WO2023117153A1 - Service-based traffic classification service - Google Patents

Service-based traffic classification service Download PDF

Info

Publication number
WO2023117153A1
WO2023117153A1 PCT/EP2022/058520 EP2022058520W WO2023117153A1 WO 2023117153 A1 WO2023117153 A1 WO 2023117153A1 EP 2022058520 W EP2022058520 W EP 2022058520W WO 2023117153 A1 WO2023117153 A1 WO 2023117153A1
Authority
WO
WIPO (PCT)
Prior art keywords
service
traffic classification
traffic
classification
consumer
Prior art date
Application number
PCT/EP2022/058520
Other languages
French (fr)
Inventor
Miguel Angel PUENTE PESTAÑA
Miguel Angel MUÑOZ DE LA TORRE ALONSO
Original Assignee
Telefonaktiebolaget Lm Ericsson (Publ)
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Telefonaktiebolaget Lm Ericsson (Publ) filed Critical Telefonaktiebolaget Lm Ericsson (Publ)
Publication of WO2023117153A1 publication Critical patent/WO2023117153A1/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
    • H04L41/5051—Service on demand, e.g. definition and deployment of services in real time
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/40—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5058—Service discovery by the service manager

Definitions

  • the present invention generally relates to services in communication networks, and more specifically, the invention relates to service-based traffic classification in communication networks.
  • the detection and classification of applications is done by means of a set of SDF (Service Data Flow) filters, PFD (Packet Flow Descriptor) and/or an application ID.
  • the application is detected at the User Plane using packet header matching.
  • the User Plane performs packet inspection functionality, e.g., in the UPF (User Plane Function), based on matching the user plane traffic with the SDFs or PFDs.
  • the UPF is provisioned with the proper SDFs and/or PFDs of the applications that are to be classified at the establishment of the data session between the User Equipment (UE) and the Data Network (DN), i.e., the PDU (Packet Data Unit) session establishment procedure in 5GC.
  • UE User Equipment
  • DN Data Network
  • the SDFs/PFDs can be also provisioned to the UPF in a parallel procedure, e.g., the PFD management procedures in 5GC.
  • PFD management procedures are typically handled by the SMF (Session Management Function) and can be of a push or pull nature.
  • SMF Session Management Function
  • pull procedures the PFDs for a certain application may be requested by the SMF to the PFDF (PFD Function) and then installed in the UPF by the SMF.
  • the PFDs are provided in a proactive manner to the SMF from the PFDF, e.g., upon a PFD update.
  • the PFDF may be deployed standalone or collocated with the NEF (Network Exposure Function).
  • NEF Network Exposure Function
  • the traffic classification procedure for a certain application is executed according to Packet Detection Rules (PDR) received from the SMF, which include the traffic filter information and an order or precedence of execution.
  • PDR Packet Detection Rules
  • the traffic filter information in the PDRs is set by the SMF based on the PFDs received at the SMF from the PFDF.
  • SMF Session Management Function
  • PCF Policy Control Function
  • PCF installs the PCC rules (with their corresponding precedence) and SMF translates them into PDRs (and associated rules: FARs, QERs, URRs, etc.) which are then installed in the UPF.
  • the FARs, QERs, URRs, etc. define the enforcement actions to be done on the detected application traffic.
  • SPI Shaallow Packet Inspection
  • L3/L4 e.g., IP/TCP
  • DPI Deep Packet Inspection
  • L7 e.g. HTTP
  • HPI Haeuristic Packet Inspection
  • ML Machine Learning
  • the SMF may control the data path of a PDU Session so that the traffic of the PDU Session traverses several UPFs (Uplink Classifier and PDU session anchors 1 and 2 in Figure 2).
  • the UPF that terminates the data path towards the Data Network (DN), referred to as PDU session anchor (PSA), is said to support PDU Session Anchor functionality, i.e., serving as anchor between the PDU session and the DN.
  • PDU Session Anchor supporting a PDU Session provides a different access to the DN(s).
  • the SMF may decide to insert in the data path of a PDU Session an "UL CL" (Uplink classifier, Figure 2).
  • the UL CL is a functionality supported by an UPF that aims at diverting (locally) some traffic matching traffic filters provided by the SMF.
  • the insertion and removal of an UL CL is decided by the SMF and controlled by the SMF using generic N4 and UPF capabilities.
  • the SMF may decide to insert in the data path of a PDU Session a UPF supporting the UL CL functionality during or after the PDU Session Establishment, or to remove from the data path of a PDU Session a UPF supporting the UL CL functionality after the PDU Session Establishment.
  • the SMF may include more than one UPF supporting the UL CL functionality in the data path of a PDU Session.
  • each node requiring traffic classification e.g., the UPF (UL CL, PSA) or the Radio Access Network (RAN) shall embed a module including the traffic classification logic and algorithms, typically a DPI module.
  • All User Plane nodes e.g., all UPFs in the user plane data path and RAN
  • All User Plane nodes shall embed a traffic classification module, which is memory and computing demanding, especially due to the large number of applications in the market that are to be classified, which is also increasing more and more. It hampers having light nodes, e.g., lightweight UPFs such as UL CLs, which require low footprint and high performance.
  • the traffic classification process is executed several times in the different nodes along the path. This impacts performance, latency, energy consumption, etc.
  • the RAN nodes may also require traffic classification functionality. Deploying DPI in RAN adds an additional burden to the problem of having several nodes in the UP path that perform traffic classification processes, adding delay and requiring extra processing resources at RAN.
  • An object of the invention is to enable a service-based traffic classification service in communication networks.
  • a first aspect of the invention relates to a method performed by a traffic classification service for enabling service-based traffic classification in a communication network.
  • the method comprises registering the traffic classification service with a service discovery entity; receiving from a traffic classification consumer a traffic classification request including traffic data to be classified, wherein the traffic classification consumer previously discovered the traffic classification service via the service discovery entity; transmitting to the traffic classification consumer a traffic classification response including the traffic classification of the traffic data.
  • Registering the traffic classification service with the service discovery entity may comprise registering at least one of: a service name associated to the traffic classification service; an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5- tuples, Packet Flow Descriptors, raw packets, or traffic traces; an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • Registering the traffic classification service at the service discovery entity may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
  • the traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
  • the traffic classification of the traffic data may be any one of an application identifier, or an application type.
  • a second aspect of the invention relates to a method performed by a traffic classification consumer for enabling service-based traffic classification in a communication network.
  • the method comprises discovering a traffic classification service via a service discovery entity, wherein the traffic classification service is registered with the service discovery entity; transmitting to the traffic classification service a traffic classification request including traffic data to be classified; receiving from the traffic classification service a traffic classification response including the traffic classification of the traffic data.
  • Discovering the traffic classification service may be based on at least one of: the service name associated to the traffic classification service; the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5- tuples, Packet Flow Descriptors, raw packets, or traffic traces; an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • Discovering the traffic classification service may comprise transmitting a discovery request to the service discovery entity comprising at least one of: the service name associated to the traffic classification service; the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; and receiving a discovery response from the service discovery entity based on the information comprised in the discovery request including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address.
  • the method may further comprise receiving in the discovery response, based on the information comprised in the discovery request, information of a further traffic classification service comprising at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and selecting the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer.
  • the traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
  • the traffic classification of the traffic data may be any one of an application identifier, or an application type.
  • a third aspect of the invention relates to a method performed by a service discovery entity for enabling service-based traffic classification in a communication network.
  • the method comprises registering a traffic classification service; receiving a discovery request from a traffic classification consumer comprising at least one of: the service name associated to the traffic classification service; the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; selecting the traffic classification service based on the information comprised in the discovery request; and transmitting a discovery response to the traffic classification consumer including at least one of the traffic classification service name, the traffic classification service identifier
  • Registering the traffic classification service at the service discovery entity may comprise registering at least one of: a service name associated to the traffic classification service; an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • Registering the traffic classification service at the service discovery entity may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
  • the method may further comprise selecting a further traffic classification service based on the information comprised in the discovery request; and including in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address.
  • aspects of the invention relate to mobile network nodes, particularly a traffic classification service, a traffic classification consumer, and a service discovery entity, each configured to perform the respective methods as described herein.
  • Other aspects of the invention relate to computer program and computer program products.
  • the traffic classification service may be hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity may be a Network Repository Function; and the traffic classification consumer may be a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node.
  • the solution disclosed herein enables offering a traffic classification service in a communications network that can be exposed and/or used by any entity (e.g., any Network Function (NF) or NF service) within the network.
  • NF Network Function
  • the solution disclosed herein enables traffic classification for NIDD (Non-IP Data Delivery).
  • traffic payload is transmitted through the Control Plane (CP) nodes.
  • CP Control Plane
  • TC Control Plane
  • the proposed solution avoids deploying traffic classification modules (e.g., DPI) in the CP nodes requiring TC classification for NIDD.
  • the solution disclosed herein enables having separated and dedicated TC services for specific scenarios, traffic types, etc.
  • TC services per slice type e.g., MBB, ULLC
  • UE type e.g., loT devices
  • traffic class e.g., large/short flows, infrequent data transmissions, Certainly, location (e.g., country, region, ...), etc.
  • location e.g., country, region, ...)
  • the solution disclosed herein enables having separated TC services depending on the TC type performed.
  • Different TC types can be e.g., deterministic (having traffic filters), heuristic, ML-based, etc.
  • the different TC types entail different characteristics.
  • deterministic classification either classifies traffic with 100% accuracy or it cannot classify it at all
  • heuristic classification can classify traffic into application types (e.g., video)
  • ML-based classification has typically lower than 100% accuracy, but it can be used to classify unknown traffic (subject to a certain accuracy level).
  • the solution disclosed herein enables having one traffic classification module that can serve different entities (e.g., User Plane entities) requiring traffic classification. This may help to reduce the delay associated with multiple traffic classifications along the user plane traffic path. It also reduces resources and energy consumption, improving performance and reducing latency.
  • entities e.g., User Plane entities
  • the solution disclosed herein enables to avoid the need of deploying traffic classification modules in all the UP entities (e.g., User Plane Functions, RAN nodes) in the communications network, which enables lightweight UPFs and RAN nodes. It enables for example a light UPF (without a DPI module) which just extracts the 3-tuple (for each flow) and requests to the TC service (which might be deployed at NEF/UDR handling the PFDs for App-IDs, or in another UPF) to identify the App-ID. There is also no need to provision and update the whole set of PFDs from NEF/UDR to every UPF (e.g., through SMF).
