CN112050397A - Method and system for regulating and controlling temperature of machine room - Google Patents
Method and system for regulating and controlling temperature of machine room Download PDFInfo
- Publication number
- CN112050397A CN112050397A CN202010880104.1A CN202010880104A CN112050397A CN 112050397 A CN112050397 A CN 112050397A CN 202010880104 A CN202010880104 A CN 202010880104A CN 112050397 A CN112050397 A CN 112050397A
- Authority
- CN
- China
- Prior art keywords
- temperature
- machine room
- prediction model
- data
- related data
- 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.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/52—Indication arrangements, e.g. displays
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
- F24F2110/12—Temperature of the outside air
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
- F24F2110/22—Humidity of the outside air
Abstract
The invention provides a method and a system for regulating and controlling the temperature of a machine room, wherein the method comprises the following steps: acquiring historical temperature related data of a machine room; constructing a temperature prediction model according to the historical temperature related data; acquiring current temperature related data of a machine room, and taking the current temperature related data as data of a temperature prediction model to acquire a predicted temperature value; and adjusting the set temperature of the air conditioner or switching on and switching off the air conditioner according to the predicted temperature value. According to the invention, the air conditioner control strategies of different machine rooms are self-adaptively learned in a mode of combining temperature prediction and reinforcement learning control strategies, so that the control parameters of the air conditioner are more accurately set, the temperature and the humidity in the machine room can meet the normal working requirements of equipment, and the temperature and the humidity in the machine room can be kept stable.
Description
Technical Field
The invention relates to a temperature regulation and control system, in particular to a method and a system for regulating and controlling the temperature of a machine room.
Background
Data computer lab and network computer lab are the infrastructure of modern communication, have a lot of service equipment in the computer lab, and these equipment require long-term steady operation, so require higher to the temperature and humidity in the computer lab, especially temperature. If the temperature in the machine room is too high or too low, the normal operation or service life of the equipment is greatly influenced, and an air conditioner is usually adopted in the machine room to regulate the temperature in the machine room. The current situation is that most machine room air conditioners do not have an automatic adjusting function, and in order to ensure that the indoor temperature (like high temperature in summer) can be maintained even under the condition of high outdoor temperature, the set parameters of the air conditioners are generally adjusted to a value which enables the temperature of the machine room to be kept relatively low and the refrigerating output to be large so as to adapt to different external environment conditions, however, when the outdoor temperature is relatively low and the refrigerating output is not required to be too much (like low temperature in winter), unnecessary electric energy waste can be caused.
Based on the problems, part of the schemes adopt a rule control method, and adopt a rule logic set artificially according to the indoor and outdoor temperature conditions, for example, the set temperature is increased by a few degrees when the temperature is low outside, and the temperature of an air conditioner is reduced by a few degrees when the temperature is high outside; the mode has no fixed parameter setting mode of automatic control, can dynamically adjust the setting of the air conditioner according to the environment, and saves unnecessary electric energy waste. The method adopting the rule control has simple logic and low implementation difficulty, has a certain effect on reducing energy consumption, adopts the temperature and humidity sensors carried by the air conditioner or a plurality of external temperature and humidity sensors, improves the heat of the condition evaluation of the whole machine room to a certain extent, but the regulation and control mode can not automatically regulate and control the rule logic and the control parameters according to the environmental conditions such as the area, the layout and the like of the machine room, still needs manual auxiliary setting, only utilizes partial temperature and humidity information in the control rule, and does not consider the information of other sensors in the machine room (such as the load power of the machine room, the opening and closing state of an access control, other temperature and humidity values and the like) to evaluate the environmental condition of the machine room inaccurately; in addition, the rule control mode is formulated according to current and historical data, future conditions are not predicted and evaluated, and the rule control mode is delay control with adjustment occurring afterwards, so that the temperature and the humidity in the machine room are kept at a stable level.
Disclosure of Invention
In order to solve the above technical problems, a first object of the present invention is to provide a method for regulating and controlling a temperature of a machine room, which adaptively learns air conditioner control strategies of different machine rooms by combining temperature prediction and reinforcement learning control strategies, so as to more accurately set control parameters of an air conditioner, so that the temperature and humidity in the machine room can meet normal operation requirements of equipment, and the temperature and humidity in the machine room can be kept stable.
The second purpose of the invention is to provide a machine room temperature regulating and controlling system, which uses the machine room temperature regulating and controlling method to regulate and control the temperature of a machine room.
In view of the above object, one aspect of the present invention provides a method for controlling a temperature of a machine room, specifically, the method includes:
acquiring historical temperature related data of a machine room;
constructing a temperature prediction model according to the historical temperature related data;
acquiring current temperature related data of a machine room, and taking the current temperature related data as data of a temperature prediction model to acquire a predicted temperature value;
and adjusting the set temperature of the air conditioner or switching on and switching off the air conditioner according to the predicted temperature value.
