CN112859789A - Method and system for constructing data center digital twin body based on CFD - Google Patents
Method and system for constructing data center digital twin body based on CFD Download PDFInfo
- Publication number
- CN112859789A CN112859789A CN202110129584.2A CN202110129584A CN112859789A CN 112859789 A CN112859789 A CN 112859789A CN 202110129584 A CN202110129584 A CN 202110129584A CN 112859789 A CN112859789 A CN 112859789A
- Authority
- CN
- China
- Prior art keywords
- data center
- digital twin
- cfd
- model
- constructing
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004088 simulation Methods 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 238000005057 refrigeration Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000010367 cloning Methods 0.000 abstract description 3
- 239000012530 fluid Substances 0.000 abstract description 3
- 230000003042 antagnostic effect Effects 0.000 abstract 1
- 238000012795 verification Methods 0.000 description 19
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000005457 optimization Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a method and a system for constructing a data center digital twin body based on CFD (computational fluid dynamics), wherein a 3D digital twin body corresponding to an actual data center is constructed by utilizing physical parameters of the actual data center, the thermal process of the data center is simulated by a CFD technology, high-precision digital cloning of physical attributes and processes of the data center is realized, the actual data center is replaced to provide data and environment basis for intelligent decision, intelligent operation and maintenance and the like, so that the optimal strategies (such as an energy-saving strategy, a task scheduling strategy and the like) obtained in the digital twin body are ensured to have practicability and deployability, the optimal strategies can be quickly and conveniently deployed in the actual physical data center, meanwhile, the 3D digital twin body can be automatically calibrated according to an automatic calibration method based on a generated antagonistic network (cGAN), the manual calibration of time consumption is avoided, and the simulation precision of the 3D digital twin body can be improved on one hand, and on the other hand, the digital twin can be quickly applied to other data centers or machine rooms.
Description
Technical Field
The invention relates to the field of data centers, in particular to a method and a system for constructing a data center digital twin body based on CFD.
Background
The data center has strong data processing capacity, can provide basic information guarantees such as storage, calculation and network for technologies and applications such as artificial intelligence, big data and intelligent manufacturing, and the high-precision digital modeling facing the industrial data center is the basis of intelligent decision making and intelligent operation and maintenance of the data center. The data center is used as a production environment, operation safety and user service quality need to be guaranteed, and some configurations of the data center, such as task load or cooling facilities, cannot be adjusted at will, so that the data center cannot directly provide data and an environment basis for working contents such as intelligent decision and intelligent operation and maintenance (such as training solution of an energy-saving optimization algorithm, strategy verification, hypothetical verification or task scheduling). Therefore, the contents of training solution, strategy verification and the like of the existing data center optimization algorithm can only depend on a mathematical model or a pure simulation environment, namely, the design is separated from the actual data center, and the data center optimization algorithm has no practicability and is difficult to be really used in the data center. In addition, the existing simulation software (including a method for simulating by using an offline data set) does not interact with the actual data center, and cannot reflect the real operation condition of the actual data center in real time, the existing Computational Fluid Dynamics (CFD) -based software can only simulate the hot and airflow processes of the data center by configuring data offline, and even if a data center CFD model constructed by using mature commercial CFD software is used, the simulation precision still cannot reach an industrial level, and the main reason is that the physical (calibration) parameters for constructing the CFD model of the data center are different from the actual parameters of the equipment after long-term operation. Therefore, the constructed data center CFD model needs to be manually calibrated (for example, ACU wind speed, server fan wind volume calibration and the like). However, manual calibration may make it difficult to quickly apply the CFD-based simulation model to other data centers or computer rooms, and any change of physical equipment/facilities requires manual recalibration of the CFD model.
Disclosure of Invention
The invention aims to solve the technical problem that an actual data center is used as a production environment and cannot directly provide data and an environment basis for working contents such as intelligent decision and intelligent operation and maintenance (such as training solution of an energy-saving optimization algorithm, strategy verification, hypothetical verification or task scheduling), and the like.
