Datacenter IoT-triggered preemptive measures using machine learning
One example method includes performing a machine learning process that involves performing an assessment of a state of a computing system, and the assessment includes analyzing information generated by an IoT edge sensor in response to a sensed physical condition in the computing system, and identifying an entity in the computing system potentially impacted by an event associated with the physical condition. The example method further includes identifying a preemptive recovery action and associating the preemptive recovery action with an entity, and the preemptive recovery action, when performed, reduces or eliminates an impact of the event on the entity, determining a cost associated with implementation of the preemptive recovery action, evaluating the cost associated with the preemptive recovery actions and identifying the preemptive recovery action with the lowest associated cost, implementing the preemptive recovery action with the lowest associated cost, and repeating part of the machine learning process.
1. A method, comprising:
performing a machine learning process that comprises the following operations:
performing an assessment of a physical environment within which a data storage system of a datacenter is located, wherein the assessment includes analyzing information generated by an loT edge sensor in response to a sensed physical condition of the physical environment, and the sensed physical condition is not associated with any particular component or components of the data storage system;
identifying one or more preemptive recovery actions and associating the one or more preemptive recovery action with the data storage system, and one of the preemptive recovery actions reduces or eliminates an impact of an event, associated with the sensed physical condition, on the data storage system;
determining a respective cost associated with implementation of the one or more preemptive recovery actions;
evaluating the costs associated with the one or more preemptive recovery actions and identifying the preemptive recovery action with the lowest associated cost; and
protecting and preserving data that is stored in the data storage system of the datacenter by implementing, or enabling the implementation of, the preemptive recovery action with the lowest associated cost.
2. The method as recited in claim 1 , wherein the data storage system comprises computing system hardware and/or software.
3. The method as recited in claim 1 , wherein the operations further comprise evaluating the one or more preemptive recovery actions and identifying a preemptive recovery action that does not conflict with other preemptive recovery actions, and which can be performed within a specified timeframe.
4. The method as recited in claim 1 , wherein when a conflict is identified between two or more preemptive recovery actions that have been identified, the operations further comprise resolving the conflict.
5. The method as recited in claim 1 , wherein implementation of the one or more preemptive recovery actions is performed automatically without intervention or input by a human user.
6. The method as recited in claim 1 , wherein repeating part of the machine learning process comprises repeating the performance of an assessment of the state of the data storage system.
7. The method as recited in claim 1 , wherein the machine learning process is an unsupervised machine learning process.
8. The method as recited in claim 1 , wherein the machine learning process is a supervised machine learning process.
9. The method as recited in claim 1 , wherein the operations further comprise determining an impact on the data storage system of implementation of the preemptive recovery action.
10. A non-transitory storage medium having stored therein instructions which are executable by one or more hardware processors to perform the following:
performing a machine learning process that comprises the following operations:
performing an assessment of a physical environment within which a data storage system of a datacenter is located, wherein the assessment includes analyzing information generated by an loT edge sensor in response to a sensed physical condition of the physical environment, and the sensed physical condition is not associated with any particular component or components of the data storage system;
identifying one or more preemptive recovery actions and associating the one or more preemptive recovery action with the data storage system, and one of the preemptive recovery actions, when performed, reduces or eliminates an impact of an event, associated with the sensed physical condition, on the data storage system;
determining a respective cost associated with implementation of the one or more preemptive recovery actions;
evaluating the costs associated with the one or more preemptive recovery actions and identifying the preemptive recovery action with the lowest associated cost; and
protecting and preserving data that is stored in the data storage system of the datacenter by implementing, or enabling the implementation of, the preemptive recovery action with the lowest associated cost.
11. The non-transitory storage medium as recited in claim 10 , wherein the data storage system comprises computing system hardware and/or software.
12. The non-transitory storage medium as recited in claim 10 , wherein the operations further comprise evaluating the one or more preemptive recovery actions and identifying a preemptive recovery action that does not conflict with other preemptive recovery actions, and which can be performed within a specified timeframe.
13. The non-transitory storage medium as recited in claim 10 , wherein when a conflict is identified between two or more preemptive recovery actions that have been identified, the operations further comprise resolving the conflict.
14. The non-transitory storage medium as recited in claim 10 , wherein implementation of the one or more preemptive recovery actions is performed automatically without intervention or input by a human user.
15. The non-transitory storage medium as recited in claim 10 , wherein repeating part of the machine learning process comprises repeating the performance of an assessment of the state of the data storage system.
16. The non-transitory storage medium as recited in claim 10 , wherein the machine learning process is an unsupervised machine learning process.
17. The non-transitory storage medium as recited in claim 10 , wherein the machine learning process is a supervised machine learning process.
18. The non-transitory storage medium as recited in claim 10 , wherein the operations further comprise determining an impact on the data storage system of implementation of the preemptive recovery action.