Automated device power conservation using machine learning techniques
Methods, apparatus, and processor-readable storage media for automated device power conservation using machine learning techniques are provided herein. An example computer-implemented method includes obtaining usage-related data from one or more processing devices; determining at least one usage pattern for the one or more processing devices by processing the obtained usage-related data using one or more machine learning techniques; automatically generating, based at least in part on the at least one determined usage pattern, instructions pertaining to controlling one or more power states of the one or more processing devices; and performing at least one automated action based at least in part on the generated instructions.
1. A computer-implemented method comprising:
obtaining usage-related data from one or more processing devices, wherein the usage-related data comprise time series data;
determining at least one usage pattern for the one or more processing devices by processing at least a portion of the obtained usage-related data using one or more machine learning techniques, wherein processing the at least a portion of the obtained usage-related data using one or more machine learning techniques comprises predicting instances of one or more usage states by processing at least a portion of the time series data using at least one autoregressive integrated moving average model, and wherein the one or more usage states comprises at least an idle state;
automatically generating, based at least in part on the at least one determined usage pattern, instructions pertaining to controlling one or more power states of the one or more processing devices; and
performing at least one automated action based at least in part on the generated instructions;
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 determining the at least one usage pattern comprises determining at least one mode value attributable to at least one instance when the one or more processing devices are in the idle state.
3. The computer-implemented method of claim 1 , wherein predicting the instances of one or more usage states comprises confirming the at least one determined usage pattern against one or more sets of historical usage-related data from the one or more processing devices.
4. The computer-implemented method of claim 1 , wherein performing the at least one automated action comprises automatically transitioning at least a portion of the one or more processing devices to a decreased power mode at one or more instances of time in accordance with the generated instructions.
5. The computer-implemented method of claim 4 , wherein automatically transitioning the at least a portion of the one or more processing devices to a decreased power mode comprises executing at least a portion of the generated instructions via at least one baseboard management controller associated with the one or more processing devices.
6. The computer-implemented method of claim 1 , wherein obtaining the usage-related data comprises retrieving the usage-related data from at least one baseboard management controller associated with the one or more processing devices.
7. The computer-implemented method of claim 1 , wherein determining the at least one usage pattern comprises determining at least one usage pattern in accordance with each of one or more temporal parameters.
8. The computer-implemented method of claim 1 , wherein the usage-related data comprise baseline power values for the one or more processing devices.
9. The computer-implemented method of claim 1 , wherein the usage-related data comprise information pertaining to one or more of central processing units, memory, system infrastructure utilization, and input-output activity.
10. The computer-implemented method of claim 1 , processing the obtained usage-related data using one or more data cleaning techniques.
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 usage-related data from one or more processing devices, wherein the usage-related data comprise time series data;
to determine at least one usage pattern for the one or more processing devices by processing at least a portion of the obtained usage-related data using one or more machine learning techniques, wherein processing the at least a portion of the obtained usage-related data using one or more machine learning techniques comprises predicting instances of one or more usage states by processing at least a portion of the time series data using at least one autoregressive integrated moving average model, and wherein the one or more usage states comprises at least an idle state;
to automatically generate, based at least in part on the at least one determined usage pattern, instructions pertaining to controlling one or more power states of the one or more processing devices; and
to perform at least one automated action based at least in part on the generated instructions.
12. The non-transitory processor-readable storage medium of claim 11 , wherein determining the at least one usage pattern comprises determining at least one mode value attributable to at least one instance when the one or more processing devices are in the idle state.
13. The non-transitory processor-readable storage medium of claim 11 , wherein predicting the instances of one or more usage states comprises confirming the at least one determined usage pattern against one or more sets of historical usage-related data from the one or more processing devices.
14. The non-transitory processor-readable storage medium of claim 11 , wherein performing the at least one automated action comprises automatically transitioning at least a portion of the one or more processing devices to a decreased power mode at one or more instances of time in accordance with the generated instructions.
15. 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 usage-related data from one or more processing devices, wherein the usage-related data comprise time series data;
to determine at least one usage pattern for the one or more processing devices by processing at least a portion of the obtained usage-related data using one or more machine learning techniques, wherein processing the at least a portion of the obtained usage-related data using one or more machine learning techniques comprises predicting instances of one or more usage states by processing at least a portion of the time series data using at least one autoregressive integrated moving average model, and wherein the one or more usage states comprises at least an idle state;
to automatically generate, based at least in part on the at least one determined usage pattern, instructions pertaining to controlling one or more power states of the one or more processing devices; and
to perform at least one automated action based at least in part on the generated instructions.
16. The apparatus of claim 15 , wherein determining the at least one usage pattern comprises determining at least one mode value attributable to at least one instance when the one or more processing devices are in the idle state.
17. The apparatus of claim 15 , wherein predicting the instances of one or more usage states comprises confirming the at least one determined usage pattern against one or more sets of historical usage-related data from the one or more processing devices.
18. The apparatus of claim 15 , wherein performing the at least one automated action comprises automatically transitioning at least a portion of the one or more processing devices to a decreased power mode at one or more instances of time in accordance with the generated instructions.
19. The apparatus of claim 15 , wherein determining the at least one usage pattern comprises determining at least one usage pattern in accordance with each of one or more temporal parameters.
20. The apparatus of claim 15 , wherein the usage-related data comprise information pertaining to one or more of central processing units, memory, system infrastructure utilization, and input-output activity.