Classifications

• • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
  • F24—HEATING; RANGES; VENTILATING
  • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
  • F24F11/00—Control or safety arrangements
  • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
• • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
  • F24—HEATING; RANGES; VENTILATING
  • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
  • F24F11/00—Control or safety arrangements
  • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
  • F24—HEATING; RANGES; VENTILATING
  • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
  • F24F11/00—Control or safety arrangements
  • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
  • F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
  • F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity

Definitions

• the present invention relates to controlling atmospheric conditions within a building.
• a rack may be defined as an Electronics Industry Association (EIA) enclosure and may be configured to house a number of personal computer (PC) boards.
• the PC boards typically include a number of electronic packages, such as processors, micro-controllers, high speed video cards, memories, semi-conductor devices, and the like.
• These electronic packages dissipate relatively significant amounts of heat during the operation of fhe respective components.
• a typical PC board comprising multiple microprocessors may dissipate approximately 250 W of power.
• a rack containing forty (40) PC boards of this type may dissipate approximately 10 KW of power.
• the power required to remove the heat dissipated by the electronic packages in a given rack is generally equal to about 10 percent of the power needed to operate the packages.
• the power required to remove the heat dissipated by a plurality of racks in a data center is generally equal to about 50 percent of the power needed to operate the packages in the racks.
• the disparity in the amount of power required to dissipate the various heat loads between racks of data centers stems frcm the additional fhermodynamic work needed in the data center to cool the air.
• Racks are typically cooled with fens that operate to move cooling fluid, such as air, across the heat dissipating components, whereas data centers often use reverse power cycle s to cool heated return air.
• the cooling of entire data centers presents major challenges beyond those faced with the cooling of individual racks of electronic packages.
• Data centers are typically cooled by operation of one or more air conditioning units.
• the compressors of the air conditioning units typically require a minimum of about thirty (30) percent of the required cooling capacity to sufficiently cool the data centers.
• the other components such as condensers, air movers (fans), etc., typically require an additional twenty (20) percent of the required cooling capacity.
• a high density data center with 100 racks, each rack having a maximum power dissipation of 10KW generally requires 1 MW of cooling capacity.
• Air conditioning units with a capacity of 1 MW of heat removal generally require a minimum of 300 KW input compressor power in addition to the power needed to drive the air moving devices, e.g., fans, blowers, etc.
• Conventional data center air conditioning units do not vary their cooling output based on the distributed, location-specific needs of the data center.
• the distribution of work among the operating electronic components in the data center is random and is not controlled. Because of work distribution, some components in one location of the data center may be operating at a maximum capacity, while other components in another location of the data center may be operating at various power levels below a maximum capacity.
• conventional cooling systems typically operate at 100 percent of capacity on a continuous basis, thereby cooling all electronic packages, regardless of need.
• data centers are air conditioned on an overall, room-level basis, thereby yielding unnecessarily high operating expenses to sufficiently cool the heat generating components contained in the racks of data centers.
• prior art attempts at cooling use relatively inaccurate and unsophisticated methods of monitoring and adjusting temperature distribution that result in less than optimal data center cooling efficiency.
• a method of controlling atmospheric conditions within a building includes the steps of supplying a conditioned fluid inside of the building and sensing one or more atmospheric parameters in various locations inside of the building. From the results of the sensing step, an empirical atmospheric map is then generated and compared to a template atmospheric map. Pattern differentials are identified between the empirical and template atmospheric maps, and corrective action is determined to reduce the pattern difFerentials. Finally, one or more of the quantity, quality, and distribution of the conditioned fluid is varied.
• FIG. 1 is a schematic illustration of an embodiment of a system of the present invention.
• Fig. 2 is a flow chart of an embodiment of a method of the present invention.
• the present invention is not limited in its application to the details of any particular arrangement described or shown, since the present invention is capable of multitudes of embodiments without departing from the spirit and scope of the present invention.
• First, the principles of the present invention are described by referring to only a limited number of embodiments for simplicity and illustrative purposes. Although only a limited number of embodiments of the invention are particularly disclosed herein, one of ordinary skill in the art would readily recognize that the same principles are equally applicable to, and can be implemented in all types of atmospheric control systems. Furthermore, numerous specific details are set forth to convey with reasonable clarity the inventor's possession of the present invention, how to make and/or use the present invention, and the best mode in carrying out the present invention known to the inventor at the time of application.
• a method and related system are configured to control one or more atmospheric conditions within a building. More specifically, the method and system are configured to adjust one or more of the quantity, quality, and distribution of a conditioned fluid throughout a data center. The method and system are configured to accomplish such control based upon atmospheric mapping and
• the amount of energy typically required to cool a data center may be relatively reduced by strategically distributing cooling fluid, or conditioned air, within the data center by substantially favoring or increasing the cooling fluid flow to locations within the data center having racks that dissipate greater amounts of heat, and by substantially disfavoring or decreasing the cooling fluid flow to locations having racks that dissipate lesser amounts of heat.