Preferably, the step of constructing a temperature prediction model according to the historical temperature-related data specifically comprises:
dividing the historical temperature related data into a training set, a verification set and a test set;
constructing a plurality of prediction models according to a training set and a gradient descent optimization algorithm;
verifying and screening the prediction model by adopting a verification set;
and testing the prediction model obtained by screening by adopting a test set, and selecting the prediction model with the best test result as the final temperature prediction model.
Preferably, the historical temperature-related data is divided into a training set, a validation set and a test set according to a ratio of 6:2: 2.
Preferably, the historical temperature-related data includes temperature-related data including machine room environment data and equipment load data.
Preferably, the computer room environment data comprises an environment temperature, entrance guard state data, door and window opening and closing state data and an outdoor temperature of the computer room;
the device load data includes heat generated by the load corresponding to the device at each time.
Preferably, the method further comprises the steps of monitoring the accuracy of the temperature prediction model in real time, counting the change trend of the error of the temperature prediction model, and automatically training and updating the temperature prediction model when the error of the temperature prediction model exceeds a threshold value.
Preferably, the error confirmation method of the temperature prediction model includes: and acquiring errors of the temperature prediction model in the past time period, and automatically starting automatic training and updating of the temperature prediction model if the average value of the errors for multiple times exceeds 0.2 ℃.
In another aspect of the present invention, a machine room temperature regulating system using the above machine room temperature regulating method is provided, the system includes a main controller and a data acquisition unit connected thereto;
the data acquisition unit is used for acquiring current machine room environment data;
the main controller is internally provided with a temperature prediction model and a temperature prediction model construction algorithm for acquiring current equipment load data, and meanwhile, the model prediction algorithm is adopted to pre-judge the temperature change trend of the machine room in a future time period according to the current temperature related data, and the set temperature of the air conditioner is regulated or the machine is started or stopped according to the pre-judged result, so that the machine room is always in a constant temperature state.
Preferably, the data acquisition unit comprises a temperature sensor, an entrance guard state detection device and a door and window opening and closing state detection device; the temperature sensors are distributed in the machine room.
Preferably, the system further comprises a display unit, and the display module is connected with the main controller and used for displaying the input and output parameters of the temperature regulation and control information of the machine room.
Compared with the prior art, the invention has the beneficial effects that:
the machine learning algorithm is utilized to fuse data of more different types of sensors and equipment, so that the environmental condition of the machine room is sensed more accurately; the temperature values of the machine room in a period of time in the future are predicted by using the sensors and equipment data of different types, the predicted values are added into a control strategy, prediction control is realized, and the future condition is judged in advance to make judgment; different air conditioner control strategy models are learned aiming at different machine room environments by combining a reinforcement learning algorithm, so that the method is suitable for different machine room environments, and better in automation and universality.
According to the invention, the air conditioner control strategies of different machine rooms are self-adaptively learned in a mode of combining temperature prediction and reinforcement learning control strategies, so that the control parameters of the air conditioner are more accurately set, the temperature and the humidity in the machine room can meet the normal working requirements of equipment, and the temperature and the humidity in the machine room can be kept stable.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of a method for regulating and controlling the temperature of a machine room in the embodiment of the invention;
FIG. 2 is a schematic diagram of a process for constructing a model using the LSTNet algorithm according to an embodiment of the present invention;
FIG. 3 is a diagram of a distribution structure of original temperature data of a computer room according to an embodiment of the present invention;
FIG. 4 is a graph of correlation analysis of various data and indoor temperature data in an embodiment of the present invention;
FIG. 5 is a schematic diagram of the loss function variation of the temperature prediction model training process in the embodiment of the present invention;
fig. 6 is a flow chart of a model reconstruction process included in the method according to the embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiment provides a machine room temperature regulation method, which specifically comprises the following steps:
acquiring historical temperature related data of a machine room;
constructing a temperature prediction model according to the historical temperature related data;
acquiring current temperature related data of a machine room, and taking the current temperature related data as data of a temperature prediction model to acquire a predicted temperature value;
and adjusting the set temperature of the air conditioner or switching on and switching off the air conditioner according to the predicted temperature value.
As a preferred embodiment, the historical temperature-related data includes temperature-related data including room environment data and equipment load data.
As a preferred embodiment, the machine room environment data includes an ambient temperature, door access state data, door and window opening and closing state data, and an outdoor temperature of the machine room;
the device load data includes heat generated by the load corresponding to the device at each time.
