Automatically detecting data offloading methods using data bucketing and machine learning techniques
Methods, apparatus, and processor-readable storage media for automatically detecting data offloading methods using data bucketing and machine learning techniques are provided herein. An example computer-implemented method includes obtaining operations data and configuration data for one or more storage objects in a database; determining one or more times at which data offloading is to be carried out for at least one of the storage objects in the database, wherein determining the one or more times includes processing at least a portion of the operations data using one or more machine learning techniques; generating at least one data offloading protocol, comprising one or more data offloading methods, by processing at least a portion of the configuration data; and automatically executing, in accordance with the one or more determined times, the at least one generated data offloading protocol for at least a portion of the one or more storage objects in the database.
1. A computer-implemented method comprising:
obtaining operations data and configuration data for one or more storage objects in at least one database;
determining one or more times at which data offloading is to be carried out for at least one of the one or more storage objects in the at least one database, wherein determining the one or more times comprises processing at least a portion of the obtained operations data using one or more machine learning techniques, wherein processing at least a portion of the obtained operations data comprises:
predicting a number of data manipulation language operations occurring for one or more temporal intervals by processing the at least a portion of the obtained operations data using at least one autoregressive model; and
determining, based at least in part on the predicted number of data manipulation language operations, at least a portion of the one or more times, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is below a threshold;
generating at least one data offloading protocol, comprising one or more data offloading methods, by processing at least a portion of the configuration data for the one or more storage objects in the at least one database; and
automatically executing, in accordance with the one or more determined times, the at least one generated data offloading protocol for at least a portion of the one or more storage objects in the at least one database;
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 at least one data offloading protocol comprises determining a cost associated with the at least one data offloading protocol.
3. The computer-implemented method of claim 2 , further comprising:
processing the at least a portion of the configuration data using data bucketing techniques upon a determination that the cost associated with the at least one data offloading protocol exceeds a given amount.
4. The computer-implemented method of claim 1 , wherein generating at least one data offloading protocol comprises building a respective data offloading script for each of the one or more objects in the at least one database, wherein each data offloading script comprises at least a portion of one or more data offloading methods.
5. The computer-implemented method of claim 1 , further comprising:
training the one or more machine learning techniques based at least in part on results from automatically executing the at least one generated data offloading protocol.
6. 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 operations data and configuration data for one or more storage objects in at least one database;
to determine one or more times at which data offloading is to be carried out for at least one of the one or more storage objects in the at least one database, wherein determining the one or more times comprises processing at least a portion of the obtained operations data using one or more machine learning techniques, wherein processing at least a portion of the obtained operations data comprises:
predicting a number of data manipulation language operations occurring for one or more temporal intervals by processing the at least a portion of the obtained operations data using at least one autoregressive model; and
determining, based at least in part on the predicted number of data manipulation language operations, at least a portion of the one or more times, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is below a threshold;
to generate at least one data offloading protocol, comprising one or more data offloading methods, by processing at least a portion of the configuration data for the one or more storage objects in the at least one database; and
to automatically execute, in accordance with the one or more determined times, the at least one generated data offloading protocol for at least a portion of the one or more storage objects in the at least one database.
7. The non-transitory processor-readable storage medium of claim 6 , wherein generating at least one data offloading protocol comprises determining a cost associated with the at least one data offloading protocol, and processing the at least a portion of the configuration data using data bucketing techniques upon a determination that the cost associated with the at least one data offloading protocol exceeds a given amount.
8. The non-transitory processor-readable storage medium of claim 6 , wherein generating at least one data offloading protocol comprises building a respective data offloading script for each of the one or more objects in the at least one database, wherein each data offloading script comprises at least a portion of one or more data offloading methods.
9. The non-transitory processor-readable storage medium of claim 6 , wherein the program code when executed by the at least one processing device further causes the at least one processing device:
to train the one or more machine learning techniques based at least in part on results from automatically executing the at least one generated data offloading protocol.
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 obtain operations data and configuration data for one or more storage objects in at least one database;
to determine one or more times at which data offloading is to be carried out for at least one of the one or more storage objects in the at least one database, wherein determining the one or more times comprises processing at least a portion of the obtained operations data using one or more machine learning techniques, wherein processing at least a portion of the obtained operations data comprises:
predicting a number of data manipulation language operations occurring for one or more temporal intervals by processing the at least a portion of the obtained operations data using at least one autoregressive model; and
determining, based at least in part on the predicted number of data manipulation language operations, at least a portion of the one or more times, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is below a threshold;
to generate at least one data offloading protocol, comprising one or more data offloading methods, by processing at least a portion of the configuration data for the one or more storage objects in the at least one database; and
to automatically execute, in accordance with the one or more determined times, the at least one generated data offloading protocol for at least a portion of the one or more storage objects in the at least one database.
11. The apparatus of claim 10 , wherein generating at least one data offloading protocol comprises determining a cost associated with the at least one data offloading protocol, and processing the at least a portion of the configuration data using data bucketing techniques upon a determination that the cost associated with the at least one data offloading protocol exceeds a given amount.
12. The apparatus of claim 10 , wherein generating at least one data offloading protocol comprises building a respective data offloading script for each of the one or more objects in the at least one database, wherein each data offloading script comprises at least a portion of one or more data offloading methods.
13. The apparatus of claim 10 , wherein the at least one processing device is further configured:
to train the one or more machine learning techniques based at least in part on results from automatically executing the at least one generated data offloading protocol.
14. The apparatus of claim 10 , wherein the at least one autoregressive model comprises at least one autoregressive integrated moving average (ARIMA) model, and wherein determining one or more times at which data offloading is to be carried out for at least one of the one or more storage objects in the at least one database comprises determining multiple times at which data offloading is to be carried out for the at least one of the one or more storage objects in the at least one database by processing the at least a portion of the obtained operations data using the at least one ARIMA model in connection with multiple temporal granularities.
15. The computer-implemented method of claim 1 , wherein the at least one autoregressive model comprises at least one ARIMA model, and wherein determining one or more times at which data offloading is to be carried out for at least one of the one or more storage objects in the at least one database comprises determining multiple times at which data offloading is to be carried out for the at least one of the one or more storage objects in the at least one database by processing the at least a portion of the obtained operations data using the at least one ARIMA model in connection with multiple temporal granularities.
16. The non-transitory processor-readable storage medium of claim 6 , wherein the at least one autoregressive model comprises at least one ARIMA model, and wherein determining one or more times at which data offloading is to be carried out for at least one of the one or more storage objects in the at least one database comprises determining multiple times at which data offloading is to be carried out for the at least one of the one or more storage objects in the at least one database by processing the at least a portion of the obtained operations data using the at least one ARIMA model in connection with multiple temporal granularities.
17. The computer-implemented method of claim 1 , wherein determining at least a portion of the one or more times, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is below a threshold comprises determining a time, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is at a minimum level.
18. The computer-implemented method of claim 1 , wherein predicting a number of data manipulation language operations occurring for one or more temporal intervals comprises predicting a number of data manipulation language operations occurring for one or more temporal intervals across each of multiple temporal granularities.
19. The non-transitory processor-readable storage medium of claim 6 , wherein determining at least a portion of the one or more times, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is below a threshold comprises determining a time, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is at a minimum level.
20. The apparatus of claim 10 , wherein determining at least a portion of the one or more times, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is below a threshold comprises determining a time, during the one or more temporal intervals, at which the predicted number of data manipulation language operations is at a minimum level.