GENERATING A CAPACITY SCHEDULE FOR A FACILITY

• US 20140257907A1
• Filed: 12/23/2011
• Published: 09/11/2014
• Est. Priority Date: 12/23/2011
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Chen, Yuan, Bash, Cullen E., Gmach, Daniel Juergen, Liu, Zhenhua
• Granted Patent: US 9,792,568 B2
• Time in Patent Office: Days
• US Class Current: 705/7.22
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/06312 Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling

Abstract

In a method for generating a capacity schedule for a facility to meet a predefined operational goal, in which the facility is to receive resources from a first resource supply, a prediction of a supply of resources available from the first resource supply for a predetermined period of time is accessed. In addition, a prediction of a demand for resources in the facility during the predetermined period of time is accessed. The prediction of the supply of resources and the prediction of the demand for resources are inputted into a constrained optimization problem and the capacity schedule for the facility is generated by finding a solution to the constrained optimization problem.

Claims

1. A method for generating a capacity schedule for a facility to meet a predefined operational goal, wherein the facility is to receive resources from a first resource supply, said method comprising:

a) accessing a prediction of a supply of resources available from the first resource supply for a predetermined period of time;

b) accessing a prediction of a demand for resources in the facility during the predetermined period of time;

c) inputting the prediction of the supply of resources and the prediction of the demand for resources into a constrained optimization problem, wherein a solution to the constrained optimization problem comprises the capacity schedule; and

d) generating the capacity schedule for the facility by finding a solution, by a processor, to the constrained optimization problem.

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

accessing a predicted supply of external cooling resources available during the predetermined period of time; and

wherein (c) further comprises inputting the predicted supply of external cooling resources into the constrained optimization problem.

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

receiving a price of resources available from the second resource supply during the predetermined period of time; and

wherein (c) further comprises inputting the received price of resources into the constrained optimization problem.

4. The method according to claim 1, wherein (b) further comprises accessing the predicted demand for resources by both resource demand machines to perform workloads and cooling system components to cool the machines in the facility during the predetermined period of time.

5. The method according to claim 4, wherein (c) further comprises inputting the predicted demand for resources by both resource demand machines to perform the workloads and the cooling systems to cool the machines into the constrained optimization problem.

6. The method according to claim 4, wherein the workloads comprise critical workloads and non-critical workloads, and wherein (g) further comprises generating the capacity schedule for the facility that substantially optimizes a scheduling of the non-critical workloads during the predetermined period of time while meeting the predefined operational goal.

7. The method according to claim 1, wherein the optimization problem is formulated as the following constrained optimization problem:

min_a,bΣ

_t((p(t)(d(t)−

r(t))⁺−

Σ

_tb(t)R),

s.t. a(t)+b(t)+f(a(t)+b(t))≦

d(t),

b(t))≧

0,

Σ

_tb(t))≦

B

0≦

a(t)+b(t)≦

D,

a(t)+b(t)≦

c(t), and

Σ

_td(t)−

Σ

_tr(t)≦

0,

wherein a(t) comprises demand for resources by a critical workload, b(t) comprises demand for resources by a non-critical workload, c(t) comprises cooling capacity of a cooling system, d(t) comprises total demand for resources in the facility, p(t) comprises a price of resources available from the second resource supply, R comprises profit generated by running non-critical workload (per unit), B comprises total demand for resources by non-critical workloads; and

D comprises total information technology capacity.

8. The method according to claim 1, wherein generating the capacity schedule further comprises solving the constrained optimization problem using convex functions.

9. The method according to claim 1, wherein the facility is to also receive resources from a second resource supply, and wherein the first resource supply differs from the second resource supply in that at least one of:

the first resource supply comprises a renewable power supply and the second power supply comprises a non-renewable power supply;

a resource available from the first resource supply is relatively less expensive than a resource available from the second resource supply; and

the first resource supply is relatively more sustainable than the second resource supply.

10. A capacity scheduler to generate a capacity schedule for a facility to meet a predefined operational goal, wherein the facility is to receive resources from a first resource supply, said capacity scheduler comprising:

a memory storing at least one module comprising machine readable instructions to;

access a prediction of a supply of resources available from the first resource supply for a predetermined period of time;

access a prediction of a demand for resources in the facility during the predetermined period of time;

input the prediction of the supply of resources and the prediction of the demand for resources into a constrained optimization problem, wherein a solution to the constrained optimization problem comprises the capacity schedule; and

generate the capacity schedule for the facility by finding solution to the constrained optimization problem; and

a processor to implement the at least one module.

11. The capacity scheduler according to claim 10, wherein the at least one module further comprises machine-readable instructions to:

access a predicted supply of external cooling resources available during the predetermined period of time; and

input the predicted supply of external cooling resources into the constrained optimization problem.

12. The capacity scheduler according to claim 10, wherein the at least one module further comprises machine-readable instructions to:

access the predicted demand for resources by both resource demand machines to perform workloads and cooling system components to cool the machines in the facility during the predetermined period of time;

input the predicted demand for resources by both resource demand machines to perform the workloads and the cooling systems to cool the machines into the constrained optimization problem; and

generate the capacity schedule for the facility that substantially optimizes a scheduling of resource demand consumption by non-critical workloads during the predetermined period of time while meeting the predefined operational goal.

13. The capacity scheduler according to claim 10, wherein the optimization problem is formulated as the following constrained optimization problem:

min_a,bΣ

_t((p(t)(d(t)−

r(t))⁺−

Σ

_tb(t)R),

s.t. a(t)+b(t)+f(a(t)+b(t))≦

d(t),

b(t))≧

0,

Σ

_tb(t))≦

B

0≦

a(t)+b(t)≦

D,

a(t)+b(t)≦

c(t), and

Σ

_td(t)−

Σ

_tr(t)≦

0,

wherein a(t) comprises demand for resources by a critical workload, b(t) comprises demand for resources by a non-critical workload, c(t) comprises cooling capacity of a cooling system, d(t) comprises total demand for resources in the facility, p(t) comprises a price of resources available from the second resource supply, R comprises profit generated by running non-critical workload (per unit), B comprises total demand for resources by non-critical workloads; and

D comprises total workload capacity.

14. The capacity scheduler according to claim 10, wherein the facility is to also receive resources from a second resource supply, and wherein the first resource supply differs from the second resource supply in that at least one of:

the first resource supply comprises a renewable power supply and the second power supply comprises a non-renewable power supply;

a resource available from the first resource supply is relatively less expensive than a resource available from the second resource supply; and

the first resource supply is relatively more sustainable than the second resource supply.

15. A non-transitory computer readable storage medium on which is embedded at least one computer program, said at least one computer program implementing a method for generating a capacity schedule for a facility to meet a predefined operational goal, wherein the facility is to receive resources from a resource supply, said at least one computer program comprising computer readable code to:

access a prediction of a supply of resources available from the first resource supply for a predetermined period of time;

access a prediction of a demand for resources in the facility during the predetermined period of time;

input the prediction of the supply of resources and the prediction of the demand for resources into a constrained optimization problem; and

generate the capacity schedule for the facility by finding a solution to the constrained optimization problem.