• strategically distributing cooling fluid, or conditioned air within the data center by substantially favoring or increasing the cooling fluid flow to locations within the data center having racks that dissipate greater amounts of heat, and by substantially disfavoring or decreasing the cooling fluid flow to locations having racks that dissipate lesser amounts of heat.
• those devices may be operated according to the actual location and area specific cooling needs.
• the racks may be positioned throughout the data center according to their anticipated heat loads to thereby enable computer room air conditioning (CRAC) units located at various positions throughout the data center to operate in a more efficient manner.
• CRAC computer room air conditioning
• the positioning of the racks and cooling strategy may be determined through implementation of modeling and metrology of the cooling fluid flow throughout the data center.
• the numerical modeling may be implemented to determine the volume flow rate and velocity of the cooling fluid flow through the data center.
• FIG. 1 a schematic view of the system 10 that may be used in accordance with an embodiment of the present invention.
• the system 10 generally includes atmospheric sensors 12, a central processing unit (CPU) 14, and an atmospheric control system 16.
• the atmospheric control system 16 can be a smart cooling system, exemplified by co-pending U.S. Patent Application Ser. No.
• any type of system directed at controlling atmospheric conditions could be employed, including air- conditioner systems, humidifier systems, filtering systems, fire suppression systems, etc.
• the atmospheric sensors 12 are used for measuring one or more atmospheric parameter and encompass temperature sensors, such as thermocouples, temperature transducers, thermistors, or the like.
• the atmospheric sensors 12 could also include humidity sensors, barometric or pressure sensors, fluid velocity sensors, particle sensors, smoke sensors, and the like.
• the atmospheric sensors 12 are located throughout the portions of a data center type of building (not shown) that are desired to be atmospherically controlled.
• the atmospheric sensors 12 can be positioned in a variety of ways.
• the atmospheric sensors 12 could be dispersed randomly in various locations and elevations, or aligned according to a predetermined coordinate grid, or placed in alignment with locations of vents and or racks, or placed in accordance with the recommendations from a computational fluid dynamics model.
• the CPU 14 can be a stand-alone personal computer, a computer board or boards docked within one of the racks in the data center, a computer chip, etc., regardless, the CPU 14 includes various software that is loaded thereto. First, the CPU 14 includes software for
• Thermal mapping software 18 is capable of processing thousands of input data points, such as thousands of sensor signals, and outputting map-like information.
• a thermal map is composed of temperature contours that define various isothermal regions, or isotherms, of distinct temperatures. The most severe of these isotherms are commonly known as "hot spots". Hot spots may not necessarily correspond in exact location to any given temperature sensor, but may be located between various temperature sensors. Nevertheless, thermal mapping software can extraplate or triangulate the location of the actual hot spot from the known locations of the temperature sensors.
• the thermal mapping software can triangulate not only the coordinate position of a hot spot, but also the elevation thereof.
• the temperature sensor readings provide temperature data and data for calculating temperature gradients, which are used to create a thermal map.
• temperature gradients can be used to locate hot spots in the data center by mathematical optimization techniques like steepest gradient, etc.
• triangulation presents a relatively accurate and efficient approximation technique and, thus, it is possible to use fewer, more sparsely distributed temperature sensors to save on equipment expense and failure modes if desired.
• the CPU 14 includes software for recognizing pattern differentials in such maps, more commonly known as pattern recognition software 20. Such software basically involves a decoding process in which discriminations in patterns are made without human intervention.
• pattern recognition software 20 basically involves a decoding process in which discriminations in patterns are made without human intervention.
• strategic software 22 is loaded on the CPU 14 and is used to determine a course of corrective action to ir- ⁇ imize or eliminate the pattern differentials by accepting
• the cooling system 16 is used to vary one or more of the quantity, quality, and distribution of the cooling fluid used to cool the data center.
• the cooling system 16 encompasses a chiller unit 24, but those skilled in the art will recognize that multitudes of other types of cooling systems are generally well-known and available for use with the present invention including, for example, refrigeration systems, cooling tower systems, cooler-condenser systems, and the like.
• the cooling system 16 also includes one or more variable-speed air movers or blowers 26, and one or more remotely controlled dampers or vents 28.
• HVAC Heating, Ventilating, and Air Conditioning
• chiller cycle can be increased or decreased between 0% and 100% of operating capacity to change the cooling quality of the cooling fluid, i.e. temperature, humidity, particulate count, etc.
• the speed and/or baffling of the blower 26 can be adjusted, and the percentage opening of the vents 28 can be varied, either individually or collectively.
• the vents 28 include individual blowers (not shown), such blowers
• HP Docket No.: 10018557-1 0 could also be adjusted in speed.
• one or more of multiple chillers, blowers, and vents can be strategically adjusted to target one or more hot spot locations within the data center. For example, if one corner of the data center is demanding the most significant portion of the cooling needs of the entire data center, then the most proximate chiller(s), blower(s), and vent(s) can be selected, while the other, relatively distant chiller(s), blower(s), and vent(s) can be deactivated or reduced. It is contemplated that any other reasonably foreseen atmospheric control system control variables could also be adjusted.
• an embodiment of a method of the present invention involves cooperation of the CPU between the temperature sensors and the cooling system.
• the method of the present invention could also be practiced using other systems besides the one disclosed herein, and thus is not limited thereby.
• the system disclosed herein is simply one of many possible physical manifestations of the method.
