Anomaly detection for multiple parameters

A system comprising:

• one or more processors coupled to a memory comprising non-transitory computer instructions that, when executed by the one or more processors, perform operations comprising:
• accessing one or more data objects including a data set that has been collected over a given span of time, the data set representing a plurality of parameters corresponding to resource utilization of a given server;
• computing first and second statistical measures based on the plurality of parameters, the first statistical measure being computed using a first model that is generated based on a sequence of recent data points, the second statistical measure being computed using a second model that is generated based on historical values of data points each associated with a recurring time period, one or more of the historical values of data points being different from the recent data points;
• obtaining current resource utilization corresponding to at least a subset of the plurality of parameters;
• determining a first condition in which values of the current resource utilization exceed a first threshold associated with the first statistical measure;
• determining a second condition in which values of the data set corresponding to a time period associated with the current resource utilization exceed a second threshold associated with the second statistical measure;
• triggering an anomaly detection operation in response to determining the first and second conditions based on a combination of outputs of the first and second models;
• and
• in response to the anomaly detection operation being triggered, changing resources allocated to the given server.

A non-transitory computer readable medium comprising non-transitory computer-readable instructions for performing operations comprising:

• accessing one or more data objects including a data set that has been collected over a given span of time, the data set representing a plurality of parameters corresponding to resource utilization of a given server;
• computing first and second statistical measures based on the plurality of parameters, the first statistical measure being computed using a first model that is generated based on a sequence of recent data points, the second statistical measure being computed using a second model that is generated based on historical values of data points each associated with a recurring time period, one or more of the historical values of data points being different from the recent data points;
• obtaining current resource utilization corresponding to at least a subset of the plurality of parameters;
• determining a first condition in which values of the current resource utilization exceed a first threshold associated with the first statistical measure;
• determining a second condition in which values of the data set corresponding to a time period associated with the current resource utilization exceed a second threshold associated with the second statistical measure;
• triggering an anomaly detection operation in response to determining the first and second conditions based on a combination of outputs of the first and second models;
• and
• in response to the anomaly detection operation being triggered, changing resources allocated to the given server.