Anomaly detection using zonal parameter characteristics and non-linear scoring

1. A computer-implemented method for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer-implemented method comprising:

identifying, by a computer, anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detecting, by the computer, anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classifying, by the computer, the anomalies into a corresponding anomaly category;

determining, by the computer, a root cause of the anomalies based on the corresponding anomaly category; and

performing, by the computer, one or more action steps to remediate the root cause of the anomalies and pre-empt the anomalies.

2. The computer-implemented method of claim 1 further comprising:

receiving, by the computer, the time series data including the parameter and the group of parameters from a client device via a network;

performing, by the computer, an analysis of the parameter and the group of parameters over a specified time interval within the time series data; and

identifying, by the computer, behavioral characteristics of the parameter and the group of parameters during the specified time interval within the time series data based on the analysis.

3. The computer-implemented method of claim 1 further comprising:

inputting, by the computer, a zone of similar parameter behavioral characteristics into the plurality of artificial intelligence models.

4. The computer-implemented method of claim 1 further comprising:

sending, by the computer, a notification to a system analyst regarding the root cause of the anomalies.

5. The computer-implemented method of claim 1 further comprising:

converting, by the computer, the parameter and the group of parameters into a sparse distributed representation in a form of bit arrays; and

inputting, by the computer, the sparse distributed representation into the optimal artificial intelligence model to determine whether parameter behavior is anomalous or non-anomalous.

6. The computer-implemented method of claim 1 , wherein the plurality of artificial intelligence models is hierarchical temporal memory.

7. The computer-implemented method of claim 1 , wherein the parameter is a univariate parameter, and wherein the group of parameters is multivariate parameters.

8. A computer-implemented method for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer-implemented method comprising:

identifying, by a computer, anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detecting, by the computer, anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classifying, by the computer, the anomalies into a corresponding anomaly category;

determining, by the computer, a root cause of the anomalies based on the corresponding anomaly category;

performing, by the computer, one or more action steps to remediate the root cause of the anomalies;

receiving, by the computer, the time series data including the parameter and the group of parameters from a client device via a network;

performing, by the computer, an analysis of the parameter and the group of parameters over a specified time interval within the time series data;

identifying, by the computer, behavioral characteristics of the parameter and the group of parameters during the specified time interval within the time series data based on the analysis;

generating, by the computer, sets of similar parameter behavioral characteristics based on identified behavioral characteristics of the parameter and the group of parameters;

placing, by the computer, each set of similar parameter behavioral characteristics into a respective zone of a plurality of zones in the specified time interval within the time series data, each zone including a particular set of similar parameter behavioral characteristics; and

marking, by the computer, each respective zone of similar parameter behavioral characteristics in the specified time interval within the time series data.

9. A computer-implemented method for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer-implemented method comprising:

identifying, by a computer, anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detecting, by the computer, anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classifying, by the computer, the anomalies into a corresponding anomaly category;

determining, by the computer, a root cause of the anomalies based on the corresponding anomaly category;

performing, by the computer, one or more action steps to remediate the root cause of the anomalies;

inputting, by the computer, a zone of similar parameter behavioral characteristics into the plurality of artificial intelligence models;

generating, by the computer, a non-linear score for each respective artificial intelligence model of the plurality of artificial intelligence models based on each respective artificial intelligence model processing the zone of similar parameter behavioral characteristics; and

identifying, by the computer, the optimal artificial intelligence model in the plurality of artificial intelligence models based on comparing the non-linear score of each respective artificial intelligence model.

10. A computer system for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer system comprising:

a bus system used to implement communications;

a storage device connected to the bus system, wherein the storage device stores program instructions; and

a processor connected to the bus system, wherein the processor executes the program instructions to:

identify anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detect anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classify the anomalies into a corresponding anomaly category;

determine a root cause of the anomalies based on the corresponding anomaly category; and

perform one or more action steps to remediate the root cause of the anomalies and pre-empt the anomalies.

11. The computer system of claim 10 , wherein the processor further executes the program instructions to:

receive the time series data including the parameter and the group of parameters from a client device via a network;

perform an analysis of the parameter and the group of parameters over a specified time interval within the time series data; and

identify behavioral characteristics of the parameter and group of parameters during the specified time interval within the time series data based on the analysis.

12. The computer system of claim 10 , wherein the processor further executes the program instructions to:

input a zone of similar parameter behavioral characteristics into the plurality of artificial intelligence models.

