Management of a virtual power infrastructure

• US 9,063,715 B2
• Filed: 06/10/2010
• Issued: 06/23/2015
• Est. Priority Date: 06/10/2010
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Sharma, Ratnesh Kumar, Shah, Amip J., Bash, Cullen E., Shih, Chih C., Patel, Chandrakant
• Primary Examiner(s): Fennema, Robert
• Assistant Examiner(s): STEVENS, THOMAS H
• Application Number:
  US12/813,012
• Publication Number:
  US 20110307110A1
• Time in Patent Office: 1,839 Days
• Field of Search: 307/11, 307/35, 700/9, 700/19, 700/22, 700/286, 700/295, 700/297
• US Class Current: 1/1
• CPC Class Codes: G06F 1/26 Power supply means, e.g. regulation thereof for memories G11C

Abstract

A virtual power infrastructure for managing distribution of power to a plurality of power demanding units from a plurality of power generators includes a demand manager having logical descriptions of the power demanding units, in which the demand manager is configured to determine power load demands of the power demanding units using the logical descriptions of the power demanding units, and a capacity manager having logical descriptions of the power generators. The capacity manager is configured to determine allocation of power capacity supplied to the power generators from one or more of the power generators to meet the power load demands of the power demanding units, while satisfying one or more predetermined constraints associated with at least one of the power demanding units and the power generators.

Claims

1. A virtual power infrastructure, comprising:

a non-transitory computer readable storage medium with instructions stored thereon for managing distribution of power to a plurality of power demanding units from a plurality of power generators, wherein the plurality of power demanding units and the plurality of power generators are each a separate non-overlapping set of a plurality of entities and the plurality of power generators includes at least two types of power generators, wherein the two types of generators includes at least two of nuclear power, natural gas power, coal-based power, solar power, wind power, and water power, said infrastructure comprising;

a demand manager having logical descriptions of the power demanding units, wherein the demand manager determines power load demands of the power demanding units using;

the logical descriptions of the power demanding units;

a determination of a reliability of at least one of the plurality of power generators; and

a first cost for a first amount of energy produced by at least one of the at least two types of power generators and a second cost for a second amount of energy produced by at least another of the at least two types of power generators;

a capacity manager having logical descriptions of the power generators, wherein the power generators supply power to the power demanding units, and wherein the capacity manager determines allocation of power capacity supplied to the power demanding units from one or more of the power generators to meet the power load demands of the power demanding units, while satisfying one or more predetermined constraints that include a selection by a consumer of the power that indicates the first cost of the first amount of energy and the second cost of the second amount of energy associated with at least one of the power demanding units, wherein the first amount of energy and the second amount of energy are selected based on a total cost for energy from the at least two types of power generators,

wherein the one or more predetermined constraints comprise one or more of service level agreement (SLA) provisions and power generator distribution constraints.

2. The virtual power infrastructure according to claim 1, wherein the demand manager determines the power load demands of the power demanding units based upon one or more aspects of workloads that are at least one of performed and scheduled to be performed by the power demanding units and one or more power demand constraints pertaining to performance of the workloads.

3. The virtual power infrastructure according to claim 1, wherein the demand manager determines at least one characteristic of the power load demand, the at least one characteristic comprising one or more of operational levels, redundancy, and cost of deployment to satisfy the power load demands of the power demanding units, and wherein the capacity manager further determines allocation of the power capacity supplied to the power generators based upon the at least one characteristic.

4. The virtual power infrastructure according to claim 1, wherein the logical descriptions of the power demanding units comprise one or more of power reliability requirements, power load demand descriptions, power load demand forecasts, power load demand recovery patterns, criticalities, and elasticity of demand based on pricing model, of the power demanding units.

5. The virtual power infrastructure according to claim 1, wherein the power load demands comprise one or more of power load demand estimates, locations of power load demands, durations of power load demands, costs of deploying the power load demands, power load demand zone designations, and sustainability limits of the power demanding units.

6. The virtual power infrastructure according to claim 1, wherein the logical descriptions of the power generators comprise one or more of descriptions, energy efficiencies, resource consumption levels, cost functions, emissions, environmental footprints, reliability levels, power output capacity limitations, and available capacities of the power generators.

7. The virtual power infrastructure according to claim 6, wherein the capacity manager determines allocation of the power capacities of the power generators to substantially optimize at least one of efficiency, cost, and fault tolerance of the power generators in supplying power to the power demanding units based upon the logical descriptions of the power generators.

8. The virtual power infrastructure according to claim 1, wherein the capacity manager determines one or more of allocation of the power supply capacities, identification of zones for allocation of the power supply capacities, estimates of the power to be supplied, a total cost of ownership, utilization levels, and environmental impact associated with supplying power to meet the power load demands as determined by the demand manager.

9. The virtual power infrastructure according to claim 1, wherein the capacity manager follows one or more of techniques in determining the allocation of the power capacity, said one or more techniques comprising a hierarchical assignment technique, a parameterized match technique, and a phase assignment technique.

10. The virtual power infrastructure according to claim 1, wherein the one or more predetermined constraints further comprise one or more of power generator capacity constraints, reliability levels of electrical power required by the power demanding units, quality of the electrical power required by the power demanding units, various regulations that the power demanding units are required to comply with, and uptime requirements of the power demanding units.