The invention is realized by the following technical scheme:
a method for constructing a data center digital twin based on CFD comprises the following steps:
s1, collecting physical parameters of an actual data center;
step S2, constructing a 3D digital twin body corresponding to the actual data center according to the physical parameters of the actual data center;
step S3, importing real-time configuration parameters of an actual data center into a 3D digital twin body;
step S4, according to the CFD technology, simulating the running state of the actual data center in real time by using the 3D digital twin body with the real-time configuration parameters imported in the step S3;
step S5, constructing a cGAN calibration model, and calibrating the model parameters of the 3D digital twin body in operation in the step S4 in real time according to the constructed cGAN calibration model to obtain a calibrated 3D digital twin body;
s6, simulating various working conditions of the actual data center by using the calibrated 3D digital twin to obtain an optimal solution; and deploying the actual data center according to the optimal solution, wherein various working conditions comprise training solution of an energy-saving optimization algorithm, strategy verification, hypothesis verification or task scheduling performed by a task center and the like.
In the prior art, because the data center is used as a production environment, data and environment bases cannot be directly provided for intelligent decision and intelligent operation and maintenance (such as training solution of an energy-saving optimization algorithm, strategy verification, hypothetical verification or task scheduling) and the like, in addition, the calibration of the simulation precision by the existing simulation software usually adopts manual calibration, the calibration precision is not high and the operation is complex, so that the data center model simulated by the simulation software lacks universality, therefore, the scheme utilizes physical parameters of the actual data center, such as a layout structure, IT (information technology), refrigeration equipment and corresponding parameters, sensor real-time data, operation historical data and the like, to construct a 3D digital twin organism corresponding to the actual data center, and simulates the thermal process of the data center by a CFD (computational fluid dynamics) technology, so as to realize high-precision digital cloning of physical attributes and processes of the data center. The 3D digital twin body not only can display the data center dynamics in real time, but also can simulate the IT load, the thermal process and the like of the data center with high precision, therefore, the constructed 3D digital twin body corresponding to the actual data center can be used as a working platform to provide data and environment basis for the working content of the actual data center operation, wherein the working content comprises training solution, strategy verification, hypothesis verification, task scheduling and the like of an energy-saving optimization algorithm, so that the practicability and the deployability of intelligent decision are ensured, and simultaneously, according to the automatic calibration method based on the generation countermeasure network (cGAN), 3D digital twins corresponding to an actual data center can be automatically calibrated, time-consuming and labor-consuming manual calibration is avoided, meanwhile, the simulation precision of the 3D digital twin body can be improved, so that the simulation model can be quickly applied to other data centers or machine rooms.
Further, the physical parameters collected in step S1 include physical parameters of the machine room, the refrigeration equipment, and the IT equipment.
Further, the physical parameters of the machine room comprise the area, height and shape of the machine room and whether the raised floor is used as a cold air channel; the physical parameters of the refrigeration equipment comprise the position, the size, the rated power consumption, the maximum and minimum wind speed and the maximum and minimum set temperature of the refrigeration equipment; the physical parameters of the IT equipment comprise the size of a cabinet of the IT equipment, the size of a rack leg, the placing position, the rated power consumption, the number of required servers and the size of the servers.
Further, the 3D digital twin body comprises a machine room 3D model, a refrigeration equipment 3D model and an IT equipment 3D model of the actual data center, which are constructed according to CFD software.
Further, the specific process of constructing the cGAN calibration model in step S5 is as follows:
step S511, inputting random noise z and a condition parameter y into a generator G to obtain generated data, wherein the condition parameter y comprises configuration parameters of the 3D digital twin;
step S512, inputting the condition parameter y into the 3D digital twin body to obtain simulation data;
step S513, inputting the generated data + the condition parameter y, the simulation data + the condition parameter y into a discriminator D to judge authenticity;
step S514, continuously and iteratively training the generator G and the discriminator D according to the judgment result of the discriminator D;
and step S515, until the generator G and the discriminator D converge, obtaining a cGAN calibration model.