• the cooling system supplies a cooling fluid within the data center to cool the equipment within the data center, as shown in block 100.
• the temperature within the data center is sensed in various locations and is communicated to the CPU.
• the thermal mapping software converts the point-specific temperature sensor data into information by generating an empirical thermal map therefrom, as depicted in block 104.
• a thermal map can triangulate hot spots from discrete sensor locations based on mathematical optirnization techniques. Hot spots are known to arise in several situations, for example, where electronic packages in a given rack draw exceptional amounts of power due to exceptionally high usage of those packages, and the data center cooling
• HP Docket No.: 10018557-1 1 fj system cannot supply enough conditioned fluid to alleviate the overheating. Hot spots may also arise when racks output nonnal amounts of heat, but the data center cooling system is malfunctioning in a specific location, or in general.
• the thermal mapping step may be executed on an instantaneous, snapshot, or sampling basis but, alternatively, this step may be done on a real-time basis. It is also contemplated that the thermal map could be generated directly, without discrete temperature sensors, using thermography technology, based on infrared detection of heat that is emitted by the equipment in the data center. It is further contemplated that the thermal map could be generated by estimating temperature as a function of the power draw to the electronic packages and/or racks within, the data center. Thus, the temperature sensing and map generating steps could be accomplished with thermographic equipment and software, or inferring temperature from power draw.
• the thermal map also provides a powerful visual tool for a data center operator.
• a typical data center is a highly thermally interdependent environment where thermal performance of each electronic package of each rack affects performance of neighboring packages and racks to various orders of magnitude.
• a thermal map also provides a pictorially informative way of identifying the thermal interdependencies across the data center landscape.
• the pattern recognition software compares the empirical thermal map to a template thennal map.
• the template thermal map could also be termed a master, or model thermal map.
• the template basically represents a thermal map of an optimally operating data center cooling system.
• the template can be dynamic, generated
• HP Docket No.: 10018557-1 either in real-time from current operating conditions, or can be static, generated prior to the comparing step 106.
• Computational fluid dynamics (CFD) software tools such as FLOVENT/AIRPACK, are widely available and known to those skilled in the art.
• the CFD tool accepts various inputs for modeling, including heat loads from the racks within the data center, velocity of the cooling fluid flowing throughout the data center, temperature, pressure, and the like in the data center.
• CFD modeling can be used in the design and layout of a data center, suggesting locations for racks and vents.
• CFD modeling can be used to output a master, template, or model thermal map to be emulated by adjusting cooling system variables. Instructive in this regard is U.S. Patent Application Ser. No.
• the pattern recognition software is also applied to recognize pattern differentials therebetween, as depicted in block 108.
• Pattern recognition is also commonly referred to as template matching, masking, etc. For example, in the case of data center cooling, thermal hot spots can be identified. Once identified, an initial classification step occurs as depicted by block 110. Certain isotherms may exceed a predetermined range of temperature, size, etc., and thus can be targeted for elimination or reduction. Alternatively, if all isotherms are within the predetermined range of temperature, size, etc., then the cooling system simply maintains current operating conditions and settings, as depicted in block 112.
• the strategic software Upon recognizing the pattern differentials, the strategic software is used to determine the corrective action required to eliminate or at least reduce pattern differentials within the
• HP Docket No.: 10018557-1 12 data center as depicted in block 114.
• Control variable data such as the location of the vents, the capacity of the blower, and the capacity of the chiller, are used to determine how most efficiently to cool the data center.
• the thermal map data is also used, such as the location, size, and intensity of the isotherms. Specifically, the above-mentioned data sets are correlated to develop an optimally efficient course of corrective action.
• one or more of the quantity, quality, and distribution of the conditioned fluid of the cooling system is varied. For example, if the size and/or intensity of an hot spot isotherm is relatively small, then the cooling system can merely adjust the opening size of the vent closest to the location of the isotherm. If, on the other hand, the size and/or intensity of an isotherm is relatively large, then multiple vents can be adjusted in addition to increasing the chiller cycle. Similarly, if the cooling system included multiple chillers, the chiller most proximate the isotherm could be increased in cycle. In general, the quantity and/or quality of the cooling fluid can be decreased, or maintained, for locations of the data center that exhibit pattern differentials within a predetermined acceptable range.
• the quantity and/or quality of the cooling fluid may be increased for locations of the data center that exhibit pattern differentials outside of a predetermined acceptable range.
• the present invention is capable of substantially reducing the energy consumption associated with cooling a data center, by virtue of using directed, location-specific cooling instead of diffused, room-level cooling. More particularly, the cooling system can be operated relatively more efficiently compared to
• the present invention provides methodology for extracting a large amount of discrete, location-specific temperature data points and converting same into more continuous, fluid-like information in the form of a thermal map.
• the present invention is suited for use with applications requiring thousands of sensors, or even just a few well-placed sensors. Regardless, the present invention enables use of the spaces between the sensor locations to be included in assessing or triangulating the locations, size, and intensity of hot spots, resulting in more accurate hot spot reduction than the prior art allows for. Therefore, compared to the prior art and for a given size data center, the present invention presents a more accurate and efficient cooling method, thus requiring fewer and smaller cooling devices and less energy consumption.