As a preferred embodiment, the step of constructing a temperature prediction model according to the historical temperature-related data specifically includes:
dividing the historical temperature related data into a training set, a verification set and a test set;
constructing a plurality of prediction models according to a training set and a gradient descent optimization algorithm;
verifying and screening the prediction model by adopting a verification set;
and testing the prediction model obtained by screening by adopting a test set, and selecting the prediction model with the best test result as the final temperature prediction model.
Need to explain: the temperature prediction model may employ different prediction model algorithms. For example, conventional time series prediction algorithms (AR, ARIMA, VAR, etc.), temporal neural networks (LSTM, GRU), hybrid time series prediction models (LSTNet, TPA-LSTM, etc.) may be used. For example, an LSTNet algorithm is adopted to construct a model, the structure of which is shown in fig. 2, wherein Time represents a Time sequence of data, multivariable Time series represents different characteristic latitudes in the Time sequence, constant Layer is a Convolutional neural network Layer, current and current-skip Layer is a loop and skip loop Layer, a fully-connected network Layer and each element summation operation are immediately followed, and meanwhile, a value obtained by an Autoregressive method (torautomatically) through a Bypass Linear process (Linear Bypass) is summed with the fully-connected summation Layer to obtain a Prediction output (Prediction).
The historical temperature related data of the machine room is screened in advance, the data collected by a certain machine room is taken as an example, the collection frequency is once in 1 minute, and the original temperature data structure is shown in fig. 3, wherein env _ temperature represents the indoor temperature, env _ humidity represents the indoor humidity, env _ outdoor _ t represents the outdoor temperature, env _ outdoor _ h represents the outdoor humidity, air _ temperature represents the return air temperature of the air conditioner, and cabin _ power _ kw represents the total load power of the cabinets in the machine room.
Which of the above data is correlated with the room temperature is determined by a correlation analysis algorithm (preferably PCA, MIC, pearson correlation coefficient, etc., which are well established correlation analysis algorithms). The correlation coefficient of pearson is used to calculate the correlation between different data variables, and the calculation formula is as follows:
wherein X, Y is two variables to be compared, where ρ is the final correlation coefficient between X and Y, cov (X, Y) is the covariance between X and Y, E is the mean, σ is the standard deviation of the variable distribution, and μ is the median of the variable distribution.
The quotient of the covariance and the standard deviation between the two variables, the value ranging between-1 and 1. The calculation results are shown in fig. 4. Wherein, negative value represents negative correlation, positive value represents positive correlation, and absolute value is taken to judge the correlation degree (positive correlation, negative correlation are all correlated). According to the first column of fig. 4, the correlation between each data and the indoor temperature can be judged, the data with the absolute value of the correlation larger than 0.6 is taken as the characteristic data, and it can be seen from fig. 4 that the total load power (cabinet _ power _ kw) of the cabinet in the machine room is smaller than 0.6, and the data needs to be removed. Therefore, four characteristic data of indoor humidity (env _ humidity), outdoor temperature (env _ outdoor _ t), outdoor humidity (env _ outdoor _ h) and air-conditioning return air temperature (air _ temperature) are finally selected as model inputs.
The historical temperature-related data is then divided proportionally (typically 6:2:2) into a training set, a validation set and a test set, and the future 30-minute data is extracted as a label. The model parameters are optimized by using a gradient descent optimization algorithm, the model parameters with better performance on the test set are taken as the final temperature prediction model, namely the parameters with the most accurate temperature prediction, the loss function change (the error between the prediction error and the true value) in the training process is shown in fig. 5, train curve is represented on the way, the horizontal axis is the training step number, the vertical axis is the loss function value, and a determined temperature prediction model (determined structure and determined parameters) is obtained, so that the predicted value of the next 30 minutes can be obtained only by inputting the current data into the model during prediction.
The invention adopts an air conditioner control model to control the set temperature of the air conditioner, the air conditioner control model is formed by adopting reinforcement learning training, and the reinforcement learning is a machine learning algorithm for control decision, and can optimize parameters and learn a control strategy from data generated in interaction with the environment. In the initial stage of the construction process of the air conditioner control model, learning is required through data, namely, in the initial stage, the air conditioner is required to be executed for a period of time (such as 1-2 weeks) according to a rule set strategy, and data are accumulated; then the air conditioner control model obtains a basic model according to a general reinforcement learning training rule; and then, the reinforcement learning model is utilized to operate, data are accumulated, and the model is continuously optimized by utilizing new data, so that the control strategy is more and more energy-saving. In the implementation process, the set temperature of the air conditioner or the process of turning on and turning off the air conditioner can be adjusted according to the predicted temperature value, and the air conditioner control model obtains control parameters of the air conditioner according to the original input data and the output of the temperature prediction model, such as: starting the machine, setting 21 ℃, executing, comparing temperature change after execution, and counting power consumption when the temperature in the standby room is stabilized at a certain temperature. Storing the input data, the air conditioner setting parameters and the power consumption data, and updating the model parameters by a reinforcement learning training updating method. Therefore, with the continuous increase of the running time, the model continuously optimizes the parameters and saves more and more energy.