Further, the calibration process in step S5 is:
step S521, inputting the real-time configuration parameters of the 3D digital twin body as target configuration parameters into the cGAN calibration model to obtain the output result of the target configuration parameters;
step S522, judging whether the error between the output result of the target configuration parameter and the measured value of the actual data center is smaller than a set value;
if the judgment result is smaller than the set value, the target configuration parameter is used as the calibrated configuration parameter;
if the determination result is greater than or equal to the set value, the target configuration parameter is adjusted, and the steps S521-S522 are repeated.
In addition, the invention provides a system for constructing a data center digital twin body based on CFD, which comprises a model construction module, a simulation module, a calibration module and an application module, wherein,
the model building module is used for building a cGAN calibration model and a 3D digital twin body corresponding to a data center;
the simulation module simulates the running state of an actual data center according to the 3D digital twin body which is constructed by the model construction module and corresponds to the data center;
the calibration module calibrates configuration parameters of the 3D digital twin according to the running state of the 3D digital twin corresponding to the data center in the simulation module;
the application module simulates various working conditions of an actual data center according to the 3D digital twin body calibrated by the calibration module to obtain an optimal solution; the actual data center is deployed according to the optimal solution.
Further, the 3D digital twin includes a machine room 3D model, a refrigeration equipment 3D model and an IT equipment 3D model corresponding to the real data center.
Further, the operation state in the simulation module comprises task scheduling of an actual data center, IT equipment load change and refrigeration equipment temperature change.
Further, the configuration parameters calibrated in the calibration module include the air speed of the refrigeration equipment, the air volume of the server fan, the IT load distribution, and the set temperature and air speed of the ACU.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention discloses a method and a system for constructing a data center digital twin body based on CFD, which construct a 3D digital twin body according to an actual data center, generate a 3D digital twin body corresponding to the actual data center, realize high-precision digital mapping on physical properties and an operation process of the actual data center, the method can replace an actual data center to provide data and environment basis for intelligent decision making, intelligent operation and maintenance and the like of the data center, the working content comprises training solution of an energy-saving optimization algorithm, strategy verification, hypothesis verification, task scheduling and the like, and simultaneously, according to the automatic calibration method based on the generation countermeasure network (cGAN), the 3D digital twin body of the data center can be automatically calibrated, the manual calibration which is time-consuming and labor-consuming is avoided, meanwhile, the simulation precision of the digital twin body can be improved, so that the constructed digital twin body can be quickly applied to other data centers or machine rooms.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is an illustration of construction and operation of a data center 3D digital twin;
fig. 3 is a flow chart for creating a cGAN calibration model.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known structures, circuits, materials, or methods have not been described in detail so as not to obscure the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "one embodiment," "an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In the description of the present invention, it is to be understood that the terms "front", "rear", "left", "right", "upper", "lower", "vertical", "horizontal", "high", "low", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and therefore, are not to be construed as limiting the scope of the present invention.
Example 1
As shown in fig. 1, the present embodiment is a method for constructing a data center digital twin based on CFD, including the following steps:
s1, collecting physical parameters of an actual data center;
step S2, constructing a 3D digital twin body corresponding to the actual data center according to the physical parameters of the actual data center;
step S3, importing real-time configuration parameters of an actual data center into a 3D digital twin body;
step S4, according to the CFD technology, simulating the running state of the actual data center in real time by using the 3D digital twin body with the real-time configuration parameters imported in the step S3;
step S5, constructing a cGAN calibration model, and calibrating real-time configuration parameters of the 3D digital twin body in operation in the step S4 in real time according to the constructed cGAN calibration model to obtain a calibrated 3D digital twin body;
s6, simulating various working conditions of the actual data center by using the calibrated 3D digital twin to obtain an optimal solution; and deploying the actual data center according to the optimal solution, wherein various working conditions comprise training solution of an energy-saving optimization algorithm, strategy verification, hypothesis verification or task scheduling performed by a task center and the like.
