CN112601423B - Temperature control method and system for optimizing energy consumption of air conditioner in large data center - Google Patents

Temperature control method and system for optimizing energy consumption of air conditioner in large data center Download PDF

Info

Publication number
CN112601423B
CN112601423B CN202011450142.XA CN202011450142A CN112601423B CN 112601423 B CN112601423 B CN 112601423B CN 202011450142 A CN202011450142 A CN 202011450142A CN 112601423 B CN112601423 B CN 112601423B
Authority
CN
China
Prior art keywords
air
conditioning
temperature
thermometers
data center
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011450142.XA
Other languages
Chinese (zh)
Other versions
CN112601423A (en
Inventor
徐勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Graduate School Harbin Institute of Technology
Original Assignee
Shenzhen Graduate School Harbin Institute of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Graduate School Harbin Institute of Technology filed Critical Shenzhen Graduate School Harbin Institute of Technology
Priority to CN202011450142.XA priority Critical patent/CN112601423B/en
Publication of CN112601423A publication Critical patent/CN112601423A/en
Application granted granted Critical
Publication of CN112601423B publication Critical patent/CN112601423B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K7/00—Constructional details common to different types of electric apparatus
    • H05K7/20—Modifications to facilitate cooling, ventilating, or heating
    • H05K7/20709—Modifications to facilitate cooling, ventilating, or heating for server racks or cabinets; for data centers, e.g. 19-inch computer racks
    • H05K7/20836—Thermal management, e.g. server temperature control
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00—Control of temperature
    • G05D23/19—Control of temperature characterised by the use of electric means
    • G05D23/20—Control of temperature characterised by the use of electric means with sensing elements having variation of electric or magnetic properties with change of temperature

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Thermal Sciences (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention provides a temperature control method for optimizing energy consumption of an air conditioner of a large-scale data center, which comprises the following steps of: s1, deploying a set of central air conditioning system for overall cooling and a plurality of air conditioning single machines for local cooling in a large data center or a machine room; s2, installing a plurality of air temperature meters at different positions of a large-scale data center or a machine room, and transmitting air temperature values of all the air temperature meters to a temperature control unit at intervals of t minutes; and S3, the temperature control unit controls the temperature. The invention has the advantages that the scheme of deploying the central air-conditioning system as the main and deploying the multiple vertical cabinet type air-conditioning units as the auxiliary is adopted for the large-scale data center and the machine room, the control of the central air-conditioning system and the vertical cabinet type air-conditioning units is automatically realized by using the designed intelligent algorithm, the optimal air temperature control of the machine room with the aim of energy saving is realized, the energy consumption is effectively reduced, and the optimal air-conditioning energy-saving effect is achieved.

