, and SMF 205 may be implemented either as a network element on a dedicated hardware, e.g. as a software instance running on a dedicated hardware, or as a virtualized function instantiated on an appropriate platform, e.g. a cloud infrastructure. Hence, each of the UPF 201 , the NWDAF 202, the MLaaS 203, the PCF 204, and the SMF 205 may also be referred to an instance, entity, network node or node in the system 200.

In Fig. 2, the User Equipment 121 may refer to any type of device communicating in the communication network 200. Examples of such devices are mobile phones, cellular phones, Personal Digital Assistants (PDAs), smart phones, tablets, sensors equipped with a UE, Laptop Mounted Equipment (LME) (e.g. USB), Laptop Embedded Equipments (LEEs), Machine Type Communication (MTC) devices, or Machine to Machine (M2M) device, Customer Premises Equipment (CPE), target device, device-to-device (D2D) wireless device, wireless device capable of machine to machine (M2M) communication, etc. Further, in Fig. 2, the RAN 110 may comprise at least one radio base station. The radio base station may serve the UE 121 in at least one cell or coverage area. The radio base station may correspond to any type of network node or radio network node capable of communicating with the UE 121 , such as, e.g. a base station, a radio base station, gNB, eNB, eNodeB, a Home Node B, a Home eNode B, femto Base Station (BS), pico BS, etc., in the system 200. Further examples of the radio base station may also be e.g. a repeater, a base station (BS), a multi-standard radio (MSR) radio node such as MSR BS, a eNodeB, a network controller, a radio network controller (RNC), a base station controller (BSC), a relay, a donor node controlling relay, a base transceiver station (BTS), an access point (AP), a transmission points, a transmission nodes, a Remote Radio Unit (RRU), a Remote Radio Head (RRH), nodes in distributed antenna system (DAS), core network node (e.g. MSC, MME, etc.), O&M, OSS, SON, positioning node (e.g. E-SMLC), MDT, etc.

Furthermore, the UPF 201 , NWDAF 202, MLaaS 203, PCF 204, and SMF 205 supports the establishment and control of the user plane connection 131 in which data content or payload in transported between the UE 121 and the DN 109 in the system 100. According to embodiments herein, the UPF 201 may be configured to communicate with the NWDAF 202 over e.g. an X3 interface. One example of such an X3 interface is defined in the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12. The UPF 201 may also be configured to establish a user plane data traffic connection 132 with the NWDAF 202. It should also be noted that there may also be one or more further UPFs located in between the UPF 201 and the NWDAF 202, which may be responsible for forwarding the user plane data traffic over the user plane data traffic connection 132 between the UPF 201 and the NWDAF 202. As shown in Fig. 2, the NWDAF 202 may be configured to communicate with the PCF 204 over e.g. an N23 interface. One example of such an N23 interface is defined in 3GPP TS 23.503, version 15.0.0, clause 5.3.11. Also, the NWDAF 202 may be configured to communicate with the Machine Learning as a Service, MLaaS 203 over e.g. a HTTP / HTTPS / SPARK interface. Here, it should also be noted the MLaas 203 may be co- located or integrated with the NWDAF 202 in the system 200. The MLaaS 203 may be a separate function, entity, instance or network node configured to perform pattern analysis and machine learning of data content in user plane data traffic.

Although embodiments below are described with reference to Fig. 2, this should not be construed as limiting to the embodiments herein, but merely as an example made for illustrative purposes.

As part of developing the embodiments described herein, it has been noted that the policy and charging decisions in the 5G wireless communications network 100 are still the viewed in the same way as in legacy EPC system architecture, wherein the policy and charging decisions are defined as per the policy rules or information defined in the PCRF and OCS nodes of the EPC network. This means that these policy rules or information in the 5G wireless communications network 100 are also static in nature, which means that no information associated with the data traffic, or the data payload comprised therein, transported across the user plane connection 130 is considered in the 5G wireless communications network 100 when establishing the policy rules or information. In other words, this means that no policy level definition considers any data content of the bit-pipe or its nature. Consequently, the 5G wireless communications network 100 currently only operates as a facilitator for the data and/or content distribution across the user plane connection 130, and may hence be view as a bandwidth provider only. Even with classification of UEs as loT devices, by means of which the user plane data traffic from these UEs may be guided into a separate part of the RAN and core network, i.e. diverted towards a dedicated network slice in the 5G wireless communications network 100, this separate part of the RAN and core network in the 5G wireless communications network 100 will be still only be used as a bandwidth provider for the bit-pipe.

Thus, it was realized that the excessive bandwidth and flexibility provided by the system architecture of the 5G wireless communications network may be reused within for further analysis of user plane data traffic in the user plane data traffic connection. Such an analysis may then, for example, be weighed and sent as an input to the PCF for policy and charging decision regarding the user plane data traffic of the user plane connection. Hence, specific user plane data traffic in the user plane data traffic connection, for example, MTC, M2M or loT user plane data traffic, could be identified and classified through the introduction of machine learning and communication pattern analysis for the data traffic of the user plane connection. When applicable, this could also be used as feedback on the communication pattern of data traffic of the user plane connection which may enable optimizations within the 5G wireless communications network.

This issue is also addressed by the embodiments of the UPF 201 , the NWDAF 202, the MLaaS 203, the PCF 204, and the SMF 205 described herein by enabling an additionally routing of user plane data traffic via a user plane data traffic connection 132 to a NWDAF 202 from a UPF 201 in a communications network 200, such that the data content of the user plane data traffic of the user plane data traffic connection 131 is able to be separately classified and analysed without significantly impacting the regular operation of the communications network 200. Furthermore, based on, for example, additional machine learning analysis of the data content of the additionally routed user plane data traffic in the MLaaS 203, this also advantageously enables context-based classification and/or context-based policy and charging decisions to be implemented in the PCF 204 in the communications network. This means that classification, policy and charging rules or information for a user plane connection 131 in the communications network 200 may be set based on the communication pattern, the communication type and/or the data content of the data traffic associated with the user plane connection 131.

Embodiments of the UPF 201 , the NWDAF 202, the MLaaS 203, the PCF 204, and the SMF 205 and methods therein will be described in more detail below with reference to Figs. 3-12.

Example of embodiments of a method performed by a User Plane Function, UPF 201 , for routing user plane data traffic in a system 200 will now be described with reference to the flowchart depicted in Fig. 3. The method may comprise the following actions.

Action 301. The UPF 201 receives information indicating that user plane data traffic being routed by the UPF 201 in a user plane connection 131 established for a user equipment, UE 121 , is to be additionally routed via a user plane data traffic connection 132 to a Network Data Analysis Function, NWDAF 202. This means that the UPF 201 may be instructed by another NF in the system 100 to also provide the user data traffic being transported in the user plane connection 131 between the UE 121 and the DN 109 to the NWDAF 202 in the system 100. It also means that user plane data traffic that has been classified and differentiated in other parts of the communications network 200 may be forked from the UPF 201 and sent to NWDAF 202 through a new interface. In some embodiments, the information may be received from a Session Management Function, SMF 205. The information may be conferred in a Session Establishment or Modification request via an N4 interface between the SMF 205 and the UPF 201.