As a preferred embodiment, as shown in fig. 6, the method further includes performing real-time accuracy monitoring on the temperature prediction model, counting a variation trend of an error of the temperature prediction model, and automatically training and updating the temperature prediction model when the error of the temperature prediction model exceeds a threshold. The automatic retraining and deployment mechanism of the model can ensure that the model can be timely updated when the environment of the machine room changes (such as replacement or new equipment addition, decoration and reconstruction). Preferably, the error confirmation method of the temperature prediction model comprises the following steps: obtaining the error of the temperature prediction model in the past time period, and if the average value of the errors of multiple times exceeds 0.2 ℃, automatically starting the automatic training and updating of the temperature prediction model, wherein the process can be specifically implemented as follows: and (4) counting average temperature prediction errors in a past period (which can be one hour, one day and one week), and when the average predicted indoor temperature error is more than 0.2 ℃, re-extracting historical data and training the model. And taking the model with better performance on the test set, and redeploying (for example, directly copying the generated model file to a specified path file by using the tf serving open source framework).
The embodiment also provides a machine room temperature regulating and controlling system applying the machine room temperature regulating and controlling method, and the system comprises a main controller and a data acquisition unit connected with the main controller;
the data acquisition unit is used for acquiring current machine room environment data;
the main controller is internally provided with a temperature prediction model and a temperature prediction model construction algorithm for acquiring current equipment load data, and meanwhile, the model prediction algorithm is adopted to pre-judge the temperature change trend of the machine room in a future time period according to the current temperature related data, and the set temperature of the air conditioner is regulated or the machine is started or stopped according to the pre-judged result, so that the machine room is always in a constant temperature state.
Preferably, the data acquisition unit comprises a temperature sensor, an entrance guard state detection device and a door and window opening and closing state detection device; the temperature sensors are distributed in the machine room.
Preferably, the system further comprises a display unit, and the display module is connected with the main controller and used for displaying the input and output parameters of the temperature regulation and control information of the machine room.
The machine learning algorithm is utilized to fuse data of more different types of sensors and equipment, so that the environmental condition of the machine room is sensed more accurately; the temperature values of the machine room in a period of time in the future are predicted by using the sensors and equipment data of different types, the predicted values are added into a control strategy, prediction control is realized, and the future condition is judged in advance to make judgment; different air conditioner control strategy models are learned aiming at different machine room environments by combining a reinforcement learning algorithm, so that the method is suitable for different machine room environments, and better in automation and universality.
According to the invention, the air conditioner control strategies of different machine rooms are self-adaptively learned in a mode of combining temperature prediction and reinforcement learning control strategies, so that the control parameters of the air conditioner are more accurately set, the temperature and the humidity in the machine room can meet the normal working requirements of equipment, and the temperature and the humidity in the machine room can be kept stable.
Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and those skilled in the art can make changes, modifications, substitutions and alterations to the above embodiments without departing from the principle and spirit of the present invention, and any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention still fall within the technical scope of the present invention.
Claims (10)
1. A method for regulating and controlling the temperature of a machine room is characterized in that,
acquiring historical temperature related data of a machine room;
constructing a temperature prediction model according to the historical temperature related data;
acquiring current temperature related data of a machine room, and taking the current temperature related data as data of a temperature prediction model to acquire a predicted temperature value;
and adjusting the set temperature of the air conditioner or switching on and switching off the air conditioner according to the predicted temperature value.
2. The machine room temperature control method according to claim 1, wherein the step of constructing a temperature prediction model according to the historical temperature-related data specifically comprises:
dividing the historical temperature related data into a training set, a verification set and a test set;
constructing a plurality of prediction models according to a training set and a gradient descent optimization algorithm;
verifying and screening the prediction model by adopting a verification set;
and testing the prediction model obtained by screening by adopting a test set, and selecting the prediction model with the best test result as the final temperature prediction model.
3. The machine room temperature regulating method according to claim 2, wherein the historical temperature-related data is divided into a training set, a verification set and a test set according to a ratio of 6:2: 2.
4. The machine room temperature regulating method according to claim 2, wherein the historical temperature-related data comprises temperature-related data including machine room environment data and equipment load data.
5. The machine room temperature control method according to claim 4, wherein the machine room environment data includes an ambient temperature, door access state data, door and window opening and closing state data, and an outdoor air temperature of the machine room;
the device load data includes heat generated by the load corresponding to the device at each time.
