IP Library › Granted Patent US 12,414,274
Granted Patent B2
US 12,414,274 · App. 18/129,499 · Granted Sep 9, 2025

Measuring utilization to adjust water flow for cooling of servers and server components

Inventors: Eric R Kern (Chapel Hill, NC); Paola Martinez Morales (Wendell, NC); Jerrod K Buterbaugh (Wake Forest, NC); Florin Cazacu (Balotesti, RO); Fadel Matar (Ottawa, CA)
Assignee: Lenovo Enterprise Solutions (Singapore) Pte. Ltd.
H05K7/20836H05K7/20772
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,414,274
App. No.
18/129,499
Granted
Sep 9, 2025
Kind
B2
Abstract

A method for measuring utilization to adjust water flow for cooling of servers and server components includes determining a utilization of a server. The server is water-cooled and includes one of a plurality of servers. Each server of the plurality of servers is water-cooled, and each server of the plurality of servers is connected to a water supply manifold by one or more valves. The method also includes determining, based at least in part on the determined utilization of the server, a water flow rate to cool the server. The method includes adjusting, based at least in part on the determined water flow rate to cool the server, a water flow rate to the server via a valve controlling the water flow rate to the server.

Claims (64)

1. A method comprising:

determining, using a processor, a utilization of a server, wherein the server is water-cooled and comprises one of a plurality of servers, wherein each server of the plurality of servers is water-cooled and wherein each server of the plurality of servers is connected to a water supply manifold by one or more valves;

determining, using the processor and based at least in part on the determined utilization of the server, a water flow rate to cool the server; and

adjusting, using the processors and based at least in part on the determined water flow rate to cool the server, a water flow rate to the server via a valve controlling the water flow rate to the server.

2. The method of claim 1 , wherein:

determining the utilization of the server comprises predicting a future utilization of the server;

determining the water flow rate to cool the server comprises determining a predicted water flow rate to cool the server based at least in part on the predicted future utilization; and

adjusting the water flow rate to the server comprises adjusting the water flow rate to the server via the valve controlling the water flow rate to the server based at least in part on the determined predicted water flow rate.

3. The method of claim 2 , wherein the water flow rate to the server is adjusted at a time of the predicted future utilization.

4. The method of claim 2 , wherein predicting the future utilization is based at least in part on the determined utilization, a future event affecting utilization, and/or a utilization-water flow model for the plurality of servers.

5. The method of claim 4 , wherein the utilization-water flow model is derived through machine learning and is based at least in part on:

data received from a number of the plurality of servers, the data comprising a temperature of each server of the number of the plurality of servers, a utilization of each server of the number of the plurality of servers, and/or a water flow rate to each server of the number of the plurality of servers;

a correlation between the temperature of each server of the number of the plurality of servers and the utilization of each server of the number of the plurality of servers; and

a correlation between the utilization of each server of the number of the plurality of servers and the water flow rate to each server of the number of the plurality of servers.

6. The method of claim 1 , wherein:

determining the utilization of the server further comprises determining a utilization of a component of the server;

determining the water flow rate to cool the server further comprises determining, based at least in part on the determined utilization of the component, a water flow rate to cool the component; and

adjusting the water flow rate to the server further comprises adjusting, based at least in part on the water flow rate to cool the component, a water flow rate to the component via a valve controlling the water flow rate to the component.

7. The method of claim 1 , wherein:

the server and a number of the plurality of servers are positioned on a rack-mounted tray; and

the water supply manifold comprises one or more cooling lines to each server of the number of the plurality of servers, wherein each cooling line of the one or more cooling lines comprises a valve of the one or more valves configured to adjust a water flow rate through the cooling line to a corresponding server.

8. The method of claim 1 , wherein the utilization of the server comprises a proportion of time during which the server is in use over a period of time.

9. An apparatus comprising:

a water supply manifold connected to a plurality of servers, wherein each server of the plurality of servers is water-cooled and wherein each server is connected to the water supply manifold by one or more valves;

a processor; and

non-transitory computer readable storage media storing code, the code being executable by the processor to perform operations comprising:

determining a utilization of a server of the plurality of servers;

determining, based at least in part on the determined utilization of the server, a water flow rate to cool the server; and

adjusting, based at least in part on the determined water flow rate to cool the server, a water flow rate to the server via a valve of the one or more valves of the water supply manifold controlling the water flow rate to the server.

10. The apparatus of claim 9 , the operations further comprising:

predicting a future utilization of the server;

determining, based at least in part on the predicted future utilization, a predicted water flow rate to cool the server; and

adjusting, based at least in part on the determined predicted water flow rate, the water flow rate to the server via the valve controlling the water flow rate to the server.

11. The apparatus of claim 10 , the operations further comprising adjusting the water flow rate to the server at a time of the predicted future utilization.

12. The apparatus of claim 10 , wherein predicting the future utilization is based at least in part on the determined utilization, a future event affecting utilization, and/or a utilization-water flow model for the plurality of servers.