11. The virtual power infrastructure according to claim 1, wherein the demand manager interprets data pertaining to the power load demands of the power demanding units through one or more of stream mining of discrete data to identify recurring patterns in the data, pattern recognition techniques, and state-wise evaluation.

12. The virtual power infrastructure according to claim 1, further comprising:

a service operator to operate as a monitoring agent and a broker for distribution of power from the power generators to the power demanding units, wherein the service operator monitors operations of the power demanding units and the power generators to substantially ensure that the power demanding units are receiving sufficient amounts of power while meeting the one or more predetermined constraints.

13. The virtual power infrastructure according to claim 1, wherein the demand manager, the capacity manager, and a service operator form part of a single overlay in an integrated power management system.

14. A method of virtualized management of power distribution, comprising:

utilizing a non-transitory computer readable storage medium with instructions stored thereon for management of power distribution among a plurality of power demanding units from a plurality of power generators, wherein the plurality of power demanding units and the plurality of power generators are each a separate non-overlapping set of a plurality of entities and the plurality of power generators includes at least two types of power generators, wherein a first type of power generator includes an exhaustible material consuming power generator at a first cost and a second type of power generator includes a renewable energy-based power generator at a second cost, the method comprising;

determining power load demands of the power demanding units;

storing the power load demands as a first set of logical descriptions;

determining characteristics of the power generators, wherein the characteristics include;

a reliability of the first and the second power generators; and

the first cost and the second cost;

storing the characteristics of the power generators as a second set of logical descriptions;

determining allocation of power capacity from at least the first and the second power generators to meet the power load demands of the power demanding units based upon the first set of logical descriptions and the second set of logical descriptions while satisfying one or more predetermined constraints that include a selection by a consumer of the power that indicates a first amount of energy to be provided by the first type of power generator at the first cost and a second amount of energy to be provided by the second type of power generator at the second cost and are associated with at least one of the power demanding units, wherein the first amount of energy and the second amount of energy are selected based on the first cost and the second cost; and

accessing the one or more predetermined constraints, wherein the one or more predetermined constraints comprise one or more constraints pertaining to service level agreement (SLA) provisions and power generator distribution constraints.

15. The method according to claim 14, wherein determining power load demands of the power demanding units further comprises determining the power load demands of the power demanding units based upon one or more aspects of workloads that are at least one of performed and scheduled to be performed by the power demanding units and one or more power demand constraints pertaining to performance of the workloads, wherein the one or more power demand constraints includes at least one of an economic cost and an environmental cost.

16. The method according to claim 14, wherein the exhaustible material consuming power generator includes a coal based power generator and the renewable energy based power generator includes at least one of a solar power generator, a wind power generator, and a water current power generator.

17. The method according to claim 14, wherein the first power generator and the second power generator are used to generate power for a single power demanding unit and a first portion of energy from the first power generator and a second portion of energy from the second power generator are determined based on the total cost of energy from the first and the second power generator.

18. The method according to claim 17, wherein the first portion of energy and the second portion of energy are further determined based on a reliability of the first and the second power generators.

19. A non-transitory machine readable storage medium on which is embedded machine readable instructions, said machine readable instructions, comprising:

instructions for virtualized management of power distribution among a plurality of power demanding units from a plurality of power generators, wherein the plurality of power demanding units and the plurality of power generators are each a separate non-overlapping set of a plurality of entities and the plurality of power generators includes at least two types of power generators, wherein a first type of power generator includes an exhaustible material consuming power generator and a second type of power generator includes a renewable energy-based power generator, said machine readable instructions comprising a set of instructions to;

determine power load demands of the power demanding units, wherein a first portion of the power load demands is selected to be generated by the first type of power generator based on a first cost of the first portion of power load demands and a second portion of the power load demands is selected to be generated by the second type of power generator based on a second cost of the second portion of power load demands;

store the power load demands as a first set of logical descriptions;

determine characteristics of the power generators, wherein the characteristics include;

a reliability of the first and the second power generators; and

the first cost and the second cost;

store the characteristics of the power generators as a second set of logical descriptions; and

determine allocation of power capacity from one or more of the power generators to meet the power load demands of the power demanding units based upon the first set of logical descriptions and the second set of logical descriptions while satisfying one or more predetermined constraints that include a selection by a consumer of the power that indicates a first amount of energy to be provided by the first type of power generator and a second amount of energy to be provided by the second type of power generator and are associated with at least one of the power demanding units, wherein the selection of the first amount and the second amount is based on the first cost of the power provided by the first type of power generator and the second cost of the second type of power generator, wherein the first amount of energy and the second amount of energy are selected based on a total cost for energy from the first type of power generator and energy from the second type of power generator;

wherein the one or more predetermined constraints comprise one or more of service level agreement (SLA) provisions and power generator distribution constraints.

20. The machine readable storage medium according to claim 19, said machine readable instructions further including a set of instructions to:

determine the power load demands of the power demanding units based upon one or more aspects of workloads that are at least one of performed and scheduled to be performed by the power demanding units and one or more power demand constraints pertaining to performance of the workloads.