Energy aware processing load distribution system and method

• US 9,753,465 B1
• Filed: 01/13/2014
• Issued: 09/05/2017
• Est. Priority Date: 07/21/2009
• Status: Active Grant

• Current Assignee: The Research Foundation for The State University of New York (State University of New York)
• Original Assignee: The Research Foundation for The State University of New York (State University of New York)
• Inventors: Ghose, Kanad
• Primary Examiner(s): Padot, Timothy
• Application Number:
  US14/153,540
• Time in Patent Office: 1,331 Days
• Field of Search: 361688, 165200, 165279
• CPC Class Codes: A61K 36/185 Magnoliopsida (dicotyledons)
• CPC Class Codes: B03B 1/00 Conditioning for facilitating separation by altering physical properties of the matter to be treated
• CPC Class Codes: B03B 11/00 Feed or discharge devices integral with washing or wet-separating equipment
• CPC Class Codes: B03B 5/02 using shaken, pulsated or stirred beds as the principal means of separation B03B5/28, B03B5/48 take precedence
• CPC Class Codes: B03B 5/58 Bowl classifiers
• CPC Class Codes: G05D 23/19 characterised by the use of electric means G05D23/1393 takes precedence
• CPC Class Codes: G06F 1/20 Cooling means
• CPC Class Codes: G06F 1/206 comprising thermal management
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 1/3209 Monitoring remote activity, e.g. over telephone lines or network connections
• CPC Class Codes: G06F 1/3228 Monitoring task completion, e.g. by use of idle timers, stop commands or wait commands
• CPC Class Codes: G06F 13/409 Mechanical coupling back panels H05K7/1438
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/4893 taking into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: G06F 9/5094 where the allocation takes into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: G06K 19/0723 the record carrier comprising an arrangement for non-contact communication, e.g. wireless communication circuits on transponder cards, non-contact smart cards or RFIDs
• CPC Class Codes: G06K 19/07705 the visual interface being a single light or small number of lights capable of being switched on or off, e.g. a series of LEDs
• CPC Class Codes: G06K 19/07722 the record carrier being multilayered, e.g. laminated sheets flat articles in general, see B32B37/00
• CPC Class Codes: H04L 69/329 : in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 : Network security protocols
• CPC Class Codes: H05K 7/20836 : Thermal management, e.g. server temperature control
• CPC Class Codes: Y02D 10/00 : Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A method for controlling a data center, comprising a plurality of server systems, each associated with a cooling system and a thermal constraint, comprising: a concurrent physical condition of a first server system; predicting a future physical condition based on a set of future states of the first server system; dynamically controlling the cooling system in response to at least the input and the predicted future physical condition, to selectively cool the first server system sufficient to meet the predetermined thermal constraint; and controlling an allocation of tasks between the plurality of server systems to selectively load the first server system within the predetermined thermal constraint and selectively idle a second server system, wherein the idle second server system can be recruited to accept tasks when allocated to it, and wherein the cooling system associated with the idle second server system is selectively operated in a low power consumption state.

Claims

1. A method for controlling a server system having an associated dynamically controllable cooling system and a predetermined thermal constraint, comprising:

receiving an input corresponding to a physical condition of at least one of the server system and an environment of the server system, the physical condition corresponding to at least a temperature associated with the server system;

predicting, with at least one automated processor, the future physical condition of the server system based on at least a model of the server system;

at least one control output of an automated controller, and a sequence of operations queued for performance by the server system, while maintaining a processing rate within a processing capacity of the server system of the sequence of operations queued for performance by the server system defined by a quality of service requirement, wherein the sequence of operations queued for performance by the server system is defined to selectively concentrate thermal stresses in a subset of available resources of the server system;

dynamically controlling the dynamically controllable cooling system with the automated controller, in response to at least the input and the predicted future physical condition of the server system to predictively cool the server system comprising the subset of available resources of the server system to which the thermal stresses are concentrated sufficient to meet the predetermined thermal constraint while maintaining the processing rate within the processing capacity of the server system of the sequence of operations queued for performance by the server system defined by the quality of service requirement, wherein the dynamically controllable cooling system is controlled by the automated controller to initiate an increased availability of cooling capacity for the server system after the predicted future physical condition indicates an increase in cooling demand and before an increase in the temperature associated with the server system and caused by the sequence of operations queued for performance by the server system is indicated by the input.

2. The method according to claim 1, further comprising selectively activating the server system from an idle state to an active state, and loading the server system in the active state to a processing load predicted to maintain the server in the active state within the predetermined thermal constraint, wherein the dynamically controllable cooling system associated with the server system is selectively operated in a low power consumption state while the server system is maintained in the idle state.

3. The method according to claim 1, wherein the associated dynamically controllable cooling system comprises an air conditioner.

4. The method according to claim 3, wherein the air conditioner comprises a control adapted to vary an air flow rate and an air temperature or air for cooling the server system, further comprising varying the air flow rate and the air temperature of air cooling the server system responsive to the control output of the automated controller.

5. The method according to claim 4, wherein the air conditioner is associated with a proportionally controllable air flow regulation baffle.

6. The method according to claim 1, wherein the predetermined thermal constraint comprises a maximum operating temperature of at least one component of the server system.

7. The method according to claim 1, wherein the predetermined thermal constraint comprises a maximum energy consumption of the server system.