Description

Temperature control method and system for optimizing energy consumption of air conditioner in large data center
Technical Field
The invention relates to a temperature control method, in particular to a temperature control method and system for optimizing energy consumption of an air conditioner in a large data center.
Background
At present, data centers equipped with large computer clusters have become one of the major sites for energy consumption. The physical cooling of a computer cluster is an important basis for its performance. The high-power central air conditioner is a common physical cooling means for a large computer cluster. Because the task distribution among the servers in the large computer cluster is unbalanced, and the consumption difference of different tasks on computing resources is large, in the conventional energy-saving control pursuing the minimization of the energy consumption of the central air conditioner, serious problems that the computing performance is affected and even the system is down and the like easily occur in the actual large computer room due to the overhigh temperature of individual servers. Conversely, the following is also likely to occur: in order to avoid the situation that the temperature of a single server is too high in an actual large machine room, the central air conditioner keeps low-temperature control on the temperature, so that great waste of energy consumption is caused.
In the traditional central air-conditioning energy-saving scheme of the large-scale computer cluster, due to the global temperature control property of the central air-conditioning and the relatively high energy consumption corresponding to the unit temperature reduction, the temperature control based on the large-scale computer room of the central air-conditioning is not only lack of flexibility, but also is difficult to achieve the optimal air-conditioning energy-saving effect.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a temperature control method and system for optimizing energy consumption of an air conditioner of a large data center.
The invention provides a temperature control method for optimizing energy consumption of an air conditioner of a large-scale data center, which comprises the following steps of:
s1, deploying a set of central air conditioning system for overall cooling and a plurality of air conditioning single machines for local cooling in a large data center or a machine room;
s2, installing a plurality of air temperature meters at different positions of a large-scale data center or a machine room, and transmitting air temperature values of all the air temperature meters to a temperature control unit at intervals of t minutes;
s3, the temperature control unit performs the following temperature control: the central air-conditioning system is in a normally open state, and the single air-conditioning unit is in a standby state; the temperature control is mainly performed by a central air-conditioning system and is assisted by a single air-conditioning unit; assuming that the specified maximum temperature threshold is T, namely the temperature of the large-scale data center or the machine room is controlled to be in a range less than or equal to T, making N air thermometers in total, assuming that the temperature report value of N air thermometers at a certain moment exceeds the maximum temperature threshold T, and if N is 0 and the average temperature value of the N air thermometers is equal to T
Figure GDA0003315870550000011
Satisfy the requirement of
Figure GDA0003315870550000021
Control maintains the status quo, T0Is the lowest temperature threshold; if N is 0 and the average temperature value of N branch thermometers
Figure GDA0003315870550000022
The target temperature value of the central air-conditioning system is increased so that the average temperature value of the N branch air thermometers meets the requirement
Figure GDA0003315870550000023
As a further development of the invention, if N/N is greater than f1If so, reducing the target temperature of the central air-conditioning system to theta, wherein theta is smaller than T until the temperature report values of all the air temperature meters do not exceed the maximum temperature threshold T; if N/N is less than or equal to f1Starting m air-conditioning units until all the air is exhaustedThe temperature report value of the thermometer does not exceed the maximum temperature threshold T, m<N and m is less than the number of the single air conditioners.
As a further improvement of the invention, the selection principle of the m air-conditioning single units is that the m air-conditioning single units are nearest to the n air thermometers with the temperature report values exceeding the maximum temperature threshold value T.
As a further improvement of the invention, the selection process of m air-conditioning single units is as follows:
let the set of n thermometers with temperature report values exceeding the maximum temperature threshold T be denoted as R ═ R1,...,rnThe positions of the n thermometers are respectively (x)1,y1),…,(xn,yn) (ii) a Assuming a total of M air-conditioning units, their set is denoted as Q ═ Q1,...,qMAre respectively(s) at the position1,t1),…,(sM,tM) (ii) a Firstly, respectively calculating respective Euclidean distances between M air-conditioning single machines and each air-conditioning single machine in n air thermometers, wherein the total Euclidean distances are nM, selecting the minimum Euclidean distance value, taking the corresponding air-conditioning single machine as the first air-conditioning single machine to be started, and then removing the corresponding air-conditioning single machine from a set Q, namely changing the set Q into a set containing M-1 elements, namely M-1 cabinet type air-conditioning single machines; at the same time, the corresponding pyrometers are removed from the set R, i.e. the set R becomes containing n-1 elements, i.e. n-1 pyrometers; then respectively calculating Euclidean distances between each of the M-1 air-conditioning single machines in the set Q and each of the n-1 air thermometers in the set R, wherein a total of (n-1) (M-1) Euclidean distance values are obtained, the smallest Euclidean distance value is selected, and the corresponding air-conditioning single machine is taken as a second air-conditioning single machine to be started; and so on until m stand cabinet air conditioners are selected and all the stand cabinet air conditioners are started.
The invention also provides a temperature control system for optimizing the energy consumption of the air conditioner in the large data center, which comprises a readable storage medium, wherein execution instructions are stored in the readable storage medium, and when being executed by a processor, the execution instructions are used for realizing the method in any one of the above.
The invention has the beneficial effects that: the scheme that a central air-conditioning system is mainly deployed and a plurality of vertical cabinet type air-conditioning units are taken as accessories for a large-scale data center and a machine room is adopted, the control of the central air-conditioning system and the vertical cabinet type air-conditioning units is automatically realized by using a designed intelligent algorithm, the optimal air temperature control of the machine room with the aim of energy conservation is realized, the energy consumption is effectively reduced, and the optimal air-conditioning energy-saving effect is achieved.