  • UP entities e.g., User Plane Functions, RAN nodes
  • FIG. 1 is a networked system in accordance with particular embodiments of the solution described herein;
  • FIG. 2 is a networked system in accordance with particular embodiments of the solution described herein;
  • Figure 3 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
  • Figure 4 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
  • Figure 5 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
  • Figure 6 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
  • Figure 7 is a flowchart illustrating a method performed by a mobile network node according to particular embodiments of the solution described herein;
  • Figure 8 is a flowchart illustrating a method performed by a mobile network node according to particular embodiments of the solution described herein;
  • Figure 9 is a flowchart illustrating a method performed by a mobile network node according to particular embodiments of the solution described herein;
  • FIG. 10 is a block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.
  • Figure 11 is a block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.
  • Figure 12 is a block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.
  • FIG. 1 is an example networked system 100 in accordance with example embodiments of the present disclosure.
  • Figure 1 specifically illustrates User Equipment (UE) 101, which may be in communication with a (Radio) Access Network ((R)AN) 102 and Access and Mobility Management Function (AMF) 106 and User Plane Function (UPF) 103.
  • UE User Equipment
  • R Radio
  • AMF Access and Mobility Management Function
  • UPF User Plane Function
  • the UPF can be of two types: UL CL and PSA.
  • the AMF 106 may, in turn, be in communication with core network services including Session Management Function (SMF) 107 and Policy Control Function (PCF) 111.
  • the core network services may also be in communication with an Application Server/ Application Function (AS/AF) 113.
  • Other networked services also include Network Slice Selection Function (NSSF) 108, Authentication Server Function (AUSF) 105, User Data Management (UDM) 112, Network Exposure Function (NEF) 109, Network Repository Function (NRF) 110, User Data Repository (UDR) 114, Network Data Analytics Function (NWDAF) 115 and Data Network (DN) 104.
  • NSSF Network Slice Selection Function
  • AUSF Authentication Server Function
  • NEF Network Exposure Function
  • NRF Network Repository Function
  • NWDAF Network Data Analytics Function
  • DN Data Network
  • an AMF 106, SMF 107, UPF 103, PCF 111, AUSF 105, NRF 110, UDM 112, NEF 109, AF 113, UDR 114, NWDAF 115, and NSSF 108 are each considered to be an NF.
  • One or more additional instances of the network functions (NF) may be incorporated into the networked system.
  • the solution described herein aims to enable a service-based traffic classification service in communication networks.
  • the proposed solution is based on a Service- Based module for Traffic Classification (TC), also referred to as traffic classification (TC) service, following the Service Based Architecture (SBA) principles as standardized in 3GPP specifications.
  • TC Traffic Classification
  • SBA Service Based Architecture
  • the traffic classification service can be discovered and used by the different entities requiring traffic classification, e.g., RAN (directly or via AMF), UL CL (directly or via SMF) and PSA (directly or via SMF).
  • RAN directly or via AMF
  • UL CL directly or via SMF
  • PSA directly or via SMF
  • CP Control Plane
  • the traffic classification service can be hosted and/or exposed by the entities that have the necessary data to perform traffic classification, e.g., UPF, UDR, NWDAF, etc. It can also be a standalone entity connected to the SBA architecture.
  • the TC service can retrieve Packet Flow Descriptors (PFD) from UDR if needed to properly perform the traffic classification.
  • PFD Packet Flow Descriptors
  • TC-service-class a new "TC-service-class" parameter in the NRF registration information associated to the TC service. This parameter indicates if the TC service is dedicated to a specific scenario.
  • the TC service registers the TC-service-class parameter in the NRF, and NFs can discover the TC service based on this parameter.
  • TC type indicates whether the classification performed in the TC service is deterministic, heuristic, ML-based, etc.
  • This disclosure provides a method for enabling service-based traffic classification in a communication network, the method being performed by a traffic classification service and a traffic classification consumer.
  • the method comprises registering the traffic classification service with a service discovery entity; discovering the traffic classification service by the traffic classification consumer; transmitting from the traffic classification consumer to the traffic classification service a traffic classification request including traffic data to be classified; receiving at the traffic classification consumer from the traffic classification service a traffic classification response including the traffic classification of the traffic data.
  • Registering the traffic classification service at the service discovery entity may comprise registering at least one of: • a service name associated to the traffic classification service;
  • the traffic classification service • an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces;
  • an indication of an association of the traffic classification service particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
  • the traffic classification mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • Registering the traffic classification service at the service discovery entity may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
  • Discovering the traffic classification service by the traffic classification consumer may be based on at least one of:
  • the supported input parameters by the traffic classification service particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces;
  • association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
  • the traffic classification mechanism particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • Discovering the traffic classification service by the traffic classification consumer may comprise transmitting a discovery request from the traffic classification consumer to the service discovery entity comprising at least one of:
  • the supported input parameters by the traffic classification service particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; • an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
  • the traffic classification mechanism particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; selecting at the service discovery entity the traffic classification service based on the information comprised in the discovery request; and receiving a discovery response at the traffic classification consumer from the service discovery entity including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address.
  • the method may further comprise selecting at the service discovery entity a further traffic classification service based on the information comprised in the discovery request; including by the service discovery entity in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and selecting at the traffic classification consumer the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer.
  • the traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
  • the traffic classification of the traffic data may be any one of an application identifier, or an application type.
  • the traffic classification service may be hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity may be a Network Repository Function; and the traffic classification consumer may be a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node.
  • This disclosure also provides mobile network nodes, particularly a traffic classification service, a traffic classification consumer, and a service discovery entity, each configured to perform the respective methods as described herein.
  • This disclosure also provides the corresponding computer program and computer program products comprising code, for example in the form of a computer program, that when run on processing circuitry of the mobile network nodes causes the mobile network nodes to perform the disclosed methods.
  • the solution disclosed herein enables offering a traffic classification service in a communications network that can be exposed and/or used by any entity (e.g., any Network Function (NF) or NF service) within the network.
  • any entity e.g., any Network Function (NF) or NF service
  • the solution disclosed herein enables traffic classification for NIDD (Non-IP Data Delivery).
  • traffic payload is transmitted through the Control Plane (CP) nodes.
  • CP Control Plane
  • TC Control Plane
  • the proposed solution avoids deploying traffic classification modules (e.g., DPI) in the CP nodes requiring TC classification for NIDD.
  • the solution disclosed herein enables having separated and dedicated TC services for specific scenarios, traffic types, etc.
  • TC services per slice type e.g., MBB, ULLC
  • UE type e.g., loT devices
  • traffic class e.g., large/short flows, infrequent data transmissions, Certainly, location (e.g., country, region, ...), etc.
  • location e.g., country, region, ...)
  • the solution disclosed herein enables having separated TC services depending on the TC type performed.
  • Different TC types can be e.g., deterministic (having traffic filters), heuristic, ML-based, etc.
  • the different TC types entail different characteristics.
  • deterministic classification either classifies traffic with 100% accuracy or it cannot classify it at all
  • heuristic classification can classify traffic into application types (e.g., video)
  • ML-based classification has typically lower than 100% accuracy, but it can be used to classify unknown traffic (subject to a certain accuracy level).
  • the solution disclosed herein enables having one traffic classification module that can serve different entities (e.g., User Plane entities) requiring traffic classification. This may help to reduce the delay associated with multiple traffic classifications along the user plane traffic path. It also reduces resources and energy consumption, improving performance and reducing latency.
  • entities e.g., User Plane entities
  • the solution disclosed herein enables to avoid the need of deploying traffic classification modules in all the UP entities (e.g., User Plane Functions, RAN nodes) in the communications network, which enables lightweight UPFs and RAN nodes. It enables for example a light UPF (without a DPI module) which just extracts the 3-tuple (for each flow) and requests to the TC service (which might be deployed at NEF/UDR handling the PFDs for App-IDs, or in another UPF) to identify the App-ID. There is also no need to provision and update the whole set of PFDs from NEF/UDR to every UPF (e.g., through SMF).
  • UP entities e.g., User Plane Functions, RAN nodes
  • Figure 3 is a signaling diagram illustrating a procedure for the registration procedure of the TC service in NRF. The procedure is performed by a TC service 301 and a NRF 110.
  • the TC service sends a registration request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service that can be used for service discovery purposes.
  • IP IP
  • TCP Transmission Control Protocol
  • HTTP HyperText Transfer Protocol
  • TC service class/type - indicates if the TC service is dedicated to a specific scenario and enables separated and dedicated TC services for specific scenarios, traffic types, etc.
  • there may be specific TC services per slice ID/type e.g., MBB, ULLC
  • UE type e.g., loT devices
  • traffic class/type e.g., large/short flows, infrequent data transmissions, Certainly, location (e.g., country, region, ...), etc. This allows to reduce the number of applications per TC service, which improves the classification performance and footprint.
  • the TC service class/type can be any one of a Slice-ID, Slice-type (e.g., MBB, ULLC), UE-type (e.g., loT device), traffic class (e.g., large/short flows, infrequent data transmissions, ...), location (e.g., country, region, ...), etc. d.
  • TC type deterministic, heuristic, ML, (7) - indicates whether the classification performed in the TC service is deterministic, heuristic, ML-based, etc., and enables to have separated TC services depending on the TC type performed.
  • Different TC types can be e.g., deterministic (having traffic filters), heuristic, ML-based, etc.
  • the different TC types entail different characteristics.
  • deterministic classification either classifies traffic with 100% accuracy or it cannot classify it at all
  • heuristic classification can classify traffic into application types (e.g., video)
  • ML-based classification has typically lower than 100% accuracy, but it can be used to classify unknown traffic (subject to a certain accuracy level).
  • the TC type can be any one of: deterministic, heuristic, ML-based, etc.
  • Figure 4 is a signaling diagram illustrating a procedure for discovery and usage procedures for the TC service.
  • the procedure is performed by a TC consumer 401, a TC service 301 and a NRF 110.
  • the TC consumer may be any Network Function in the networked system 100.
