US 12,436,863 B2
Power capacity planning for a computing system
Jerome Lecuivre, Gières (FR)
Assigned to EATON INTELLIGENT POWER LIMITED, Dublin (IE)
Appl. No. 18/256,106
Filed by Eaton Intelligent Power Limited, Dublin (IE)
PCT Filed Nov. 30, 2021, PCT No. PCT/EP2021/083644
§ 371(c)(1), (2) Date Jun. 6, 2023,
PCT Pub. No. WO2022/122486, PCT Pub. Date Jun. 16, 2022.
Claims priority of application No. 2019470 (GB), filed on Dec. 10, 2020.
Prior Publication US 2024/0037008 A1, Feb. 1, 2024
Int. Cl. G06F 11/34 (2006.01); G06F 1/28 (2006.01); G06F 9/455 (2018.01); G06F 9/50 (2006.01); G06F 11/30 (2006.01); G06N 20/20 (2019.01)
CPC G06F 11/3442 (2013.01) [G06F 11/3419 (2013.01); G06F 11/3433 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A computer-implemented method for power capacity planning for a computing system comprising the following:
a) evaluating an activity of the computing system, wherein the activity comprises the number of program instances executed by the computing system and the load incurred by the executed program instances;
b) predicting an evolution of the activity based on the evaluated activity by using a first machine learning algorithm configured for activity evolution prediction;
c) predicting a power consumption of the computing system as a first power metric based on the predicted activity evolution and by using a second machine learning algorithm configured for power consumption prediction of the computing system;
d) predicting an autonomy of one or more uninterruptible power supplies of the computing system as a second power metric based on the predicted power consumption and by using a third machine learning algorithm configured for uninterruptible power supplies autonomy prediction and receiving as input the power consumption prediction of the computing system; and,
e) predicting a redundancy level of the computing system as a third power metric based on the predicted power consumption and a power architecture of the computing system;
f) generating output data related to power capacity planning by processing the first, second and third power metrics;
g) generating a warning based on determining that at least one of the first power metric, the second power metric, or the third power metric exceeds a degradation threshold;
h) receiving a user defined scenario related to the power capacity planning;
i) performing the predicting acts c)-e) based on the received user defined scenario to obtain the first, second and third power metrics for the received user defined scenario;
j) generating output data related to power capacity planning by processing the first, second and third power metrics for the received user defined scenario; and
k) altering the received user defined scenario to tune the power architecture based on the output data related to power capacity planning.