In one embodiment, the physical parameters collected in step S1 include the area and height of the machine room, and the raised floor as a cold air duct; the position, size, rated power consumption, maximum and minimum wind speed and maximum and minimum set temperature of the refrigeration equipment; the size of the cabinet, the size of the rack legs and the placing position of the rack legs, the number and the size of the servers, the rated power consumption and other relevant parameters are required; the size of a cabinet, the size of a leg, the placement position, the rated power consumption, the number of required servers and the size of the servers of the IT equipment are determined, and the parameters of the position, the size, the power consumption and the like of other equipment (such as PDU (power distribution unit), UPS (uninterrupted power supply) and the like) of a machine room are also required to be acquired.
Specifically, the 3D digital twin body constructed by the CFD software according to the physical parameters of the actual data center in step S2 includes a machine room 3D model, a refrigeration equipment 3D model, and an IT equipment 3D model, and the CFD software may use OpenFoam,6Sigma, energy plus, ANSYS, or the like.
Specifically, as shown in fig. 2, an illustration of construction and operation of a data center 3D digital twin is shown, in fig. 2, (a) is a 3D structure diagram of an actual data center, and CFD software is used, as shown in fig. 2, (b), a data center 3D digital twin corresponding to the actual data center is constructed according to physical parameters such as a machine room structure (area shape, wall, ceiling, pipe, etc.), IT equipment (cabinet, machine location, server parameters, etc.), and the number and arrangement of refrigeration equipment (ACU, sensor arrangement, etc.); then, setting configuration parameters (such as IT load distribution, ACU set temperature and wind speed and the like) for the data center 3D digital twin body or importing real-time configuration parameters of an actual data center; finally, the operation state (such as task scheduling, load variation, temperature variation, etc.) of the real data center is simulated by using the CFD technology as shown in (c) of fig. 2.
In another embodiment, as shown in fig. 3, fig. 3 is a process for constructing a cGAN calibration model by training a cGAN model with random noise z and a condition parameter y, where the process includes steps S511-S515:
step S511, inputting random noise z and a condition parameter y into a generator G to obtain generated data, wherein the condition parameter y comprises configuration parameters of the 3D digital twin;
step S512, inputting the condition parameter y into the 3D digital twin body to obtain simulation data;
step S513, inputting the generated data + the condition parameter y, the simulation data + the condition parameter y into a discriminator D to judge authenticity;
step S514, continuously and iteratively training the generator G and the discriminator D according to the judgment result of the discriminator D;
and step S515, until the generator G and the discriminator D converge, obtaining a cGAN calibration model.
In one embodiment, the calibration process in step S5 includes steps S521-S522:
step S521, inputting the real-time configuration parameters of the 3D digital twin body as target configuration parameters into the cGAN calibration model to obtain the output result of the target configuration parameters;
step S522, judging whether the error between the output result of the target configuration parameter and the measured value of the actual data center is smaller than a set value;
if the judgment result is smaller than the set value, the target configuration parameter is used as the calibrated configuration parameter;
if the determination result is greater than or equal to the set value, the target configuration parameter is adjusted, and the steps S521-S522 are repeated.
