CN111814388A - CFD simulation verification method for lower air supply data center based on neural network - Google Patents
CFD simulation verification method for lower air supply data center based on neural network Download PDFInfo
- Publication number
- CN111814388A CN111814388A CN202010533104.4A CN202010533104A CN111814388A CN 111814388 A CN111814388 A CN 111814388A CN 202010533104 A CN202010533104 A CN 202010533104A CN 111814388 A CN111814388 A CN 111814388A
- Authority
- CN
- China
- Prior art keywords
- neural network
- cabinet
- machine room
- actual
- air conditioner
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 52
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012795 verification Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 28
- 238000001816 cooling Methods 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims abstract description 6
- 210000002569 neuron Anatomy 0.000 claims description 17
- 238000007664 blowing Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H05K7/20009—Modifications to facilitate cooling, ventilating, or heating using a gaseous coolant in electronic enclosures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Thermal Sciences (AREA)
- Algebra (AREA)
- Fluid Mechanics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a CFD simulation verification method for a lower air supply data center based on a neural network, which comprises the following steps: step 1: selecting initial data of a machine room to establish a CFD simulation model of the machine room, and calculating through CFD software to obtain a simulation result; step 2: acquiring the actual inlet air temperature of the cabinet and the actual power of the air conditioner according to a certain sampling period as training samples of the neural network; and step 3: establishing a neural network model; and 4, step 4: inputting the training samples into a neural network to predict the predicted power of the air conditioners, and obtaining the influence degree of the cooled condition of the cabinet and the actual power of each air conditioner; and 5: and comparing the flow field result under the floor of the machine room obtained by the neural network prediction with the simulation result, and adjusting the position of the cabinet in the machine room by the adjusted initial data to optimize the airflow layout of the machine room. The method has the advantages that the cooling effect of the cabinet is more obvious, and the cabinet is convenient to use.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a CFD simulation verification method for a lower air supply data center based on a neural network.
Background
In the whole life cycle of the computer room data center, along with the updating and upgrading of the IT equipment, the power density of the computer room equipment is greatly improved compared with the power density of the computer room equipment in the initial construction stage, and therefore higher requirements are put forward on a computer room cooling system. The problem of equipment overheating cannot be thoroughly solved by blindly increasing the number of air conditioners or reducing the set temperature of the air conditioners, and the energy consumption of a computer room data center can be greatly increased, which also becomes a main bottleneck limiting the capacity expansion of the computer room data center. In fact, if the airflow organization of the data center of the computer room is not reasonable, even if the total cooling capacity of the air conditioner is far greater than the heat production capacity of the IT equipment, the phenomenon that the inlet temperature of part of the equipment is overhigh still occurs. And the problem of excessive cooling can be caused by reducing the set temperature of the air conditioner, and the refrigeration energy consumption is high.
In the existing process of utilizing CFD software to conduct energy-saving reconstruction on a data center, air is colorless and transparent, so that whether the gas flow range in a CFD simulation result is consistent with the actual situation or not cannot be judged intuitively and efficiently. In view of this, we propose a lower blowing data center CFD simulation verification method based on a neural network.
Disclosure of Invention
The invention aims to provide a CFD simulation verification method of a lower air supply data center based on a neural network, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a lower air supply data center CFD simulation verification method based on a neural network comprises the following steps:
step 1: selecting initial data of a machine room to establish a CFD simulation model of the machine room, and calculating through CFD software to obtain a simulation result;
step 2: acquiring the actual inlet air temperature of the cabinet according to a certain sampling period, and simultaneously carving the actual power of the air conditioner, and taking the actual inlet air temperature of the cabinet and the actual power of the air conditioner as training samples of a neural network;
and step 3: preprocessing a training sample, establishing a neural network model of the actual inlet air temperature and time of a certain cabinet and the actual power and time of each air conditioner, and determining the number of layers and nodes of the neural network of the model;
and 4, step 4: inputting the training samples into a neural network to be calculated to be convergent, predicting the predicted power of the air conditioner through the actual inlet air temperature of the cabinet by the neural network, and carrying out correlation analysis on the predicted power and the actual power data of the air conditioner to obtain the influence degree of the cooled condition of the cabinet and the actual power of each air conditioner;
and 5: and predicting to obtain a flow field result under the floor of the machine room through a neural network, comparing the flow field result under the floor of the machine room with the simulation result, repeatedly adjusting the initial data of the simulation model to enable the flow field result under the floor to be close to the simulation result, adjusting the position of a cabinet in the machine room according to the adjusted initial data, and optimizing the airflow layout of the machine room.