  • the TC consumer sends a discovery request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service to be discovered. b. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. c. TC service class/type - indicating the TC service class supported by the TC service as defined in step 310. d. TC type - indicating the type of the TC service as defined in step 310.
  • the TC consumer can be any NF (or NF service), both CP (e.g., AMF, SMF) and UP entities (e.g., UPF, gNB).
  • NF or NF service
  • CP e.g., AMF, SMF
  • UP entities e.g., UPF, gNB
  • the NRF selects a TC service (or a set of TC services) according to or matching the previous parameters and sends to the TC consumer the address of the selected TC service or set of TC services.
  • the NRF may send to the TC consumer any means allowing the TC consumer to contact the TC service.
  • the TC consumer sends to the TC service a TC request including the traffic information according to the input supported by the TC service, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
  • the TC service returns to the consumer the TC result, e.g., an App-ID.
  • the TC service may return any means allowing the TC consumer to identify the application or traffic type.
  • Figure 5 is a signaling diagram illustrating the embodiment in which the RAN discovers and uses the TC service.
  • the discovery can be performed with the AMF as intermediator, or directly from RAN to NRF if RAN has direct access to the NRF.
  • the procedure is performed by a RAN 102, an AMF 106, a TC service 301 and a NRF 110.
  • the RAN sends a TC service discovery request to the AMF including: a. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. b. TC service class - of the TC service, as defined in step 310. c. TC type - of the TC service, as defined in step 310.
  • the AMF sends a discovery request to NRF including: a. Service name, e.g., "TC service”, indicating the name of the service b. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. c. TC service class - of the TC service, as defined in step 310. d. TC type - of the TC service, as defined in step 310.
  • the NRF selects the TC service according to the previous parameters and sends to the AMF the address of the selected TC service.
  • the NRF may send to the AMF any means allowing the AMF to contact the TC service.
  • the AMF responds to RAN with the address of the selected TC service.
  • the RAN sends to the TC service a TC request including the traffic information according to the input supported by the TC service, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
  • the TC service returns to the RAN the TC result, e.g., an App-ID.
  • the TC service may return any means allowing the TC consumer to identify the application or traffic type.
  • Figure 6 is a signaling diagram illustrating the embodiment in which the RAN directly requests a TC service offered by AMF, and in turn, AMF discovers and uses the TC service.
  • the procedure is performed by a RAN 102, an AMF 106, a TC service 301 and a NRF 110.
  • the RAN sends to the AMF a TC request including the traffic information to be classified by the TC service, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
  • the TC service e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
  • the AMF sends a discovery request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service. b. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. c. TC service class - of the TC service, as defined in step 310. d. TC type - of the TC service, as defined in step 310.
  • the NRF selects the TC service according to or matching the previous parameters and sends to the AMF the address of the selected TC service. The NRF may send to the AMF any means allowing the AMF to contact the TC service.
  • the AMF sends to the TC service a TC request including the traffic information sent by the RAN, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
  • the TC service returns to the AMF the TC result, e.g., an App-ID.
  • the AMF returns to the RAN the TC result, e.g., an App-ID.
  • the response from the AMF to the RAN may be a redirect message (e.g., an HTTP 3xx redirection), prompting the RAN to send the TC service request to the redirection target (e.g., the TC service IP address) indicated in the redirect message.
  • the RAN can transmit the TC service request to the TC service as per the step 514 and receive the App-ID as per the step 515. In this case the steps 613 and 614 may not take place.
  • FIG. 7 is a flowchart illustrating a method performed by a traffic classification service for enabling service-based traffic classification in a communication network.
  • the traffic classification service may be hosted by a User Plane Function 103, a user plane Service Function, a User Data Repository 114 or a Network Data Analytics Function 115.
  • the traffic classification service registers the traffic classification service with a service discovery entity. This step may comprise registering at least one of:
  • the traffic classification service • an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces;
  • an indication of an association of the traffic classification service particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
  • the traffic classification mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • This step may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
  • the traffic classification service receives from a traffic classification consumer a traffic classification request including traffic data to be classified, wherein the traffic classification consumer previously discovered the traffic classification service via the service discovery entity.
  • the traffic classification service transmits to the traffic classification consumer a traffic classification response including the traffic classification of the traffic data.
  • the traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
  • the traffic data may be any one of an application identifier, or an application type.
  • FIG 8 is a flowchart illustrating a method performed by a traffic classification consumer for enabling service-based traffic classification in a communication network.
  • the traffic classification consumer may be any Network Function within the networked system 100, particularly an Access and Mobility Management Function 106 or a User Plane Function 103, or a Radio Access Network node 102.
  • the traffic classification consumer discovers a traffic classification service via a service discovery entity, wherein the traffic classification service is registered with the service discovery entity.
  • This step may be based on at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • This step may comprise transmitting a discovery request to the service discovery entity comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification;
  • the traffic classification consumer receives a discovery response from the service discovery entity based on the information comprised in the discovery request including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address.
  • This step may also comprise receiving in the discovery response, based on the information comprised in the discovery request, information of a further traffic classification service comprising at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and
  • the traffic classification consumer selects the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer.
  • the traffic classification consumer transmits to the traffic classification service a traffic classification request including traffic data to be classified.
  • the traffic classification consumer receives from the traffic classification service a traffic classification response including the traffic classification of the traffic data.
  • the traffic data to be classified is any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
  • the traffic classification of the traffic data is any one of an application identifier, or an application type.
  • Figure 9 is a flowchart illustrating a method performed by a service discovery entity for enabling service-based traffic classification in a communication network.
  • the service discovery entity may be a Network Repository Function 110.
  • the service discovery entity registers a traffic classification service.
  • This step may comprise registering at least one of: a. a service name associated to the traffic classification service; b. an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
  • This step may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
  • the service discovery entity receives a discovery request from a traffic classification consumer comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d.
  • the service discovery entity selects the traffic classification service based on the information comprised in the discovery request. This step may comprise selecting a further traffic classification service based on the information comprised in the discovery request.
  • the service discovery entity transmits a discovery response to the traffic classification consumer including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address.
  • This step may comprise including in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address.
  • FIG 10 is a block diagram illustrating elements of a mobile network node 1000 of a mobile communications network.
  • the mobile network node 1000 is a TC service 301.
  • the mobile network node may include network interface circuitry 1001 (also referred to as a network interface) configured to provide communications with other nodes of the core network and/or the network.
  • the mobile network node may also include a processing circuitry 1002 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 1003 (also referred to as memory) coupled to the processing circuitry.
  • the memory circuitry 1003 may include computer readable program code that when executed by the processing circuitry 1002 causes the processing circuitry to perform operations according to embodiments disclosed herein.
  • processing circuitry 1002 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 1002 and/or network interface circuitry 1001. For example, processing circuitry 1002 may control network interface circuitry 1001 to transmit communications through network interface circuitry 1001 to one or more other network nodes and/or to receive communications through network interface circuitry from one or more other network nodes. Moreover, modules may be stored in memory 1003, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 1002, processing circuitry 1002 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).
  • FIG 11 is a block diagram illustrating elements of a mobile network node 1100 of a mobile communications network.
  • the mobile network node 1100 is a NRF 110.
  • the mobile network node may include network interface circuitry 1101 (also referred to as a network interface) configured to provide communications with other nodes of the core network and/or the network.
  • the mobile network node may also include a processing circuitry 1102 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 1103 (also referred to as memory) coupled to the processing circuitry.
  • the memory circuitry 1103 may include computer readable program code that when executed by the processing circuitry 1102 causes the processing circuitry to perform operations according to embodiments disclosed herein.
  • processing circuitry 1102 may be defined to include memory so that a separate memory circuitry is not required.
  • operations of the mobile network node may be performed by processing circuitry 1102 and/or network interface circuitry 1101.
  • processing circuitry 1102 may control network interface circuitry 1101 to transmit communications through network interface circuitry 1101 to one or more other network nodes and/or to receive communications through network interface circuitry from one or more other network nodes.
  • modules may be stored in memory 1103, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 1102, processing circuitry 1102 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).
  • FIG. 12 is a block diagram illustrating elements of a mobile network node 1200 of a mobile communications network.
  • the mobile network node 1200 is any NF, particularly an Access and Mobility Management Function 106 or a User Plane Function 103, or a Radio Access Network node 102.
  • the mobile network node may include network interface circuitry 1201 (also referred to as a network interface) configured to provide communications with other nodes of the core network and/or the network.
  • the mobile network node may also include a processing circuitry 1202 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 1203 (also referred to as memory) coupled to the processing circuitry.
  • a processing circuitry 1202 also referred to as a processor
  • memory circuitry 1203 also referred to as memory
  • the memory circuitry 1203 may include computer readable program code that when executed by the processing circuitry 1202 causes the processing circuitry to perform operations according to embodiments disclosed herein. According to other embodiments, processing circuitry 1202 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 1202 and/or network interface circuitry 1201. For example, processing circuitry 1202 may control network interface circuitry 1201 to transmit communications through network interface circuitry 1201 to one or more other network nodes and/or to receive communications through network interface circuitry from one or more other network nodes.
  • modules may be stored in memory 1203, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 1202, processing circuitry 1202 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).

