Classifying traffic data
A method of classifying traffic data in a network comprises at a Network Data Analytics Function (NWDAF), receiving information relating to traffic data with a known classification from one or more first network functions, and developing a model for classifying future traffic data based on the information relating to the traffic data with a known classification. The method also involves at a second network function, storing a representation of the developed model. The method also involves at a third network function, receiving the representation of the developed model from the second network function, and installing the representation of the developed model at a fourth network function. The method also involves at the fourth network function, classifying traffic data using the developed model.
1 . A computer-implemented method of classifying traffic data in a communications network, the method comprising:
at a Network Data Analytics Function (NWDAF) of the communications network, receiving, from one or more first network functions of the communication network, information relating to traffic data with a known classification; and developing a model for classifying future traffic data based on the information relating to the traffic data with a known classification;
at a second network function of the communications network, storing a representation of the developed model;
at a third network function of the communications network, receiving the representation of the developed model from the second network function; and
installing the representation of the developed model at a fourth network function of the communications network; and
at the fourth network function, classifying traffic data using the developed model.
2 . The method of claim 1 , wherein the method further comprises, at the NWDAF, receiving a request, from a fifth network function of the communications network, for a model for classifying future traffic data.
3 . The method of claim 1 , wherein the request for a model for classifying future traffic data further comprises information identifying an application for which future traffic data is to be classified.
4 . The method of claim 3 , wherein the request for a model for classifying future traffic data further comprises an accuracy indicator, wherein the accuracy indicator represents a minimum likelihood for the developed model to correctly classify future traffic data for the application.
5 . The method of claim 1 , wherein the one or more first network functions comprise at least one of the following: a unified data repository (UDR) arranged to store user subscription data; a user plane function (UPF) arranged to handle user data traffic, or a network exposure function (NEF) arranged to interact with application functions (AFs) external to the communications network.
6 . The method of claim 1 , wherein the information relating to traffic data with a known classification comprises at least one preexisting rule describing the traffic data with a known classification.
7 . The method of claim 1 , wherein the information relating to traffic data with a known classification comprises raw traffic data with a known classification.
8 . The method of claim 1 , wherein the method further comprises, at the NWDAF, determining an accuracy measure for the developed model, wherein the accuracy measure indicates a likelihood that the developed model correctly classifies future traffic data.
9 . The method of claim 8 , wherein the accuracy measure indicates the likelihood that the developed model correctly classifies future traffic data for a particular application.
10 . The method of claim 8 , wherein the representation of the developed model also includes the determined accuracy measure for the developed model.
11 . The method of claim 1 , wherein the representation of the developed model also includes information relating to an application for which future traffic data is to be classified by the model.
12 . The method of claim 1 , wherein the representation of the developed model also includes metadata relating to the developed model.
13 . The method of claim 1 , wherein the method further comprises, at the NWDAF, notifying the fifth network function that the model has been developed.
14 . The method of claim 1 , wherein the step of developing the model for classifying future traffic data based on the information relating to the traffic data with a known classification comprises developing the model using a machine-learning technique.
15 . The method of claim 1 , wherein:
the communications network is a 5G network;
the second network function is a unified data repository (UDR) arranged to store user subscription data;
the third network function is a session management function (SMF) arranged to manage user data sessions; and
the fourth network function is a user plane function (UPF) arranged to handle user data traffic.
16 . A system for classifying traffic data in a communications network, the system comprising:
one or more data processing and control units arranged to execute computer-readable instructions associated with the following network functions of the communications network: a Network Data Analytics Function (NWDAF), a second network function, a third network function, and a fourth network function,
wherein execution of the instructions configures the system to perform operations corresponding to the method of claim 1 .
17 . The system of claim 16 , wherein:
the communications network is a 5G network;
the second network function is a unified data repository (UDR) arranged to store user subscription data;
the third network function is a session management function (SMF) arranged to manage user data sessions; and
the fourth network function is a user plane function (UPF) arranged to handle user data traffic,
the one or more first network functions include one or more the following: the UDR, the UPF or another UPF, and a network exposure function (NEF) arranged to interact with application functions (AFs) external to the communications network.
18 . A non-transitory, computer readable medium storing computer-executable instructions associated with a system comprising a Network Data Analytics Function (NWDAF), a second network function, a third network function, and a fourth network function of a communications network, wherein execution of the instructions by one or more data processing and control units causes the system to perform operations corresponding to the method of claim 1 .