In some embodiments, the received information may comprise a dedicated usage type indicator of the UE 121. Here, the dedicated usage type indicator may, for example, be a UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018- 01. However, the dedicated usage type indicator may also be other information indicative of a communication usage pattern of the UE 121. Additionally, or alternatively, the received information may comprise an identification of the UE 121. The identification may, for example, be one of: a International Mobile Equipment Identity, IMEI-SV, or Permanent Equipment Identifier, PEI; or International Mobile Subscriber Identity, IMSI, or Subscription Permanent Identifier, SUPI. Additionally, or alternatively, the received information may comprise an identification of a service application in the UE 121. The identification of a service application may be a Service Application identification, such as, for example, an Application Identity or Application Uniform Resource Locator, URL. Additionally, or alternatively, the received information may comprise an Access Point Name, APN, or a Data Network Name, DNN, associated with the user plane connection 131. Additionally, or alternatively, the received information may comprise a network slice information associated with the user plane connection 131. Here, the network slice information may, for example, be one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID. Additionally, or alternatively, the received information may comprise policy information set in the Policy Control Function, PCF 204, in the system 200 associated with the user plane connection 131. This means that the received information may comprise many different types of triggers indicating to the UPF 201 that it should start to additionally route user plane data traffic of one or more user plane connections of one or more UEs to the NWDAF 202. The received information may thus include different parameters for separating data traffic of specific UEs and/or specific subscription categories, e.g. UEs or subscriptions associated with loT, M2M, D2D, or others type of communications or communication patterns.

Action 302. After receiving the information in Action 301 , the UPF 201 routes user plane data traffic in the user plane connection 131 additionally towards the NWDAF 202 via the user plane data traffic connection 132. This means that in addition to routing the user plane data traffic in the user plane connection 131 , the UPF 201 should also route the user plane data traffic towards the NWDAF 202 via the user plane data traffic connection 132. This also means that the UPF 201 may use one or more Deep Packet Inspection, DPI, techniques to filter out the required or desired data packets of the data traffic to forward to the NWDAF 202. According to some embodiments, this may be performed by the UPF 201 by duplicating the user plane data traffic in the user plane connection 131 , and outputting the duplicated user plane data traffic via the user plane data traffic connection 132 to the NWDAF 202. In some embodiments, the user plane data traffic connection 132 may be established via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12. This means that the data traffic of the user plane data traffic connection 132 may be diverted based on a similar structure as that of the Lawful Interception, LI, framework 3GPP TS 33.107. The user plane data traffic connection 132 may be set up using a GTP tunneling protocol.

In some embodiments, the UPF 201 feedback the received information, such as, e.g. a dedicated usage type indicator of the UE 121 , to an AMF 101 in the

communications network 200 to optimize the handling of the UE 121. This information may also be feedbacked to an MME (not shown in Fig. 2) and/or an (R)AN 1 10 of the communications network 200 to further optimize the handling of the UE 121. This would limit the need to get this information from an AF 104, such as, for example, described in 3GPP TS 23.682, version 15.4.0, 2018-03 in which an Application Function, AF, provides communication pattern parameters to a Service Capability Exposure Function, SCEF, which then forwards them to a Home Subscriber Service, HSS, which a Mobility

Management Entity, MME, downloads together with subscription data and forwards to the Radio Access Network, RAN.

Example of embodiments of a method performed by a Network Data Analysis Function, NWDAF 202, in a system 200 will now be described with reference to the flowchart depicted in Fig. 4. The method may comprise the following actions.

Action 401. The NWDAF 202 receives user plane data traffic associated with a user plane connection 131 established for a UE 121 in the system 200 via a user plane data traffic connection 132 from a UPF 201. As described above in Action 302, the user plane data traffic connection 132 may be established via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12, and may be set up using a GTP tunneling protocol. Action 402. After receiving the information in Action 401 , the NWDAF 202 may determine at least one user plane data traffic characteristic based on the user plane data traffic. This means that the NWDAF 202 may be configured to separately classify and analyse the data content of the user plane data traffic received via the user plane data traffic connection 132 without significantly impacting the regular operation of the communications network 200.

In some embodiments, the NWDAF 202 may transmit the received user plane data traffic to a Machine Learning as a Service, MLaaS 203, function. This may be performed in order for the MLaaS 203 to be able to perform communication pattern analysis and learning based on the user plane data traffic. In response, the NWDAF 202 may receive at least one user plane data traffic characteristic based on the transmitted user plane data traffic from the MLaaS 203. This communications between the NWDAF 202 and the MLaaS 203 may, for example, be performed over a HTTP / HTTPS / SPARK interface, since it may include audio, video, image and text data. However, it should also be noted that the NWDAF 202 may use any existing or any modified API for the user plane data traffic transmission to MLaaS 203 depending on which machine learning application will perform the pattern analysis and machine learning based on the user plane data traffic.

Here, the at least one user plane data traffic characteristic may comprise at least one output parameter of the MLaaS 203 configured for user plane data traffic. This means that when the MLaas 203 has identified and classified the received data plane traffic as a specific communication pattern or communication usage type, the MLaas 203 may return one or more parameters, or parametrized weighted output, indicative of the specific communication pattern or communication usage type to the NWDAF 202. The one or more parameters, or parametrized weighted output, may thus separate data traffic of specific UEs and/or specific subscription categories, e.g. UEs or subscriptions associated with loT, M2M, D2D, or other type of communications or communication patterns, according to the specific communication pattern or communication usage types established by the MLaaS 203 using communication pattern analysis and learning based on previous user plane data traffic.

In some embodiments, the at least one user plane data traffic characteristic comprise at least one output parameter associated with a communication pattern. Here, the communication pattern may be a communication pattern as defined in 3GPP TS 23.682, version 15.3.0, 2017-12 or 3GPP TS 23.401 , version 15.2.0, 2017-12. Optionally, the communication pattern may be an Expected UE behaviour. Here, the Expected UE behaviour may be a Expected UE behaviour as defined in 3GPP TS 23.501 , version 15.0.0, 2017-12, section 5.4.6.2, or 3GPP TS 23.502, version 15.0.0, 2017-12, section 4.15.6.3. In some embodiments, the at least one user plane data traffic characteristic may comprise network slice specific information associated with the user plane data traffic.

Action 403. After determining the at least one user plane data traffic characteristic in Action 402, the NWDAF 202 transmits the determined at least one user plane data traffic characteristic to a PCF 204, and/or to a User Data Management/Repository, UDM/UDR 107, in the system 200. This means that the NWDAF 202 may transmit the determined at least one user plane data traffic characteristic to be used for policy or charging decisions in the PCF 204.

Optionally, the NWDAF 202 may store the determined at least one user plane data traffic characteristic in subscriptions, for example, via UDM 107 in a UDR. Here, according to some embodiments, the transmission of the determined at least one user plane data traffic characteristic to a UDM/UDR function 107 may be performed via a Network Exposure Function, NEF. This is described in more detail with reference to Fig. 9 below. According to another option, the NWDAF 202 may tie the determined at least one user plane data traffic characteristic to a certain UE identification, such as, an equipment type and/or software version, e.g. specific IMEI-SV or PEI or to a specific IMSI or SUPI. This type of tying of a communication pattern may, for example, be performed when an extreme communication pattern is discovered, e.g. due to faulty implementation or a communication pattern that is not aligned with a communication transfer pattern agreed between the Network Service Provider and the Application Layer Service Provider, e.g. through negotiations for future background data transfer of the AF 104.

Example of embodiments of a method performed by a Policy Control Function,

PCF 204, for adapting policy information for a user plane connection 131 established for a UE 121 in a system 200 will now be described with reference to the flowchart depicted in Fig. 5. The method may comprise the following actions.

Action 501. The PCF 204 receives at least one user plane data traffic

characteristic from the NWDAF 202 associated with the user plane connection 131 , wherein the at least one user plane data traffic characteristic is based on user plane data traffic of the user plane connection 131 that is additionally routed by the UPF 201 via a user plane data traffic connection 132 to a NWDAF 202. This means that the PCF 204 may receive via the NWDAF 202 the one or more parameters, or parametrized weighted output, from the MLaaS 203 that is indicative of the specific communication pattern or communication usage type of the user plane data traffic of the user plane connection 131.