6. The machine room temperature regulation and control method according to claim 1, further comprising performing real-time accuracy monitoring on the temperature prediction model, counting the variation trend of the error of the temperature prediction model, and automatically training and updating the temperature prediction model when the error of the temperature prediction model exceeds a threshold value.
7. The machine room temperature control method according to claim 6, wherein the error confirmation method of the temperature prediction model comprises: and acquiring errors of the temperature prediction model in the past time period, and automatically starting automatic training and updating of the temperature prediction model if the average value of the errors for multiple times exceeds 0.2 ℃.
8. The machine room temperature regulation and control system applying the method according to any one of claims 1 to 7, characterized by comprising a main controller and a data acquisition unit connected with the main controller;
the data acquisition unit is used for acquiring current machine room environment data;
the main controller is internally provided with a temperature prediction model and a temperature prediction model construction algorithm for acquiring current equipment load data, and meanwhile, the model prediction algorithm is adopted to pre-judge the temperature change trend of the machine room in a future time period according to the current temperature related data, and the set temperature of the air conditioner is regulated or the machine is started or stopped according to the pre-judged result, so that the machine room is always in a constant temperature state.
9. The machine room temperature regulating and controlling system according to claim 8, wherein the data acquisition unit comprises a temperature sensor, an entrance guard state detection device, a door and window opening and closing state detection device; the temperature sensors are distributed in the machine room.
10. The computer room temperature regulating and controlling system of claim 8, further comprising a display unit, wherein the display module is connected to the main controller and is configured to display input and output parameters of the computer room temperature regulating and controlling information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010880104.1A CN112050397A (en) | 2020-08-27 | 2020-08-27 | Method and system for regulating and controlling temperature of machine room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010880104.1A CN112050397A (en) | 2020-08-27 | 2020-08-27 | Method and system for regulating and controlling temperature of machine room |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112050397A true CN112050397A (en) | 2020-12-08 |
Family
ID=73599524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010880104.1A Pending CN112050397A (en) | 2020-08-27 | 2020-08-27 | Method and system for regulating and controlling temperature of machine room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112050397A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112668773A (en) * | 2020-12-24 | 2021-04-16 | 北京百度网讯科技有限公司 | Method and device for predicting warehousing traffic and electronic equipment |
| CN112677730A (en) * | 2020-12-23 | 2021-04-20 | 泰州可以信息科技有限公司 | Vehicle-mounted air conditioner priority management system |
| CN112696803A (en) * | 2020-12-30 | 2021-04-23 | 江苏国洪送变电工程有限公司 | Intelligent environment monitoring method and system for electric power machine room and storage medium |
| CN112948230A (en) * | 2021-03-31 | 2021-06-11 | 中国建设银行股份有限公司 | Data processing method and device based on machine room confidential air conditioner |
| CN113327325A (en) * | 2021-08-02 | 2021-08-31 | 湖南雷诺科技发展有限公司 | 5G computer lab intelligent management system based on big data |
| CN113685962A (en) * | 2021-10-26 | 2021-11-23 | 南京群顶科技有限公司 | Machine room temperature efficient control method and system based on correlation analysis |
| CN113849023A (en) * | 2021-09-23 | 2021-12-28 | 国电南瑞科技股份有限公司 | Logic method for regulating and controlling environment in offshore wind power converter cabinet |
| CN114017904A (en) * | 2021-11-04 | 2022-02-08 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
| CN114065898A (en) * | 2021-12-21 | 2022-02-18 | 特斯联科技集团有限公司 | Air conditioner energy use measurement and control method and system based on decision-making technology |
| CN114216248A (en) * | 2022-02-22 | 2022-03-22 | 深圳雪芽创新科技有限公司 | Intelligent cooling method applied to data center machine room |
| CN114322260A (en) * | 2021-12-21 | 2022-04-12 | 上海美控智慧建筑有限公司 | Air conditioner automatic driving and model training and predicting method, device and equipment |
