# US 2013/0085611 A1 · Unified and flexible control of multiple data center cooling mechanisms

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2013/0085611 A1
- Document ID: US20130085611A1
- Status: Published application
- Kind: A1
- Application number: 13/684,612
- Filed: 2012-11-26
- Published: 2013-04-04
- Earliest claimed: 2011-05-10
- Assignees: International Business Machines Corporation
- Inventors: Tony A. Bentivegna; Bradley L. Brech; Rajarshi Das; Murthy V. Devarakonda; Hendrik F. Hamann; Jeffrey O. Kephart; Bret W. Lehman; Jonathan Lenchner; Christopher L. Molloy
- Web page: https://patentgrep.com/patent/US20130085611A1

## CPC

- G05B 13/02: electric
- G05D 23/1934: {each space being provided with one sensor acting on one or more control means}
- H05K 7/20836: {Thermal management, e.g. server temperature control}
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- H05K: PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS

## Abstract

Techniques are described for controlling the climate in a data center. Using the input of an administrator, multiple desired attributes of a data center (e.g., temperature, energy consumption, costs, or system performance) may be balanced using a utility function that maximizes the utility of the computing systems in the data center according to the administrator's preferences. Additionally, a cooling model is generated that represents the affect of a control parameter (e.g., the fan speed of a CRAC) on the desire attributes of the data center. The cooling model may then be substituted into the utility function to replace the desired attributes. Using this new utility function, the control parameters may be varied such that the maximum utility is achieved.

## Claims

### Claim 1

A method of controlling temperature in a computing environment, comprising:
receiving a plurality of desired attributes for the computing environment, wherein a first desired attribute relates to a first system condition of the computing environment and a second desired attribute relates to a second system condition of the computing environment, wherein the first system condition is temperature;
providing at least one control parameter in a computing environment, wherein the control parameter affects at least the temperature and the second system condition of the computing environment;
generating a cooling model representing the affect of the control parameter on at least the first and second desired attributes;
generating a utility function for the computing environment based on the cooling model and at least the first and second desired attributes; and
setting a value of the control parameter based on the utility function.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the utility function for the computing environment further comprises:
generating a first utility function for each desired attribute;
creating a second utility function, wherein the second utility function is a combination of the first utility functions; and
generating the utility function for the computing environment based on the cooling model and the second utility function.

### Claim 3 (depends on 1)

The method of claim 1, wherein the second system condition comprises one of: energy consumption, cost of energy consumption, cost of hardware replacement, environmental impact, system performance, life expectancy of hardware, and combinations thereof.

### Claim 4 (depends on 1)

The method of claim 1, wherein the cooling model represents the affect of a plurality of control parameters on at least the first and second desired attributes.

### Claim 5 (depends on 4)

The method of claim 4, wherein the plurality of control parameters comprise of at least two of: a control setting of a fluid-cooling device, a layout of structures in the computing environment, snorkel, perforated floor tile, workload scheduler, and workload migration component.

### Claim 6

A method of controlling at least one system condition in a computing environment, comprising:
receiving a desired attribute for the computing environment, wherein the desired attribute specifies a desired value of the at least one system condition;
providing a plurality of control parameters in a computing environment, wherein the control parameters affect the at least one system condition of the computing environment;
generating a cooling model to relate the at least one system condition and the control parameters, wherein each control parameter manages a different type of cooling system, and wherein each type of cooling system uses a different cooling technique of affecting the at least one system condition of the computing environment;
determining a value for each of the control parameters based on the cooling model; and
operating the cooling systems based on the values of the control parameters to achieve the desired attribute.

### Claim 7 (depends on 6)

The method of claim 6, wherein different types of cooling systems comprises at least two of: air-cooling units, liquid-cooling units, a layout of a computer environment, and data center tasking software.

### Claim 8 (depends on 6)

The method of claim 6, wherein a desired attribute of the computing environment comprises of at least one of: temperature, energy consumption, cost of energy consumption, cost of hardware replacement, environmental impact, system performance, life expectancy of hardware, and combinations thereof.

### Claim 9 (depends on 6)

The method of claim 6, wherein determining the values of the control parameters based on the cooling model further comprises,
generating a first utility function for the desired attribute;
generating a second utility function for the computing environment by substituting the cooling model into the first utility function; and
determining the values of the control parameters based on the second utility function.