In the prior art, the data center cannot be directly used as a working platform to provide data and environment basis for training solution, strategy verification, hypothesis verification or task scheduling of a task center and the like of an energy-saving optimization algorithm, so that the energy-saving optimization algorithm cannot be used for intelligent energy saving of the data center, or the solution of an optimal strategy and the like in an actual data center, and the existing simulation software generally adopts manual calibration for calibrating the simulation precision, the calibration precision is not high and the operation is complex, so that the data center model simulated by the simulation software lacks universality, therefore, the scheme utilizes physical parameters of the actual data center, such as a layout structure, IT and refrigeration equipment and corresponding parameters, sensor real-time data, operation historical data and the like, to construct a 3D digital twin organism of the data center, and simulates the thermal process of the data center by a CFD technology, and high-precision digital cloning of physical attributes and processes of the data center is realized. The data center 3D digital twin body not only can display the data center dynamics in real time, but also can simulate the IT load, the thermal process and the like of the data center with high precision, therefore, the constructed 3D digital twin body corresponding to the actual data center can be used as a working platform to provide data and environment basis for the working content which needs to be operated by the actual data center instead of the actual data center, the working content comprises training solution, strategy verification, hypothesis verification or task scheduling of an energy-saving optimization algorithm, and the like, so that the practicability and the deployability of the working content are ensured, and simultaneously, according to the automatic calibration method based on the generation countermeasure network (cGAN), the 3D digital twin body of the data center can be automatically calibrated, the manual calibration which is time-consuming and labor-consuming is avoided, meanwhile, the simulation precision of the 3D digital twin body of the data center can be improved, so that the simulation model can be quickly applied to other data centers or machine rooms.
Example 2
As shown in fig. 2, the present embodiment is different from embodiment 1 in that, based on the method of embodiment 1, the present embodiment proposes a system for constructing a data center digital twin based on CFD, which includes a model construction module, a simulation module, a calibration module, and an application module, wherein,
the model building module is used for building a cGAN calibration model and a 3D digital twin body corresponding to a data center;
the simulation module simulates the running state of an actual data center according to the 3D digital twin body which is constructed by the model construction module and corresponds to the data center;
the calibration module calibrates configuration parameters of the 3D digital twin according to the running state of the 3D digital twin corresponding to the data center in the simulation module;
the application module simulates various working conditions of an actual data center according to the 3D digital twin body calibrated by the calibration module to obtain an optimal solution; the actual data center is deployed according to the optimal solution.
The data center 3D digital twin comprises a machine room 3D model, a refrigeration equipment 3D model and an IT equipment 3D model corresponding to the actual data center.
Specifically, the operation state includes task scheduling of the real data center, IT equipment load variation, and refrigeration equipment temperature variation.
Specifically, the configuration parameters calibrated in the calibration module include the air speed of the refrigeration equipment, the air volume of the server fan, the IT load distribution, and the set temperature and air speed of the ACU.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for constructing a data center digital twin body based on CFD is characterized by comprising the following steps:
s1, collecting physical parameters of an actual data center;
step S2, constructing a 3D digital twin body corresponding to the actual data center according to the physical parameters of the actual data center;
step S3, importing real-time configuration parameters of an actual data center into a 3D digital twin body;
step S4, according to the CFD technology, simulating the running state of the actual data center in real time by using the 3D digital twin body with the real-time configuration parameters imported in the step S3;
step S5, constructing a cGAN calibration model, and calibrating the model parameters of the 3D digital twin body in operation in the step S4 in real time according to the constructed cGAN calibration model to obtain a calibrated 3D digital twin body;
s6, simulating various working conditions of the actual data center by using the calibrated 3D digital twin to obtain an optimal solution; the actual data center is deployed according to the optimal solution.
2. The method for constructing the data center digital twin based on the CFD of claim 1, wherein the physical parameters collected in the step S1 include physical parameters of a machine room, refrigeration equipment and IT equipment.
3. The method for constructing the data center digital twin based on the CFD as claimed in claim 2, wherein the physical parameters of the data center machine room include area, height, shape of the machine room and whether to use the raised floor as a cold air channel; the physical parameters of the refrigeration equipment comprise the position, the size, the rated power consumption, the maximum and minimum wind speed and the maximum and minimum set temperature of the refrigeration equipment; the physical parameters of the IT equipment comprise the size of a cabinet of the IT equipment, the size of a rack leg, the placing position, the rated power consumption, the number of required servers and the size of the servers.