Action 502. After receiving the user plane data traffic characteristic from the NWDAF 202, the PCF 204 may adapt, if needed, policy information for the user plane connection 131 based on the received at least one user plane data traffic characteristic. This means that the PCF 204 may adapt the policy rules and information in the PCF 204 based on the one or more parameters, or parametrized weighted output, from the MLaaS 203 that is indicative of the specific communication pattern or communication usage type of the user plane data traffic of the user plane connection 131. Additionally, based on the one or more parameters, or parametrized weighted output, the PCF 204 may adapt policy and charging rules and information in other nodes or functions associated with the PCF 204 in the system 200, such as, e.g. an Online Charging System, OCS.

In some embodiments, the PCF 204 may further adapt policy information for other user plane connections based on the received at least one user plane data traffic characteristic associated with the user plane connection 131. This means that the PCF 204 may adapt the policy and charging rules and information in the PCF 204, or in other associated nodes or functions in the system 200, such as, e.g. an Online Charging System, OCS, for other user plane connections based on the one or more parameters, or parametrized weighted output, from the MLaaS 203 that is indicative of the specific communication pattern or communication usage type of the user plane data traffic of the user plane connection 131. This may, for example, be the case when the one or more parameters, or parametrized weighted output, may be applied to data traffic of multiple UEs and/or specific subscription categories, e.g. UEs or subscriptions associated with loT, M2M, D2D, or other type of communications or communication patterns. Example of embodiments of a method performed by a Session Management Function, SMF 205, for enabling routing of user plane data traffic in a system 200 will now be described with reference to the flowchart depicted in Fig. 6. The method may comprise the following actions.

Action 601. The SMF 205 obtains subscriber data associated with a user plane connection 131 established for a UE 121 in the system 200. This means that the SMF 205 may retrieve or receive the subscriber data from a User Data Management/Repository, UDM/UDR, function 107 in the system 200.

In some embodiments, the subscriber data may comprise a dedicated usage type indicator of the UE 121. Here, the dedicated usage type indicator may, for example, be a UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01. However, the dedicated usage type indicator may also be other information indicative of a communication usage pattern of the UE 121. Additionally, or alternatively, the subscriber data may comprise an identification of the UE 121. The identification may, for example, be one of: a International Mobile Equipment Identity, IMEI-SV, or Permanent Equipment Identifier, PEI; or International Mobile Subscriber Identity, IMSI, or Subscription

Permanent Identifier, SUPI. Additionally, or alternatively, the subscriber data may comprise an identification of a service application in the UE 121. The identification of a service application may be a Service Application identification, such as, for example, an Application Identity or Application Uniform Resource Locator, URL. Additionally, or alternatively, the subscriber data may comprise an Access Point Name, APN, or a Data Network Name, DNN, associated with the user plane connection 131. Additionally, or alternatively, the subscriber data may comprise a network slice information associated with the user plane connection 131. Here, the network slice information may, for example, be one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID. This means that the subscriber data may may comprise many different types of indicators indicating to the SMF 205 that it should trigger an additional routing of user plane data traffic of the user plane connection

131 in a corresponding UPF 201.

Action 602. After receiving the subscriber data in Action 601 , the SMF 205 determines, based on the received subscriber data, that user plane data traffic of the user plane connection 131 is to be additionally routed via a user plane data traffic connection

132 to a Network Data Analysis, NWDAF 202. This means that the SMF 205 decide to trigger an additional routing of user plane data traffic of the user plane connection 131 in a corresponding UPF 201 based on subscriber data of the user plane connection 131. In some embodiments, the SMF 205 may further obtain policy information, based on the received subscriber data in Action 601 , from a Policy Control Function, PCF 204, also indicating that user plane data traffic of the user plane connection 131 is to be additionally routed via a user plane data traffic connection 132 to the NWDAF 202. This means that the SMF 205 may decide to trigger an additional routing of user plane data traffic of the user plane connection 131 in a corresponding UPF 201 also based on policy rules and information of the user plane connection 131 comprised in the PCF 204.

Action 603. After the determination in Action 603, the SMF 205 transmits to a User Plane Function, UPF 201 , information indicating that the user plane data traffic being routed by the UPF 201 in the user plane connection 131 is to be additionally routed via the user plane data traffic connection 132 to the NWDAF 202. This means that the SMF 205 provide instructions to the UPF 201 to start additionally route the user plane data traffic of the user plane connection 131 via a user plane data traffic connection 132 to the NWDAF 202.

In some embodiments, the transmitted information may comprise a dedicated usage type indicator of the UE 121. Here, the dedicated usage type indicator may, for example, be a UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01. However, the dedicated usage type indicator may also be other information indicative of a communication usage pattern of the UE 121. Additionally, or alternatively, the transmitted information may comprise an identification of the UE 121. The identification may, for example, be one of: a International Mobile Equipment Identity, IMEI-SV, or Permanent Equipment Identifier, PEI; or International Mobile Subscriber Identity, I MSI , or Subscription Permanent Identifier, SUPI. Additionally, or alternatively, the transmitted information may comprise an identification of a service application in the UE 121. The identification of a service application may be a Service Application identification, such as, for example, an Application Identity or Application Uniform Resource Locator, URL. Additionally, or alternatively, the transmitted information may comprise an Access Point Name, APN, or a Data Network Name, DNN, associated with the user plane connection 131. Additionally, or alternatively, the transmitted information may comprise a network slice information associated with the user plane connection 131. Here, the network slice information may, for example, be one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID. Additionally, or alternatively, the transmitted information may comprise policy information set in the Policy Control Function, PCF 204, in the system 200 associated with the user plane connection 131. In some embodiments, the transmitted information comprise tunneling information in order to establish the user plane data traffic connection 132 via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12. In order to illustrate how the above-mentioned embodiments may be implemented and work together for a specific technical realization, a use case example will now be described. This use case example may be applied for detection and pattern learning of user plane data traffic related to vehicles.

For example, the UE 121 may transmit snapshots of vehicular traffic video images in data packets over the user plane connection 131 in the system 200. The core network, i.e. the NFs, of the system 200 may then identify the UE 121 , e.g. as a‘Delay Tolerant MTC’ or‘Video MTC’. This information may then be transmitted to the SMF 205 in a UE_Usage_Type parameter. For example, the subscriber data obtained from the UDM 107 may comprise the UE_Usage_Type parameter, which may comprise a value indicating that the user plane data traffic from the UE 121 is classified as MTC. Based on this information, the SMF 205 may determine that this MTC related user plane data traffic is in need of being analysed. Thus, the SMF 205 may transmit an initiate a message towards the UPF 201 to fork out, i.e. duplicate and divert, the user plane data traffic towards the NWDAF 202. According to one example, this message may be realized as a N4 interface Session Modification request message comprising an additional parameter, such as, e.g. an‘lnitiate_Traffic_Analysis’ parameter indicating‘Yes’. Upon receiving this message, the UPF 201 may initiate the user plane data traffic connection 132 towards NWDAF 202 and start additionally route the user plane data traffic of the user plane connection 131 onto the user plane data traffic connection 132. This user plane data traffic may comprise, for example, images of a vehicular traffic streaming video snapshot. These images may thus be transmitted to NWDAF 202 and from there it may further be transmitted to the MLaaS 203. The MLaaS 203 performs the required learning and pattern analysis based on these images. Thus, the MLaaS 203 may understand and classify the data content of the user plane data traffic of the user plane connection 131 as, for example, images of a vehicle traffic situation that show a LOW, MEDIUM, or HIGH ongoing vehicular traffic. Hence, the MLaaS 203 may return a parameter Traffic_Density’ comprising a value indicating‘HIGH’ back to the NWDAF 202. In turn, the NWDAF 202 may send this additional customized parameter along with network slice specific analytic information, in a message to the PCF 204. Upon receiving the parameter Traffic_Density’ comprising a value indicating‘HIGH’, the PCF 204 may apply policy rule which increased the QoS for the PDU session, i.e. for the user plane data traffic of the user plane connection 131. If required, PCF 204 may inform other NFs to stabilize and increase the network slice resources in the system 200 for the PDU session. Also, the PCF 204 may then also inform UPF 201 of the policy rule applied for higher QoS. It should be noted that the different session messages parameters exemplified above may be different depending on the loT use case.

