Denial-of-service detection system
A denial-of-service detection system includes a denial-of-service detection subsystem coupled to a plurality of storage systems via a network. The denial-of-service detection subsystem receives current first storage system data for each of a plurality of different storage system operating metrics from a first storage system included in the plurality of storage systems. Based on a historical storage system data for each of the plurality of different storage system operating metrics that was previously received from the plurality of storage devices, the denial-of-service subsystem detects an operating anomaly in the current first storage system data for at least one of the plurality of different storage system operating metrics, identifies a time-series similarity in a subset of respective time-series of the current first storage system data for each of the plurality of different storage system operating metrics for which the operating anomaly was detected and, in response, performs a denial-of-service remediation action.
1. A denial-of-service detection system, comprising:
a plurality of storage systems; and
a denial-of-service detection subsystem that is coupled to the plurality of storage systems via a network, wherein the denial-of-service detection subsystem is configured to:
receive, from a first storage system that is included in the plurality of storage systems, current first storage system data for each of a plurality of different storage system operating metrics;
detect, based on a historical storage system data for each of the plurality of different storage system operating metrics that was previously received from the plurality of storage devices, an operating anomaly in the current first storage system data for at least one of the plurality of different storage system operating metrics;
generate, in response to detecting the operating anomaly in the current first storage system data, a respective time-series of the current first storage system data for each of the plurality of different storage system operating metrics for which the operating anomaly was detected;
determine a plurality of time-series comparisons for each of the respective time-series;
weight each of the plurality of time-series comparisons for each of the respective time-series to provide respective weighted time-series;
compare a respective shape of each of the respective time series to a corresponding anomaly detection time-series included in an anomaly detection model by comparing each respective weighted time-series to the corresponding anomaly detection time-series included in the anomaly detection model;
identify, based on the comparison of the respective shape of each of the respective time series to the corresponding anomaly detection time-series included in the anomaly detection model, a time-series similarity between each of a subset of the respective time-series and the corresponding anomaly detection time-series for that respective time-series; and
perform, in response to identifying the time-series similarity between each of the subset of the respective time-series and the corresponding anomaly detection time-series for that respective time-series, a denial-of-service remediation action.
2. The system of claim 1 , wherein the denial-of-service detection subsystem is configured to:
receive, from each of the plurality of storage systems prior to receiving the current first storage system data from the first storage system, the historical storage system data for each of the plurality of different storage system operating metrics; and
generate, using the historical storage system data, the anomaly detection model.
3. The system of claim 2 , wherein the anomaly detection model is generated using a machine-learning algorithm that is included in the denial-of-service detection subsystem.
4. The system of claim 1 , wherein the identifying the time-series similarity between each of the subset of respective time-series and the corresponding anomaly detection time-series for that respective time-series includes:
identifying at least one first storage system performance time-series similarity; and
identifying at least one first storage system network time-series similarity.
5. The system of claim 1 , wherein the plurality of different storage system operating metrics include at least one storage system performance metric and at least one storage system network metric.
6. The system of claim 1 , wherein the detecting the operating anomaly in the current first storage system data for the at least one of the plurality of different storage system operating metrics includes:
detecting the operating anomaly in the current first storage system data for each of the plurality of different storage system operating metrics.
7. An Information Handling System (IHS), comprising:
a processing system; and
a memory system that is coupled to the processing system and that includes instructions that, when executed by the processing system, cause the processing system to provide a denial-of-service detection engine that is configured to:
receive, from a first storage system that is included in a plurality of storage systems, current first storage system data for each of a plurality of different storage system operating metrics;
detect, based on a historical storage system data for each of the plurality of different storage system operating metrics that was previously received from the plurality of storage devices, an operating anomaly in the current first storage system data for at least one of the plurality of different storage system operating metrics;
generate, in response to detecting the operating anomaly in the current first storage system data, a respective time-series of the current first storage system data for each of the plurality of different storage system operating metrics for which the operating anomaly was detected;
determine a plurality of time-series comparisons for each of the respective time-series;
weight each of the plurality of time-series comparisons for each of the respective time-series to provide respective weighted time-series;
compare a respective shape of each of the respective time series to a corresponding anomaly detection time-series included in an anomaly detection model by comparing each respective weighted time-series to the corresponding anomaly detection time-series included in the anomaly detection model;
identify, based on the comparison of the respective shape of each of the respective time series to the corresponding anomaly detection time-series included in the anomaly detection model, a time-series similarity between each of a subset of the respective time-series and the corresponding anomaly detection time-series for that respective time-series; and
perform, in response to identifying the time-series similarity between each of the subset of the respective time-series and the corresponding anomaly detection time-series for that respective time-series, a denial-of-service remediation action.