Drawings
Fig. 1 is a schematic view of the joint deployment of a central air-conditioning system and a plurality of stand-alone air conditioners for the temperature control method for optimizing the energy consumption of the air conditioners in a large data center.
FIG. 2 is a schematic diagram of an overall control strategy of the temperature control method for optimizing energy consumption of an air conditioner in a large data center.
Detailed Description
The invention is further described with reference to the following description and embodiments in conjunction with the accompanying drawings.
As shown in fig. 1 to 2, a temperature control method for optimizing energy consumption of an air conditioner in a large data center is provided, in which multiple temperature sensors are installed in the data center, a scheme of deploying a central air conditioning system as a main part and deploying multiple cabinet air conditioners as an auxiliary part for the large data center and a machine room is adopted, and a designed intelligent algorithm is used for automatically controlling the central air conditioning system and the cabinet air conditioners, and the method mainly comprises the following steps:
1. a set of central air-conditioning system is deployed for a large-scale data center and a machine room, and the physical cooling is mainly carried out by depending on the central air-conditioning system. Meanwhile, a plurality of vertical cabinet type air-conditioning single machines are arranged in a large-scale data center and a machine room to assist a central air-conditioning system in physical cooling, and the key point is to control local high temperature. The scheme that the central air-conditioning system is a main air-conditioning system and a plurality of vertical cabinet type air-conditioning units are auxiliary aims at obtaining the energy-saving effect of the air-conditioning system compared with the single central air-conditioning system under the support of a corresponding algorithm. A schematic representation of the joint deployment of a central air conditioning system and multiple cabinet air conditioning units for large data centers and computer rooms is shown in fig. 1.
2. Enough air temperature meters are installed at different positions of the large-scale data center and the machine room, and all air temperature values are transmitted every t minutes. And if the temperature exceeds the specified temperature value, starting a corresponding air conditioner control algorithm.
3. The overall control strategy of the air conditioner control algorithm is as follows: the central air-conditioning system is in a normally open state, and the stand-alone air-conditioning unit is in a standby state; the temperature control is mainly a central air-conditioning system and is assisted by a stand-cabinet air-conditioning unit. Assume that the prescribed room temperature threshold is T (i.e., the room temperature should be controlled to a range of T or less). Let a total of N thermometers assume that the temperature report value of N thermometers exceeds a predetermined temperature value at a certain time. If N is 0 and the average temperature value of N branch thermometers
Figure GDA0003315870550000031
Satisfy the requirement of
Figure GDA0003315870550000032
Air conditioning control maintains the current situation. If N is 0 and the average temperature value of N branch thermometers
Figure GDA0003315870550000033
The target temperature value of the central air-conditioning system is increased so that the average temperature value of the N branch air thermometers meets the requirement
Figure GDA0003315870550000034
If N/N is greater than f1The temperature control algorithm then adjusts the target temperature of the central air conditioning system to θ (to achieve a faster and reliable cool down, the temperature control target value is set to be lower than the prescribed temperature value) until the temperature report values for all of the air temperature meters do not exceed the prescribed temperature value. If N/N is less than or equal to f1Then the temperature control algorithm starts m (m)<N and m is less than the number of the stand-alone air conditioners) until the temperature report values of all the air temperature meters do not exceed the specified temperature value. The selection principle of the m stand type air-conditioning single machines is that the m stand type air-conditioning single machines which are nearest to the n air thermometers with the temperature report values exceeding the specified temperature values.
The selection algorithm of m stand cabinet type air-conditioners is as follows:
let the set of n branch air thermometers whose reported temperature value exceeds the predetermined temperature value be R ═ { R }1,...,rnThe positions of the n thermometers are respectively (x)1,y1),…,(xn,yn). Assuming a common M cabinet type air conditioner units, their set is denoted as Q ═ Q { (Q)1,...,qMAre respectively(s) at the position1,t1),…,(sM,tM). Firstly, respectively calculating respective Euclidean distances (one total nM Euclidean distance value) between each of M stand-type air-conditioning single machines and each of n air thermometers, selecting the smallest Euclidean distance value, and taking the corresponding stand-type air-conditioning single machine as the first air-conditioning single machine to be started. Then, the corresponding stand-alone air conditioner is removed from the set Q, i.e., the set Q becomes M-1 elements (i.e., M-1 stand-alone air conditioners). At the same time, the corresponding air temperature meter is removed from the set R, i.e. the set R becomes containing n-1 elements (i.e. n-1 air temperature meters). Then, respectively calculating Euclidean distances between M-1 stand-alone air conditioners in the set Q and each of n-1 air thermometers in the set R (a total of (n-1) (M-1) Euclidean distance values), selecting the minimum Euclidean distance value, and taking the corresponding stand-alone air conditioners as the second stand-alone air conditioners to be started. And so on until m stand cabinet air conditioners are selected and all the stand cabinet air conditioners are started.
The invention also provides a temperature control system for optimizing the energy consumption of the air conditioner in the large data center, which comprises a readable storage medium, wherein execution instructions are stored in the readable storage medium, and when being executed by a processor, the execution instructions are used for realizing the method in any one of the above.
The invention provides a temperature control method and system for optimizing air conditioner energy consumption of a large data center. The reasonability of the scheme and the algorithm is that under some conditions, the power consumption of the multiple vertical cabinet type air conditioners is obviously smaller than that of the target temperature value of the central air conditioning system, and the temperature control is simple, convenient and feasible under the control of the automatic algorithm.
The temperature control method and system for optimizing the energy consumption of the air conditioner of the large-scale data center are suitable for the large-scale data center and the machine room which are provided with a central air conditioning system with the power of more than 500 kilowatts.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.