4. The method for constructing a data center digital twin based on CFD according to claim 1, wherein the 3D digital twin includes a machine room 3D model, a refrigeration equipment 3D model and an IT equipment 3D model of an actual data center constructed according to CFD software.
5. The method for constructing a data center digital twin based on CFD as claimed in claim 1, wherein the specific process of constructing the cGAN calibration model in step S5 is as follows:
step S511, inputting random noise z and a condition parameter y into a generator G to obtain generated data, wherein the condition parameter y comprises configuration parameters of the 3D digital twin;
step S512, inputting the condition parameter y into the 3D digital twin body to obtain simulation data;
step S513, inputting the generated data + the condition parameter y, the simulation data + the condition parameter y into a discriminator D to judge authenticity;
step S514, continuously and iteratively training the generator G and the discriminator D according to the judgment result of the discriminator D;
and step S515, until the generator G and the discriminator D converge, obtaining a cGAN calibration model.
6. The method for constructing a data center digital twin based on CFD as claimed in claim 1, wherein the calibration procedure in step S5 is:
step S521, inputting the real-time configuration parameters of the 3D digital twin body as target configuration parameters into the cGAN calibration model to obtain the output result of the target configuration parameters;
step S522, judging whether the error between the output result of the target configuration parameter and the measured value of the actual data center is smaller than a set value;
if the judgment result is smaller than the set value, the target configuration parameter is used as the calibrated configuration parameter;
if the determination result is greater than or equal to the set value, the target configuration parameter is adjusted, and the steps S521-S522 are repeated.
7. A system for constructing a data center digital twin body based on CFD is characterized by comprising a model construction module, a simulation module, a calibration module and an application module, wherein,
the model building module is used for building a cGAN calibration model and a 3D digital twin body corresponding to a data center;
the simulation module simulates the running state of an actual data center according to the 3D digital twin body which is constructed by the model construction module and corresponds to the data center;
the calibration module calibrates configuration parameters of the 3D digital twin according to the running state of the 3D digital twin corresponding to the data center in the simulation module;
the application module simulates various working conditions of an actual data center according to the 3D digital twin body calibrated by the calibration module to obtain an optimal solution; the actual data center is deployed according to the optimal solution.
8. The system for constructing a data center digital twin based on CFD according to claim 7, wherein the 3D digital twin includes a machine room 3D model, a refrigeration equipment 3D model and an IT equipment 3D model corresponding to an actual data center.
9. The system for constructing a data center digital twin based on CFD according to claim 7, wherein the operation status in the simulation module includes task scheduling of real data center, IT equipment load variation and refrigeration equipment temperature variation.
10. The system for constructing a data center digital twin based on CFD according to claim 7, wherein the configuration parameters calibrated in the calibration module include wind speed of refrigeration equipment, server fan wind volume, IT load distribution and ACU set temperature and wind speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110129584.2A CN112859789B (en) | 2021-01-29 | 2021-01-29 | CFD-based method and system for constructing digital twin body of data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110129584.2A CN112859789B (en) | 2021-01-29 | 2021-01-29 | CFD-based method and system for constructing digital twin body of data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112859789A true CN112859789A (en) | 2021-05-28 |
| CN112859789B CN112859789B (en) | 2024-02-06 |
Family
