SYSTEM AND METHODS FOR RACK COOLING ANALYSIS

• US 20120158387A1
• Filed: 12/16/2010
• Published: 06/21/2012
• Est. Priority Date: 12/16/2010
• Status: Active Grant

• Current Assignee: Schneider Electric IT Corporation (Schneider Electric SE)
• Original Assignee: American Power Conversion Corporation (Schneider Electric SE)
• Inventors: VanGilder, James W., Zhang, Xuanhang
• Granted Patent: US 8,825,451 B2
• Time in Patent Office: Days
• US Class Current: 703/9
• CPC Class Codes: G06F 1/20 Cooling means
• CPC Class Codes: G06F 2113/02 Data centres
• CPC Class Codes: G06F 2119/08 Thermal analysis or thermal optimisation
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 30/23 using finite element methods [FEM] or finite difference methods [FDM]
• CPC Class Codes: G06F 30/28 using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
• CPC Class Codes: H05K 7/20836 Thermal management, e.g. server temperature control
• CPC Class Codes: H05K 9/0041 Ventilation panels having provisions for screening

Abstract

According to at least one embodiment, a computer-implemented method for modeling cooling performance is provided. The method includes acts of receiving, by a computer, input data from a storage device, the input data including data related to physical structures within at least one equipment rack, selecting, based on the data related to physical structures, at least one first equation of a plurality of predetermined equations that describe pressure values in a plurality of spaces within the at least one equipment rack, determining pressure values in identified spaces of the plurality of spaces by solving the at least one first equation using the input data, determining airflow values between identified spaces by calculating a difference between the pressure values and storing, on the storage device, the airflow values as equipment rack airflow values within the at least one equipment rack.

Claims

1. A computer-implemented method for modeling cooling performance, the method comprising:

receiving, by a computer, input data from a storage device, the input data including data related to physical structures within at least one equipment rack;

selecting, based on the data related to physical structures, at least one first equation of a plurality of predetermined equations that describe pressure values in a plurality of spaces within the at least one equipment rack;

determining pressure values in identified spaces of the plurality of spaces by solving the at least one first equation using the input data;

determining airflow values between identified spaces by calculating a difference between the pressure values; and

storing, on the storage device, the airflow values as equipment rack airflow values within the at least one equipment rack.

2. The method according to claim 1, wherein receiving input data includes receiving input data describing at least one of a front door, a server plane, a rear door, a rear cooling coil and an inlet in the at least one equipment rack.

3. The method according to claim 1, wherein determining the pressure values includes determining pressure values in identified spaces adjacent to at least one server positioned within the at least one equipment rack.

4. The method according to claim 3, further comprising:

determining a predicted airflow value for at least one fan of the at least one server based on the difference between the pressure values;

determining a predicted value of power delivered to the at least one fan based on the predicted airflow value for the at least one fan;

determining a predicted temperature value at an inlet of the at least one server based on an airflow value for leakage of ambient air into the at least one equipment rack; and

providing the predicted airflow value, the predicted value of power and the predicted temperature value to an external entity.

5. The method according to claim 1, further comprising:

(A) determining a temperature value at an outlet of the at least one equipment rack based on the equipment rack airflow values and a temperature value at an inlet of the at least one equipment rack;

(B) executing a room cooling performance model using the equipment rack airflow values and the temperature value at the outlet;

(C) receiving, from the room cooling performance model, an updated temperature value at the inlet of the at least one equipment rack;

(D) storing, on the storage device, the updated temperature value as the temperature value at the inlet;

(E) determining whether a difference between the updated temperature value and a previous temperature value at the inlet is greater than a threshold; and

(F) repeating acts (A) through (E) until the difference is not greater than the threshold.

6. The method according to claim 1, further comprising tuning the at least one equation to compensate for resistance values located within the at least one equipment rack.

7. The method according to claim 1, further comprising:

(A) dividing the at least one equipment rack into a plurality of grid cells;

(B) using a first iterative method based on the equipment rack airflow values, determine a value for airflow velocity for each of the grid cells;

(C) determining an air pressure value in each of the identified spaces based on the airflow velocity;

(D) using a second iterative method, determine new airflow values between the identified spaces based on the air pressure values in the identified spaces;

(E) storing the new airflow values as the equipment rack airflow values within the at least one equipment rack;

(F) determining whether differences between the new airflow values and previous airflow values is greater than a threshold; and

(G) repeating acts (B) through (F) until the differences are not greater than the threshold.