Preferably, in step 1, the initial data includes, but is not limited to, the size and shape of the machine room, the position and size of the obstacle, the height of the raised floor, the type and position of the air conditioner, the air volume and cooling capacity of the air conditioner, the size of the under-floor piping and cable bridge, the position and opening area of the air supply floor, the position, geometry, and orientation of the server cabinet, and the actual heat load of the server cabinet.
Preferably, in step 1, the simulation result includes, but is not limited to, a cloud map and a flow chart of the flow field distribution under the floor of the machine room.
Preferably, in step 2, a temperature sensor is installed at the cabinet air inlet position to obtain the actual cabinet air inlet temperature.
Preferably, in step 3, the training samples are preprocessed by a normalization method, so that the actual intake air temperature data and the actual power data are in the same order of magnitude.
Preferably, in step 3, the number of neurons in the hidden layer is preliminarily determined according to an empirical formula, and the number of neurons is finally determined by using training samples and training and comparing networks containing different numbers of neurons.
Compared with the prior art, the invention has the beneficial effects that: the CFD simulation verification method for the lower air supply data center based on the neural network comprises the steps of selecting initial data of a machine room, establishing a CFD simulation model of the machine room, calculating by CFD software to obtain a simulation result, taking actual air inlet temperature of a cabinet and actual power of an air conditioner as training samples of the neural network, training and learning the training samples by a manager neural network model, predicting a flow field result under the floor of the machine room by the neural network, comparing the flow field result under the floor of the machine room with the simulation result, repeatedly adjusting the initial data of the simulation model to enable the flow field result under the floor to be close to the simulation result, adjusting the position of the cabinet in the machine room according to the adjusted initial data, optimizing the airflow layout of the machine room, enabling the cooling effect of the cabinet to be more obvious and facilitating use.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a line graph of the relationship between the measured cabinet inlet air temperature and time in the present invention;
fig. 3 is a line graph of the relationship between the measured total power of the air conditioner and time according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, a technical solution provided by the present invention is:
a CFD simulation verification method of a lower air supply data center based on a neural network comprises the following steps:
step 1: selecting initial data of a machine room to establish a CFD simulation model of the machine room, and calculating by CFD software to obtain a simulation result;
step 2: acquiring the actual inlet air temperature of the cabinet according to a certain sampling period, and simultaneously carving the actual power of the air conditioner, and taking the actual inlet air temperature of the cabinet and the actual power of the air conditioner as training samples of a neural network;
and step 3: preprocessing a training sample, establishing a neural network model of the actual inlet air temperature and time of a certain cabinet and the actual power and time of each air conditioner, and determining the number of layers and nodes of the neural network of the model;
and 4, step 4: inputting the training samples into a neural network to be calculated to be convergent, predicting the predicted power of the air conditioner through the actual inlet air temperature of the cabinet by the neural network, and carrying out correlation analysis on the predicted power and the actual power data of the air conditioner to obtain the influence degree of the cooled condition of the cabinet and the actual power of each air conditioner;
and 5: and predicting to obtain a flow field result under the floor of the machine room through a neural network, comparing the flow field result under the floor of the machine room with the simulation result, repeatedly adjusting the initial data of the simulation model to enable the flow field result under the floor to be close to the simulation result, adjusting the position of a cabinet in the machine room according to the adjusted initial data, and optimizing the airflow layout of the machine room.