Abstract

A method for enabling service-based traffic classification in a communication network. The method comprises registering a traffic classification service with a service discovery entity, discovering the traffic classification service by a traffic classification consumer, transmitting from the traffic classification consumer to the traffic classification service a traffic classification request including traffic data to be classified and receiving at the traffic classification consumer from the traffic classification service a traffic classification response including the traffic classification of the traffic data. The registering and discovery of the traffic classification service may be based on the name, supported input parameters and characteristics of the traffic classification service. The traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace. The traffic classification of the traffic data may be any one of an application identifier or an application type.

Description

SERVICE-BASED TRAFFIC CLASSIFICATION SERVICE
TECHNICAL FIELD
The present invention generally relates to services in communication networks, and more specifically, the invention relates to service-based traffic classification in communication networks.
BACKGROUND
In 5GC, the detection and classification of applications is done by means of a set of SDF (Service Data Flow) filters, PFD (Packet Flow Descriptor) and/or an application ID. The application is detected at the User Plane using packet header matching. The User Plane performs packet inspection functionality, e.g., in the UPF (User Plane Function), based on matching the user plane traffic with the SDFs or PFDs. The UPF is provisioned with the proper SDFs and/or PFDs of the applications that are to be classified at the establishment of the data session between the User Equipment (UE) and the Data Network (DN), i.e., the PDU (Packet Data Unit) session establishment procedure in 5GC. The SDFs/PFDs can be also provisioned to the UPF in a parallel procedure, e.g., the PFD management procedures in 5GC. These PFD management procedures are typically handled by the SMF (Session Management Function) and can be of a push or pull nature. In pull procedures, the PFDs for a certain application may be requested by the SMF to the PFDF (PFD Function) and then installed in the UPF by the SMF. In push procedures, the PFDs are provided in a proactive manner to the SMF from the PFDF, e.g., upon a PFD update. The PFDF may be deployed standalone or collocated with the NEF (Network Exposure Function).
Other application detection or traffic classification procedures in UPF include heuristics or Machine Learning (ML)-based mechanisms. These mechanisms match the traffic against patterns or models and produce a classification result which may imply a certain degree of accuracy.
In the UPF, the traffic classification procedure for a certain application is executed according to Packet Detection Rules (PDR) received from the SMF, which include the traffic filter information and an order or precedence of execution. The traffic filter information in the PDRs is set by the SMF based on the PFDs received at the SMF from the PFDF. When a packet arrives at UPF, it is matched against the list of PDRs for different applications according to the order or precedence. This order or precedence is defined by the PCC rules that are provisioned to the Session Management Function (SMF) by the Policy Control Function (PCF). Each PCC rule for each application includes a precedence, and this precedence is translated into the PDR order at UPF. At PDU session establishment, based on the subscription data, PCF installs the PCC rules (with their corresponding precedence) and SMF translates them into PDRs (and associated rules: FARs, QERs, URRs, etc.) which are then installed in the UPF. The FARs, QERs, URRs, etc., define the enforcement actions to be done on the detected application traffic.
Different levels of packet inspection are possible, e.g., SPI (Shallow Packet Inspection) supports packet inspection at L3/L4 (e.g., IP/TCP), DPI (Deep Packet Inspection) supports packet inspection at L7 (e.g. HTTP), HPI (Heuristic Packet Inspection) supports packet inspection using advanced techniques, e.g. by measuring rates in a packet flow, ML (Machine Learning) techniques can be used to classify traffic (e.g. by means of generating a model on a per service basis, through training with labelled traces).
As illustrated in Figure 2, the SMF may control the data path of a PDU Session so that the traffic of the PDU Session traverses several UPFs (Uplink Classifier and PDU session anchors 1 and 2 in Figure 2). The UPF that terminates the data path towards the Data Network (DN), referred to as PDU session anchor (PSA), is said to support PDU Session Anchor functionality, i.e., serving as anchor between the PDU session and the DN. Each PDU Session Anchor supporting a PDU Session provides a different access to the DN(s). The SMF may decide to insert in the data path of a PDU Session an "UL CL" (Uplink classifier, Figure 2). The UL CL is a functionality supported by an UPF that aims at diverting (locally) some traffic matching traffic filters provided by the SMF. The insertion and removal of an UL CL is decided by the SMF and controlled by the SMF using generic N4 and UPF capabilities. The SMF may decide to insert in the data path of a PDU Session a UPF supporting the UL CL functionality during or after the PDU Session Establishment, or to remove from the data path of a PDU Session a UPF supporting the UL CL functionality after the PDU Session Establishment. The SMF may include more than one UPF supporting the UL CL functionality in the data path of a PDU Session.
A problematic aspect of the traffic classification solutions in communication networks is that each node requiring traffic classification, e.g., the UPF (UL CL, PSA) or the Radio Access Network (RAN) shall embed a module including the traffic classification logic and algorithms, typically a DPI module. All User Plane nodes (e.g., all UPFs in the user plane data path and RAN) requiring traffic classification shall embed a traffic classification module, which is memory and computing demanding, especially due to the large number of applications in the market that are to be classified, which is also increasing more and more. It hampers having light nodes, e.g., lightweight UPFs such as UL CLs, which require low footprint and high performance. Additionally, if there are several User Plane nodes in the path that require traffic classification (e.g., an UL CL and a PSA), the traffic classification process is executed several times in the different nodes along the path. This impacts performance, latency, energy consumption, etc. The RAN nodes may also require traffic classification functionality. Deploying DPI in RAN adds an additional burden to the problem of having several nodes in the UP path that perform traffic classification processes, adding delay and requiring extra processing resources at RAN.
SUMMARY
An object of the invention is to enable a service-based traffic classification service in communication networks.
A first aspect of the invention relates to a method performed by a traffic classification service for enabling service-based traffic classification in a communication network. The method comprises registering the traffic classification service with a service discovery entity; receiving from a traffic classification consumer a traffic classification request including traffic data to be classified, wherein the traffic classification consumer previously discovered the traffic classification service via the service discovery entity; transmitting to the traffic classification consumer a traffic classification response including the traffic classification of the traffic data. Registering the traffic classification service with the service discovery entity may comprise registering at least one of: a service name associated to the traffic classification service; an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5- tuples, Packet Flow Descriptors, raw packets, or traffic traces; an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. Registering the traffic classification service at the service discovery entity may comprise transmitting a registration request from the traffic classification service to the service discovery entity. The traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace. The traffic classification of the traffic data may be any one of an application identifier, or an application type.
A second aspect of the invention relates to a method performed by a traffic classification consumer for enabling service-based traffic classification in a communication network. The method comprises discovering a traffic classification service via a service discovery entity, wherein the traffic classification service is registered with the service discovery entity; transmitting to the traffic classification service a traffic classification request including traffic data to be classified; receiving from the traffic classification service a traffic classification response including the traffic classification of the traffic data. Discovering the traffic classification service may be based on at least one of: the service name associated to the traffic classification service; the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5- tuples, Packet Flow Descriptors, raw packets, or traffic traces; an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. Discovering the traffic classification service may comprise transmitting a discovery request to the service discovery entity comprising at least one of: the service name associated to the traffic classification service; the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; and receiving a discovery response from the service discovery entity based on the information comprised in the discovery request including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address. The method may further comprise receiving in the discovery response, based on the information comprised in the discovery request, information of a further traffic classification service comprising at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and selecting the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer. The traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace. The traffic classification of the traffic data may be any one of an application identifier, or an application type.