From the use case example above, it may be seen how the nature of the data content of the user plane data traffic in the user plane connection 131 may be analysed to obtain the context of the data content. Other use cases may also be conceived, such as, for example:

any video or audio data content viewed over social media may be learned based on its context, such as, political, scientific, industrial featured, etc.;

public street surveillance video analysis whether the footage consists of vehicular traffic, crowd density, etc;

a temperature threshold between a certain range of degrees may, for example, be given a higher QoS and thus charged more for; or

temperature thresholds sent by an industrial equipment sensors for pattern learning and analytics and policy decisions accordingly applied;

agriculture crop produce monitoring sensor information, such as, e.g. texture, size, color, etc. may be charged lower until it is ready to harvest.

This illustrated that the pattern analysis and machine learning of the MLaaS 203 may be realized in the system 200 through the use of the extended functionality of the NWDAF 202 in order to not significantly affect the regular operations of the system 200. This also means that the development of the pattern analysis and machine learning methodology and algorithms may be kept separate from the core network of the system 200. This leaves a minimal impact on the NFs from the processing and computing resource load of the pattern analysis and machine learning methodology and algorithms of the MLaaS 203, which may be considerably large. Another advantage of the

embodiments described herein is that an operator of the system 200 may monetize the use of these embodiments in the system 200 with their introduction of context-based charging and policy decisions. For example, a desired pattern analysis and learning of specific user plane data traffic may be customized for each customer to accommodate different loT use cases. A further advantage of the embodiments described herein is that the need to get similar information from external parties is limited. Fig. 7 shows a signalling diagram depicting embodiments of a method in the UPF 201 , the NWDAF 202, the PCF 204 and the SMF 205.

Action 701. The UE 121 may initiate a PDU session establishment or modification procedure by the transmission of a PDU Session Establishment or Modification Request message comprising a PDU session ID from the UE 121 to the AMF 101.

Action 702. In response, the AMF 101 may send a Session Modification-Non- Access Stratum, SM-NAS, message to the SMF 205. This may comprise a SM request comprising a PDU session Modification Request. Depending on the access type, e.g. if the UE 121 was in CN-IDLE mode, this SM-NAS message is may be preceded by a Service Request procedure from AMF 101 to SMF 205.

Action 703. Upon, for example, making a policy decision or upon receiving a request from an AF 104, the PCF 204 may initiate a PDU-CAN Session Modification procedure between the PCF 204 and the SMF 205.

Action 704. The SMF 205 may obtain an Insert Subscriber Data message, which may comprise a Subscriber Permanent Identity and Subscription Data, from the UDM 107. This message may here be modified to comprise additional information, for example, at least one user plane data traffic characteristic, such as, e.g. a dedicated usage type indicator, e.g. a UE_Usage_Type information. This UE_Usage_Type information classifies whether the UE 121 is a loT or non-loT device.

Action 705. The SMF 205 may then update the Subscription Data in the UDM 107 and acknowledge the obtained Insert Subscriber Data message by returning an Insert Subscriber Data Ack message, comprising the Subscriber Permanent Identity, to the UDM 107.

Action 706. The SMF 205 may decide to modify the QoS of the PDU session for the UE 121.

Action 707. The SMF 205 may then interact with the PCF 204 in order to retrieve policy rules or information from the PCF 204. This may be performed using a PDU CAN Session Modification procedure.

Action 708. The SMF 205 may then initiate an N4 Session Establishment/ Modification procedure with the UPF 201 in order to send the GTP tunnelling information for establishing the user plane data traffic connection 132 from the UPF 201 towards the NWDAF 202. This means that the SMF 205 may also transmit a message, e.g. a N4 Session Establishment/ Modification Request, which comprises the UE_Usage_Type information that will trigger the additional routing of the user plane data traffic of the user plane connection 131 in the UPF 201 onto the user plane data traffic connection 132 towards the NWDAF 202.

Action 709. In response, the UPF 201 may provide a N4 Session

Establishment/Modification Response to the SMF 205.

Action 710. The UPF 201 may then additionally route user plane data traffic of the user plane connection 131 , which in this case may be MTC UE User plane data traffic, over an X3 interface towards the NWDAF 202. In some cases, the UPF 201 may filter the user plane data traffic using DPI techniques and only send required information, or relevant data packets , for pattern analysis and learning to the NWDA 202. The NWDAF 202 may transmit the received user plane data traffic towards a MLaaS node 203. After the pattern analysis and machine learning is performed by the MLaaS node 203, the MLaaS node 203 may return an output of the learning and pattern analysis in the form of one or more parameters, or parametrized weighted output, to the NWDAF 202.

Action 711. In response, the NWDAF 202 will send these one or more

parameters, or parametrized weighted output, to the PCF 204. This one or more parameters, or parametrized weighted output, may also be sent along with Network Slice specific analytic information to PCF 204. The PCF 204 may then use the one or more parameters, or parametrized weighted output, and any additional information from the NWDAF 202, for applying the relevant policy rule and decisions based on the one or more parameters, or parametrized weighted output, and/or any additional information.

Fig. 8 shows a signalling diagram of a UE-requested PDU Session Establishment for non-roaming and roaming with local breakout according to Figure 4.3.2.2.1-1 in the standard 3GPP TS 23.502, version 2.0.0, 2017-12. This signalling procedure assumes that the UE 121 has already registered on the AMF 101. Thus, unless the UE 121 is Emergency registered, the AMF 101 has already retrieved the subscription data for the user plane connection 131 from the UDM 107. According to some embodiments herein, some modifications may be implemented in this signalling procedure as described below:

In stage 4, the subscription data may further comprise a dedicated usage type indicator of the UE 121 , such as, e.g. a UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01.

In stage 9, the PCF 204 may also provide forwarding rules indicating that the data packets of the user plane data traffic in the user plane connection 131 are to be forked to a NWDAF 202, or a separate UPF, for example, controlled by the NWDA 202. In stage 16a, if the UE_Usage_Type is one of a defined set of UE_Usage_Types which are to be analysed by NWDAF 202, or PCF 204 provides applicable data packet forwarding rules, then the SMF 205 may include forwarding rules in the N4 Session Modification procedure, such that the UPF 201 additionally forwards the user plane data traffic of the user plane connections 131 towards the NWDAF 202 or separate UPF.

As previously described, according to some embodiments, the transmission of the determined at least one user plane data traffic characteristic to a UDM/UDR function 107 may be performed by the NWDAF 202 via a Network Exposure Function, NEF. Fig. 9 shows a signalling diagram describing these embodiments of the method in the NWDAF 202 in more detail.

