Estimating replication completion time using machine learning techniques

Patent metadata

Field	Value
Publication number	US-11436396-B2
Application number	US-202016830527-A
Country	US
Kind code	B2
Filing date	Mar 26, 2020
Priority date	Mar 26, 2020
Publication date	Sep 6, 2022
Grant date	Sep 6, 2022

Abstract

Methods, apparatus, and processor-readable storage media for estimating replication completion time using machine learning techniques are provided herein. An example computer-implemented method includes obtaining, from one or more data deduplication storage systems, data related to one or more historical replication operations; generating at least one curve fitting function by processing at least a portion of the obtained data using one or more machine learning techniques; generating an estimate for completion time of at least one unexecuted replication operation associated with at least one of the one or more data deduplication storage systems by processing input data from the at least one data deduplication storage system using the at least one curve fitting function; and performing one or more automated actions based at least in part on the generated estimate.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining, from one or more data deduplication storage systems, data related to one or more historical replication operations;
generating at least one curve fitting function by processing at least a portion of the obtained data using one or more machine learning techniques;
generating an estimate for completion time of at least one unexecuted replication operation associated with at least one of the one or more data deduplication storage systems by processing input data from the at least one data deduplication storage system using the at least one curve fitting function; and
performing one or more automated actions based at least in part on the generated estimate;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2. The computer-implemented method of claim 1 , wherein generating the at least one curve fitting function comprises generating at least one regression equation by processing at least a portion of the obtained data using an aggregated Mondrian forest algorithm.

3. The computer-implemented method of claim 2 , wherein processing the at least a portion of the obtained data using an aggregated Mondrian forest algorithm comprises:
creating one or more decision trees by analyzing the at least a portion of the obtained data using one or more Mondrian processes; and
implementing at least one aggregation algorithm over at least a portion of the one or more decision trees.

4. The computer-implemented method of claim 1 , further comprising:
updating the at least one curve fitting function by processing, using the one or more machine learning techniques, the at least a portion of the obtained data and one or more items of data related to at least one historical replication operation executed subsequent to the generating of the at least one curve function.

5. The computer-implemented method of claim 4 , wherein updating the at least one curve fitting function comprises updating at least a portion of one or more decision trees created by analyzing the at least a portion of the obtained data using the one or more machine learning techniques, wherein updating the at least a portion of the one or more decision trees comprises ensuring that each leaf in the at least a portion of the one or more decision trees contains at most one data point.

6. The computer-implemented method of claim 5 , wherein updating the at least one curve fitting function comprises updating a prediction function that aggregates one or more decision functions associated with the at least a portion of the one or more decision trees.

7. The computer-implemented method of claim 1 , wherein the data related to one or more historical replication operations comprise values for multiple variables derived from one or more successful replication operations.

8. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises outputting the generated estimate to the at least one data deduplication storage system via one or more graphical user interfaces.

9. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises outputting the generated estimate to the at least one data deduplication storage system via one or more command line interfaces.

10. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises automatically executing the at least one unexecuted replication operation at a time determined based at least in part on the generated estimate.

11. 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 obtain, from one or more data deduplication storage systems, data related to one or more historical replication operations;
to generate at least one curve fitting function by processing at least a portion of the obtained data using one or more machine learning techniques;
to generate an estimate for completion time of at least one unexecuted replication operation associated with at least one of the one or more data deduplication storage systems by processing input data from the at least one data deduplication storage system using the at least one curve fitting function; and
to perform one or more automated actions based at least in part on the generated estimate.

12. The non-transitory processor-readable storage medium of claim 11 , wherein generating the at least one curve fitting function comprises generating at least one regression equation by processing at least a portion of the obtained data using an aggregated Mondrian forest algorithm.

13. The non-transitory processor-readable storage medium of claim 12 , wherein processing the at least a portion of the obtained data using an aggregated Mondrian forest algorithm comprises:
creating one or more decision trees by analyzing the at least a portion of the obtained data using one or more Mondrian processes; and
implementing at least one aggregation algorithm over at least a portion of the one or more decision trees.

14. The non-transitory processor-readable storage medium of claim 11 , wherein the program code when executed by the at least one processing device causes the at least one processing device:
to update the at least one curve fitting function by processing, using the one or more machine learning techniques, the at least a portion of the obtained data and one or more items of data related to at least one historical replication operation executed subsequent to the generating of the at least one curve function.

15. The non-transitory processor-readable storage medium of claim 14 , wherein updating the at least one curve fitting function comprises updating at least a portion of one or more decision trees created by analyzing the at least a portion of the obtained data using the one or more machine learning techniques, wherein updating the at least a portion of the one or more decision trees comprises ensuring that each leaf in the at least a portion of the one or more decision trees contains at most one data point.

16. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain, from one or more data deduplication storage systems, data related to one or more historical replication operations;
to generate at least one curve fitting function by processing at least a portion of the obtained data using one or more machine learning techniques;
to generate an estimate for completion time of at least one unexecuted replication operation associated with at least one of the one or more data deduplication storage systems by processing input data from the at least one data deduplication storage system using the at least one curve fitting function; and
to perform one or more automated actions based at least in part on the generated estimate.

17. The apparatus of claim 16 , wherein generating the at least one curve fitting function comprises generating at least one regression equation by processing at least a portion of the obtained data using an aggregated Mondrian forest algorithm.

18. The apparatus of claim 17 , wherein processing the at least a portion of the obtained data using an aggregated Mondrian forest algorithm comprises:
creating one or more decision trees by analyzing the at least a por

Assignees

• Emc Ip Holding Co Llc

Inventors

• Singh Jitendra
• Vishwakarma Rahul D
• Chopra Shelesh

Classifications

• G06F16/1748 Primary

  De-duplication implemented within the file system, e.g. based on file segments (de-duplication techniques in storage systems for the management of data blocks G06F3/0641) · CPC title

• G06F30/27 Primary

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06F18/24323

  Tree-organised classifiers · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title