In this embodiment, in step 1, the initial data includes, but is not limited to, the size and shape of the machine room, the position and size of the obstacle, the height of the raised floor, the type and position of the air conditioner, the air volume and cooling capacity of the air conditioner, the size of the under-floor piping and the cable bridge, the position and opening area of the air supply floor, the position, geometric size and orientation of the server cabinet, the actual heat load of the server cabinet, and the more detailed information provided about the layout and size of the devices in the machine room in the initial data, so that the simulation result of the CFD is closer to the actual condition.
Further, in step 1, the simulation result includes, but is not limited to, a cloud map and a flow map of the airflow distribution under the floor of the machine room, so that information about the airflow distribution in the machine room, which is included in the simulation result, can be displayed more intuitively.
It is worth to be noted that, in the step 2, a temperature sensor is installed at the cabinet air inlet position to obtain the actual air inlet temperature of the cabinet, the model of the temperature sensor can be LM35DZ, and a matched circuit and a power supply of the temperature sensor are also provided by the manufacturer; in addition, the invention relates to circuits, electronic components and modules which are all in the prior art, and can be completely realized by a person skilled in the art, and needless to say, the protection content of the invention also does not relate to the improvement of software and a method, and the temperature change of an air inlet position of a cabinet is convenient to monitor in real time.
Specifically, in step 3, the training samples are preprocessed by a normalization method, so that the actual intake air temperature data and the actual power data are in the same order of magnitude.
In addition, in step 3, the number of neurons in the hidden layer is preliminarily determined according to an empirical formula, and the number of neurons is finally determined by training and comparing the training samples and the networks containing different numbers of neurons.
Further, in step 2, the sampling period time interval is preferably 30 minutes, and is used for collecting the influence of the cold air of the air conditioner on the cabinets in different time periods.
Specifically, in step 4, when the correlation analysis is performed on the predicted power and the actual power data of the air conditioner in this embodiment, if the analyzed value is within the (-1, -0.5) interval, it is determined that the position of the cabinet is covered by the output airflow range of the air conditioner, and if the value is outside the interval, it is determined that the output airflow range of the air conditioner is covered by the cabinet.
It should be noted that when the result of the under-floor flow field is close to the simulation result, the position of the cabinet in the machine room does not need to be moved, and when the difference between the result of the under-floor flow field and the simulation result is large, the initial data is repeatedly adjusted to make the result close, and the position and the size of the equipment in the machine room are adjusted according to the initial data, so that the effects of optimizing the air flow layout in the machine room, improving the air inlet temperature distribution of the cabinet and improving the refrigeration efficiency of the air conditioner are achieved.
Specifically, the formula of the neural network model is as follows:
l is the number of neural network layers, the 0 th layer is an input layer, the last layer is an output layer, and the middle layer is a hidden layer;
w is a weight of the image,
representing the weight value between the k neuron of the l-1 layer and the j neuron of the l layer;
b is the offset for correction;
the nonlinear activation function is:
wherein,
the inlet air temperature of each cabinet and the power of each air conditioner are used as input data, the result of each layer is calculated by the output of the previous layer, and the weight and the offset value of each layer are corrected through training, so that the error between the predicted output and the target output is controlled within an acceptable range.
In addition, the normalization method is to map the cabinet inlet air temperature and the air conditioner power data into the range of 0-1 for processing, namely changing the numerical value into a decimal between (0, 1) for the convenience of data processing;
and the normalization method adopts the following formula:
it is worth noting that generally, increasing the number of hidden layers can reduce network errors and improve accuracy, but also complicates the network, thereby increasing network training time, but at present, there is no formula capable of determining the number of hidden layer neurons. The number of neurons in the hidden layer can be preliminarily determined only according to the past empirical formula, and then the network containing different numbers of neurons is trained and compared by using the sample set, so that the number of neurons is finally determined.
The empirical formula is:
wherein h is the number of neurons in the hidden layer, m and n are the numbers of neurons in the input layer and the output layer respectively, and a is a regulation constant between 1 and 10.
