Calculating normalized metrics

Patent metadata

Field	Value
Publication number	US-10152302-B2
Application number	US-201715404599-A
Country	US
Kind code	B2
Filing date	Jan 12, 2017
Priority date	Jan 12, 2017
Publication date	Dec 11, 2018
Grant date	Dec 11, 2018

Abstract

Examples relate to calculating normalize metrics. The examples disclosed herein calculate respective normalized first metric values for each of a plurality of first metric values that are on a time scale and respective normalized second metric values for each of the plurality of raw second metric values that are on the time scale, where the plurality of first metric values are associated with a first metric, and the plurality of second metric values are associated with a second metric. An extremum of the normalized first metric value and the normalized second metric value at each time of the time scale is averaged to calculate a plurality of extremum baseline values. Examples herein calculate a plurality of sleeve values of the plurality of extremum baseline values based on a standard deviation of the plurality of extremum baseline values.

First claim

What is claimed is:

1. A method executed by a computing device, comprising:
calculating respective normalized first metric values for each of a plurality of first metric values that are on a time scale and respective normalized second metric values for each of a plurality of second metric values that are on the time scale, wherein the plurality of first metric values are associated with a first metric, and the plurality of second metric values are associated with a second metric;
identifying an extremum of the normalized first metric value and the normalized second metric value at each time of the time scale to determine a plurality of extremum baseline values;
determining a plurality of sleeve values of the plurality of extremum baseline values;
identifying an anomaly in a computing system based on the plurality of extremum baseline values and the plurality of sleeve values; and
in response to the identifying of the anomaly, performing an automated remedial action to address the anomaly in the computing system.

2. The method of claim 1 , further comprising identifying an outlier value by identifying at least one of the plurality of extremum baseline values that is beyond a threshold value of the sleeve value at a corresponding time of the time scale.

3. The method of claim 2 , further comprising identifying a problematic metric based on the outlier value, the problematic metric corresponding to the anomaly.

4. The method of claim 2 , wherein:
the plurality of extremum baseline values comprises a maximum of the normalized first metric value and the normalized second metric value at each time of the time scale;
the plurality of sleeve values comprises a plurality of upper sleeve values; and
the outlier value is identified by identifying at least one of the plurality of maximum baseline values that is greater than the upper sleeve value at a corresponding time of the time scale.

5. The method of claim 2 , wherein:
the plurality of extremum baseline values comprises a minimum of the normalized first metric value and the normalized second metric value at each time of the time scale;
the plurality of sleeve values comprises a plurality of lower sleeve values; and
the outlier value is identified by identifying at least one of the plurality of minimum baseline values that is less than the lower sleeve value at a corresponding time of the time scale.

6. The method of claim 1 , wherein:
calculating each normalized first metric value is based on comparing a difference between a first metric value and an average first metric value with a standard deviation of the plurality of first metric values;
calculating each normalized second metric value is based on comparing a difference between a second metric value and an average second metric value with a standard deviation of the plurality of second metric values; and
the average first metric value and the average second metric value are calculated based on a forgetting factor.

7. The method of claim 6 , wherein:
the standard deviation of the plurality of first metric values is calculated based on a square of the average first metric value and an average of squares of the plurality of first metric values; and
the standard deviation of the plurality of second metric values is calculated based on a square of the average second metric value and an average of squares of the plurality of second metric values.

8. The method of claim 1 , further comprising:
in addition to performing the automated remedial action, presenting the plurality of extremum baseline values and the plurality of sleeve values to a user.

9. The method of claim 8 , further comprising generating a graphical representation comprising the plurality of extremum baseline values and the plurality of sleeve values aligned with a first axis representing the time scale and a second axis representing normalized metric values.

10. The method of claim 1 , wherein the first metric is a first computer performance metric and the second metric is a second computer performance metric.

11. A non-transitory machine-readable storage medium encoded with instructions that upon execution cause a computing device to:
calculate respective normalized first metric values for each of a plurality of first metric values that are on a time scale and respective normalized second metric values for each of a plurality of second metric values that are on the time scale, wherein the plurality of first metric values are associated with a first computing metric, and the plurality of second metric values are associated with a second computing metric;
identify an extremum of the normalized first metric value and the normalized second metric value at each time of the time scale to determine a plurality of extremum baseline values; and
determine a plurality of sleeve values of the plurality of extremum baseline values;
identify an outlier value by identifying at least one of the plurality of extremum baseline values that is beyond a threshold value of the sleeve value at a corresponding time of the time scale;
identify a problematic metric based on the outlier value, the problematic metric representing an anomaly in a computing system; and
cause performance of an automated remedial action to address the anomaly in the computing system.

12. The non-transitory machine-readable storage medium of claim 11 , wherein:
the plurality of extremum baseline values comprises a maximum of the normalized first metric value and the normalized second metric value at each time of the time scale;
the plurality of sleeve values comprises a plurality of upper sleeve values; and
the outlier value is identified by identifying at least one of the plurality of maximum baseline values that is greater than the upper sleeve value at a corresponding time of the time scale.

13. The non-transitory machine-readable storage medium of claim 11 , wherein:
the plurality of extremum baseline values comprises a minimum of the normalized first metric value and the normalized second metric value at each time of the time scale;
the plurality of sleeve values comprises a plurality of lower sleeve values; and
the outlier value is identified by identifying at least one of the plurality of minimum baseline values that is less than the lower sleeve value at a corresponding time of the time scale.

14. The non-transitory machine-readable storage medium of claim 11 , wherein:
each normalized first metric value is calculated based on comparing a difference between a first metric value and an average first metric value with a standard deviation of the plurality of first metric values;
each normalized second metric value is calculated based on comparing a difference between a second metric value and an average second metric value with a standard deviation of the plurality of second metric values; and
the average first metric value and the average second metric value are calculated based on a forgetting factor.

15. The non-transitory machine-readable storage medium of claim 14 , wherein:
the standard deviation of the plurality of first metric values is calculated based on a square of the average first metric value and an average of squares of the plurality of first metric values; and
the standard deviation of the plurality of second metric values is calculated based on a square of the average second metric value and an average of squares of the plurality of second metric values.

16. The non-transitory machine-readable storage medium of claim 11 , wherein the instructions upon execution cause the computing device to generate a graphical represe

Assignees

• Hewlett Packard Entpr Dev Lp
• Entit Software Llc

Inventors

• Dayan Gabriel
• Revach Eli
• Danichev Pavel
• Mor Avihay

Classifications

• G06F7/544

  for evaluating functions by calculation {(G06F7/4824 takes precedence)} · CPC title

• G06F17/18 Primary

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• G06F5/01 Primary

  for shifting, e.g. justifying, scaling, normalising {(digital stores in which the information is moved stepwise, e.g. shift-registers G11C19/00; digital stores in which the information circulates G11C21/00)} · CPC title