Action 901. The NWDAF 202 provides the determined at least one user plane data traffic characteristic, i.e. the one or more parameters or parametrized weighted output of the MLaaS 203, to the NEF 910. This update of the NEF 910 may be performed via a Nnef_ParameterProvision_Update Request.

Action 902. Here, if the NWDAF 202 is authorised by the NEF 910 to provide the determined at least one user plane data traffic characteristic, the NEF 910 may request to update and store the determined at least one user plane data traffic characteristic as part of the subscriber data in the UDM 107 via Update Request message. This message may comprise the determined at least one user plane data traffic characteristic and NEF reference ID. However, if the NWDAF 202 is not authorised to provide determined at least one user plane data traffic characteristic, then the NEF 910 may continue to Action 804 and indicate the reason for the failure in a Nnef_ParameterProvision_Update response to the NWDAF 202.

Action 903. The UDM 107 may then store the determined at least one user plane data traffic characteristic as part of the subscription data, e.g. in a UDR, and respond with an update response message back to the NEF 910. For example, the determined at least one user plane data traffic characteristic may be an updated UE_Usage_Type, wherein the pattern analysis and machine learning in the MLaaS 203 shows that the

communication pattern of the UE 121 has changed such that the UE 121 should belong to a new UE_Usage_Type.

Action 904. The NEF 910 responds to the request from the NWDAF 202 with Nnef_ParameterProvision_Update response. If the procedure failed, a cause value may be comprised therein to indicate the reason for the failure. Action 905. The UDM 107 may notify the related NF, such as, e.g. the AMF 101 or SMF 202 of the updated subscriber data, e.g. via a Nudm_SDM_UpdateNotification Notify message. Here, when the related NF is the AMF 101 , then the determined at least one user plane data traffic characteristic may be e.g. Expected UE Behaviour parameters. The AMF 101 may then use the Expected UE Behaviour parameters as described, for example, in the standard 3GPP TS 23.501 , version 15.0.0., 2017-12, clause 5.20.

To perform the method actions in the User Plane Function, UPF 201 , for routing user plane data traffic in a system 200, the UPF 201 may comprise the following arrangement depicted in Fig 10. Fig 10 shows a schematic block diagram of

embodiments of a UPF 201.

The UPF 201 may comprise processing circuitry 1010 and a memory 1020. The UPF 201 and/or the processing circuitry 1010 may also comprise a receiving module 1011 and a transmitting module 1012. The receiving module 101 1 and the transmitting module 1012 may also form part of a single transceiver. It should also be noted that some or all of the functionality described in the embodiments above as being performed by the UPF 201 may be provided by the processing circuitry 1010 executing instructions stored on a computer-readable medium, such as, e.g. the memory 1020 shown in Fig. 10.

Alternative embodiments of the UPF 201 may comprise additional components, such as, for example, a routing module 1013, which may be responsible for providing its respective functionality necessary to support the embodiments described herein.

The UPF 201 or processing circuitry 1010 is configured to, or may comprise an receiving module 1011 configured to, receive information indicating that user plane data traffic being routed by the UPF 201 in a user plane connection 131 established for a UE 121 is to be additionally routed via a user plane data traffic connection 132 to a Network Data Analysis, NWDA, function 202. Also, the UPF 201 or processing circuitry 1010 is configured to, or may comprise a routing module 1013 configured to, route user plane data traffic in the user plane connection 131 additionally towards the NWDAF 202 via the user plane data traffic connection 132.

In some embodiments, the UPF 201 or processing circuitry 1010 may be configured to, or may comprise the routing module 1013 configured to, duplicate the user plane data traffic in the user plane connection 131 , and output the duplicated user plane data traffic via the user plane data traffic connection 132 to the NWDAF 202. In some embodiments, the user plane data traffic connection 132 may be established via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12. In some embodiments, the received information may comprises one or more of: a dedicated usage type indicator of the UE 121 , wherein the dedicated usage type indicator is UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01 , or other information indicative of a communication usage pattern of the UE 121 ; an identification of the UE 121 , wherein the identification is one of a IMEI-SV, I MSI , PEI, or SUPI; an identification of a service application in the UE 121 , wherein the identification is an Application ID or Application URL; an Access Point Name, APN, or Data Network Name, DNN, associated with the user plane connection 131 ; a network slice information associated with the user plane connection 131 , wherein the network slice information is one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID; and policy information set in a Policy Control Function, PCF 204, in the system 200 associated with the user plane connection 131. In some embodiments, the UPF 201 or processing circuitry 1010 may configured to, or may comprise an receiving module 1011 configured to, receive the information from a Session Management Function, SMF 205 in a Session Establishment or Modification request via an N4 interface.

To perform the method actions in the Network Data Analysis Function, NWDAF 202, for determining information associated with a user plane connection 131 established for a UE 121 in a system 200, the NWDAF 202 may comprise the following arrangement depicted in Fig 11. Fig 1 1 shows a schematic block diagram of embodiments of a NWDAF 202.

The NWDAF 202 may comprise processing circuitry 1110 and a memory 1120. The NWDAF 202 and/or the processing circuitry 11 10 may also comprise a receiving module 1111 and a transmitting module 1112. The receiving module 1 11 1 and the transmitting module 1 112 may also form part of a single transceiver. It should also be noted that some or all of the functionality described in the embodiments above as being performed by the NWDAF 202 may be provided by the processing circuitry 1 110 executing instructions stored on a computer-readable medium, such as, e.g. the memory 1 120 shown in Fig. 11. Alternative embodiments of the NWDAF 202 may comprise additional components, such as, for example, a determining module 1113, which may be responsible for providing its respective functionality necessary to support the embodiments described herein.

The NWDAF 202 or processing circuitry 1110 is configured to, or may comprise an receiving module 11 11 configured to, receive user plane data traffic associated with a user plane connection 131 established for a user equipment, UE 121 , in the system 200 via a user plane data traffic connection 132 from a User Plane Function, UPF 201. Also, the NWDAF 202 or processing circuitry 1 110 is configured to, or may comprise a determining module 11 13 configured to, determine at least one user plane data traffic characteristic based on the user plane data traffic. Further, the NWDAF 202 or processing circuitry 11 10 is configured to, or may comprise a transmitting module 1 112 configured to, transmit the determined at least one user plane data traffic characteristic to a Policy Control Function, PCF 204, and/or to a User Data Management/Repository, UDM/UDR, function 107 in the system 200.

In some embodiments, the NWDAF 202 or processing circuitry 11 10 may configured to, or may comprise an transmitting module 1 112 configured to, transmit the received user plane data traffic to a Machine Learning as a Service, MLaaS, function 203. Here, the NWDAF 202 or processing circuitry 1 110 may configured to, or may comprise an receiving module 1 11 1 configured to, in response, receive at least one user plane data traffic characteristic based on the transmitted user plane data traffic. In some

embodiments, the at least one user plane data traffic characteristic comprise at least one output parameter of the MLaaS function 203 configured for user plane data traffic. Also, in some embodiments, the at least one user plane data traffic characteristic comprise at least one output parameter associated with a communication pattern, wherein the communication pattern is defined in 3GPP TS 23.682, version 15.3.0, 2017-12 or 3GPP TS 23.401 , version 15.2.0, 2017-12, or an Expected UE behaviour, wherein the Expected UE behaviour is defined in 3GPP TS 23.501 , version 15.0.0, 2017-12, section 5.4.6.2, or 3GPP TS 23.502, version 15.0.0, 2017-12, section 4.15.6.3. Further, in some

embodiments, the at least one user plane data traffic characteristic comprise network slice specific information associated with the user plane data traffic. In some

embodiments, the NWDAF 202 or processing circuitry 11 10 may configured to, or may comprise an transmitting module 11 12 configured to, transmit the determined at least one user plane data traffic characteristic to a UDM/UDR function 107 via a Network Exposure Function, NEF.