8. The method according to claim 1, wherein the input is received from a thermal sensor, sensing a temperature of a component within the server system.

9. The method according to claim 1, wherein the input represents an energy consumption of at least one component within the server system.

10. The method according to claim 1, further comprising providing a queue for ordering the sequence of operations for performance by the server system, and receiving new tasks in the queue except when the server system is at risk of at least one of exceeding the predetermined thermal constraint and failing to meet the processing rate defined by a quality of service requirement.

11. The method according to claim 1, further comprising providing a queue for ordering the sequence of operations for performance by the server system, an removing at least a portion of the sequence of operations from the queue when the server system is at risk of at least one of exceeding the predetermined thermal constraint, and failing to meet the processing rate defined by a quality of service requirement.

12. The method according to claim 1, wherein the server system comprises a plurality of processing units, each processing unit executing under a respective operating system, wherein at least a portion of said predicting or said controlling is executed as a part of the respective operating system of a respective processing unit.

13. The method according to claim 1, further comprising controlling the server system by the automated controller, external to the server system, adapted to allocate tasks representing respective sequences of instructions, to the server system, in dependence on at least the input and the predicting.

14. A method for controlling a server system having an associated dynamically controllable cooling system and a predetermined thermal constraint, comprising:

predicting, with at least one automated processor, a future physical condition of the server system and the associated dynamically controllable cooling system based on a model of the server system and the associated dynamically controllable cooling system, and a sequence of operations queued for performance by the server system prior to processing by the server system, wherein the sequence of operations queued for performance by the server system is selectively defined to concentrate thermal stresses in a subset of available resources of the server system;

dynamically controlling the dynamically controllable cooling system with an automated controller, in response to at least the sequence of operations queued for performance by the server system prior to processing by the server system and the predicted future physical condition, to change a capacity of the associated dynamically controllable cooling system to cool the server system comprising the subset of available resources of the server system to which the thermal stresses are concentrated, to achieve a cooling capacity predicted to be sufficient to meet the predetermined thermal constraint while meeting a quality of service requirement representing a rate of performance by the server system, wherein the dynamically controllable cooling system is controlled by the automated controller to alter a cooling of the server system after the predicted future physical condition indicates a change in a predicted cooling demand and before a change in temperature of the server system resulting from performance of the operations queued for performance by the server system.

15. The method according to claim 14, wherein the server system comprises a plurality of separately activatable components, further comprising selectively activating at least one activatable component from an idle state to an active state, selectively in dependence on a predicted inability of the server system to meet the predetermined thermal constraint and the quality of service requirement representing the rate of performance by the server system.

16. The method according to claim 14, further comprising providing a queue for ordering the sequence of operations queued for performance by the server system, and receiving new tasks into the queue and removing existing tasks from the queue selectively dependent on a predicted ability of the server system to meet both the predetermined thermal constraint and the quality of service requirement representing the rate of performance by the server system for the sequence of operations queued for performance by the server system.

17. The method according to claim 14, wherein the server system comprises a plurality of processing units each having a predetermined thermal constraint, a distinct sequence of operations queued for performance, a predicted future physical condition, and a distinct cooling capacity from the associated dynamically controllable cooling system, wherein the dynamically controllable cooling system is dynamically controlled based on at least the sequence of operations queued for performance by each respective processing unit and the model of the server system comprising the plurality of processing units, to change the respective distinct cooling capacity of the associated dynamically controllable cooling system to cool the respective processing unit.

18. A system for controlling a server system, having an associated dynamically controllable cooling system and a predetermined thermal constraint, comprising:

an interface port configured to receive an input corresponding to a physical condition of a server system and an environment of the server system; and

at least one processor, configured to;

estimate a future physical condition based on a set of tasks to be processed by the server system while maintaining a rate within a capacity of the server system defined by a quality of service requirement, wherein the tasks to be processed are allocated to a subset of elements of the server system to concentrate thermal stresses;

dynamically control the dynamically controllable cooling system in response to at least the input and the estimated future physical condition to selectively cool the server system comprising the subset of the elements of the server system which reflect the concentrated thermal stresses, after the estimated future physical condition indicates a change in a predicted cooling demand and before a change in temperature of the server system resulting from performance of the tasks to be processed by the server system, sufficient to meet the predetermined thermal constraint while processing the tasks while maintaining the rate defined by the quality of service requirement; and

optimize a schedule of tasks for the server system seeking to selectively achieve a peak loading level for processing the tasks while maintaining the rate defined by the quality of service requirement of the server system while maintaining operation of the server system within the predetermined thermal constraint.

19. The system according to claim 18, wherein the server system comprises at least one of a rack comprising a plurality of servers and a plurality of server blades, the associated dynamically controllable cooling system comprises an air conditioner, having at least one of:

a control adapted to vary an air flow rate and an air temperature or air for cooling the server system, and a proportionally controllable baffle, wherein the predetermined thermal constraint comprises at least one of;

a maximum operating temperature of at least one component of the server system, and a maximum power dissipation of the server system.

20. The system according to claim 18, wherein the estimated future physical condition comprises a temperature of at least one processing component within the server system, the temperature being predicted by the at least one processor based on a model of the server system and a sequence of operations performed by the server system comprising the at least one processing component, and a control parameter which varies a processing performance of the at least one processing component, the variation in processing performance of the processing component causing a change in both a rate of processing and a power dissipation.