| CN114353273A (en) * | 2022-01-13 | 2022-04-15 | 北京小米移动软件有限公司 | Device control method, device, electronic device and storage medium |
| CN114379325A (en) * | 2022-02-22 | 2022-04-22 | 上海汽车集团股份有限公司 | Method for adjusting temperature of vehicle-mounted air conditioner and related device |
| CN114415756A (en) * | 2022-01-17 | 2022-04-29 | 厦门宇电自动化科技有限公司 | Temperature control method and system for nucleic acid detection reagent raw material based on deep reinforcement learning |
| WO2022124276A1 (en) * | 2020-12-07 | 2022-06-16 | ダイキン工業株式会社 | Indoor air quality prediction method and indoor air quality detection system |
| CN114777305A (en) * | 2022-04-11 | 2022-07-22 | 富联智能工坊(郑州)有限公司 | Regulating and controlling method and regulating and controlling model establishing method for air conditioning system and related device |
| CN114967804A (en) * | 2022-07-11 | 2022-08-30 | 国网江苏省电力有限公司泰州供电分公司 | Power distribution room temperature and humidity regulation and control method |
| CN114963458A (en) * | 2021-02-23 | 2022-08-30 | 海信集团控股股份有限公司 | Thermal comfort parameter prediction method and device |
| CN115032906A (en) * | 2022-05-30 | 2022-09-09 | 青岛海尔科技有限公司 | Digital twin room temperature prediction method, intelligent household equipment control method and device |
| CN115183419A (en) * | 2022-06-07 | 2022-10-14 | 清华大学 | Heating ventilation air conditioner load optimization control method based on simulation learning and reinforcement learning |
| CN115200171A (en) * | 2022-07-14 | 2022-10-18 | 东联信息技术有限公司 | Air conditioner control method and system based on time series prediction |
| CN115685941A (en) * | 2022-11-04 | 2023-02-03 | 中国电子工程设计院有限公司 | Machine room operation regulation and control method and device based on cabinet hot spot temperature prediction |
| CN115875809A (en) * | 2021-09-26 | 2023-03-31 | 中国移动通信集团浙江有限公司 | Energy-saving method and device for heat exchange equipment of machine room and computer readable storage medium |
| CN116193819A (en) * | 2023-01-19 | 2023-05-30 | 中国长江三峡集团有限公司 | Energy-saving control method, system and device for data center machine room and electronic equipment |
| CN116624971A (en) * | 2023-07-26 | 2023-08-22 | 北京麦斯特节能建筑工程有限公司 | Air conditioner monitoring system |
| CN116792890A (en) * | 2023-05-17 | 2023-09-22 | 浙江省邮电工程建设有限公司 | Intelligent control method and system for machine room air conditioner based on strategy distillation |
| CN116963482A (en) * | 2023-09-21 | 2023-10-27 | 广东云下汇金科技有限公司 | Intelligent energy-saving method and related equipment based on data center heating and ventilation system |
| WO2024016586A1 (en) * | 2022-07-18 | 2024-01-25 | 中国电信股份有限公司 | Machine room temperature control method and apparatus, and electronic device and storage medium |
| CN117606109A (en) * | 2024-01-22 | 2024-02-27 | 南京群顶科技股份有限公司 | Method and system for judging optimal temperature of air conditioner in machine room |
| CN117632664A (en) * | 2024-01-11 | 2024-03-01 | 深圳市柏特瑞电子有限公司 | Machine room equipment monitoring method and system based on automatic comparison |
| CN117632664B (en) * | 2024-01-11 | 2024-04-26 | 深圳市柏特瑞电子有限公司 | Machine room equipment monitoring method and system based on automatic comparison |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108344104A (en) * | 2017-12-27 | 2018-07-31 | 青岛海尔空调器有限总公司 | A kind of indoor temperature prediction technique and air conditioner for air conditioner |
| CN108518804A (en) * | 2018-03-21 | 2018-09-11 | 武汉物联远科技有限公司 | A kind of machine room humiture environmental forecasting method and system |
| JP2019203652A (en) * | 2018-05-24 | 2019-11-28 | サンデン・リテールシステム株式会社 | Shop air-conditioning system |
| CN110969306A (en) * | 2019-12-05 | 2020-04-07 | 国网辽宁省电力有限公司沈阳供电公司 | Power distribution low-voltage distribution area load prediction method and device based on deep learning |
-
2020
- 2020-08-27 CN CN202010880104.1A patent/CN112050397A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108344104A (en) * | 2017-12-27 | 2018-07-31 | 青岛海尔空调器有限总公司 | A kind of indoor temperature prediction technique and air conditioner for air conditioner |
| CN108518804A (en) * | 2018-03-21 | 2018-09-11 | 武汉物联远科技有限公司 | A kind of machine room humiture environmental forecasting method and system |
| JP2019203652A (en) * | 2018-05-24 | 2019-11-28 | サンデン・リテールシステム株式会社 | Shop air-conditioning system |
| CN110969306A (en) * | 2019-12-05 | 2020-04-07 | 国网辽宁省电力有限公司沈阳供电公司 | Power distribution low-voltage distribution area load prediction method and device based on deep learning |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022124276A1 (en) * | 2020-12-07 | 2022-06-16 | ダイキン工業株式会社 | Indoor air quality prediction method and indoor air quality detection system |