To perform the method actions in the Policy Control Function, PCF 204, for adapting policy information for a user plane connection 131 established for a UE 121 in a system 200, the PCF 204 may comprise the following arrangement depicted in Fig 12. Fig 12 shows a schematic block diagram of embodiments of a PCF 204. The PCF 204 may comprise processing circuitry 1210 and a memory 1220. The PCF 204 and/or the processing circuitry 1210 may also comprise a receiving module 1211 and a transmitting module 1212. The receiving module 121 1 and the transmitting module 1212 may also form part of a single transceiver. It should also be noted that some or all of the functionality described in the embodiments above as being performed by the PCF 204 may be provided by the processing circuitry 1210 executing instructions stored on a computer-readable medium, such as, e.g. the memory 1220 shown in Fig. 12.

Alternative embodiments of the PCF 204 may comprise additional components, such as, for example, a adapting module 1213, which may be responsible for providing its respective functionality necessary to support the embodiments described herein.

The PCF 204 or processing circuitry 1210 is configured to, or may comprise an receiving module 1211 configured to, receive at least one user plane data traffic characteristic from the NWDAF 202 associated with the user plane connection 131 , wherein the at least one user plane data traffic characteristic is based on the user plane data traffic of the user plane connection 131 that is additionally routed by the UPF 201 via a user plane data traffic connection 132 to the NWDAF 202. Also, the PCF 204 or processing circuitry 1210 is configured to, or may comprise an adapting module 1213 configured to, adapt, if needed, policy information for the user plane connection 131 based on the received at least one user plane data traffic characteristic.

In some embodiments, the PCF 204 or processing circuitry 1210 may be configured to, or may comprise an adapting module 1211 configured to, adapt policy information for other user plane connections based on the received at least one user plane data traffic characteristic associated with the user plane connection 131.

To perform the method actions in the Session Management Function, SMF 205, for enabling routing of user plane data traffic in a system 200, the SMF 205 may comprise the following arrangement depicted in Fig 13. Fig 13 shows a schematic block diagram of embodiments of a SMF 205.

The SMF 205 may comprise processing circuitry 1310 and a memory 1320.

The SMF 205 and/or the processing circuitry 1310 may also comprise a receiving module 1311 and a transmitting module 1312. The receiving module 1311 and the transmitting module 1312 may also form part of a single transceiver. It should also be noted that some or all of the functionality described in the embodiments above as being performed by the SMF 205 may be provided by the processing circuitry 1310 executing instructions stored on a computer-readable medium, such as, e.g. the memory 1320 shown in Fig. 13. Alternative embodiments of the SMF 205 may comprise additional components, such as, for example, an obtaining module 1313 and a determining module 1314, which may be responsible for providing its respective functionality necessary to support the embodiments described herein.

The SMF 205 or processing circuitry 1310 is configured to, or may comprise an obtaining module 1313 configured to, obtain subscriber data associated with a user plane connection 131 established for a UE 121 in the system 200. Also, the SMF 205 or processing circuitry 1310 is configured to, or may comprise an determining module 1314 configured to, determine, based on the received subscriber data, that user plane data traffic of the user plane connection 131 is to be additionally routed via a user plane data traffic connection 132 to a Network Data Analysis Function, NWDAF 202. Further, the SMF 205 or processing circuitry 1310 is configured to, or may comprise an transmitting module 1312 configured to, transmit, to a User Plane Function, UPF 201 , information indicating that the user plane data traffic being routed by the UPF 201 in the user plane connection 131 is to be additionally routed via the user plane data traffic connection 132 to the NWDAF 202.

In some embodiments, the subscriber data comprises one or more of: a dedicated usage type indicator of the UE 121 , wherein the dedicated usage type indicator is

UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01 , or other information indicative of a communication usage pattern of the UE 121 ; an identification of the UE 121 , wherein the identification is one of a IMEI-SV, I MSI , PEI, or SUPI; an identification of a service application in the UE 121 , wherein the identification is an Application ID or Application URL; an Access Point Name, APN, or Data Network Name, DNN, associated with the user plane connection 131 ; and a network slice information associated with the user plane connection 131 , wherein the network slice information is one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID.

Further, the SMF 205 or processing circuitry 1310 may be configured to, or may comprise an obtaining module 1313 configured to, obtain policy information, based on the received subscriber data, from a Policy Control Function, PCF 204, indicating that user plane data traffic of the user plane connection 131 is to be additionally routed via a user plane data traffic connection 132 to the NWDAF 202. In some embodiments, the transmitted information comprises one or more of: a dedicated usage type indicator of the UE 121 , wherein the dedicated usage type indicator is UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01 , or other information indicative of a communication usage pattern of the UE 121 ; an identification of the UE 121 , wherein the identification is one of a IMEI-SV, I MSI, PEI, or SUPI; an identification of a service application in the UE 121 , wherein the identification is an Application ID or Application URL; an Access Point Name, APN, or Data Network Name, DNN, associated with the user plane connection 131 ; a network slice information associated with the user plane connection 131 , wherein the network slice information is one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID; and policy information set in the PCF 204 associated with the user plane connection 131. In some embodiments, the transmitted information comprise tunneling information in order to establish the user plane data traffic connection 132 via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12.

Furthermore, the embodiments for enabling routing of user plane data traffic, for routing user plane data traffic in a communications network, for determining information associated with a user plane connection, and for adapting policy information for a user plane connection described above may be implemented through one or more processing circuitries, such as, e.g. the processing circuitry 1010 in the UPF 201 depicted in Fig. 10, the processing circuitry 11 10 in the NWDAF 202 depicted in Fig. 11 , the processing circuitry 1210 in the PCF 204 depicted in Fig. 11 , or the processing circuitry 1310 in the SMF 205 depicted in Fig. 13, together with computer program code for performing the functions and actions of the embodiments herein. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code or code means for performing the embodiments herein when being loaded into one or more processing circuitries, e.g. the processing circuitries 1010, 11 10, 1210, 1310 in the UPF 201 , NWDAF 202, PCF 204 and SMF 205, respectively. The computer program code may e.g. be provided as pure program code in the UPF 201 , NWDAF 202, PCF 204 and SMF 205, respectively, or on a server and downloaded to the UPF 201 , NWDAF 202, PCF 204 and SMF 205, respectively. Thus, it should be noted that the modules of the UPF 201 , NWDAF 202, PCF 204 and SMF 205, respectively, may in some embodiments be implemented as computer programs stored in memory (e.g. the memory modules 1020, 1 120, 1220, 1320) for execution by one or more processing circuitries or processing modules (e.g. the processing circuitries 1010, 1 110, 1210, 1310).

Those skilled in the art will also appreciate that the processing circuitries 1010, 1 110, 1210, 1310 and the memories 1020, 1120, 1220, 1320 described above may refer to a combination of analog and digital circuits, and/or one or more processors configured with software and/or firmware, e.g. stored in a memory, that when executed by the one or more processors such as the processing circuitries 1010, 11 10, 1210, 1310 perform as described above. One or more of these processing circuitries, as well as the other digital hardware, may be comprised in a single application-specific integrated circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a system-on-a- chip (SoC).

