DATA CENTER EFFICIENCY ANALYSES AND OPTIMIZATION

• US 20130096905A1
• Filed: 12/08/2012
• Published: 04/18/2013
• Est. Priority Date: 03/10/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Iyengar, Madhusudan K., Schmidt, Robert R.
• Granted Patent: US 8,965,748 B2
• Time in Patent Office: Days
• US Class Current: 703/21
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• 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

Abstract

Method, system and computer program product for estimating the overall energy efficiency of a data center over a period of time. In one embodiment, a computer processor coupled to computer readable memory is configured to receive time parameters indicating the period of time over which the overall energy efficiency of the data center is to be estimated, receive component parameters indicating the performance characteristics of data center components and the operational interactions between the data center components, simulate the operation and interaction of the data center components based, at least in part, on the component parameters for the period of time over which the energy efficiency is estimated, and output results of the simulation to estimate the overall energy efficiency of the data center.

Claims

1. A method for estimating the overall energy efficiency of a data center over a period of time by a computer, the method comprising:

receiving one or more time parameters, the time parameters indicating the period of time over which the overall energy efficiency of the data center is estimated;

receiving a plurality of component parameters, the component parameters indicating performance characteristics of data center components and operational interactions between the data center components;

simulating, by a computer processor, the operation and interaction of the data center components based, at least in part, on the component parameters for the period of time over which the energy efficiency is estimated; and

outputting results of the simulation, the results indicating the overall energy efficiency of the data center.

2. The method of claim 1, wherein simulating the operation and interaction of the data center components comprises:

receiving a plurality of environment parameters, the environment parameters indicating characteristics of an ambient environment over one or more time intervals within the period of time over which the overall energy efficiency is estimated, the characteristics of the ambient environment are selected from at least one of air temperature, air humidity, dew point, atmospheric pressure, and precipitation;

generating a thermodynamic model of heat exchanges resulting from the operational interactions between the data center components and heat exchanges between the data center components and the ambient environment; and

utilizing the thermodynamic model to estimate energy consumption by the data center components.

3. The method of claim 2, wherein receiving the environment parameters comprises:

receiving one or more geographical parameters, the geographical parameters including an indication of the geographic location of the data center;

querying a database of environmental information based on the geographical parameters and the period of time over which the overall energy efficiency is estimated, the database of environmental information including information about environmental characteristics for a plurality of geographic locations over one or more time intervals; and

receiving from the database of environmental information the environment parameters based on the geographical parameters.

4. The method of claim 1, wherein each of the data center components comprises one or more individual units, the one or more individual units are selected from at least one of air conditioner (AC), computer room air conditioner (CRAC), free cooling unit (FCU), pressurized air plenum, chilled water (CHW) pipe, CHW pipe valve, CHW pump, boosted cold water (BCW) pump, chiller plant, chiller compressor, cooling tower, water side economizer, computer server, network switch, computer server rack, computer server rack fan, uninterruptible power supply (UPS), and electrical co-generation system.

5. The method of claim 1, wherein the performance characteristics of the data center components are selected from at least one of electrical power consumption, natural gas consumption, water consumption, heat generation, heat dissipation, air volume, air pressure, water volume, water pressure, maximum area that can be cooled, and maximum number of floors that can be serviced.

6. The method of claim 1, further comprising:

receiving a plurality of data center parameters, the data center parameters including at least one of number of data center buildings, number of floors, number of server rooms, size of server rooms, maximum server room temperature, and operating hours of data center; and

wherein simulating the operation and interaction of the data center components includes determining an optimal data center configuration based on the data center parameters.

7. The method of claim 1, wherein the results of the simulation are selected from at least one of total energy consumption for the data center, energy consumption per data center component, total energy consumption for the data center per time interval in a plurality of time intervals within the time period over which overall energy efficiency is estimated, energy consumption per data center component per time interval in a plurality of time intervals within the time period over which overall energy efficiency is estimated, average server room temperature for the time period over which overall energy efficiency is estimated, and maximum server room temperature for the time period over which overall energy efficiency is estimated.

8. The method of claim 1, further comprising:

receiving a plurality of cost parameters, the cost parameters indicating unit costs of energy resources consumed by the data center, the energy resources are selected from at least one of electrical power, natural gas, and water;

wherein simulating the operation and interaction of the data center components is based, at least in part, on the cost parameters; and

wherein the results of the simulation are selected from at least one of total energy cost for the data center, energy cost per data center component, total energy cost for the data center per time interval in a plurality of time intervals within the time period over which overall energy efficiency is estimated, energy cost per data center component per time interval in a plurality of time intervals within the time period over which overall energy efficiency is estimated, and total energy cost per energy resource.

9. The method of claim 1, wherein receiving the component parameters comprises:

receiving one or more model parameters, the model parameters indicating a data center component model, the data center component model comprising a plurality of data center components configured to operate and interact together;

querying a database of data center component models based on the model parameters, the database of data center component models including information about the performance characteristics and operational interactions of data center components for a plurality of data center component models;

receiving from the database of data center component models the component parameters based on the model parameters.

10. The method of claim 1, wherein receiving the component parameters comprises:

receiving one or more data center type parameters, the data center type parameters indicating a data center type, the data center type comprising a plurality of data center components configured to operate and interact together;

querying a database of data center types based on the received data center type parameters, the database of data center types including information about the performance characteristics and operational interactions of data center components for a plurality of data center types;

receiving from the database of data center types the component parameters based on the data center type parameters.

11. The method of claim 1, wherein the method further comprises:

storing intermediate data from simulating the operation and interaction of the data center components, the intermediate data comprising simulation results per data center component per time interval in a plurality of time intervals within the time period over which overall energy efficiency is estimated;

receiving one or more component reporting parameters, the component reporting parameters indicating one or more data center components;

receiving one or more time reporting parameters, the time reporting parameters indicating one or more time intervals within the time period over which overall energy efficiency is estimated; and

displaying the stored intermediate data for the received component reporting parameters and the received time reporting parameters.

12. The method of claim 1, wherein the method further comprises:

storing the results of the simulation of the operation and interaction of the data center components in a results database, the results database containing the results of a plurality of simulations of the operation and interaction of the data center components;

receiving one or more simulation reporting parameters indicating one or more simulations of the operation and interaction of the data center components;

querying the results database based on the simulation reporting parameters to retrieve the results of one or more simulations; and

displaying the retrieved results of the one or more simulations.