Artificial intelligence techniques for prediction of data protection operation duration
Techniques are provided for predicting a time to complete a data protection operation. One method comprises obtaining metadata for (i) a given data protection appliance, and/or (ii) a cluster of similar data protection appliances comprising the given data protection appliance; evaluating first level features using the obtained metadata; evaluating a second level feature using some of the evaluated first level features; and processing one or more of the first level features, and the second level feature, using a model that provides a predicted time to complete a data protection operation with respect to data of a protected device associated with the given data protection appliance. The predicted time may comprise a tolerance based on a robustness factor. The predicted time may be based on a number of protected devices that are concurrently undergoing a data protection operation with the protected device for one or more time intervals.
1. A method, comprising:
obtaining metadata for at least one of: (i) a given data protection appliance, and (ii) a cluster of similar data protection appliances comprising the given data protection appliance, based at least in part on one or more similarity criteria;
evaluating a plurality of first level features using the obtained metadata;
evaluating at least one second level feature using at least some of the evaluated first level features; and
processing (i) one or more of the first level features, and (ii) the at least one second level feature, using at least one model that provides a predicted time to complete a data protection operation with respect to data of a protected device associated with the given data protection appliance;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The method of claim 1 , wherein the at least one second level feature comprises one or more of a previous data protection speed feature and a deduplication ratio feature for the protected device associated with the given data protection appliance.
3. The method of claim 2 , wherein the previous data protection speed feature is based at least in part on an elapsed time and an amount of data protected in one or more prior data protection operations for the protected device associated with the given data protection appliance.
4. The method of claim 2 , wherein the deduplication ratio feature is based at least in part on an amount of data protected in one or more prior data protection operations after a deduplication operation relative to an amount of data included in the one or more prior data protection operations before the deduplication operation for the protected device associated with the given data protection appliance.
5. The method of claim 1 , wherein the at least one model comprises one or more of at least one machine learning model and at least one statistical model.
6. The method of claim 1 , wherein the protected device comprises one or more of a user device, a server device, and one or more storage devices.
7. The method of claim 1 , wherein the predicted time to complete the data protection operation comprises a tolerance based at least in part on a robustness factor.
8. The method of claim 1 , wherein the at least one model comprises a plurality of models, and wherein a particular model is selected using one or more of at least one error function and at least one loss function that approximates a standard deviation of the predicted time.
9. The method of claim 1 , wherein the predicted time to complete the data protection operation is based at least in part on a number of protected devices associated with the given data protection appliance that are concurrently undergoing a data protection operation with the protected device for one or more time intervals.
10. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured to implement the following steps:
obtaining metadata for at least one of: (i) a given data protection appliance, and (ii) a cluster of similar data protection appliances comprising the given data protection appliance, based at least in part on one or more similarity criteria;
evaluating a plurality of first level features using the obtained metadata;
evaluating at least one second level feature using at least some of the evaluated first level features; and
processing (i) one or more of the first level features, and (ii) the at least one second level feature, using at least one model that provides a predicted time to complete a data protection operation with respect to data of a protected device associated with the given data protection appliance.
11. The apparatus of claim 10 , wherein the at least one second level feature comprises one or more of: (i) a previous data protection speed feature based at least in part on an elapsed time and an amount of data protected in one or more prior data protection operations for the protected device associated with the given data protection appliance; and (ii) a deduplication ratio feature based at least in part on an amount of data protected in one or more prior data protection operations after a deduplication operation relative to an amount of data included in the one or more prior data protection operations before the deduplication operation for the protected device associated with the given data protection appliance.
12. The apparatus of claim 10 , wherein the at least one model comprises one or more of at least one machine learning model and at least one statistical model.
13. The apparatus of claim 10 , wherein the predicted time to complete the data protection operation comprises a tolerance based at least in part on a robustness factor.
14. The apparatus of claim 10 , wherein the at least one model comprises a plurality of models, and wherein a particular model is selected using one or more of at least one error function and at least one loss function that approximates a standard deviation of the predicted time.
15. The apparatus of claim 10 , wherein the predicted time to complete the data protection operation is based at least in part on a number of protected devices associated with the given data protection appliance that are concurrently undergoing a data protection operation with the protected device for one or more time intervals.
16. 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 causes the at least one processing device to perform the following steps:
obtaining metadata for at least one of: (i) a given data protection appliance, and (ii) a cluster of similar data protection appliances comprising the given data protection appliance, based at least in part on one or more similarity criteria;
evaluating a plurality of first level features using the obtained metadata;
evaluating at least one second level feature using at least some of the evaluated first level features; and
processing (i) one or more of the first level features, and (ii) the at least one second level feature, using at least one model that provides a predicted time to complete a data protection operation with respect to data of a protected device associated with the given data protection appliance.
17. The non-transitory processor-readable storage medium of claim 16 , wherein the at least one second level feature comprises one or more of: (i) a previous data protection speed feature based at least in part on an elapsed time and an amount of data protected in one or more prior data protection operations for the protected device associated with the given data protection appliance; and (ii) a deduplication ratio feature based at least in part on an amount of data protected in one or more prior data protection operations after a deduplication operation relative to an amount of data included in the one or more prior data protection operations before the deduplication operation for the protected device associated with the given data protection appliance.
18. The non-transitory processor-readable storage medium of claim 16 , wherein the predicted time to complete the data protection operation comprises a tolerance based at least in part on a robustness factor.
19. The non-transitory processor-readable storage medium of claim 16 , wherein the at least one model comprises a plurality of models, and wherein a particular model is selected using one or more of at least one error function and at least one loss function that approximates a standard deviation of the predicted time.
20. The non-transitory processor-readable storage medium of claim 16 , wherein the predicted time to complete the data protection operation is based at least in part on a number of protected devices associated with the given data protection appliance that are concurrently undergoing a data protection operation with the protected device for one or more time intervals.