Claims (2)

1. A temperature control method for optimizing energy consumption of an air conditioner of a large data center is characterized by comprising the following steps:
s1, deploying a set of central air conditioning system for overall cooling and a plurality of air conditioning single machines for local cooling in a large data center or a machine room;
s2, installing a plurality of air temperature meters at different positions of a large-scale data center or a machine room, and transmitting air temperature values of all the air temperature meters to a temperature control unit at intervals of t minutes;
s3, the temperature control unit performs the following temperature control: the central air-conditioning system is in a normally open state, and the single air-conditioning unit is in a standby state; the temperature control is mainly performed by a central air-conditioning system and is assisted by a single air-conditioning unit; assuming that the specified maximum temperature threshold is T, namely the temperature of the large-scale data center or the machine room is controlled to be in a range less than or equal to T, making N air thermometers in total, assuming that the temperature report value of N air thermometers at a certain moment exceeds the maximum temperature threshold T, and if N is 0 and the average temperature value T of the N air thermometers meets T0T is less than or equal to T, the current situation is controlled and maintained, T0Is the lowest temperature threshold; if N is 0 and the average temperature T of N branch thermometers is less than T0Increasing the target temperature value of the central air-conditioning system so that the average temperature value of the N branch air thermometers meets T0≤T≤T；
If N/N is larger than a set threshold, reducing the target temperature of the central air-conditioning system to theta, wherein theta is smaller than T until the temperature report values of all the air temperature meters do not exceed a maximum temperature threshold T; if N/N is less than or equal to a set threshold, starting m air-conditioning single machines until the temperature report values of all the air thermometers do not exceed a maximum temperature threshold T, wherein m is less than N and m is less than the number of the air-conditioning single machines;
the selection principle of the m air-conditioning single machines is that the m air-conditioning single machines closest to the n air thermometers with the temperature report values exceeding the maximum temperature threshold T;
the selection process of the m air-conditioning single units is as follows:
let the set of n thermometers with temperature report values exceeding the maximum temperature threshold T be denoted as R ═ R1,...,rnThe positions of the n thermometers are respectively (x)1,y1),…,(xn,yn) (ii) a Assuming a total of M air-conditioning units, their set is denoted as Q ═ Q1,...,qMAre respectively(s) at the position1,t1),…,(sM,tM) (ii) a Firstly, respectively calculating respective Euclidean distances between M air-conditioning single machines and each air-conditioning single machine in n air thermometers, wherein the total Euclidean distances are nM, selecting the minimum Euclidean distance value, taking the corresponding air-conditioning single machine as the first air-conditioning single machine to be started, and then removing the corresponding air-conditioning single machine from a set Q, namely changing the set Q into a set containing M-1 elements, namely M-1 cabinet type air-conditioning single machines; at the same time, the corresponding pyrometers are removed from the set R, i.e. the set R becomes containing n-1 elements, i.e. n-1 pyrometers; then respectively calculating Euclidean distances between each of the M-1 air-conditioning single machines in the set Q and each of the n-1 air thermometers in the set R, wherein a total of (n-1) (M-1) Euclidean distance values are obtained, the smallest Euclidean distance value is selected, and the corresponding air-conditioning single machine is taken as a second air-conditioning single machine to be started; and so on until m stand cabinet air conditioners are selected and all the stand cabinet air conditioners are started.
2. The utility model provides a temperature control system towards optimization of large-scale data center air conditioner energy consumption which characterized in that: comprising a readable storage medium having stored therein execution instructions for, when executed by a processor, implementing the method of claim 1.
CN202011450142.XA 2020-12-09 2020-12-09 Temperature control method and system for optimizing energy consumption of air conditioner in large data center Active CN112601423B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011450142.XA CN112601423B (en) 2020-12-09 2020-12-09 Temperature control method and system for optimizing energy consumption of air conditioner in large data center