A third aspect of the invention relates to a method performed by a service discovery entity for enabling service-based traffic classification in a communication network. The method comprises registering a traffic classification service; receiving a discovery request from a traffic classification consumer comprising at least one of: the service name associated to the traffic classification service; the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; selecting the traffic classification service based on the information comprised in the discovery request; and transmitting a discovery response to the traffic classification consumer including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address. Registering the traffic classification service at the service discovery entity may comprise registering at least one of: a service name associated to the traffic classification service; an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. Registering the traffic classification service at the service discovery entity may comprise transmitting a registration request from the traffic classification service to the service discovery entity. The method may further comprise selecting a further traffic classification service based on the information comprised in the discovery request; and including in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address.
Other aspects of the invention relate to mobile network nodes, particularly a traffic classification service, a traffic classification consumer, and a service discovery entity, each configured to perform the respective methods as described herein. Other aspects of the invention relate to computer program and computer program products.
The traffic classification service may be hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity may be a Network Repository Function; and the traffic classification consumer may be a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node.
Advantageously, the solution disclosed herein enables offering a traffic classification service in a communications network that can be exposed and/or used by any entity (e.g., any Network Function (NF) or NF service) within the network. Further advantageously, the solution disclosed herein enables traffic classification for NIDD (Non-IP Data Delivery). In NIDD solutions traffic payload is transmitted through the Control Plane (CP) nodes. These CP nodes involved in NIDD may require TC as well. The proposed solution avoids deploying traffic classification modules (e.g., DPI) in the CP nodes requiring TC classification for NIDD.
Further advantageously, the solution disclosed herein enables having separated and dedicated TC services for specific scenarios, traffic types, etc. For example, there may be specific TC services per slice type (e.g., MBB, ULLC), UE type (e.g., loT devices), traffic class (e.g., large/short flows, infrequent data transmissions, ...), location (e.g., country, region, ...), etc. This allows to reduce the number of applications per TC service, which improves the classification performance and footprint.
Further advantageously, the solution disclosed herein enables having separated TC services depending on the TC type performed. Different TC types can be e.g., deterministic (having traffic filters), heuristic, ML-based, etc. The different TC types entail different characteristics. E.g., deterministic classification either classifies traffic with 100% accuracy or it cannot classify it at all, heuristic classification can classify traffic into application types (e.g., video), ML-based classification has typically lower than 100% accuracy, but it can be used to classify unknown traffic (subject to a certain accuracy level).
Further advantageously, the solution disclosed herein enables having one traffic classification module that can serve different entities (e.g., User Plane entities) requiring traffic classification. This may help to reduce the delay associated with multiple traffic classifications along the user plane traffic path. It also reduces resources and energy consumption, improving performance and reducing latency.
Further advantageously, the solution disclosed herein enables to avoid the need of deploying traffic classification modules in all the UP entities (e.g., User Plane Functions, RAN nodes) in the communications network, which enables lightweight UPFs and RAN nodes. It enables for example a light UPF (without a DPI module) which just extracts the 3-tuple (for each flow) and requests to the TC service (which might be deployed at NEF/UDR handling the PFDs for App-IDs, or in another UPF) to identify the App-ID. There is also no need to provision and update the whole set of PFDs from NEF/UDR to every UPF (e.g., through SMF).
Other objectives, features and advantages of the enclosed embodiments will be apparent from the following detailed disclosure, from the attached dependent claims as well as from the drawings.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the element, apparatus, component, means, module, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, module, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention may best be understood by referring to the following description and accompanying drawings that are used to illustrate particular embodiments of the invention. In the drawings:
Figure 1 is a networked system in accordance with particular embodiments of the solution described herein;
Figure 2 is a networked system in accordance with particular embodiments of the solution described herein;
Figure 3 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
Figure 4 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
Figure 5 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
Figure 6 is a signaling diagram illustrating a procedure according to particular embodiments of the solution described herein;
Figure 7 is a flowchart illustrating a method performed by a mobile network node according to particular embodiments of the solution described herein;
Figure 8 is a flowchart illustrating a method performed by a mobile network node according to particular embodiments of the solution described herein;
Figure 9 is a flowchart illustrating a method performed by a mobile network node according to particular embodiments of the solution described herein;
Figure 10 is a block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.
Figure 11 is a block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein. Figure 12 is a block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.
DETAILED DESCRIPTION
The invention will now be described in detail hereinafter with reference to the accompanying drawings, in which examples of embodiments or implementations of the invention are shown. The invention may, however, be embodied or implemented in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of present invention to those skilled in the art. It should also be noted that these embodiments are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present/used in another embodiment. These embodiments of the disclosed subject matter are presented as teaching examples and are not to be construed as limiting the scope of the disclosed subject matter. For example, certain details of the described embodiments may be modified, omitted, or expanded upon without departing from the scope of the described subject matter.
The example embodiments described herein arise in the context of a telecommunications network, including but not limited to a telecommunications network that conforms to and/or otherwise incorporates aspects of a fifth generation (5G) architecture. Figure 1 is an example networked system 100 in accordance with example embodiments of the present disclosure. Figure 1 specifically illustrates User Equipment (UE) 101, which may be in communication with a (Radio) Access Network ((R)AN) 102 and Access and Mobility Management Function (AMF) 106 and User Plane Function (UPF) 103. As described in the background section, the UPF can be of two types: UL CL and PSA. The AMF 106 may, in turn, be in communication with core network services including Session Management Function (SMF) 107 and Policy Control Function (PCF) 111. The core network services may also be in communication with an Application Server/ Application Function (AS/AF) 113. Other networked services also include Network Slice Selection Function (NSSF) 108, Authentication Server Function (AUSF) 105, User Data Management (UDM) 112, Network Exposure Function (NEF) 109, Network Repository Function (NRF) 110, User Data Repository (UDR) 114, Network Data Analytics Function (NWDAF) 115 and Data Network (DN) 104. In some example implementations of embodiments of the present disclosure, an AMF 106, SMF 107, UPF 103, PCF 111, AUSF 105, NRF 110, UDM 112, NEF 109, AF 113, UDR 114, NWDAF 115, and NSSF 108 are each considered to be an NF. One or more additional instances of the network functions (NF) may be incorporated into the networked system. The solution described herein aims to enable a service-based traffic classification service in communication networks.
This disclosure proposes a solution to the above-mentioned problematic aspects of the current traffic classification mechanisms in communication networks. The proposed solution is based on a Service- Based module for Traffic Classification (TC), also referred to as traffic classification (TC) service, following the Service Based Architecture (SBA) principles as standardized in 3GPP specifications. The main features of the proposed solution are:
• The traffic classification service registers in NRF.
• The traffic classification service can be discovered and used by the different entities requiring traffic classification, e.g., RAN (directly or via AMF), UL CL (directly or via SMF) and PSA (directly or via SMF).
• Additionally, any potential Control Plane (CP) node requiring TC for NIDD (Non-IP Data Delivery) can discover and use the TC service.
The traffic classification service can be hosted and/or exposed by the entities that have the necessary data to perform traffic classification, e.g., UPF, UDR, NWDAF, etc. It can also be a standalone entity connected to the SBA architecture. The TC service can retrieve Packet Flow Descriptors (PFD) from UDR if needed to properly perform the traffic classification.
It is proposed to include a new "TC-service-class" parameter in the NRF registration information associated to the TC service. This parameter indicates if the TC service is dedicated to a specific scenario. The TC service registers the TC-service-class parameter in the NRF, and NFs can discover the TC service based on this parameter.
It is also proposed to include a new "TC type" parameter in the NRF registration information associated to the TC service. This parameter indicates whether the classification performed in the TC service is deterministic, heuristic, ML-based, etc.
This disclosure provides a method for enabling service-based traffic classification in a communication network, the method being performed by a traffic classification service and a traffic classification consumer. The method comprises registering the traffic classification service with a service discovery entity; discovering the traffic classification service by the traffic classification consumer; transmitting from the traffic classification consumer to the traffic classification service a traffic classification request including traffic data to be classified; receiving at the traffic classification consumer from the traffic classification service a traffic classification response including the traffic classification of the traffic data. Registering the traffic classification service at the service discovery entity may comprise registering at least one of: • a service name associated to the traffic classification service;
