Usage-banded anomaly detection and remediation utilizing analysis of system metrics
A method comprises collecting a set of data from an information processing system, wherein the set of data represents one or more system metrics associated with the information processing system. The method tags data values in the collected set of data with usage bands selected from a plurality of predefined usage bands, wherein each usage band represents a unique range of values within which data values in the set of data can be categorized. Further, the tagged data values are segregated into at least a first set and a second set based on the usage bands. A first anomaly detection algorithm is applied to the first set and a second anomaly detection algorithm is applied to the second set to generate anomaly data sets. The anomaly data sets are mapped back to the collected set of data to identify one or more specific anomalies.
1. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory, the at least one processing device, when executing program code, is configured to:
collect a set of data from an information processing system, wherein the set of data represents one or more system metrics associated with the information processing system;
tag data values in the collected set of data with usage bands selected from a plurality of predefined usage bands, wherein each usage band in the plurality of predefined usage bands represents a unique range of values within which data values in the set of data can be categorized;
detect one or more usage band anomalies associated with the one or more system metrics of the set of data and the tagged data values;
segregate the tagged data values into at least a first set and a second set based on the usage bands, the first set containing data associated with the detected one or more usage band anomalies, and the second set containing data which does not belong to the first set;
apply a first anomaly detection algorithm to the first set and a second anomaly detection algorithm to the second set to generate anomaly data sets; and
map the anomaly data sets back to the collected set of data to identify one or more specific anomalies in the set of data;
wherein the first anomaly detection algorithm searches for first data concentrations for at least the first set, and the second anomaly detection algorithm searches for second data concentrations for at least the second set.
2. The apparatus of claim 1 , wherein the processing device, when executing program code, is further configured to cause a remediation of the one or more specific anomalies.
3. The apparatus of claim 1 , wherein the processing device, when executing program code, is further configured to normalize the collected set of data.
4. The apparatus of claim 3 , wherein the collected set of data is normalized using a normal curve distribution.
5. The apparatus of claim 1 , wherein the set of data collected from the information processing system comprises different types of system metrics.
6. The apparatus of claim 5 , wherein one type of system metric comprises determinants and another type of system metric comprises variables.
7. The apparatus of claim 6 , wherein the processing device, when executing program code, is further configured to apply anomaly detection to the determinants and the variables such that, when no anomalies are found, one or more of the variables are tagged as non-influencers, while remaining ones of the variables are tagged as influencers.
8. The apparatus of claim 7 , wherein the first set comprises data which has average values of influencers.
9. The apparatus of claim 8 , wherein segregating at least a portion of the tagged data values into a third set containing mixed data with average values and other values.
10. The apparatus of claim 1 , wherein the first data concentrations comprise minimal data concentrations and wherein the second data concentrations comprise maximal data concentrations.
11. A method comprising:
collecting a set of data from an information processing system, wherein the set of data represents one or more system metrics associated with the information processing system;
tagging data values in the collected set of data with usage bands selected from a plurality of predefined usage bands, wherein each usage band in the plurality of predefined usage bands represents a unique range of values within which data values in the set of data can be categorized;
detecting one or more usage band anomalies associated with the one or more system metrics of the set of data and the tagged data values;
segregating the tagged data values into at least a first set and a second set based on the usage bands, the first set containing data associated with the detected one or more usage band anomalies, and the second set containing data which does not belong to the first set;
applying a first anomaly detection algorithm to the first set and a second anomaly detection algorithm to the second set to generate anomaly data sets; and
mapping the anomaly data sets back to the collected set of data to identify one or more specific anomalies in the set of data;
wherein the first anomaly detection algorithm searches for first data concentrations for at least the first set, and the second anomaly detection algorithm searches for second data concentrations for at least the second set; and
wherein the steps are performed by at least one processing device, comprising a processor coupled to a memory, executing program code.
12. The method of claim 11 , further comprising causing remediation of the one or more specific anomalies.
13. The method of claim 11 , further comprising normalizing the collected set of data using a normal curve distribution.
14. The method of claim 11 , wherein the set of data collected from the information processing system comprises different types of system metrics.
15. The method of claim 14 , wherein one type of system metric comprises determinants and another type of system metric comprises variables.
16. The method of claim 15 , wherein the processing device, when executing program code, is further configured to apply anomaly detection to the determinants and the variables such that, when no anomalies are found, one or more of the variables are tagged as non-influencers, while remaining ones of the variables are tagged as influencers.
17. The method of claim 16 , wherein the first set comprises data which has average values of influencers.
18. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device cause the at least one processing device to:
collect a set of data from an information processing system, wherein the set of data represents one or more system metrics associated with the information processing system;
tag data values in the collected set of data with usage bands selected from a plurality of predefined usage bands, wherein each usage band in the plurality of predefined usage bands represents a unique range of values within which data values in the set of data can be categorized;
detect one or more usage band anomalies associated with the one or more system metrics of the set of data and the tagged data values;
segregate the tagged data values into at least a first set and a second set based on the usage bands, the first set containing data associated with the detected one or more usage band anomalies, and the second set containing data which does not belong to the first set;
apply a first anomaly detection algorithm to the first set and a second anomaly detection algorithm to the second set to generate anomaly data sets; and
map the anomaly data sets back to the collected set of data to identify one or more specific anomalies in the set of data;
wherein the first anomaly detection algorithm searches for first data concentrations for at least the first set, and the second anomaly detection algorithm searches for second data concentrations for at least the second set.
19. The computer program product of claim 18 , further comprising causing a remediation of the one or more specific anomalies.
20. The method of claim 11 , wherein the first data concentrations comprise minimal data concentrations and wherein the second data concentrations comprise maximal data concentrations.