Granted Patent B2

US 12,267,988 · App. 17/294,996 · Granted Apr 1, 2025

Inventors: Yijun Lu (Hangzhou, CN); Jun Song (Tacoma, WA); Youquan Feng (Beijing, CN)

Assignee: Alibaba Group Holding Limited

H05K7/20836G06F1/206G06F30/20H05K7/20745G06F2111/10G06F2119/08

Abstract

Claims (60)

1. A method comprising:

collecting data of a plurality of systems, each of the plurality of systems including at least one first cooling element and at least one first heat-generating element;

conducting a first simulation using a simulation model based on the collected data to generate a first set of simulation results;

conducting a first training on a control system to obtain a first trained control system based on the first set of simulation results and a result generated by the simulation model based on the collected data;

using the first trained control system to monitor a field system with a space having at least one second cooling element and at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element;

generating a set of conditions using the first trained control system, the set of conditions including an extraordinary condition;

sending the set of conditions to the simulation model;

conducting a second simulation using the simulation model based on the set of conditions to obtain a second set of simulation results;

conducting a second training on the first trained control system to obtain a second trained control system based on the second set of simulation results and feedbacks from the field system; and

using the second trained control system to monitor the field system with the space having the at least one second cooling element and the at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element.

2. The method of claim 1 , further comprising:

receiving feedback data from the field system with the space having the at least one second cooling element and the at least one second heat-generating element; and

updating the second trained control system by conducting an additional training on the second trained control system using the feedback data.

3. The method of claim 1 , wherein the simulation model comprises a Computational Fluid Dynamics (CFD) model.

4. The method of claim 1 , wherein:

the first set of simulation results includes a first set of thermal maps and/or airflow maps; and

the second set of simulation results includes a second set of thermal maps and/or airflow maps.

5. The method of claim 1 , wherein the plurality of systems comprises one or more of a computing device, a server, a rack of servers, or an Internet Data Center (IDC).

6. The method of claim 1 , wherein the control system comprises one or more of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Long Short-Term Memory network (LSTM), a Reinforcement learning (RL) network, a Machine Learning (ML) network, a Deep Learning (DL) network, or a decision tree.

7. A computer-readable storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:

collecting data of one or more systems, each of the one or more systems including at least one first cooling element and at least one first heat-generating element;

conducting a first simulation using a simulation model based on the collected data to generate a first set of simulation results;

conducting a first training on a control system to obtain a first trained control system based on the first set of simulation results and a result generated by the simulation model based on the collected data;

using the first trained control system to monitor a field system with a space having at least one second cooling element and at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element;

generating a set of conditions using the first trained control system;

sending the set of conditions to the simulation model;

conducting a second simulation using the simulation model based on the set of conditions to obtain a second set of simulation results;

conducting a second training on the first trained control system to obtain a second trained control system based on the second set of simulation results and feedbacks from the field system; and

using the second trained control system to monitor the field system with the space having the at least one second cooling element and the at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element.

8. The computer-readable storage medium of claim 7 , wherein the acts further comprise:

receiving feedback data from the field system with the space having the at least one second cooling element and the at least one second heat-generating element; and

updating the second trained control system by conducting an additional training on the second trained control system using the feedback data.

9. The computer-readable storage medium of claim 7 , wherein the simulation model comprises a Computational Fluid Dynamics (CFD) model.

10. The computer-readable storage medium of claim 7 , wherein:

the first set of simulation results includes a first set of thermal maps and/or airflow maps; and

the second set of simulation results includes a second set of thermal maps and/or airflow maps.

11. The computer-readable storage medium of claim 7 , wherein

the one or more systems comprise one or more of a computing device, a server, a rack of servers, or an Internet Data Center (IDC).

12. The computer-readable storage medium of claim 7 , wherein the control system comprises a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Long Short-Term Memory network (LSTM), a Reinforcement learning (RL) network, a Machine Learning (ML) network, a Deep Learning (DL) network, or a decision tree.

13. An apparatus comprising:

one or more processors; and

memory coupled to the one or more processors, the memory storing computer-executable modules that, when executed by the one or more processors, perform acts comprising:

collecting data of one or more systems, each of the one or more systems including at least one first cooling element and at least one first heat-generating element;

conducting a first simulation using a simulation model based on the collected data to generate a first set of simulation results;

conducting a first training on a control system to obtain a first trained control system based on the first set of simulation results and a result generated by the simulation model based on the collected data;

using the first trained control system to monitor a field system with a space having at least one second cooling element and at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element;

generating a set of conditions using the first trained control system;

sending the set of conditions to the simulation model;

conducting a second simulation using the simulation model based on the set of conditions to obtain a second set of simulation results;

conducting a second training on the first trained control system to obtain a second trained control system based on the second set of simulation results and feedbacks from the field system; and

using the second trained control system to monitor the field system with the space having the at least one second cooling element and the at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element.

14. The apparatus of claim 13 , wherein the acts further comprise receiving feedback data from the field system.

15. The apparatus of claim 13 , wherein the simulation model comprises a Computational Fluid Dynamics (CFD) model.

16. The apparatus of claim 13 , wherein:

the first set of simulation results includes a ifrst set of thermal maps and/or airflow maps; and

the second set of simulation results includes a second set of thermal maps and/or airflow maps.

17. The apparatus of claim 13 , wherein each of the one or more systems comprises at least one of one or more computing devices, one or more servers, one or more racks of servers, and one or more Internet Data Centers (IDCs).

18. The method of claim 1 , wherein the set of conditions further include an emergent condition.

19. The computer-readable storage medium of claim 7 , wherein the set of conditions include an extraordinary condition or an emergent condition.

20. The apparatus of claim 13 , wherein the set of conditions include an extraordinary condition or an emergent condition.

Assignments (2)

Continuity (1)

References Cited (33)