| CN112677730A (en) * | 2020-12-23 | 2021-04-20 | 泰州可以信息科技有限公司 | Vehicle-mounted air conditioner priority management system |
| CN112668773A (en) * | 2020-12-24 | 2021-04-16 | 北京百度网讯科技有限公司 | Method and device for predicting warehousing traffic and electronic equipment |
| CN112696803A (en) * | 2020-12-30 | 2021-04-23 | 江苏国洪送变电工程有限公司 | Intelligent environment monitoring method and system for electric power machine room and storage medium |
| CN114963458B (en) * | 2021-02-23 | 2023-09-05 | 海信集团控股股份有限公司 | Thermal comfort parameter prediction method and equipment thereof |
| CN114963458A (en) * | 2021-02-23 | 2022-08-30 | 海信集团控股股份有限公司 | Thermal comfort parameter prediction method and device |
| CN112948230A (en) * | 2021-03-31 | 2021-06-11 | 中国建设银行股份有限公司 | Data processing method and device based on machine room confidential air conditioner |
| CN113327325A (en) * | 2021-08-02 | 2021-08-31 | 湖南雷诺科技发展有限公司 | 5G computer lab intelligent management system based on big data |
| CN113849023A (en) * | 2021-09-23 | 2021-12-28 | 国电南瑞科技股份有限公司 | Logic method for regulating and controlling environment in offshore wind power converter cabinet |
| CN113849023B (en) * | 2021-09-23 | 2022-06-07 | 国电南瑞科技股份有限公司 | Logic method for regulating and controlling environment in offshore wind power converter cabinet |
| CN115875809A (en) * | 2021-09-26 | 2023-03-31 | 中国移动通信集团浙江有限公司 | Energy-saving method and device for heat exchange equipment of machine room and computer readable storage medium |
| CN113685962A (en) * | 2021-10-26 | 2021-11-23 | 南京群顶科技有限公司 | Machine room temperature efficient control method and system based on correlation analysis |
| CN114017904A (en) * | 2021-11-04 | 2022-02-08 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
| CN114017904B (en) * | 2021-11-04 | 2023-01-20 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
| CN114322260A (en) * | 2021-12-21 | 2022-04-12 | 上海美控智慧建筑有限公司 | Air conditioner automatic driving and model training and predicting method, device and equipment |
| CN114065898B (en) * | 2021-12-21 | 2022-05-17 | 特斯联科技集团有限公司 | Air conditioner energy use measurement and control method and system based on decision-making technology |
| CN114065898A (en) * | 2021-12-21 | 2022-02-18 | 特斯联科技集团有限公司 | Air conditioner energy use measurement and control method and system based on decision-making technology |
| CN114322260B (en) * | 2021-12-21 | 2023-09-08 | 上海美控智慧建筑有限公司 | Air conditioner automatic driving, model training and predicting method, device and equipment |
| CN114353273A (en) * | 2022-01-13 | 2022-04-15 | 北京小米移动软件有限公司 | Device control method, device, electronic device and storage medium |
| CN114415756A (en) * | 2022-01-17 | 2022-04-29 | 厦门宇电自动化科技有限公司 | Temperature control method and system for nucleic acid detection reagent raw material based on deep reinforcement learning |
| CN114415756B (en) * | 2022-01-17 | 2023-09-05 | 厦门宇电自动化科技有限公司 | Method and system for controlling temperature of nucleic acid detection reagent raw material based on deep reinforcement learning |
| CN114379325A (en) * | 2022-02-22 | 2022-04-22 | 上海汽车集团股份有限公司 | Method for adjusting temperature of vehicle-mounted air conditioner and related device |
| CN114216248A (en) * | 2022-02-22 | 2022-03-22 | 深圳雪芽创新科技有限公司 | Intelligent cooling method applied to data center machine room |
| CN114777305A (en) * | 2022-04-11 | 2022-07-22 | 富联智能工坊(郑州)有限公司 | Regulating and controlling method and regulating and controlling model establishing method for air conditioning system and related device |
| CN114777305B (en) * | 2022-04-11 | 2024-01-26 | 富联智能工坊(郑州)有限公司 | Regulation and control method of air conditioning system, regulation and control model building method and related devices |
| CN115032906A (en) * | 2022-05-30 | 2022-09-09 | 青岛海尔科技有限公司 | Digital twin room temperature prediction method, intelligent household equipment control method and device |
| CN115183419A (en) * | 2022-06-07 | 2022-10-14 | 清华大学 | Heating ventilation air conditioner load optimization control method based on simulation learning and reinforcement learning |
| CN114967804A (en) * | 2022-07-11 | 2022-08-30 | 国网江苏省电力有限公司泰州供电分公司 | Power distribution room temperature and humidity regulation and control method |
| CN115200171A (en) * | 2022-07-14 | 2022-10-18 | 东联信息技术有限公司 | Air conditioner control method and system based on time series prediction |
| WO2024016586A1 (en) * | 2022-07-18 | 2024-01-25 | 中国电信股份有限公司 | Machine room temperature control method and apparatus, and electronic device and storage medium |
| CN115685941B (en) * | 2022-11-04 | 2023-06-13 | 中国电子工程设计院有限公司 | Machine room operation regulation and control method and device based on machine cabinet hot spot temperature prediction |