8. The IHS of claim 7 , wherein the denial-of-service detection engine is configured to:
receive, from each of the plurality of storage systems prior to receiving the current first storage system data from the first storage system, the historical storage system data for each of the plurality of different storage system operating metrics; and
generate, using the historical storage system data, the anomaly detection model.
9. The IHS of claim 8 , wherein the anomaly detection model is generated using a machine-learning algorithm that is included in the denial-of-service detection engine.
10. The IHS of claim 7 , wherein the identifying the time-series similarity between each of the subset of respective time-series and the corresponding anomaly detection time-series for that respective time-series includes:
identifying at least one first storage system performance time-series similarity; and
identifying at least one first storage system network time-series similarity.
11. The IHS of claim 7 , wherein the plurality of different storage system operating metrics include at least one storage system performance metric and at least one storage system network metric.
12. The IHS of claim 7 , wherein the respective time-series of the current first storage system data for each of the plurality of different storage system operating metrics includes a covariance for the time-series, a Dynamic Time Warping (DTW) distance for the time-series, and a Shape-Based Distance (SBD) distance for the time series.
13. The IHS of claim 7 , wherein the detecting the operating anomaly in the current first storage system data for the at least one of the plurality of different storage system operating metrics includes:
detecting the operating anomaly in the current first storage system data for each of the plurality of different storage system operating metrics.
14. A method for detecting denial-of-service situations, comprising:
receiving, by a denial-of-service subsystem from a first storage system that is included in a plurality of storage systems, current first storage system data for each of a plurality of different storage system operating metrics;
detecting, by the denial-of-service subsystem based on a historical storage system data for each of the plurality of different storage system operating metrics that was previously received from the plurality of storage devices, an operating anomaly in the current first storage system data for at least one of the plurality of different storage system operating metrics;
generating, by the denial-of-service subsystem in response to detecting the operating anomaly in the current first storage system data, a respective time-series of the current first storage system data for each of the plurality of different storage system operating metrics for which the operating anomaly was detected;
determining, by the denial-of-service subsystem, a plurality of time-series comparisons for each of the respective time-series;
weighting, by the denial-of-service subsystem, each of the plurality of time-series comparisons for each of the respective time-series to provide respective weighted time-series;
comparing, by the denial-of-service subsystem, a respective shape of each of the respective time series to a corresponding anomaly detection time-series included in an anomaly detection model by comparing each respective weighted time-series to the corresponding anomaly detection time-series included in the anomaly detection model;
identifying, by the denial-of-service subsystem based on the comparison of the respective shape of each of the respective time series to the corresponding anomaly detection time-series included in the anomaly detection model, a time-series similarity between each of a subset of the respective time-series and the corresponding anomaly detection time-series for that respective time-series; and
performing, by the denial-of-service subsystem in response to identifying the time-series similarity between each of the subset of the respective time-series and the corresponding anomaly detection time-series for that respective time-series, a denial-of-service remediation action.
15. The method of claim 14 , further comprising:
receiving, by the denial-of-service subsystem from each of the plurality of storage systems prior to receiving the current first storage system data from the first storage system, the historical storage system data for each of the plurality of different storage system operating metrics; and
generating, by the denial-of-service subsystem using the historical storage system data, the anomaly detection model.
16. The method of claim 15 , wherein the anomaly detection model is generated using a machine-learning algorithm that is included in the denial-of-service detection engine.
17. The method of claim 14 , wherein the identifying the time-series similarity between each of the subset of respective time-series and the corresponding anomaly detection time-series for that respective time-series includes:
identifying at least one first storage system performance time-series similarity; and
identifying at least one first storage system network time-series similarity.
18. The method of claim 14 , wherein the plurality of different storage system operating metrics include at least one storage system performance metric and at least one storage system network metric.
19. The method of claim 14 , wherein the respective time-series of the current first storage system data for each of the plurality of different storage system operating metrics includes a covariance for the time-series, a Dynamic Time Warping (DTW) distance for the time-series, and a Shape-Based Distance (SBD) distance for the time series.
20. The method of claim 14 , wherein the detecting the operating anomaly in the current first storage system data for the at least one of the plurality of different storage system operating metrics includes:
detecting the operating anomaly in the current first storage system data for each of the plurality of different storage system operating metrics.