System and method for sequential placement of cooling resources within data center layouts
View Patent ↗A computer-implemented method for sequential placement of cooling resources in a data center comprises: defining a weighted, higher-order cooling metric, , representing an overall performance of the cooling resources in the data center; enumerating all possible locations in the data center for placing an additional c cooling resources; and placing the c cooling resources in locations in the data center for which is closest to an optimum value. For a performance metric M i , the weighted, higher-order cooling performance metric can be defined as M ^ = ∑ k = 0 C - 1 ∑ i = 1 R a ( i , k ) M i ( k ) , where R represents a number of racks in the data center, C represents a total number of cooling resources placed in the data center, i represents one of the R racks in the data center, M i (k) represents a value of metric M i when k cooling resources are shut down, and a(i,k) is a weighting function for rack i with the k cooling resources shut down. A system performing the method and computer-readable media having stored thereon instructions causing a processor to perform the method are also provided.
1. A computer-implemented method for sequential placement of cooling resources in a data center model, the method comprising:
defining a weighted, higher-order cooling metric, , representing an overall performance of the cooling resources in the data center model, being based on a calculation of at least one performance metric M, wherein k cooling resources having greater impact on M than other cooling resources are omitted from the calculation;
enumerating all possible locations in the data center model for placing an additional c cooling resources; and
placing the c cooling resources in locations in the data center model for which {circumflex over (M)} is closest to an optimum value.
2. The method of claim 1 , further comprising:
defining the higher-order cooling metric, , in terms of a cooling index M i , such that
M
^
=
∑
k
=
0
C
-
1
∑
i
=
1
R
a
(
i
,
k
)
M
i
(
k
)
,
where R represents a number of racks in the data center model, C represents a total number of cooling resources placed in the data center model, i represents one of the R racks in the data center model, M i (k) represents a value of metric M i when k cooling resources are shut down, and a(i,k) is a weighting function for rack i with the k cooling resources shut down.
3. The computer-implemented method of claim 1 , further comprising:
repeating enumerating and placing until a desired stopping condition is met by a resulting placement of cooling resources.
4. The computer-implemented method of claim 3 , wherein the stopping condition is a desired redundancy level.
5. The computer-implemented method of claim 3 , further comprising:
testing whether the desired stopping condition is met by a new resulting placement of cooling resources after removing one cooling resource from the resulting placement of cooling resources.
6. The computer-implemented method of claim 5 , further comprising:
identifying that cooling resource which when removed results in a value of closest to an optimum value; and
removing that cooling resource identified.
7. The computer-implemented method of claim 2 , wherein M i is capture index.
8. A system for sequential placement of cooling resources in a data center layout, comprising:
a computer storage system in which is stored a database holding a numerical computer model of the data center layout; and
a computer processor executing a sequence of instructions directing:
defining a weighted, higher-order cooling metric, , representing an overall performance of the cooling resources in the computer model of the data center layout, being based on a calculation of at least one performance metric M, wherein k cooling resources having greater impact on M than other cooling resources are omitted from the calculation;
enumerating all possible locations in the computer model of the data center layout for placing an additional c cooling resources; and
placing the c cooling resources in locations in the computer model of the data center layout for which {circumflex over (M)} is closest to an optimum value.
9. The system of claim 8 , wherein defining further comprises:
defining the higher-order cooling metric, , in terms of a cooling index M i , such that
M
^
=
∑
k
=
0
C
-
1
∑
i
=
1
R
a
(
i
,
k
)
M
i
(
k
)
,
where R represents a number of racks in the computer model of the data center layout, C represents a total number of cooling resources placed in the computer model of the data center layout, i represents one of the R racks in the computer model of the data center layout, M i (k) represents a value of metric M, when k cooling resources are shut down, and a(i,k) is a weighting function for rack i with the k cooling resources shut down.
10. The system of claim 8 , the sequence of instructions further comprising:
repeating enumerating and placing until a desired stopping condition is met by a resulting placement of cooling resources.
11. The system of claim 10 , wherein the stopping condition is a desired redundancy level.
12. The system of claim 10 , the sequence of instructions further comprising:
testing whether the desired stopping condition is met by a new resulting placement of cooling resources after removing one cooling resource from the resulting placement of cooling resources.
13. The system of claim 12 , the sequence of instructions further comprising:
identifying that cooling resource which when removed results in a value of M closest to an optimum value; and
removing that cooling resource identified.
14. A non-transitory computer-readable medium having stored thereon sequences of instructions for sequentially placing cooling resources in a data center model, the sequences of instructions including instructions that will cause at least one processor to:
define a weighted, higher-order cooling metric, , representing an overall performance of the cooling resources in the data center model, being based on a calculation of at least one performance metric M, wherein k cooling resources having greater impact on M than other cooling resources are omitted from the calculation;
enumerate all possible locations in the data center model for placing an additional c cooling resources; and
place the c cooling resources in locations in the data center model for which is closest to an optimum value.
15. The non-transitory computer-readable medium of claim 14 , wherein defining further comprises:
defining the higher-order cooling metric, , in terms of a cooling index M i , such that
M
^
=
∑
k
=
0
C
-
1
∑
i
=
1
R
a
(
i
,
k
)
M
i
(
k
)
,
where R represents a number of racks in the data center model, C represents a total number of cooling resources placed in the data center model, i represents one of the R racks in the data center model, M i (k) represents a value of metric M i when k cooling resources are shut down, and a(i,k) is a weighting function for rack i with the k cooling resources shut down.
16. The non-transitory computer-readable medium of claim 14 , the sequences of instructions further causing the processor to:
repeat enumerating and placing until a desired stopping condition is met by a resulting placement of cooling resources.
17. The non-transitory computer-readable medium of claim 16 , wherein the stopping condition is a desired redundancy level.
18. The non-transitory computer-readable medium of claim 16 , the sequences of instructions further causing the processor to test whether the desired stopping condition is met by a new resulting placement of cooling resources after removing one cooling resource from the resulting placement of cooling resources.
19. The non-transitory computer-readable medium of claim 18 , the sequences of instructions further causing the processor to:
identify that cooling resource which when removed results in a value of {circumflex over (M)} closest to an optimum value; and
remove that cooling resource identified.
20. The non-transitory computer-implemented method of claim 15 , wherein M i is a capture index metric.