Landscapes

• Engineering & Computer Science (AREA)
• Chemical & Material Sciences (AREA)
• Combustion & Propulsion (AREA)
• Mechanical Engineering (AREA)
• General Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Fluid Mechanics (AREA)
• Fuzzy Systems (AREA)
• Mathematical Physics (AREA)
• Signal Processing (AREA)
• Air Conditioning Control Device (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Publications (1)

Family

ID=29214485

Family Applications (1)

Country Status (6)

Cited By (1)

Families Citing this family (91)

Citations (4)

Family Cites Families (21)

• 2002
  • 2002-04-17 US US10/123,403 patent/US6718277B2/en not_active Expired - Lifetime
• 2003
  • 2003-04-16 DE DE60319688T patent/DE60319688T2/de not_active Expired - Lifetime
  • 2003-04-16 JP JP2003586537A patent/JP4616558B2/ja not_active Expired - Fee Related
  • 2003-04-16 EP EP03724032A patent/EP1495270B1/en not_active Expired - Lifetime
  • 2003-04-16 WO PCT/US2003/011545 patent/WO2003089845A1/en not_active Ceased
  • 2003-04-16 CN CNB038141949A patent/CN1328554C/zh not_active Expired - Fee Related

Patent Citations (4)

Non-Patent Citations (2)

Also Published As

Similar Documents

Legal Events