Techniques for management data analytics (mda) process and service

One or more non-transitory, computer-readable media (NTCRM) having instructions, stored thereon, that when executed by one or more processors cause a management data analytics (MDA) service producer to:

• receive training data from a MDA consumer, the training data including a training input and a corresponding desired output;
• train a machine learning model based on the training data;
• receive raw data associated with one or more managed networks or services;
• apply the trained machine learning model to the raw data to generate analytics output data;
• and
• send the analytics output data to a MDA consumer.

One or more non-transitory, computer-readable media (NTCRM) having instructions, stored thereon, that when executed by one or more processors cause a management data analytics (MDA) consumer to:

• provide training data related to network functions associated with a network or service to a MDA producer to train a machine learning model;
• receive analytics output data from the trained machine learning model that indicates a recommended action to address a conflict between the network functions;
• and
• perform the recommended action.

An apparatus to implement a management data analytics (MDA) service producer, the apparatus comprising:

• processing circuitry to:
• receive training data from a MDA consumer associated with a managed network or service, wherein the training data includes a training input and a corresponding desired output;
• provide the training data to a machine learning model to train the machine learning model;
• receive raw data associated with network functions;
• and
• provide the raw data to the trained machine learning model to generate output data that indicates a conflict associated with the network functions and a recommended action to address the conflict;
• and
• a memory to store the raw data and the analytics output data.