| CN115685941A (en) * | 2022-11-04 | 2023-02-03 | 中国电子工程设计院有限公司 | Machine room operation regulation and control method and device based on cabinet hot spot temperature prediction |
| CN116193819A (en) * | 2023-01-19 | 2023-05-30 | 中国长江三峡集团有限公司 | Energy-saving control method, system and device for data center machine room and electronic equipment |
| CN116193819B (en) * | 2023-01-19 | 2024-02-02 | 中国长江三峡集团有限公司 | Energy-saving control method, system and device for data center machine room and electronic equipment |
| CN116792890A (en) * | 2023-05-17 | 2023-09-22 | 浙江省邮电工程建设有限公司 | Intelligent control method and system for machine room air conditioner based on strategy distillation |
| CN116624971A (en) * | 2023-07-26 | 2023-08-22 | 北京麦斯特节能建筑工程有限公司 | Air conditioner monitoring system |
| CN116963482A (en) * | 2023-09-21 | 2023-10-27 | 广东云下汇金科技有限公司 | Intelligent energy-saving method and related equipment based on data center heating and ventilation system |
| CN116963482B (en) * | 2023-09-21 | 2023-12-05 | 广东云下汇金科技有限公司 | Intelligent energy-saving method and related equipment based on data center heating and ventilation system |
| CN117632664A (en) * | 2024-01-11 | 2024-03-01 | 深圳市柏特瑞电子有限公司 | Machine room equipment monitoring method and system based on automatic comparison |
| CN117632664B (en) * | 2024-01-11 | 2024-04-26 | 深圳市柏特瑞电子有限公司 | Machine room equipment monitoring method and system based on automatic comparison |
| CN117606109A (en) * | 2024-01-22 | 2024-02-27 | 南京群顶科技股份有限公司 | Method and system for judging optimal temperature of air conditioner in machine room |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112050397A (en) | Method and system for regulating and controlling temperature of machine room | |
| Ding et al. | OCTOPUS: Deep reinforcement learning for holistic smart building control | |
| AU2018328266B2 (en) | Cooling unit energy optimization via smart supply air temperature setpoint control | |
| CN110298487B (en) | Indoor temperature prediction method for meeting personalized demands of users | |
| CN102301288B (en) | Systems and methods to control energy consumption efficiency | |
| CN111365828A (en) | Model prediction control method for realizing energy-saving temperature control of data center by combining machine learning | |
| CN106842914B (en) | Temperature control energy-saving processing method, device and system | |
| US20130204812A1 (en) | Method for computer-aided closed-loop and/or open-loop control of a technical system | |
| Ouf et al. | A simulation-based method to investigate occupant-centric controls | |
| CN114383299A (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| Pargfrieder et al. | An integrated control system for optimizing the energy consumption and user comfort in buildings | |
| Homod et al. | Deep clustering of cooperative multi-agent reinforcement learning to optimize multi chiller HVAC systems for smart buildings energy management | |
| Kontes et al. | Adaptive-fine tuning of building energy management systems using co-simulation | |
| Abdellatif et al. | A thermal control methodology based on a machine learning forecasting model for indoor heating | |
| CN116907036A (en) | Deep reinforcement learning water chilling unit control method based on cold load prediction | |
| CN115451534A (en) | Energy-saving method for machine room air conditioner based on reinforcement learning score scene | |
| Zhang et al. | Energy Efficient Operation Optimization of Building Air-conditioners via Simulator-assisted Asynchronous Reinforcement Learning | |
| Shi et al. | Adaptive Data-Driven Predictive Control as a Module in Building Control Hierarchy: A Case Study of Demand Response in Switzerland | |
| EP4361740A1 (en) | A computer-implemented method for configuring a controller for a technical system | |
| CN117329665B (en) | Air conditioner indoor linkage control method and system based on intelligent AI algorithm | |
| Saranya et al. | AI buildings: design of artificially intelligent buildings in the energy sector with an autonomous federated learning approach | |
| Yazdkhasti et al. | A model-based short-term load forecast methodology for aggregated power consumption of thermostatically controlled appliances in dsm | |
| US20240142921A1 (en) | Computer-implemented method for configuring a controller for a technical system | |
| AU2021103181A4 (en) | Air Conditioning Load Forecasting Method Based on Artificial Intelligence | |
| CN117950438A (en) | Dynamic temperature and humidity balance control method for return air unit for laboratory |
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 |