Event-based operational data collection for impacted components
A method comprises receiving a notification of an issue with at least one component of a plurality of components in a computing environment. One or more machine learning algorithms are used to determine one or more components of the plurality of components impacted by the issue with the at least one component. The method further comprises collecting operational data for the at least one component and the one or more impacted components.
1. An apparatus comprising:
at least one processing platform comprising a plurality of processing devices;
said at least one processing platform being configured:
to receive a notification of an issue with at least one component of a plurality of components in a computing environment;
to determine, using one or more machine learning algorithms, one or more components of the plurality of components impacted by the issue with the at least one component, and an impact hierarchy of the one or more impacted components, wherein the impact hierarchy arranges the one or more impacted components in an order of impact by the issue with the at least one component;
to collect operational data for the at least one component and the one or more impacted components, wherein the operational data is collected starting from the at least one component and from the one or more impacted components in the order corresponding to the impact hierarchy; and
to train the one or more machine learning algorithms with data corresponding to operation of the plurality of components and how the plurality of components interact with each other.
2. The apparatus of claim 1 wherein said at least one processing platform is configured to perform the determining and the collecting as a real-time response to the receiving of the notification of the issue with the at least one component.
3. The apparatus of claim 1 wherein, in determining the one or more impacted components, said at least one processing platform is configured:
to compute physical distances of respective ones of the plurality of components from the at least one component; and
to determine whether the respective ones of the plurality of components are impacted by the issue with the at least one component based at least in part on their computed physical distances.
4. The apparatus of claim 1 wherein, in determining the one or more impacted components, said at least one processing platform is configured:
to predict failure dates of respective ones of the plurality of components based at least in part on manufacture dates of the respective ones of the plurality of components; and
to determine whether the respective ones of the plurality of components are impacted by the issue with the at least one component based at least in part on their predicted failure dates.
5. The apparatus of claim 1 wherein, in determining the one or more impacted components, said at least one processing platform is configured:
to compute mean times between failure of respective ones of the plurality of components; and
to determine whether the respective ones of the plurality of components are impacted by the issue with the at least one component based at least in part on their computed mean times between failure.
6. The apparatus of claim 1 wherein, in determining the one or more impacted components, said at least one processing platform is configured:
to calculate heat resistance values of respective ones of the plurality of components; and
to determine whether the respective ones of the plurality of components are impacted by the issue with the at least one component based at least in part on their calculated heat resistance values.
7. The apparatus of claim 1 wherein the one or more machine learning algorithms comprises a k-Nearest Neighbor (KNN) algorithm.
8. The apparatus of claim 7 wherein, in determining the one or more impacted components, said at least one processing platform is configured to analyze one or more parameters with the KNN algorithm, and wherein the one or more parameters comprise at least one of physical distances of respective ones of the plurality of components from the at least one component, failure dates of the respective ones of the plurality of components, mean times between failure of the respective ones of the plurality of components, and heat resistance values of the respective ones of the plurality of components.
9. The apparatus of claim 1 wherein the operational data comprises at least one of states of the at least one component and the one or more impacted components, and operational logs of the at least one component and the one or more impacted components.
10. The apparatus of claim 9 wherein said at least one processing platform is configured to collect the operational data for the at least one component and the one or more impacted components at a time of generation of the notification.
11. The apparatus of claim 1 wherein said at least one processing platform is further configured to upload the collected operational data to a cloud storage platform.
12. A method comprising:
receiving a notification of an issue with at least one component of a plurality of components in a computing environment;
determining, using one or more machine learning algorithms, one or more components of the plurality of components impacted by the issue with the at least one component, and an impact hierarchy of the one or more impacted components, wherein the impact hierarchy arranges the one or more impacted components in an order of impact by the issue with the at least one component;
collecting operational data for the at least one component and the one or more impacted components, wherein the operational data is collected starting from the at least one component and from the one or more impacted components in the order corresponding to the impact hierarchy; and
training the one or more machine learning algorithms with data corresponding to operation of the plurality of components and how the plurality of components interact with each other;
wherein the method is performed by at least one processing platform comprising at least one processing device comprising a processor coupled to a memory.
13. The method of claim 12 wherein the determining and the collecting are performed as a real-time response to the receiving of the notification of the issue with the at least one component.
14. The method of claim 12 wherein the one or more machine learning algorithms comprises a k-Nearest Neighbor (KNN) algorithm.
15. The method of claim 14 wherein determining the one or more impacted components comprises analyzing one or more parameters with the KNN algorithm, and wherein the one or more parameters comprise at least one of physical distances of respective ones of the plurality of components from the at least one component, failure dates of the respective ones of the plurality of components, mean times between failure of the respective ones of the plurality of components, and heat resistance values of the respective ones of the plurality of components.
16. The method of claim 12 further comprising uploading the collected operational data to a cloud storage platform.
17. 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 platform causes said at least one processing platform:
to receive a notification of an issue with at least one component of a plurality of components in a computing environment;
to determine, using one or more machine learning algorithms, one or more components of the plurality of components impacted by the issue with the at least one component, and an impact hierarchy of the one or more impacted components, wherein the impact hierarchy arranges the one or more impacted components in an order of impact by the issue with the at least one component;
to collect operational data for the at least one component and the one or more impacted components, wherein the operational data is collected starting from the at least one component and from the one or more impacted components in the order corresponding to the impact hierarchy; and
to train the one or more machine learning algorithms with data corresponding to operation of the plurality of components and how the plurality of components interact with each other.
18. The computer program product according to claim 17 wherein the one or more machine learning algorithms comprises a k-Nearest Neighbor (KNN) algorithm.
19. The computer program product according to claim 18 wherein, in determining the one or more impacted components, the program code causes said at least one processing platform to analyze one or more parameters with the KNN algorithm, and wherein the one or more parameters comprise at least one of physical distances of respective ones of the plurality of components from the at least one component, failure dates of the respective ones of the plurality of components, mean times between failure of the respective ones of the plurality of components, and heat resistance values of the respective ones of the plurality of components.
20. The computer program product according to claim 17 wherein the program code further causes said at least one processing platform to upload the collected operational data to a cloud storage platform.