The description of the example embodiments provided herein have been presented for purposes of illustration. The description is not intended to be exhaustive or to limit example embodiments to the precise form disclosed, and modifications and variations are possible in light of the above teachings or may be acquired from practice of various alternatives to the provided embodiments. The examples discussed herein were chosen and described in order to explain the principles and the nature of various example embodiments and its practical application to enable one skilled in the art to utilize the example embodiments in various manners and with various modifications as are suited to the particular use contemplated. The features of the embodiments described herein may be combined in all possible combinations of methods, apparatus, modules, systems, and computer program products. It should be appreciated that the example embodiments presented herein may be practiced in any combination with each other.

It should be noted that the word“comprising” does not necessarily exclude the presence of other elements or steps than those listed and the words“a” or“an” preceding an element do not exclude the presence of a plurality of such elements. It should further be noted that any reference signs do not limit the scope of the claims, that the example embodiments may be implemented at least in part by means of both hardware and software, and that several“means”,“units” or“devices” may be represented by the same item of hardware.

It should also be noted that the various example embodiments described herein are described in the general context of method steps or processes, which may be implemented in one aspect by a computer program product, embodied in a computer- readable medium, including computer-executable instructions, such as program code, executed by computers in networked environments. A computer-readable medium may include removable and non-removable storage devices including, but not limited to, Read Only Memory (ROM), Random Access Memory (RAM), compact discs (CDs), digital versatile discs (DVD), etc. Generally, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of program code for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps or processes.

The embodiments herein are not limited to the above described preferred embodiments. Various alternatives, modifications and equivalents may be used.

Therefore, the above embodiments should not be construed as limiting.

Abbreviations

APN Access Point Name

AF Application Function

AUSF Authentication Server Function

DN Data Network

DNN Data Network Name

DPI Deep Packet Inspection

EPC Evolved Packet Core

GPRS General Packet Radio Services

GTP GPRS Tunnelling Protocol

IMSI International Mobile Subscriber Identity

IMEI-SV International Mobile Equipment Identity

HSS Home Subscriber Service

LI Lawful Interception

MME Mobility Management Entity

NAS Non-Access Stratum

NEF Network Exposure Function

NF Network Function

NRF NF Repository Function

NSSF Network Slice Selection Function

NWDAF Network Data Analysis Function

PCF Policy Control Function

PEI Permanent Equipment Identifier

PGW PDN Gateway

PDN Packet Data Network

RAN Radio Access Network

SGW Serving Gateway

SMF Session Management Function

SCEF Service Capability Exposure Function

SUPI Subscription Permanent Identifier

UDM User Data Management

UPF User Plane Function

Claims

1. A method performed by a User Plane Function, UPF (201 ), for routing user plane data traffic in a system (200), the method comprising

receiving (301 ) information indicating that user plane data traffic being routed by the UPF (201 ) in a user plane connection (131 ) established for a user equipment, UE, (121 ) is to be additionally routed via a user plane data traffic connection (132) to a Network Data Analysis, NWDA, function (202); and

routing (302) user plane data traffic in the user plane connection (131 ) additionally towards the NWDAF (202) via the user plane data traffic connection (132).

2. The method according to claim 1 , wherein the routing (302) comprise duplicating the user plane data traffic in the user plane connection (131 ), and outputting the duplicated user plane data traffic via the user plane data traffic connection (132) to the NWDAF (202).

3. The method according to claim 1 or 2, wherein the user plane data traffic

connection (132) is established via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12.

4. The method according to any of claims 1-3, wherein the received information comprises one or more of:

a dedicated usage type indicator of the UE (121 ), wherein the dedicated usage type indicator is UE_Usage_Type information as defined in 3GPP TS 23.401 , version 15.2.0, 2018-01 , or other information indicative of a communication usage pattern of the UE (121 );

an identification of the UE (121 ), wherein the identification is one of a IMEI- SV, I MSI , PEI, or SUPI;

an identification of a service application in the UE(121 ), wherein the identification is an Application ID or Application URL;

an Access Point Name, APN, or Data Network Name, DNN, associated with the user plane connection (131 );

a network slice information associated with the user plane connection (131 ), wherein the network slice information is one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID; and

policy information set in a Policy Control Function, PCF (204) in the system (200) associated with the user plane connection (131 ).

5. The method according to any of claims 1-4, wherein the information is received from a Session Management Function, SMF (205) in a Session Establishment or Modification request via an N4 interface. 6. A User Plane Function, UPF (201 ), for routing user plane data traffic in a system

(200), the UPF (201 ) being configured to

receive information indicating that user plane data traffic being routed by the UPF (201 ) in a user plane connection (131 ) established for a user equipment, UE, (121 ) is to be additionally routed via a user plane data traffic connection (132) to a Network Data Analysis, NWDA, function (202), and route user plane data traffic in the user plane connection (131 ) additionally towards the NWDAF (202) via the user plane data traffic connection (132).

7. The UPF (201 ) according to claim 6, further configured to duplicate the user plane data traffic in the user plane connection (131 ), and output the duplicated user plane data traffic via the user plane data traffic connection (132) to the NWDAF (202).

8. The UPF (201 ) according to claim 6 or 7, wherein the user plane data traffic

9. The UPF (201 ) according to any of claims 6-8, wherein the received information comprises one or more of:

an identification of the UE (121 ), wherein the identification is one of a IMEI- SV, I MSI , PEI, or SUPI; an identification of a service application in the UE(121 ), wherein the identification is an Application ID or Application URL;

10. The UPF (201 ) according to any of claims 6-9, further configured to receive the information from a Session Management Function, SMF (205) in a Session Establishment or Modification request via an N4 interface.

1 1. A method performed by a Network Data Analysis Function, NWDAF (202), in a system (200), the method comprising

receiving (401 ) user plane data traffic associated with a user plane connection (131 ) established for a user equipment, UE (121 ), in the system (200) via a user plane data traffic connection (132) from a User Plane Function, UPF (201 );

determining (402) at least one user plane data traffic characteristic based on the user plane data traffic; and

transmitting (403) the determined at least one user plane data traffic characteristic to a Policy Control Function, PCF (204), and/or to a User Data Management/Repository, UDM/UDR, function (107) in the system (200).

12. The method according to claim 11 , wherein determining (402) comprises

transmitting the received user plane data traffic to a Machine Learning as a Service, MLaaS, function (203), and in response, receiving at least one user plane data traffic characteristic based on the transmitted user plane data traffic.

13. The method according to claim 12, wherein the at least one user plane data traffic characteristic comprise at least one output parameter of the MLaaS function (203) configured for user plane data traffic.

14. The method according to claim 12 or 13, wherein the at least one user plane data traffic characteristic comprise at least one output parameter associated with a communication pattern, wherein the communication pattern is defined in 3GPP TS 23.682, version 15.3.0, 2017-12 or 3GPP TS 23.401 , version 15.2.0, 2017-12, or an Expected UE behaviour, wherein the Expected UE behaviour is defined in 3GPP TS 23.501 , version 15.0.0, 2017-12, section 5.4.Q.2, or 3GPP TS 23.502, version 15.0.0, 2017-12, section 4.15.6.3.

15. The method according to any of claims 1 1-14, wherein the at least one user plane data traffic characteristic comprise network slice specific information associated with the user plane data traffic.

16. The method according to any of claims 11-15, wherein the transmitting (403) of the determined at least one user plane data traffic characteristic to a UDM/UDR function (107) is performed via a Network Exposure Function, NEF.

17. A Network Data Analysis Function, NWDAF (202), for determining information associated with a user plane connection (131 ) established for a user equipment, UE, (121 ) in a system (200), the NWDAF (202) being configured to

receive user plane data traffic associated with a user plane connection (131 ) established for a user equipment, UE (121 ), in the system (200) via a user plane data traffic connection (132) from a User Plane Function, UPF (201 ), determine at least one user plane data traffic characteristic based on the user plane data traffic, and transmit the determined at least one user plane data traffic

characteristic to a Policy Control Function, PCF (204), and/or to a User Data Management/Repository, UDM/UDR, function (107) in the system (200).