13. The apparatus of claim 12 , wherein the utilization-water flow model is derived through machine learning and is based at least in part on at least one of:

data received from a number of the plurality of servers, the data comprising a temperature of each server of the number of the plurality of servers, a utilization of each server of the number of the plurality of servers, and/or a water flow rate to each server of the number of the plurality of servers;

a correlation between the temperature of each server of the plurality of servers and the utilization of each server of the plurality of servers; and/or

a correlation between the utilization of each server of the plurality of servers and the water flow rate to each server of the plurality of servers.

14. The apparatus of claim 9 , wherein:

determining the utilization of the server further comprises determining a utilization of a component of the server;

determining the water flow rate to cool the server further comprises determining, based at least in part on the determined utilization of the component, a water flow rate to cool the component; and

adjusting the water flow rate to the server further comprises adjusting, based at least in part on the water flow rate to cool the component, a water flow rate to the component via a valve controlling the water flow rate to the component.

15. The apparatus of claim 9 , wherein:

the server and a number of the plurality of servers are positioned on a rack-mounted tray; and

the water supply manifold comprises one or more cooling lines to each server of the number of the plurality of servers, wherein each cooling line of the one or more cooling lines comprises a valve of the one or more valves configured to adjust a water flow rate through the cooling line to a corresponding server.

16. A system comprising:

a plurality of servers, wherein each server of the plurality of servers is water-cooled;

a water supply manifold connected to the plurality of servers;

a number of valves, wherein each valve of the number of valves controls a water flow rate to at least one server of the plurality of servers;

a processor; and

non-transitory computer readable storage media storing code, the code being executable by the processor to perform operations comprising:

determining a utilization of a server of the plurality of servers;

determining, based at least in part on the determined utilization of the server, a water flow rate to cool the server; and

actuating the valve controlling the water flow rate to the server to adjust, based at least in part on the determined water flow rate to cool the server, the water flow rate to the server.

17. The system of claim 16 , wherein:

determining the utilization of the server further comprises predicting a future utilization of the server;

determining the water flow rate to cool the server further comprises determining a predicted water flow rate to cool the server based at least in part on the predicted future utilization; and

adjusting the water flow rate to the server further comprises adjusting predicted water flow rate the water flow rate to the server via the valve controlling the water flow rate to the server based on the determined predicted water flow rate.

18. The system of claim 17 , wherein predicting the future utilization is based at least in part on the determined utilization, a future event affecting utilization, and/or a utilization-water flow model for the plurality of servers.

19. The system of claim 16 , further comprising an additional number of valves, wherein each valve of the additional number of valves controls a water flow rate to a component of at least one server of the plurality of servers.

20. The system of claim 16 , wherein:

the server and a number of the plurality of servers are positioned on a rack-mounted tray; and

the water supply manifold comprises one or more cooling lines to each server of the number of the plurality of servers, wherein each cooling line of the one or more cooling lines comprises a valve of the number of valves configured to adjust a water flow rate through the cooling line to a corresponding server.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 8, 2024
From: LENOVO GLOBAL TECHNOLOGY (UNITED STATES) INC.
To: LENOVO ENTERPRISE SOLUTIONS (SINGAPORE) PTE LTD.
Reel/Frame 067929/0952 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 4, 2023
From: KERN, ERIC R; MORALES, PAOLA MARTINEZ; BUTERBAUGH, JERROD K; CAZACU, FLORIN; MATAR, FADEL
To: LENOVO GLOBAL TECHNOLOGY (UNITED STATES) INC.
Reel/Frame 063216/0728 →
Continuity (1)
Related Publication 20240334658A1 · Oct 3, 2024
References Cited (9)
US 20200100394A1 · Albinger · 2020 [cited by examiner]
JP 2012098916A · 2012 [cited by examiner]
Lazic et al., “Data center cooling using model-predictive control”, NeurIPS 2018, date known about Nov. 29, 2022, pp. 1-10. [cited by applicant]
Baojun et al., “Temperature prediction and cooling structure optimization of explosion-proof high pressure water-cooled double speed motor”, Elsevier, date published Feb. 23, 2022, pp. 1-11. [cited by applicant]
Lingling et al., “The Research of Cooling Water Temperature and Flow Rate Control System Based on Heat Transfer and Neural Network”, IEEE 2015 5th International Conference on Instrumentation and Measurement, Computer, C… [cited by applicant]
Acun et al., “Support for Power Efficient Proactive Cooling Mechanisms”, IEEE 2017 24th International Conference on High Performance Computing (HiPC), Dec. 18-21, 2017, p. 1. [cited by applicant]
Mcevoy et al., “Adaptive Liquid Cooling Methods in Microchannel”, ESIPP Dept. of Mechanical & Manufacturing Engineering, pp. 1-6. [cited by applicant]
Nisa et al., “Comparative Assessment to Predict and Forecast Water-Cooled Chiller Power Consumption Using Machine Learning and Deep Learning Algorithms”, MDPI Sustainability 2021, Jan. 14, 2021, pp. 1-18. [cited by applicant]
Wang et al., “Development of supervisory control strategy for online control of central cooling water systems”, ResearchGate International Building Performance Simulation Association 2007, Jan. 2007, pp. 1-9. [cited by applicant]