When the lower air supply data center CFD simulation verification method based on the neural network is used, initial data of the machine room is selected to establish a CFD simulation model of the machine room, a simulation result is obtained through CFD software calculation, the actual air inlet temperature of the cabinet and the actual power of the air conditioner are collected according to a certain sampling period, the actual air inlet temperature of the cabinet and the actual power of the air conditioner are taken as training samples of the neural network, the training samples are preprocessed, a neural network model of the actual air inlet temperature and time of a certain cabinet and the actual power and time of each air conditioner is established, the number of layers and the number of nodes of the neural network of the model are determined, the training samples are input into the neural network to be calculated to be convergent, the neural network predicts the predicted power of the air conditioner through the actual air inlet temperature of the cabinet, and the predicted power and the actual power data of the air conditioner are subjected to correlation analysis, the influence degree of the cabinet cold condition and the actual power of each air conditioner is obtained, the underfloor flow field result of the machine room is obtained through neural network prediction, the underfloor flow field result of the machine room is compared with the simulation result, the initial data of the simulation model is adjusted repeatedly, the underfloor flow field result and the simulation result are close to each other, the position of the cabinet in the machine room is adjusted according to the adjusted initial data, the airflow layout of the machine room is optimized, the cooling effect of the cabinet is more remarkable, and the cabinet cooling device is convenient to use.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. A CFD simulation verification method of a lower air supply data center based on a neural network is characterized by comprising the following steps: the method comprises the following steps:
step 1: selecting initial data of a machine room to establish a CFD simulation model of the machine room, and calculating through CFD software to obtain a simulation result;
step 2: acquiring the actual inlet air temperature of the cabinet according to a certain sampling period, and simultaneously carving the actual power of the air conditioner, and taking the actual inlet air temperature of the cabinet and the actual power of the air conditioner as training samples of a neural network;
and step 3: preprocessing a training sample, establishing a neural network model of the actual inlet air temperature and time of a certain cabinet and the actual power and time of each air conditioner, and determining the number of layers and nodes of the neural network of the model;
and 4, step 4: inputting the training samples into a neural network to be calculated to be convergent, predicting the predicted power of the air conditioner through the actual inlet air temperature of the cabinet by the neural network, and carrying out correlation analysis on the predicted power and the actual power data of the air conditioner to obtain the influence degree of the cooled condition of the cabinet and the actual power of each air conditioner;
and 5: and predicting to obtain a flow field result under the floor of the machine room through a neural network, comparing the flow field result under the floor of the machine room with the simulation result, repeatedly adjusting the initial data of the simulation model to enable the flow field result under the floor to be close to the simulation result, adjusting the position of a cabinet in the machine room according to the adjusted initial data, and optimizing the airflow layout of the machine room.
2. The lower blowing data center CFD simulation verification method based on the neural network as claimed in claim 1, wherein: in step 1, the initial data includes, but is not limited to, the size and shape of the machine room, the position and size of the obstacle, the height of the raised floor, the type and position of the air conditioner, the air volume and cooling capacity of the air conditioner, the size of the under-floor piping system and the cable bridge, the position and opening area of the air supply floor, the position, geometric size and orientation of the server cabinet, and the actual heat load of the server cabinet.
3. The lower blowing data center CFD simulation verification method based on the neural network as claimed in claim 1, wherein: in step 1, the simulation result includes, but is not limited to, a cloud chart and a flow chart of the flow field distribution under the floor of the machine room.
4. The lower blowing data center CFD simulation verification method based on the neural network as claimed in claim 1, wherein: and step 2, installing a temperature sensor at the air inlet position of the cabinet to obtain the actual air inlet temperature of the cabinet.
5. The lower blowing data center CFD simulation verification method based on the neural network as claimed in claim 1, wherein: in step 3, the training sample is preprocessed by a normalization method, so that the actual inlet air temperature data and the actual power data are in the same order of magnitude.
