Generating a training data set for a pattern-recognition model for electronic prognostication for a computer system

A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for training a pattern-recognition model for electronic prognostication for a computer system, the method comprising:

• monitoring a performance parameter in a set of performance parameters from a set of computer systems that includes at least two computer systems, wherein monitoring the performance parameter includes systematically monitoring and recording the set of performance parameters from computer systems in the set of computer systems, and wherein the recording process keeps track of the temporal relationships between events in different performance parameters in the set of performance parameters;
• generating a training data set based on the performance parameter monitored from the set of computer systems, wherein generating the training data set includes concatenating two or more time-series of the performance parameter from computer systems in the set of computer systems;
• training the pattern-recognition model using the training data set;
• and
• using the pattern-recognition model to look for anomalies in performance parameters gathered during normal operation of a target computer system;
• and
• generating an alarm when the pattern-recognition model detects an anomaly in the performance parameters from the target computer system.

An apparatus for electronic prognostication for a computer system, the apparatus comprising:

• a monitoring mechanism configured to monitor a performance parameter in a set of performance parameters from a set of computer systems, wherein the set of computer systems includes at least two computer systems, and wherein the monitoring mechanism is further configured to systematically monitor and record performance parameters in the set of performance parameters from computer systems in the set of computer systems and wherein the monitoring mechanism is further configured to keep track of the temporal relationships between events in different performance parameters in the set of performance parameters;
• and
• a generating mechanism configured to generate a training data set based on the performance parameter monitored from the set of computer systems, wherein the generating mechanism is configured to concatenate two or more time-series of the performance parameter from computer systems in the set of computer systems;
• a training mechanism configured to train the pattern-recognition model using the training data set;
• a surveillance mechanism configured to use the pattern-recognition model to look for anomalies in performance parameters gathered during operation of a monitored computer system;
• and
• an alarm-generation mechanism configured to generate an alarm when the pattern-recognition model detects an anomaly in the performance parameters from the monitored computer system.