Networking data collection in 5G network functions for zooming using machine learning

A method for analyzing network traffic in a communications network, comprising:

• collecting a subset of module-level statistics from a plurality of network functions (NFs) within the network;
• analyzing the module-level statistics to identify a deviation from a normal state of operation of the network, wherein identifying the deviation from the normal state of operation comprises:
• defining the normal state of operation for the network based on the module-level statistics during a first period of time;
• and
• comparing the module-level statistics during a second period of time to the defined normal state to identify the deviation;
• identifying a network stage where a current network issue causes the deviation to occur using a machine learning model trained on features associated with the deviation;
• collecting additional module-level statistics or packet-level statistics at the identified network stage based on the deviation;
• and
• providing suggestions for debugging, optimizing, or testing the current network issue based on the deviation and the identified network stage.

A non-transitory computer-readable medium storing computer-executable code that when executed by one or more processors causes the one or more processors to:

• collect a subset of module-level statistics from a plurality of network functions (NFs) within the network;
• analyze the module-level statistics to identify a deviation from a normal state of operation of the network, wherein the code to identify the deviation from the normal state of operation comprises code to:
• define the normal state of operation for the network based on the module-level statistics during a first period of time;
• and
• compare the module-level statistics during a second period of time to the defined normal state to identify the deviation;
• identify a network stage where a current network issue causes the deviation to occur using a machine learning model trained on features associated with the deviation;
• collect additional module-level statistics or packet-level statistics at the identified network stage based on the deviation;
• and
• provide suggestions for debugging, optimizing, or testing the current network issue based on the deviation and the identified network stage.