18. The NWDAF (202) according to claim 17, further configured to transmit the

received user plane data traffic to a Machine Learning as a Service, MLaaS, function (203), and, in response, receive at least one user plane data traffic characteristic based on the transmitted user plane data traffic.

19. The NWDAF (202) according to claim 18, wherein the at least one user plane data traffic characteristic comprise at least one output parameter of the MLaaS function (203) configured for user plane data traffic.

20. The NWDAF (202) according to claim 17 or 18, wherein the at least one user plane data traffic characteristic comprise at least one output parameter associated with a communication pattern, wherein the communication pattern is defined in 3GPP TS 23.682, version 15.3.0, 2017-12 or 3GPP TS 23.401 , version 15.2.0, 2017-12, or an Expected UE behaviour, wherein the Expected UE behaviour is defined in 3GPP TS 23.501 , version 15.0.0, 2017-12, section 5.4.6.2, or 3GPP TS 23.502, version 15.0.0, 2017-12, section 4.15.6.3.

21. The NWDAF (202) according to any of claims 16-20, wherein the at least one user plane data traffic characteristic comprise network slice specific information associated with the user plane data traffic.

22. The NWDAF (202) according to any of claims 16-21 , further configured to transmit the determined at least one user plane data traffic characteristic to a UDM/UDR function (107) via a Network Exposure Function, NEF.

23. A method performed by a Policy Control Function, PCF (204), for adapting policy information for a user plane connection (131 ) established for a user equipment, UE, (121 ) in a system (200), the method comprising

receiving (501 ) at least one user plane data traffic characteristic from the NWDAF (202) associated with the user plane connection (131 ), wherein the at least one user plane data traffic characteristic is based on the user plane data traffic of the user plane connection (131 ) that is additionally routed by the UPF (201 ) via a user plane data traffic connection (132) to the NWDAF (202); and

adapting (502), if needed, policy information for the user plane connection (131 ) based on the received at least one user plane data traffic characteristic.

24. The method according to claim 23, wherein the adapting (502) further comprises adapting policy information for other user plane connections based on the received at least one user plane data traffic characteristic associated with the user plane connection (131 ).

25. A Policy Control Function, PCF (204), for adapting policy information for a user plane connection (131 ) established for a user equipment, UE, (121 ) in a system (200), the PCF (204) being configured to

receive at least one user plane data traffic characteristic from the NWDAF (202) associated with the user plane connection (131 ), wherein the at least one user plane data traffic characteristic is based on the user plane data traffic of the user plane connection (131 ) that is additionally routed by the UPF (201 ) via a user plane data traffic connection (132) to the NWDAF (202), and adapt, if needed, policy information for the user plane connection (131 ) based on the received at least one user plane data traffic characteristic.

26. The PCF (204) according to claim 25, further configured to adapt policy

information for other user plane connections based on the received at least one user plane data traffic characteristic associated with the user plane connection (131 ).

27. A method performed by a Session Management Function, SMF (205), for

enabling routing of user plane data traffic in a system (200), the method comprising

obtaining (601 ) subscriber data associated with a user plane connection (131 ) established for a user equipment, UE (121 ), in the system (200);

determining (602), based on the received subscriber data, that user plane data traffic of the user plane connection (131 ) is to be additionally routed via a user plane data traffic connection (132) to a Network Data Analysis Function, NWDAF (202); and

transmitting (603), to a User Plane Function, UPF (201 ), information indicating that the user plane data traffic being routed by the UPF (201 ) in the user plane connection (131 ) is to be additionally routed via the user plane data traffic connection (132) to the NWDAF (202).

28. The method according to claim 27, wherein the subscriber data comprises one or more of:

a dedicated usage type indicator of the UE (121 ), wherein the dedicated usage type indicator is UE_Usage_Type information as defined in 3GPP TS

23.401 , version 15.2.0, 2018-01 , or other information indicative of a communication usage pattern of the UE (121 );

an identification of the UE(121 ), wherein the identification is one of a IMEI- SV, I MSI , PEI, or SUPI;

an Access Point Name, APN, or Data Network Name, DNN, associated with the user plane connection (131 ); and

a network slice information associated with the user plane connection (131 ), wherein the network slice information is one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID.

29. The method according to claim 27 or 28, wherein the determining (602) further comprise obtaining policy information, based on the received subscriber data, from a Policy Control Function, PCF (204), indicating that user plane data traffic of the user plane connection (131 ) is to be additionally routed via a user plane data traffic connection (132) to the NWDAF (202).

30. The method according to any of claims 27-29, wherein the transmitted information comprises one or more of:

an identification of a service application in the UE (121 ), wherein the identification is an Application ID or Application URL;

a network slice information associated with the user plane connection (131 ), wherein the network slice information is one of a Single Network Slice Selection Assistance Information, S-NSSAI, or a Network Slice Instance Identification, NS-ID; and policy information set in the PCF (204) associated with the user plane connection (131 ).

31. The method according to any of claims 27-30, wherein the transmitted information comprise tunneling information in order to establish the user plane data traffic connection (132) via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12.

32. A Session Management Function, SMF (205), for enabling routing of user plane data traffic in a system (200), the SMF (205) being configured to

obtain subscriber data associated with a user plane connection (131 ) established for a user equipment, UE (121 ), in the system (200), determine, based on the received subscriber data, that user plane data traffic of the user plane connection (131 ) is to be additionally routed via a user plane data traffic connection (132) to a Network Data Analysis Function, NWDAF (202), and transmit, to a User Plane Function, UPF (201 ), information indicating that the user plane data traffic being routed by the UPF (201 ) in the user plane connection (131 ) is to be additionally routed via the user plane data traffic connection (132) to the NWDAF (202).

33. The SMF (205) according to claim 32, wherein the subscriber data comprises one or more of:

34. The SMF (205) according to claim 32 or 33, further configured to obtain policy information, based on the received subscriber data, from a Policy Control Function, PCF (204), indicating that user plane data traffic of the user plane connection (131 ) is to be additionally routed via a user plane data traffic connection (132) to the NWDAF (202).

35. The SMF (205) according to any of claims 32-34, wherein the transmitted

information comprises one or more of:

policy information set in the PCF (204) associated with the user plane connection (131 ).

36. The SMF (205) according to any of claims 32-35, wherein the transmitted

information comprise tunneling information in order to establish the user plane data traffic connection (132) via an X3 interface as defined for the LI architecture in 3GPP TS 33.107, version 15.0.0, 2017-12.

37. A system (200) comprising one or more of:

the UPF (201 ) according to any of claims 6-10, the NWDAF (202) according to any of claims 17-22, the PCF (204) according to any of claims 25-26, and

the SMF (205) according to any of claims 32-36; and

wherein the system (200) comprises at least one processing circuitry (1010, 1 110, 1210, 1310) and at least one memory (1020, 1120, 1220, 1320), wherein the at least one memory (1020, 1120, 1220, 1320) is containing instructions executable by the at least one processing circuitry (1010, 11 10, 1210, 1310). 38. A computer program product, comprising instructions which, when executed on at least one processor (1010, 1 110, 1210, 1310), cause the at least one processor (1010, 1 110, 1210, 1310) to carry out the method according to any of claims 1-5, 1 1-16, 23-24 or 27-31. 39. A carrier containing the computer program product according to claim 38, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer- readable storage medium.