6. The lower blowing data center CFD simulation verification method based on the neural network as claimed in claim 1, wherein: in step 3, the number of neurons in the hidden layer is preliminarily determined according to an empirical formula, and the number of the neurons is finally determined by utilizing training samples and training and comparing networks containing different neuron numbers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010533104.4A CN111814388B (en) | 2020-06-12 | 2020-06-12 | CFD simulation verification method for lower air supply data center based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010533104.4A CN111814388B (en) | 2020-06-12 | 2020-06-12 | CFD simulation verification method for lower air supply data center based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111814388A true CN111814388A (en) | 2020-10-23 |
| CN111814388B CN111814388B (en) | 2023-06-06 |
Family
ID=72844926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010533104.4A Active CN111814388B (en) | 2020-06-12 | 2020-06-12 | CFD simulation verification method for lower air supply data center based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814388B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112616292A (en) * | 2020-11-27 | 2021-04-06 | 湖南大学 | Data center energy efficiency optimization control method based on neural network model |
| CN113091262A (en) * | 2021-04-12 | 2021-07-09 | 国家计算机网络信息与安全管理中心 | Data center temperature and humidity set value determination method based on model predictive control |
| CN113158593A (en) * | 2021-04-13 | 2021-07-23 | 中南建筑设计院股份有限公司 | Intelligent design method of hospital ward ventilation system based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104633856A (en) * | 2015-01-27 | 2015-05-20 | 天津大学 | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network |
| CN107906687A (en) * | 2017-11-27 | 2018-04-13 | 中山路得斯空调有限公司 | A kind of central air-conditioning demand response control system based on local end's temperature adjustment |
| US20190075687A1 (en) * | 2017-09-06 | 2019-03-07 | Vertiv Corporation | Cooling unit energy optimization via smart supply air temperature setpoint control |
| CN109435630A (en) * | 2018-11-15 | 2019-03-08 | 无锡英捷汽车科技有限公司 | A kind of crew module's temprature control method based on artificial neural network algorithm |
| CN109631238A (en) * | 2019-01-28 | 2019-04-16 | 宁波溪棠信息科技有限公司 | A kind of control system and control method improving air-conditioning system operational energy efficiency |
| CN110059801A (en) * | 2019-03-20 | 2019-07-26 | 青岛海尔空调器有限总公司 | Energy efficiency of air conditioner control method neural network based |
-
2020
- 2020-06-12 CN CN202010533104.4A patent/CN111814388B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104633856A (en) * | 2015-01-27 | 2015-05-20 | 天津大学 | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network |
| US20190075687A1 (en) * | 2017-09-06 | 2019-03-07 | Vertiv Corporation | Cooling unit energy optimization via smart supply air temperature setpoint control |
| CN107906687A (en) * | 2017-11-27 | 2018-04-13 | 中山路得斯空调有限公司 | A kind of central air-conditioning demand response control system based on local end's temperature adjustment |
| CN109435630A (en) * | 2018-11-15 | 2019-03-08 | 无锡英捷汽车科技有限公司 | A kind of crew module's temprature control method based on artificial neural network algorithm |
| CN109631238A (en) * | 2019-01-28 | 2019-04-16 | 宁波溪棠信息科技有限公司 | A kind of control system and control method improving air-conditioning system operational energy efficiency |
| CN110059801A (en) * | 2019-03-20 | 2019-07-26 | 青岛海尔空调器有限总公司 | Energy efficiency of air conditioner control method neural network based |
Non-Patent Citations (12)
| Title |
|---|
| JAYATI ATHAVALE ET AL.: "Artificial Neural Network Based Prediction of Temperature and Flow Profile in Data Centers", 《IEEE XPLORE》 * |
| JAYATI ATHAVALE ET AL.: "Artificial Neural Network Based Prediction of Temperature and Flow Profile in Data Centers", 《IEEE XPLORE》, 26 July 2018 (2018-07-26) * |
| 刘红敏等: "基于神经网络的船舶舱室热舒适度研究", 《上海海事大学学报》 * |
| 刘红敏等: "基于神经网络的船舶舱室热舒适度研究", 《上海海事大学学报》, no. 01, 26 March 2020 (2020-03-26) * |
| 曹双华等: "基于神经网络的空调负荷混沌优化预测", 《东华大学学报(自然科学版)》 * |
