System and method for applying machine learning algorithms to compute health scores for workload scheduling
Disclosed is a method that includes collecting first temporal statistics for a port element in a computing environment, collecting second temporal statistics for a switch element in the computing environment, collecting third temporal statistics for the computing environment generally, computing a spatial correlation between network features and network elements comprising the port element and the switch element and computing, via a machine learning technique, a port dynamic weight for the port element and a switch dynamic weight for the switch element. The method can also include scheduling workload to consume compute resources within the compute environment based at least in part on the port dynamic weight for the port element and the switch dynamic weight for the switch element.
1. A computer-implemented method comprising:
collecting a plurality of temporal statistics associated with a plurality of elements in a network computing environment;
computing a spatial correlation associated with the plurality of elements and network features for providing network service access through the network computing environment, wherein the spatial correlation is associated with both physical locations and virtual locations of the plurality of elements and network features;
computing a dynamic weight for one or more of the plurality of elements based on historic data of the network features providing the network service access through the network computing environment;
scheduling a workload for performance in the network computing environment as part of providing network service access through the network computing environment based at least in part on the plurality of temporal statistics, the spatial correlation, and the dynamic weight; and
facilitating deployment of the workload into the network computing environment for performance in the network environment.
2. The method of claim 1 , wherein the collecting of the plurality of temporal statistics includes collecting historical and current metrics for a port element.
3. The method of claim 1 , wherein the collecting of the plurality of temporal statistics includes collecting historical and current metrics for a switch element.
4. The method of claim 1 , wherein the plurality of temporal statistics include temporal statistics for a port in the computing environment, a switch element in the computing environment, and/or historical and current metrics for the computing environment.
5. The method of claim 1 , wherein the plurality of elements including a port element and a switch element.
6. The method of claim 5 , further comprising:
computing a health score for one of the port element and the switch element using an equation as follows:
H
f
t
=
(
∑
i
=
1
n
(
W
i
*
P
i
)
*
(
∏
j
=
1
m
R
j
t
)
)
*
(
∏
k
=
1
n
W
k
*
P
k
)
,
wherein:
H is a health of a respective one of the plurality of elements “f” at a time “t”;
W is a weight calibrated using a neural network model for each of the plurality of elements;
P is a normalized numeric value for each respective fabric element at the time “t”;
(Π j=1 m R j t ): represents spatial dependencies of other attributes on the respective one of the plurality of elements;
“R” is a reward computed using reinforcement learning, for the spatial dependencies on the respective one of the plurality of elements and multiplied to accommodate a dependency of other attributes;
(Π k=1 n W k *P k ): where “P” is a normalized boolean value for each attribute and multiplied into the equation.
7. The method of claim 1 , wherein the dynamic weight includes for a switch element dynamic weight and a port element dynamic weight.
8. A system comprising:
at least one processor; and
a computer-readable storage device storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
collecting a plurality of temporal statistics associated with a plurality of elements in a network computing environment;
computing a spatial correlation associated with the plurality of elements and network features for providing network service access through the network computing environment, wherein the spatial correlation is associated with both physical locations and virtual locations of the plurality of elements and network features;
computing a dynamic weight for one or more of the plurality of elements based on historic data of the network features providing the network service access through the network computing environment;
scheduling a workload for performance in the network computing environment as part of providing network service access through the network computing environment based at least in part on the plurality of temporal statistics, the spatial correlation, and the dynamic weight; and
facilitating deployment of the workload into the network computing environment for performance in the network environment.
9. The system of claim 8 , wherein the collecting of the plurality of temporal statistics includes collecting historical and current metrics for a port element.
10. The system of claim 8 , wherein the collecting of the plurality of temporal statistics includes collecting historical and current metrics for a switch element.
11. The system of claim 8 , wherein the plurality of temporal statistics include temporal statistics for a port in the computing environment, a switch element in the computing environment, and/or historical and current metrics for the computing environment.
12. The system of claim 8 , wherein the spatial correlation associated with the plurality of elements is between network features and the plurality of elements including a port element and a switch element.
13. The system of claim 12 , wherein the operations include computing a health score for one of the port element and the switch element using an equation as follows:
H
f
t
=
(
∑
i
=
1
n
(
W
i
*
P
i
)
*
(
∏
j
=
1
m
R
j
t
)
)
*
(
∏
k
=
1
n
W
k
*
P
k
)
,
wherein:
H is a health of a respective one of the plurality of elements “f” at a time “t”;
W is a weight calibrated using a neural network model for each of the plurality of elements;
P is a normalized numeric value for each respective fabric element at the time “t”;
(Π j=1 m R j t ): represents spatial dependencies of other attributes on the respective one of the plurality of elements;
“R” is a reward computed using reinforcement learning, for all the spatial dependencies on the respective one of the plurality of elements and multiplied to accommodate a dependency of other attributes;
(Π k=1 n W k *P k ): where “P” is a normalized boolean value for each attribute and multiplied into the equation.
14. The system of claim 8 , wherein the dynamic weight includes for a switch element dynamic weight and a port element dynamic weight.
15. A non-transitory computer-readable storage device storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
collecting a plurality of temporal statistics associated with a plurality of elements in a network computing environment;
computing a spatial correlation associated with the plurality of elements and network features for providing network service access through the network computing environment, wherein the spatial correlation is associated with both physical locations and virtual locations of the plurality of elements and network features;
computing a dynamic weight for one or more of the plurality of elements based on historic data of the network features providing the network service access through the network computing environment;
scheduling a workload for performance in the network computing environment as part of providing network service access through the network computing environment based at least in part on the plurality of temporal statistics, the spatial correlation, and the dynamic weight; and
facilitating deployment of the workload into the network computing environment for performance in the network environment.
16. The non-transitory computer-readable storage device of claim 15 , wherein the collecting of the plurality of temporal statistics includes collecting historical and current metrics for a port element.
17. The non-transitory computer-readable storage device of claim 15 , wherein the collecting of the plurality of temporal statistics includes collecting historical and current metrics for a switch element.
18. The non-transitory computer-readable storage device of claim 15 , wherein the plurality of temporal statistics include temporal statistics for a port in the computing environment, a switch element in the computing environment, and/or historical and current metrics for the computing environment.
19. The non-transitory computer-readable storage device of claim 15 , wherein the spatial correlation associated with the plurality of elements is between network features and the plurality of elements including a port element and a switch element.
20. The non-transitory computer-readable storage device of claim 19 , wherein the operations include computing a health score for one of the port element and the switch element using an equation as follows:
H
f
t
=
(
∑
i
=
1
n
(
W
i
*
P
i
)
*
(
∏
j
=
1
m
R
j
t
)
)
*
(
∏
k
=
1
n
W
k
*
P
k
)
,
wherein:
H is a health of a respective one of the plurality of elements “f” at a time “t”;
W is a weight calibrated using a neural network model for each of the plurality of elements;
P is a normalized numeric value for each respective fabric element at the time “t”;
(Π j=1 m R j t ): represents spatial dependencies of other attributes on the respective one of the plurality of elements;
“R” is a reward computed using reinforcement learning, for all the spatial dependencies on the respective one of the plurality of elements and multiplied to accommodate a dependency of other attributes;
(Π k=1 n W k *P k ): where “P” is a normalized boolean value for each attribute and multiplied into the equation.