13. A computer system for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer system comprising:

a bus system used to implement communications;

a storage device connected to the bus system, wherein the storage device stores program instructions; and

a processor connected to the bus system, wherein the processor executes the program instructions to:

identify anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detect anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classify the anomalies into a corresponding anomaly category;

determine a root cause of the anomalies based on the corresponding anomaly category;

perform one or more action steps to remediate the root cause of the anomalies;

receive the time series data including the parameter and the group of parameters from a client device via a network;

perform an analysis of the parameter and the group of parameters over a specified time interval within the time series data;

identify behavioral characteristics of the parameter and group of parameters during the specified time interval within the time series data based on the analysis

generate sets of similar parameter behavioral characteristics based on identified behavioral characteristics of the parameter and the group of parameters;

place each set of similar parameter behavioral characteristics into a respective zone of a plurality of zones in the specified time interval within the time series data, each zone including a particular set of similar parameter behavioral characteristics; and

mark each respective zone of similar parameter behavioral characteristics in the specified time interval within the time series data.

14. A computer system for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer system comprising:

a bus system used to implement communications;

a storage device connected to the bus system, wherein the storage device stores program instructions; and

a processor connected to the bus system, wherein the processor executes the program instructions to:

identify anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detect anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classify the anomalies into a corresponding anomaly category;

determine a root cause of the anomalies based on the corresponding anomaly category;

perform one or more action steps to remediate the root cause of the anomalies;

input a zone of similar parameter behavioral characteristics into the plurality of artificial intelligence models;

generate a non-linear score for each respective artificial intelligence model of the plurality of artificial intelligence models based on each respective artificial intelligence model processing the zone of similar parameter behavioral characteristics; and

identify the optimal artificial intelligence model in the plurality of artificial intelligence models based on comparing the non-linear score of each respective artificial intelligence model.

15. A computer program product for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions, when executed by a computer, cause the computer to perform a method comprising:

identifying, by the computer, anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detecting, by the computer, anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classifying, by the computer, the anomalies into a corresponding anomaly category;

determining, by the computer, a root cause of the anomalies based on the corresponding anomaly category; and

performing, by the computer, one or more action steps to remediate the root cause of the anomalies and pre-empt the anomalies.

16. The computer program product of claim 15 further comprising:

receiving, by the computer, the time series data including the parameter and the group of parameters from a client device via a network;

performing, by the computer, an analysis of the parameter and the group of parameters over a specified time interval within the time series data; and

identifying, by the computer, behavioral characteristics of the parameter and the group of parameters during the specified time interval within the time series data based on the analysis.

17. The computer program product of claim 15 further comprising:

inputting, by the computer, a zone of similar parameter behavioral characteristics into the plurality of artificial intelligence models.

18. The computer program product of claim 15 further comprising:

sending, by the computer, a notification to a system analyst regarding the root cause of the anomalies.

19. A computer program product for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions, when executed by a computer, cause the computer to perform a method comprising:

identifying, by the computer, anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detecting, by the computer, anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classifying, by the computer, the anomalies into a corresponding anomaly category;

determining, by the computer, a root cause of the anomalies based on the corresponding anomaly category;

performing, by the computer, one or more action steps to remediate the root cause of the anomalies;

receiving, by the computer, the time series data including the parameter and the group of parameters from a client device via a network;

performing, by the computer, an analysis of the parameter and the group of parameters over a specified time interval within the time series data;

identifying, by the computer, behavioral characteristics of the parameter and the group of parameters during the specified time interval within the time series data based on the analysis;

generating, by the computer, sets of similar parameter behavioral characteristics based on identified behavioral characteristics of the parameter and the group of parameters;

placing, by the computer, each set of similar parameter behavioral characteristics into a respective zone of a plurality of zones in the specified time interval within the time series data, each zone including a particular set of similar parameter behavioral characteristics; and

marking, by the computer, each respective zone of similar parameter behavioral characteristics in the specified time interval within the time series data.

20. A computer program product for anomaly detection using zonal parameter characteristics and non-linear scoring, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions, when executed by a computer, cause the computer to perform a method comprising:

identifying, by the computer, anomalous behavior characteristics of a parameter and group of parameters within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models;

detecting, by the computer, anomalies based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data;

classifying, by the computer, the anomalies into a corresponding anomaly category;

determining, by the computer, a root cause of the anomalies based on the corresponding anomaly category;

performing, by the computer, one or more action steps to remediate the root cause of the anomalies;

inputting, by the computer, a zone of similar parameter behavioral characteristics into the plurality of artificial intelligence models;

generating, by the computer, a non-linear score for each respective artificial intelligence model of the plurality of artificial intelligence models based on each respective artificial intelligence model processing the zone of similar parameter behavioral characteristics; and

identifying, by the computer, the optimal artificial intelligence model in the plurality of artificial intelligence models based on comparing the non-linear score of each respective artificial intelligence model.