• an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces;
• an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
• an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
Registering the traffic classification service at the service discovery entity may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
Discovering the traffic classification service by the traffic classification consumer may be based on at least one of:
• the service name associated to the traffic classification service;
• the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces;
• an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
• the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
Discovering the traffic classification service by the traffic classification consumer may comprise transmitting a discovery request from the traffic classification consumer to the service discovery entity comprising at least one of:
• the service name associated to the traffic classification service;
• the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; • an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
• the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; selecting at the service discovery entity the traffic classification service based on the information comprised in the discovery request; and receiving a discovery response at the traffic classification consumer from the service discovery entity including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address.
The method may further comprise selecting at the service discovery entity a further traffic classification service based on the information comprised in the discovery request; including by the service discovery entity in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and selecting at the traffic classification consumer the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer.
The traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
The traffic classification of the traffic data may be any one of an application identifier, or an application type.
The traffic classification service may be hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity may be a Network Repository Function; and the traffic classification consumer may be a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node.
This disclosure also provides mobile network nodes, particularly a traffic classification service, a traffic classification consumer, and a service discovery entity, each configured to perform the respective methods as described herein. This disclosure also provides the corresponding computer program and computer program products comprising code, for example in the form of a computer program, that when run on processing circuitry of the mobile network nodes causes the mobile network nodes to perform the disclosed methods. Advantageously, the solution disclosed herein enables offering a traffic classification service in a communications network that can be exposed and/or used by any entity (e.g., any Network Function (NF) or NF service) within the network.
Further advantageously, the solution disclosed herein enables traffic classification for NIDD (Non-IP Data Delivery). In NIDD solutions traffic payload is transmitted through the Control Plane (CP) nodes. These CP nodes involved in NIDD may require TC as well. The proposed solution avoids deploying traffic classification modules (e.g., DPI) in the CP nodes requiring TC classification for NIDD.
Further advantageously, the solution disclosed herein enables having separated and dedicated TC services for specific scenarios, traffic types, etc. For example, there may be specific TC services per slice type (e.g., MBB, ULLC), UE type (e.g., loT devices), traffic class (e.g., large/short flows, infrequent data transmissions, ...), location (e.g., country, region, ...), etc. This allows to reduce the number of applications per TC service, which improves the classification performance and footprint.
Further advantageously, the solution disclosed herein enables having separated TC services depending on the TC type performed. Different TC types can be e.g., deterministic (having traffic filters), heuristic, ML-based, etc. The different TC types entail different characteristics. E.g., deterministic classification either classifies traffic with 100% accuracy or it cannot classify it at all, heuristic classification can classify traffic into application types (e.g., video), ML-based classification has typically lower than 100% accuracy, but it can be used to classify unknown traffic (subject to a certain accuracy level).
Further advantageously, the solution disclosed herein enables having one traffic classification module that can serve different entities (e.g., User Plane entities) requiring traffic classification. This may help to reduce the delay associated with multiple traffic classifications along the user plane traffic path. It also reduces resources and energy consumption, improving performance and reducing latency.
Further advantageously, the solution disclosed herein enables to avoid the need of deploying traffic classification modules in all the UP entities (e.g., User Plane Functions, RAN nodes) in the communications network, which enables lightweight UPFs and RAN nodes. It enables for example a light UPF (without a DPI module) which just extracts the 3-tuple (for each flow) and requests to the TC service (which might be deployed at NEF/UDR handling the PFDs for App-IDs, or in another UPF) to identify the App-ID. There is also no need to provision and update the whole set of PFDs from NEF/UDR to every UPF (e.g., through SMF).
Hereinafter, drawings showing examples of embodiments of the solution are described in detail. Figure 3 is a signaling diagram illustrating a procedure for the registration procedure of the TC service in NRF. The procedure is performed by a TC service 301 and a NRF 110.
At step 310, the TC service sends a registration request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service that can be used for service discovery purposes. b. Supported input parameters/protocols (3-tuple/5-tuple/PFD/packet/...) - The inputs supported by the TC service. It can be e.g., a raw packet, a 3/5-tuple, a PFD, a decapsulated packet including a subset of the protocol headers, etc. It can also be an indication of the protocol of the PDU taken as input (e.g., IP, TCP, HTTP, etc.) c. TC service class/type - indicates if the TC service is dedicated to a specific scenario and enables separated and dedicated TC services for specific scenarios, traffic types, etc. For example, there may be specific TC services per slice ID/type (e.g., MBB, ULLC), UE type (e.g., loT devices), traffic class/type (e.g., large/short flows, infrequent data transmissions, ...), location (e.g., country, region, ...), etc. This allows to reduce the number of applications per TC service, which improves the classification performance and footprint.
The TC service class/type can be any one of a Slice-ID, Slice-type (e.g., MBB, ULLC), UE-type (e.g., loT device), traffic class (e.g., large/short flows, infrequent data transmissions, ...), location (e.g., country, region, ...), etc. d. TC type (deterministic, heuristic, ML, ...) - indicates whether the classification performed in the TC service is deterministic, heuristic, ML-based, etc., and enables to have separated TC services depending on the TC type performed. Different TC types can be e.g., deterministic (having traffic filters), heuristic, ML-based, etc. The different TC types entail different characteristics. E.g., deterministic classification either classifies traffic with 100% accuracy or it cannot classify it at all, heuristic classification can classify traffic into application types (e.g., video), ML-based classification has typically lower than 100% accuracy, but it can be used to classify unknown traffic (subject to a certain accuracy level).
The TC type can be any one of: deterministic, heuristic, ML-based, etc.
At step 311, the NRF acknowledges the registration Figure 4 is a signaling diagram illustrating a procedure for discovery and usage procedures for the TC service. The procedure is performed by a TC consumer 401, a TC service 301 and a NRF 110. The TC consumer may be any Network Function in the networked system 100.
At step 410, the TC consumer sends a discovery request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service to be discovered. b. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. c. TC service class/type - indicating the TC service class supported by the TC service as defined in step 310. d. TC type - indicating the type of the TC service as defined in step 310.
The TC consumer can be any NF (or NF service), both CP (e.g., AMF, SMF) and UP entities (e.g., UPF, gNB).
At step 411, the NRF selects a TC service (or a set of TC services) according to or matching the previous parameters and sends to the TC consumer the address of the selected TC service or set of TC services. The NRF may send to the TC consumer any means allowing the TC consumer to contact the TC service.
At step 412, the TC consumer sends to the TC service a TC request including the traffic information according to the input supported by the TC service, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
At step 413, the TC service returns to the consumer the TC result, e.g., an App-ID. The TC service may return any means allowing the TC consumer to identify the application or traffic type.
Figure 5 is a signaling diagram illustrating the embodiment in which the RAN discovers and uses the TC service. The discovery can be performed with the AMF as intermediator, or directly from RAN to NRF if RAN has direct access to the NRF. The procedure is performed by a RAN 102, an AMF 106, a TC service 301 and a NRF 110.
At step 510, the RAN sends a TC service discovery request to the AMF including: a. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. b. TC service class - of the TC service, as defined in step 310. c. TC type - of the TC service, as defined in step 310.
At step 511, the AMF sends a discovery request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service b. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. c. TC service class - of the TC service, as defined in step 310. d. TC type - of the TC service, as defined in step 310.
At step 512, the NRF selects the TC service according to the previous parameters and sends to the AMF the address of the selected TC service. The NRF may send to the AMF any means allowing the AMF to contact the TC service.
At step 513, the AMF responds to RAN with the address of the selected TC service.
At step 514, the RAN sends to the TC service a TC request including the traffic information according to the input supported by the TC service, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
At step 515, the TC service returns to the RAN the TC result, e.g., an App-ID. The TC service may return any means allowing the TC consumer to identify the application or traffic type.