ID=75987070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110129584.2A Active CN112859789B (en) | 2021-01-29 | 2021-01-29 | CFD-based method and system for constructing digital twin body of data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112859789B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113835460A (en) * | 2021-11-23 | 2021-12-24 | 中铁建设集团有限公司 | Data computer lab intelligence environmental control system based on hydrodynamics analog digital twin |
| CN116055324A (en) * | 2022-12-30 | 2023-05-02 | 重庆邮电大学 | Digital twin method for self-optimization of data center network |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102404834A (en) * | 2011-12-16 | 2012-04-04 | 重庆邮电大学 | Method for calibrating transmitting power of nonlinear power amplifying system |
| CN102921284A (en) * | 2012-10-11 | 2013-02-13 | 浙江省环境保护科学设计研究院 | Method and device for controlling NOx concentration in smoke gas of cement kiln |
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| CN107291973A (en) * | 2016-04-12 | 2017-10-24 | 达索系统西姆利亚公司 | For the emulation augmented reality system of urgent behavior |
| CN108919765A (en) * | 2018-07-20 | 2018-11-30 | 王德权 | A kind of the intelligence manufacture factory Virtual Debugging and virtual monitor method and method twin based on number |
| CN109819233A (en) * | 2019-01-21 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of digital twinned system based on virtual image technology |
| CN109991918A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | Parallel control method based on the sampling of multicycle difference with the twin technology of number |
| CN110121749A (en) * | 2016-11-23 | 2019-08-13 | 通用电气公司 | Deep learning medical system and method for Image Acquisition |
| US20190313164A1 (en) * | 2018-04-05 | 2019-10-10 | Honeywell International Inc. | System and method for connected metering |
| CN110347131A (en) * | 2019-07-18 | 2019-10-18 | 中国电子科技集团公司第三十八研究所 | The digital twinned system of facing to manufacture |
| CN110462644A (en) * | 2017-01-24 | 2019-11-15 | 西门子股份公司 | The system and method for the cognitive engineering technology of automation and control for system |
| CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
| CN111161410A (en) * | 2019-12-30 | 2020-05-15 | 中国矿业大学(北京) | Mine digital twinning model and construction method thereof |
| CN111242974A (en) * | 2020-01-07 | 2020-06-05 | 重庆邮电大学 | Vehicle real-time tracking method based on twin network and back propagation |
| CN111492321A (en) * | 2017-12-18 | 2020-08-04 | 西门子股份公司 | Method for replacing traditional programmable logic controller |
| CN112083698A (en) * | 2020-09-10 | 2020-12-15 | 南昌市言诺科技有限公司 | Production line real-time control method and device based on digital twin model |
| CN112131782A (en) * | 2020-08-27 | 2020-12-25 | 浙江大学 | Multi-loop intelligent factory edge side digital twin scene coupling device |
| CN112163325A (en) * | 2020-09-10 | 2021-01-01 | 浙江工业大学 | RV reducer service life prediction method based on digital twinning |
-
2021
- 2021-01-29 CN CN202110129584.2A patent/CN112859789B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102404834A (en) * | 2011-12-16 | 2012-04-04 | 重庆邮电大学 | Method for calibrating transmitting power of nonlinear power amplifying system |
| CN102921284A (en) * | 2012-10-11 | 2013-02-13 | 浙江省环境保护科学设计研究院 | Method and device for controlling NOx concentration in smoke gas of cement kiln |
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| CN107291973A (en) * | 2016-04-12 | 2017-10-24 | 达索系统西姆利亚公司 | For the emulation augmented reality system of urgent behavior |
| CN110121749A (en) * | 2016-11-23 | 2019-08-13 | 通用电气公司 | Deep learning medical system and method for Image Acquisition |
| CN110462644A (en) * | 2017-01-24 | 2019-11-15 | 西门子股份公司 | The system and method for the cognitive engineering technology of automation and control for system |
| CN111492321A (en) * | 2017-12-18 | 2020-08-04 | 西门子股份公司 | Method for replacing traditional programmable logic controller |
| US20190313164A1 (en) * | 2018-04-05 | 2019-10-10 | Honeywell International Inc. | System and method for connected metering |
| CN108919765A (en) * | 2018-07-20 | 2018-11-30 | 王德权 | A kind of the intelligence manufacture factory Virtual Debugging and virtual monitor method and method twin based on number |
| CN109819233A (en) * | 2019-01-21 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of digital twinned system based on virtual image technology |