8. The method according to claim 7, wherein act (D) includes determining whether airflows in the at least one equipment rack satisfy a mass balance equation.

9. A system for modeling cooling performance, the system including a memory and a processor coupled to the memory and being configured to:

receive input data from a storage device, the input data including data related to physical structures within at least one equipment rack;

select, based on the data related to physical structures, at least one first equation of a plurality of predetermined equations that describe pressure values in a plurality of spaces within the at least one equipment rack;

determine pressure values in identified spaces of the plurality of spaces by solving the at least one first equation using the input data;

determine airflow values between identified spaces by calculating a difference between the pressure values; and

store, on the storage device, the airflow values as equipment rack airflow values within the at least one equipment rack.

10. The system according to claim 9, wherein the input data describes at least one of a front door, a server plane, a rear door, a rear cooling coil and an inlet in the at least one equipment rack.

11. The system according to claim 9, wherein the identified spaces include spaces adjacent to at least one server positioned within the at least one equipment rack.

12. The system according to claim 11, wherein the system is further configured to:

determine a predicted airflow value for at least one fan of the at least one server based on the difference between the pressure values;

determine a predicted value of power delivered to the at least one fan based on the predicted airflow value for the at least one fan;

determine a predicted temperature value at an inlet of the at least one server based on an airflow value for leakage of ambient air into the at least one equipment rack; and

provide the predicted airflow value, the predicted value of power and the predicted temperature value to an external entity.

13. The system according to claim 9, wherein the system is further configured to:

(A) determine a temperature value at an outlet of the at least one equipment rack based on the equipment rack airflow values and a temperature value at an inlet of the at least one equipment rack;

(B) execute a room cooling performance model using the equipment rack airflow values and the temperature value at the outlet;

(C) receive, from the room cooling performance model, an updated temperature value at the inlet of the at least one equipment rack;

(D) store, on the storage device, the updated temperature value as the temperature value at the inlet;

(E) determine whether a difference between the updated temperature value and a previous temperature value at the inlet is greater than a threshold; and

(F) repeat acts (A) through (E) until the difference is not greater than the threshold.

14. The system according to claim 9, wherein the system is further configured to receive information that tunes the at least one equation to compensate for resistance values located within the at least one equipment rack.

15. The system according to claim 9, wherein the system is further configured to:

(A) divide the at least one equipment rack into a plurality of grid cells;

(B) execute a first iterative method based on the equipment rack airflow values to determine a value for airflow velocity for each of the grid cells;

(C) determine an air pressure value in each of the identified spaces based on the airflow velocity;

(D) execute a second iterative method to determine new airflow values between the identified spaces based on the air pressure values in the identified spaces;

(E) store the new airflow values as the equipment rack airflow values within the at least one equipment rack;

(F) determine whether differences between the new airflow values and previous airflow values is greater than a threshold; and

(G) repeat acts (B) through (F) until the differences are not greater than the threshold.

16. The system according to claim 15, wherein at least one grid cell of the plurality of grid cells has a size different from a size of another grid cell of the plurality of grid cells and each of the plurality of grid cells has a size based on characteristics of the at least one equipment rack.

17. The system according to claim 15, wherein the system is further configured to determine whether airflows in the at least one equipment rack satisfy a mass balance equation.

18. A non-transitory computer readable medium having stored thereon sequences of instruction for modeling cooling performance including instructions that will cause at least one processor to:

receive input data from a storage device, the input data including data related to physical structures within at least one equipment rack;

select, based on the data related to physical structures, at least one first equation of a plurality of predetermined equations that describe pressure values in a plurality of spaces within the at least one equipment rack;

determine pressure values in identified spaces of the plurality of spaces by solving the at least one first equation using the input data;

determine airflow values between identified spaces by calculating a difference between the pressure values; and

store, on the storage device, the airflow values as equipment rack airflow values within the at least one equipment rack.

19. The computer readable medium according to claim 18, wherein the sequences of instruction include instructions that will cause the at least one processor to determine the pressure values by determining pressure values in identified spaces adjacent to at least one server positioned within the at least one equipment rack.

20. The computer readable medium according to claim 19, wherein the sequences of instruction include instructions that will cause the at least one processor to determine a predicted airflow value for at least one fan of the at least one server based on the difference between the pressure values.