Figure 6 is a signaling diagram illustrating the embodiment in which the RAN directly requests a TC service offered by AMF, and in turn, AMF discovers and uses the TC service. The procedure is performed by a RAN 102, an AMF 106, a TC service 301 and a NRF 110.
At step 610, the RAN sends to the AMF a TC request including the traffic information to be classified by the TC service, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
At step 611, the AMF sends a discovery request to NRF including: a. Service name, e.g., "TC service", indicating the name of the service. b. Supported input parameters (3-tuple/5-tuple/PFD/packet/...) - The type of input parameters the TC service shall support, as defined in step 310. c. TC service class - of the TC service, as defined in step 310. d. TC type - of the TC service, as defined in step 310. At step 612, the NRF selects the TC service according to or matching the previous parameters and sends to the AMF the address of the selected TC service. The NRF may send to the AMF any means allowing the AMF to contact the TC service.
At step 613, the AMF sends to the TC service a TC request including the traffic information sent by the RAN, e.g., any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces.
At step 614, the TC service returns to the AMF the TC result, e.g., an App-ID.
At step 615, the AMF returns to the RAN the TC result, e.g., an App-ID.
In this step, the response from the AMF to the RAN may be a redirect message (e.g., an HTTP 3xx redirection), prompting the RAN to send the TC service request to the redirection target (e.g., the TC service IP address) indicated in the redirect message. Subsequently, the RAN can transmit the TC service request to the TC service as per the step 514 and receive the App-ID as per the step 515. In this case the steps 613 and 614 may not take place.
Figure 7 is a flowchart illustrating a method performed by a traffic classification service for enabling service-based traffic classification in a communication network. The traffic classification service may be hosted by a User Plane Function 103, a user plane Service Function, a User Data Repository 114 or a Network Data Analytics Function 115.
At step 701, the traffic classification service registers the traffic classification service with a service discovery entity. This step may comprise registering at least one of:
• a service name associated to the traffic classification service;
• an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces;
• an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type;
• an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
This step may comprise transmitting a registration request from the traffic classification service to the service discovery entity. At step 702, the traffic classification service receives from a traffic classification consumer a traffic classification request including traffic data to be classified, wherein the traffic classification consumer previously discovered the traffic classification service via the service discovery entity.
At step 703, the traffic classification service transmits to the traffic classification consumer a traffic classification response including the traffic classification of the traffic data.
The traffic data to be classified may be any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
The traffic data may be any one of an application identifier, or an application type.
Figure 8 is a flowchart illustrating a method performed by a traffic classification consumer for enabling service-based traffic classification in a communication network. The traffic classification consumer may be any Network Function within the networked system 100, particularly an Access and Mobility Management Function 106 or a User Plane Function 103, or a Radio Access Network node 102.
At step 801, the traffic classification consumer discovers a traffic classification service via a service discovery entity, wherein the traffic classification service is registered with the service discovery entity. This step may be based on at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
This step may comprise transmitting a discovery request to the service discovery entity comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification;
At step 802, the traffic classification consumer receives a discovery response from the service discovery entity based on the information comprised in the discovery request including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address.
This step may also comprise receiving in the discovery response, based on the information comprised in the discovery request, information of a further traffic classification service comprising at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and
At step 803, the traffic classification consumer selects the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer.
At step 804, the traffic classification consumer transmits to the traffic classification service a traffic classification request including traffic data to be classified.
At step 805, the traffic classification consumer receives from the traffic classification service a traffic classification response including the traffic classification of the traffic data.
The traffic data to be classified is any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace.
The traffic classification of the traffic data is any one of an application identifier, or an application type. Figure 9 is a flowchart illustrating a method performed by a service discovery entity for enabling service-based traffic classification in a communication network. The service discovery entity may be a Network Repository Function 110.
At step 901, the service discovery entity registers a traffic classification service. This step may comprise registering at least one of: a. a service name associated to the traffic classification service; b. an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification.
This step may comprise transmitting a registration request from the traffic classification service to the service discovery entity.
At step 902, the service discovery entity receives a discovery request from a traffic classification consumer comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; At step 903, the service discovery entity selects the traffic classification service based on the information comprised in the discovery request. This step may comprise selecting a further traffic classification service based on the information comprised in the discovery request.
At step 904, the service discovery entity transmits a discovery response to the traffic classification consumer including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address. This step may comprise including in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address.
Figure 10 is a block diagram illustrating elements of a mobile network node 1000 of a mobile communications network. In some embodiments, the mobile network node 1000 is a TC service 301. As shown, the mobile network node may include network interface circuitry 1001 (also referred to as a network interface) configured to provide communications with other nodes of the core network and/or the network. The mobile network node may also include a processing circuitry 1002 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 1003 (also referred to as memory) coupled to the processing circuitry. The memory circuitry 1003 may include computer readable program code that when executed by the processing circuitry 1002 causes the processing circuitry to perform operations according to embodiments disclosed herein. According to other embodiments, processing circuitry 1002 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 1002 and/or network interface circuitry 1001. For example, processing circuitry 1002 may control network interface circuitry 1001 to transmit communications through network interface circuitry 1001 to one or more other network nodes and/or to receive communications through network interface circuitry from one or more other network nodes. Moreover, modules may be stored in memory 1003, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 1002, processing circuitry 1002 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).
Figure 11 is a block diagram illustrating elements of a mobile network node 1100 of a mobile communications network. In some embodiments, the mobile network node 1100 is a NRF 110. As shown, the mobile network node may include network interface circuitry 1101 (also referred to as a network interface) configured to provide communications with other nodes of the core network and/or the network. The mobile network node may also include a processing circuitry 1102 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 1103 (also referred to as memory) coupled to the processing circuitry. The memory circuitry 1103 may include computer readable program code that when executed by the processing circuitry 1102 causes the processing circuitry to perform operations according to embodiments disclosed herein. According to other embodiments, processing circuitry 1102 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 1102 and/or network interface circuitry 1101. For example, processing circuitry 1102 may control network interface circuitry 1101 to transmit communications through network interface circuitry 1101 to one or more other network nodes and/or to receive communications through network interface circuitry from one or more other network nodes. Moreover, modules may be stored in memory 1103, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 1102, processing circuitry 1102 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).
Figure 12 is a block diagram illustrating elements of a mobile network node 1200 of a mobile communications network. In some embodiments, the mobile network node 1200 is any NF, particularly an Access and Mobility Management Function 106 or a User Plane Function 103, or a Radio Access Network node 102. As shown, the mobile network node may include network interface circuitry 1201 (also referred to as a network interface) configured to provide communications with other nodes of the core network and/or the network. The mobile network node may also include a processing circuitry 1202 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 1203 (also referred to as memory) coupled to the processing circuitry. The memory circuitry 1203 may include computer readable program code that when executed by the processing circuitry 1202 causes the processing circuitry to perform operations according to embodiments disclosed herein. According to other embodiments, processing circuitry 1202 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 1202 and/or network interface circuitry 1201. For example, processing circuitry 1202 may control network interface circuitry 1201 to transmit communications through network interface circuitry 1201 to one or more other network nodes and/or to receive communications through network interface circuitry from one or more other network nodes. Moreover, modules may be stored in memory 1203, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 1202, processing circuitry 1202 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).