| CN109991918A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | Parallel control method based on the sampling of multicycle difference with the twin technology of number |
| CN110347131A (en) * | 2019-07-18 | 2019-10-18 | 中国电子科技集团公司第三十八研究所 | The digital twinned system of facing to manufacture |
| CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
| CN111161410A (en) * | 2019-12-30 | 2020-05-15 | 中国矿业大学(北京) | Mine digital twinning model and construction method thereof |
| CN111242974A (en) * | 2020-01-07 | 2020-06-05 | 重庆邮电大学 | Vehicle real-time tracking method based on twin network and back propagation |
| CN112131782A (en) * | 2020-08-27 | 2020-12-25 | 浙江大学 | Multi-loop intelligent factory edge side digital twin scene coupling device |
| CN112083698A (en) * | 2020-09-10 | 2020-12-15 | 南昌市言诺科技有限公司 | Production line real-time control method and device based on digital twin model |
| CN112163325A (en) * | 2020-09-10 | 2021-01-01 | 浙江工业大学 | RV reducer service life prediction method based on digital twinning |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113835460A (en) * | 2021-11-23 | 2021-12-24 | 中铁建设集团有限公司 | Data computer lab intelligence environmental control system based on hydrodynamics analog digital twin |
| CN113835460B (en) * | 2021-11-23 | 2022-05-03 | 中铁建设集团有限公司 | Data computer lab intelligence environmental control system based on hydrodynamics analog digital twin |
| CN116055324A (en) * | 2022-12-30 | 2023-05-02 | 重庆邮电大学 | Digital twin method for self-optimization of data center network |
| CN116055324B (en) * | 2022-12-30 | 2024-05-07 | 重庆邮电大学 | Digital twin method for self-optimization of data center network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112859789B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112859789B (en) | CFD-based method and system for constructing digital twin body of data center | |
| CN104566868B (en) | A kind of central air conditioning system and its control method | |
| CN108036468B (en) | Aggregation control method for air conditioning system | |
| CN107036652B (en) | A kind of indoor environment monitoring system and method for the simulation of combination architectural environment | |
| CN102359735B (en) | Energy-saving monitoring system for large public building air conditioner | |
| CN111780332B (en) | Household metering method and device for central air conditioner | |
| CN107355963A (en) | A kind of detecting system for being used to build the monitoring of O＆M device temperature based on threedimensional model | |
| CN105046595A (en) | Internet-of-things technology based energy efficiency assessment and diagnosis cloud system and method | |
| CN102238763B (en) | Base station energy consumption computing system and method | |
| Turner et al. | Demand-side characterization of the smart city for energy modelling | |
| CN112413762A (en) | Parameter optimization method and system for cooling water system of refrigerating room | |
| CN103310067B (en) | Realize the method for equipment real-time analog simulation monitor | |
| Liang et al. | Energy saving potential of heat removal using natural cooling water in the top zone of buildings with large interior spaces | |
| CN101650760B (en) | Heat dissipation simulation method and device of computer | |
| CN113065190A (en) | Uncertainty-based residential building heat supply amount calculation method | |
| CN103839476B (en) | Three-dimensional Simulation System made by a kind of transformer assembling prison | |
| CN111415036B (en) | Load optimization distribution method for parallel connection cold machines of central air-conditioning system | |
| CN116306370A (en) | Display method, display device, air conditioning system and medium for indoor environment model | |
| CN107133372B (en) | Mobile communication base station energy consumption benchmarking scene evaluation method and device | |
| Lan et al. | Optimal zoning for building zonal model of large-scale indoor space | |
| Diddeniya et al. | IoT based energy efficient smart classroom | |
| Cai et al. | A study on stratified air conditioning cooling load calculation model for a large space building | |
| CN104598678B (en) | Power transmission network logic geography drawing generating method | |
| CN204853838U (en) | Central air conditioning control system | |
| JP6023683B2 (en) | How to determine the floor outlet area |
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 |