Creating robustness scores for selected portions of a computing infrastructure

A system comprising:

• a memory for storing a machine learning model;
• and
• at least one processing device coupled to the memory, the processing device to:
• obtain first telemetry data associated with a selected portion of a computing infrastructure, the selected portion including a first node and a first hardware component;
• obtain first metadata associated with the selected portion;
• input one or more telemetry inputs corresponding to the first telemetry data into the machine learning model;
• input one or more metadata inputs corresponding to the first metadata into the machine learning model;
• generate, from the machine learning model, a first robustness score for the first hardware component representing a health state of the first hardware component;
• and
• retrain the machine learning model based, at least in part, on an event history of the first hardware component.

A method comprising:

• obtaining first telemetry data associated with a selected portion of a computing infrastructure, the selected portion including a first node and a first hardware component;
• obtaining first metadata associated with the selected portion;
• inputting one or more telemetry inputs corresponding to the first telemetry data into a machine learning model;
• inputting one or more metadata inputs corresponding to the first metadata into the machine learning model;
• generating, from the machine learning model, a first robustness score for the first hardware component representing a health state of the first hardware component;
• and
• retraining the machine learning model based, at least in part, on an event history of the first hardware component.