Claims

- 22 -
CLAIMS A method for enabling service-based traffic classification in a communication network, the method being performed by a traffic classification service and a traffic classification consumer, the method comprising: registering the traffic classification service with a service discovery entity; discovering the traffic classification service by the traffic classification consumer; transmitting from the traffic classification consumer to the traffic classification service a traffic classification request including traffic data to be classified; receiving at the traffic classification consumer from the traffic classification service a traffic classification response including the traffic classification of the traffic data. The method of any of the preceding claims, wherein registering the traffic classification service with the service discovery entity comprises registering at least one of: a. a service name associated to the traffic classification service; b. an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. The method of any of the preceding claims, wherein registering the traffic classification service at the service discovery entity comprises transmitting a registration request from the traffic classification service to the service discovery entity. The method of any of the preceding claims, wherein discovering the traffic classification service by the traffic classification consumer is based on at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. The method of any of the preceding claims, wherein discovering the traffic classification service by the traffic classification consumer comprises: transmitting a discovery request from the traffic classification consumer to the service discovery entity comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; selecting at the service discovery entity the traffic classification service based on the information comprised in the discovery request; and receiving a discovery response at the traffic classification consumer from the service discovery entity including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address. The method of the previous claim, further comprising: selecting at the service discovery entity a further traffic classification service based on the information comprised in the discovery request; including by the service discovery entity in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and selecting at the traffic classification consumer the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer. The method of any of the preceding claims, wherein the traffic data to be classified is any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace. The method of any of the preceding claims, wherein the traffic classification of the traffic data is any one of an application identifier, or an application type. The method of any of the preceding claims, wherein the traffic classification service is hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity is a Network Repository Function; and the traffic classification consumer is a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node. A method for enabling service-based traffic classification in a communication network, the method being performed by a traffic classification service, the method comprising: registering the traffic classification service with a service discovery entity; receiving from a traffic classification consumer a traffic classification request including traffic data to be classified, wherein the traffic classification consumer previously discovered the traffic classification service via the service discovery entity; transmitting to the traffic classification consumer a traffic classification response including the traffic classification of the traffic data. The method of claim 10, wherein registering the traffic classification service with the service discovery entity comprises registering at least one of: a. a service name associated to the traffic classification service; b. an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. - 25 - The method of any one of claims 10 to 11, wherein registering the traffic classification service at the service discovery entity comprises transmitting a registration request from the traffic classification service to the service discovery entity. The method of any one of claims 10 to 12, wherein the traffic data to be classified is any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace. The method of any one of claims 10 to 13, wherein the traffic classification of the traffic data is any one of an application identifier, or an application type. The method of any one of claims 10 to 14, wherein the traffic classification service is hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity is a Network Repository Function; and the traffic classification consumer is a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node. A method for enabling service-based traffic classification in a communication network, the method being performed by a traffic classification consumer, the method comprising: discovering a traffic classification service via a service discovery entity, wherein the traffic classification service is registered with the service discovery entity; transmitting to the traffic classification service a traffic classification request including traffic data to be classified; receiving from the traffic classification service a traffic classification response including the traffic classification of the traffic data. The method of claim 16, wherein discovering the traffic classification service is based on at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. - 26 - The method of any one of claims 16 to 17, wherein discovering the traffic classification service comprises: transmitting a discovery request to the service discovery entity comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; receiving a discovery response from the service discovery entity based on the information comprised in the discovery request including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address. The method of the previous claim, further comprising: receiving in the discovery response, based on the information comprised in the discovery request, information of a further traffic classification service comprising at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address; and selecting the traffic classification service or the further traffic classification service, particularly wherein the selection is performed based on the proximity of the traffic classification service and the further traffic classification service with the traffic classification consumer. The method of any one of claims 16 to 19, wherein the traffic data to be classified is any one of a 3-tuple, a 5-tuple, a Packet Flow Descriptor, a raw packet, a set of raw packets, or a traffic trace. The method of any one of claims 16 to 20, wherein the traffic classification of the traffic data is any one of an application identifier, or an application type. The method of any one of claims 16 to 21, wherein the traffic classification service is hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity is a Network Repository Function; and the traffic classification consumer is a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node. - 1 - A method for enabling service-based traffic classification in a communication network, the method being performed by a service discovery entity, the method comprising: registering a traffic classification service; receiving a discovery request from a traffic classification consumer comprising at least one of: a. the service name associated to the traffic classification service; b. the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification; selecting the traffic classification service based on the information comprised in the discovery request; and transmitting a discovery response to the traffic classification consumer including at least one of the traffic classification service name, the traffic classification service identifier, and the traffic classification service IP address. The method of claim 23, wherein registering the traffic classification service at the service discovery entity comprises registering at least one of: a. a service name associated to the traffic classification service; b. an indication of the supported input parameters by the traffic classification service, particularly wherein the input parameters are any one of 3-tuples, 5-tuples, Packet Flow Descriptors, raw packets, or traffic traces; c. an indication of an association of the traffic classification service, particularly wherein the association is with any one of a location, an area, a network slice, a network slice type, a User Equipment type, or a traffic type; d. an indication of the traffic classification mechanism, particularly wherein the mechanism is any one or a combination of deterministic classification, heuristic classification, or machine learning based classification. - 28 - The method of any one of claims 23 to 24, wherein registering the traffic classification service at the service discovery entity comprises transmitting a registration request from the traffic classification service to the service discovery entity. The method of any one of claims 23 to 25, further comprising: selecting a further traffic classification service based on the information comprised in the discovery request; and including in the discovery response at least one of the further traffic classification service name, the further traffic classification service identifier, and the further traffic classification service IP address. The method of any one of claims 23 to 26, wherein the traffic classification service is hosted by a User Plane Function, a user plane Service Function, a User Data Repository or a Network Data Analytics Function; the service discovery entity is a Network Repository Function; and the traffic classification consumer is a Network Function, particularly an Access and Mobility Management Function or a User Plane Function, or a Radio Access Network node. Apparatus for enabling service-based traffic classification in a communications network, the apparatus comprising a processor and a memory, the memory containing instructions executable by the processor such that the apparatus is operable to perform the method of any of claims 10 to 15. Apparatus for enabling service-based traffic classification in a communications network, the apparatus comprising a processor and a memory, the memory containing instructions executable by the processor such that the apparatus is operable to perform the method of any of claims 16 to 22. Apparatus for enabling service-based traffic classification in a communications network, the apparatus comprising a processor and a memory, the memory containing instructions executable by the processor such that the apparatus is operable to perform the method of any of claims 23 to l. A system comprising an apparatus as claimed in claim 28, an apparatus as claimed in claim 29, and an apparatus as claimed in claim 30. A computer program comprising instructions which, when executed on at least one processor, cause the at least one processor to carry out a method according to any of claims 1 to 27. - 29 - A computer program product, embodied on a non-transitory machine-readable medium, comprising instructions which are executable by a processor, causing the processor to perform the method according to any of claims 1 to 27.
PCT/EP2022/058520 2021-12-21 2022-03-31 Service-based traffic classification service WO2023117153A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP21383175.3 2021-12-21
EP21383175 2021-12-21

Publications (1)

Publication Number Publication Date
WO2023117153A1 true WO2023117153A1 (en) 2023-06-29

Family

ID=78957522

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/058520 WO2023117153A1 (en) 2021-12-21 2022-03-31 Service-based traffic classification service

Country Status (1)

Country Link
WO (1) WO2023117153A1 (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021151520A1 (en) * 2020-01-27 2021-08-05 Telefonaktiebolaget Lm Ericsson (Publ) Classifying traffic data

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021151520A1 (en) * 2020-01-27 2021-08-05 Telefonaktiebolaget Lm Ericsson (Publ) Classifying traffic data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
NGMN ALLIANCE ET AL: "Service-Based Architecture in 5G Document Type: Final Deliverable (approved) Confidentiality Class: P -Public Authorised Recipients: Project: Service-based Architecture in 5G Editor / Submitter: Dan Wang ,Tao Sun (China Mobile) Contributors: AT&T(Farooq Bari) , Bell Canada (Erfanian Javan),China Mob", 19 January 2018 (2018-01-19), XP055727383, Retrieved from the Internet <URL:https://www.ngmn.org/wp-content/uploads/Publications/2018/180119_NGMN_Service_Based_Architecture_in_5G_v1.0.pdf> [retrieved on 20200903] *

Similar Documents

Publication Publication Date Title
EP3695639B1 (en) Monitoring and reporting service performance
US11621916B2 (en) Information transmission method and device in IAB architecture
KR101868070B1 (en) Service layer southbound interface and quality of service
CN112913212A (en) Control of user plane functions with control plane-user plane separation
US20120314568A1 (en) Interoperable quality of service pre-negotiation
KR20090031778A (en) Methods and apparatus for policy enforcement in a wireless communication system
US11855846B2 (en) Communication method and communication apparatus
US11516118B2 (en) Methods and nodes for enabling management of traffic
EP4197136B1 (en) Policy control for redundant transmissions
WO2021233564A1 (en) Improving classification accuracy in user plane function re-selection scenarios
CN113747479A (en) Method, equipment and system for acquiring network resources
EP4052431A1 (en) Nodes and methods for enabling user plane traffic classification in a communications system
US20230336432A1 (en) Traffic classification rules based on analytics
US11777806B2 (en) Methods, system, UE, PGW-U and MME for managing traffic differentiation
US20220303201A1 (en) Traffic Monitoring in a Network Node
US20230269574A1 (en) Apparatus and method for providing data measured by user plane function in a wireless communication system
WO2023117153A1 (en) Service-based traffic classification service
WO2013071860A1 (en) Policy deciding method and network device
KR102225394B1 (en) Method and Apparatus for Controlling Network Node
CN116803112A (en) Method, network node and computer readable medium for dynamically discovering a serving network node in a core network
KR102173015B1 (en) Control plane apparatus, user plane apparatus and method for processing packet using the same
WO2021137180A1 (en) Using dnai to identify a smf supporting connection to a local dn
WO2022069931A1 (en) Methods providing consolidation of policies and related network nodes
WO2021018420A1 (en) Packet detection
WO2022165857A1 (en) Communication method and device and computer readable storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22719589

Country of ref document: EP

Kind code of ref document: A1