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011450142.XA CN112601423B (en) 2020-12-09 2020-12-09 Temperature control method and system for optimizing energy consumption of air conditioner in large data center

Publications (2)

Publication Number Publication Date
CN112601423A CN112601423A (en) 2021-04-02
CN112601423B true CN112601423B (en) 2022-01-11

Family

ID=75192002

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011450142.XA Active CN112601423B (en) 2020-12-09 2020-12-09 Temperature control method and system for optimizing energy consumption of air conditioner in large data center

Country Status (1)

Country Link
CN (1) CN112601423B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114364239B (en) * 2022-03-21 2022-05-24 南京工业大学 Temperature control method for optimizing energy consumption of air conditioner in large data center
CN116880278A (en) * 2023-07-11 2023-10-13 广东云下汇金科技有限公司 Control method for efficient operation of precision air conditioner of data center

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105444346A (en) * 2015-11-13 2016-03-30 上海斐讯数据通信技术有限公司 Data central machine room management and control system and method
CN106052033A (en) * 2016-06-22 2016-10-26 华中科技大学 Air conditioner control system and multi-level intelligent temperature control scheduling method of data center

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10361965B2 (en) * 2016-06-30 2019-07-23 Microsoft Technology Licensing, Llc Datacenter operations optimization system
CN107787155A (en) * 2016-08-24 2018-03-09 中国机房设施工程有限公司 A kind of low energy consumption data center machine room and its building method
CN209214037U (en) * 2018-11-05 2019-08-06 镇江香江云动力科技有限公司 A kind of Water cooled air conditioners circulation energy-saving system for large-scale data center cooling

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105444346A (en) * 2015-11-13 2016-03-30 上海斐讯数据通信技术有限公司 Data central machine room management and control system and method
CN106052033A (en) * 2016-06-22 2016-10-26 华中科技大学 Air conditioner control system and multi-level intelligent temperature control scheduling method of data center

Also Published As

Publication number Publication date
CN112601423A (en) 2021-04-02

Similar Documents

Publication Publication Date Title
CN112601423B (en) Temperature control method and system for optimizing energy consumption of air conditioner in large data center
CN109059195B (en) Control method and control system for central air conditioner for reducing load peak value of power grid
CN100443814C (en) System of adjusting quantity of cold, and adjustment method for central cooling in region
CN105571063B (en) A kind of shallow layer ground-temperature energy energy management system and its implementation
CN109917646B (en) System and method for optimizing operation of regional cooling and heating equipment
CN204730411U (en) Central air conditioning cooling water system energy-saving controller
CN105004002A (en) Energy saving control system and energy saving control method used for central air conditioner cooling water system
CN202310410U (en) Air supply control system of machine room equipment
CN109975052B (en) Air conditioner refrigerating performance test system and method without cold load state
CN107917509A (en) A kind of computer-room air conditioning system control method
CN212132815U (en) Intelligent cold station control system
CN113606693A (en) Data center refrigerating system and air-water coupling energy-saving control method thereof
CN110486896B (en) Cascade air conditioning system optimization control method based on water chilling unit energy consumption model
CN200975766Y (en) Cold quantity regulation system of region centralization cold feeding
CN104964394B (en) It is a kind of based on wind power ganged central air conditioner energy efficiency managing and control system and control method
CN117029196B (en) Intelligent energy-saving variable frequency control method, system and storage medium for central air conditioner
CN103062864B (en) For the outdoor true temperature method of accurate acquisition in VMC
CN102679649B (en) Energy conservation control device and energy conservation control method of refrigerating system
CN116880278A (en) Control method for efficient operation of precision air conditioner of data center
CN114413458B (en) Water pump parallel operation control method, device, equipment and medium for air-conditioning water system
CN213811936U (en) Cooling tower control device
CN106440188B (en) Automatic air conditioner operation capacity adjusting system and method
CN211084939U (en) High-energy-efficiency power station natural cooling control system
CN210130052U (en) Energy-saving modified module and modified machine room air conditioning system
CN113757856A (en) Control method and device for air conditioner cooling water system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant