Network analytics

1. A network monitoring method comprising:

obtaining analytics data from one or more network data analytics functions of a mobile communication system using a probe network function which subscribes to the network data analytics functions operating in a passive mode to receive the subscribed network data analytics functions;

obtaining control plane data from one or more control plane probes, wherein the control plane data comprises signaling between one or more user devices and a network of the mobile communication system;

obtaining user plane data from one or more user plane probes;

processing the analytics data, control plane data and user plane data, including correlating at least some of said analytics, user plane and control plane data and identifying at least one anomaly in said data;

triggering an active mode by the probe network function to acquire a subset of analytics data related to said at least one anomaly;

determining one or more of (1) a root cause of said at least one anomaly using said subset of analytics data, and (2) a fault point of said at least one anomaly by inspecting said subset of analytics data; and

subsequent to determining the one or more of the root cause and the fault point, returning to operating the probe network function in the passive mode.

2. A method as claimed in claim 1 , further comprising:

creating a relevant network topology map using said subset of analytics data and said obtained control plane data and user plane data; and

determining the root cause of said at least one anomaly using said subset of analytics data and said network topology map.

3. A method as claimed in claim 1 , wherein processing said analytics data, control plane data and user plane data includes using one or more machine-learned algorithms.

4. A method as claimed in claim 1 , wherein identifying said at least one anomaly comprises identifying differences between at least some of the analytics data, user plane data and control plane data indicative of an anomaly.

5. A method as claimed in claim 1 , further comprising providing processed analytics data, control plane data and user plane data to a dashboard.

6. A method as claimed in claim 1 , further comprising determining which users were impacted by said at least one anomaly.

7. A method as claimed in claim 1 , wherein:

obtaining analytics data comprises receiving analytics IDs;

obtaining control plane data comprises receiving call data records; and/or

obtaining user plane data comprises receiving evolved session data records.

8. A method as claimed in claim 1 , further comprising providing the obtained analytics data, control plane data and user plane data to a data pool for processing.

9. A method as claimed in claim 1 , wherein obtaining said analytics data includes receiving messages from one or more of said network data analytics functions.

10. A method as claimed in claim 9 , wherein each message includes slice identity, instance identity and load level data.

11. A method as claimed in claim 1 , wherein obtaining said analytics data includes receiving information about events from the one or more network data analytics functions from a network exposure function.

12. A method as claimed in claim 1 , wherein obtaining said analytics data includes extracting said analytics data from communications sent from said one or more network data analytics functions to other modules of the mobile communication system over an internal core messaging bus.

13. A method as claimed in claim 12 , further comprising identifying analytics data on the core messaging bus.

14. A method as claimed in claim 1 , wherein obtaining said analytics data includes obtaining network data analytics function data sent from the one or more network data analytics functions to: a policy control function of the mobile communication system and/or a network service slice function of the mobile communication system.

15. A method as claimed in claim 1 , wherein said one or more control plane probes obtain said control plane data from one or more of N1/N2, SBA and SBI interfaces of said mobile communication system.

16. A method as claimed in claim 1 , wherein said one or more user plane probes obtain said user plane data from one or more of N3 and N4 interfaces of said mobile communication system.

17. An apparatus comprising a data processor for processing analytics data, control plane data and user plane data of a mobile communication system, including correlating at least some of said analytics, user plane and control plane data, identifying at least one anomaly in said data and triggering an active mode by a probe network function to acquire a subset of analytics data related to said at least one anomaly, wherein:

The analytics data are obtained from one or more network data analytics functions of the mobile communication system using the probe network function which subscribes to the network data analytics functions operating in a passive mode to receive the subscribed network data analytics functions;

the control plane data are obtained from one or more control plane probes, wherein the control plane data comprises signaling between one or more user devices and a network of the mobile communication system;

the user plane data are obtained from one or more user plane probes;

the data processor is further configured to determine one or more of (1) a root cause of said at least one anomaly using said subset of analytics data, and (2) a fault point of said at least one anomaly by inspecting said subset of analytics data; and

subsequent to determining the one or more of the root cause and the fault point, the probe network function is returned to operate in the passive mode.

18. A non-transitory computer-readable medium comprising instructions for causing an apparatus to perform at least the following:

obtain analytics data from one or more network data analytics functions of a mobile communication system using a probe network function which subscribes to the network data analytics functions operating in a passive mode to receive the subscribed network data analytics functions;

obtain control plane data from one or more control plane probes, wherein the control plane data comprises signaling between one or more user devices and a network of the mobile communication system;

obtain user plane data from one or more user plane probes;

process the analytics data, control plane data and user plane data, including correlating at least some of said analytics, user plane and control plane data and identifying at least one anomaly in said data;

trigger an active mode by the probe network function to acquire a subset of analytics data related to said at least one anomaly; and

determining one or more of (1) a root cause of said at least one anomaly using said subset of analytics data, and (2) a fault point of said at least one anomaly by inspecting said subset of analytics data,

wherein both the root cause and the fault point are determined,

wherein the root cause is determined based on a plurality of (1) identifying which network function and associated topology caused said at least one anomaly, (2) analyzing call data records (CDRs), and (3) analyzing evolved session data record (eSDRs), and

wherein the fault point is determined based on identifying the network function caused said at least one anomaly.

19. A non-transitory computer-readable medium as claimed in claim 18 , wherein the instructions further cause the apparatus to perform at least the following:

subsequent to determining the one or more of the root cause and the fault point, returning to operating the probe network function in the passive mode.

20. A method as claimed in claim 1 , wherein both the root cause and the fault point are determined,

wherein the root cause is determined based on a plurality of (1) identifying which network function and associated topology caused said at least one anomaly, (2) analyzing call data records (CDRs), and (3) analyzing evolved session data records (eSDRs), and

wherein the fault point is determined based on identifying the network function caused said at least one anomaly.