| 曹双华等: "基于神经网络的空调负荷混沌优化预测", 《东华大学学报(自然科学版)》, vol. 29, no. 1, 28 February 2003 (2003-02-28) * |
| 王哲斌等: "夏季普通教室下送风的CFD模拟分析", 《万方数据》 * |
| 王哲斌等: "夏季普通教室下送风的CFD模拟分析", 《万方数据》, 28 August 2008 (2008-08-28) * |
| 赵相相: "某计算机房空调气流组织方式的数值模拟", 《万方数据》 * |
| 赵相相: "某计算机房空调气流组织方式的数值模拟", 《万方数据》, 24 July 2008 (2008-07-24) * |
| 邱秀君等: "神经网络预测控制在变风量空调系统中的应用", 《低压电器》 * |
| 邱秀君等: "神经网络预测控制在变风量空调系统中的应用", 《低压电器》, no. 12, 30 June 2009 (2009-06-30) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112616292A (en) * | 2020-11-27 | 2021-04-06 | 湖南大学 | Data center energy efficiency optimization control method based on neural network model |
| CN112616292B (en) * | 2020-11-27 | 2022-04-22 | 湖南大学 | Data center energy efficiency optimization control method based on neural network model |
| CN113091262A (en) * | 2021-04-12 | 2021-07-09 | 国家计算机网络信息与安全管理中心 | Data center temperature and humidity set value determination method based on model predictive control |
| CN113158593A (en) * | 2021-04-13 | 2021-07-23 | 中南建筑设计院股份有限公司 | Intelligent design method of hospital ward ventilation system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111814388B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814388A (en) | CFD simulation verification method for lower air supply data center based on neural network | |
| CN101589656B (en) | System and method for evaluating equipment rack cooling performance | |
| CN110866592B (en) | Model training method, device, energy efficiency prediction method, device and storage medium | |
| Gao et al. | Fault detection and diagnosis method for cooling dehumidifier based on LS-SVM NARX model | |
| Sun et al. | Optimization of support vector regression model based on outlier detection methods for predicting electricity consumption of a public building WSHP system | |
| Fang et al. | A neural-network enhanced modeling method for real-time evaluation of the temperature distribution in a data center | |
| CN112183826A (en) | Building energy consumption prediction method based on deep cascade generation countermeasure network and related product | |
| CN115310727B (en) | Building cooling, heating and power load prediction method and system based on transfer learning | |
| CN112152840B (en) | Sensor deployment method and system based on BIM and analog simulation | |
| CN110852498A (en) | Method for predicting data center energy consumption efficiency PUE based on GRU neural network | |
| CN112884012A (en) | Building energy consumption prediction method based on support vector machine principle | |
| CN117251695A (en) | Training method, device, equipment and storage medium of data prediction model | |
| CN113552855B (en) | Industrial equipment dynamic threshold setting method and device, electronic equipment and storage medium | |
| Su et al. | Operating optimization of air-conditioning water system in a subway station using data mining and dynamic system models | |
| Chen et al. | A novel machine learning-based model predictive control framework for improving the energy efficiency of air-conditioning systems | |
| CN109657695A (en) | A kind of fuzzy division clustering method and device based on definitive operation | |
| CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
| CN114636212B (en) | GRNN-based running control method for multiple water chilling unit systems | |
| CN116976488A (en) | Air conditioner energy consumption prediction method for optimizing BP neural network based on sparrow search algorithm | |
| Yu et al. | Improved energy management of chiller system with AI-based regression | |
| CN118133145B (en) | Data center rack air outlet temperature prediction method based on support vector machine | |
| Han et al. | Optimization of workload distribution of data centers based on a self-learning in situ adaptive tabulation model | |
| Simin et al. | Data center temperature prediction and management based on a Two-stage self-healing model | |
| Zhou et al. | Optimization of Metro Central Air Conditioning Cold Source System Based on PCA-ANN Data Model | |
| Yu | Application of Digital Twin Combined LSSVM Algorithm in Control Loop State Monitoring |
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 |