CN116266253A - Optimization control method, system and computer readable storage medium for air conditioner parameters - Google Patents
Optimization control method, system and computer readable storage medium for air conditioner parameters Download PDFInfo
- Publication number
- CN116266253A CN116266253A CN202111550594.XA CN202111550594A CN116266253A CN 116266253 A CN116266253 A CN 116266253A CN 202111550594 A CN202111550594 A CN 202111550594A CN 116266253 A CN116266253 A CN 116266253A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- parameters
- data
- machine room
- power
- 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
-
- 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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Fluid Mechanics (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present disclosure provides an optimal control method, system and computer readable storage medium for air conditioner parameters. The method comprises the following steps: collecting data of a water-cooling data center machine room, processing the data, transmitting the processed data to a database for recording and storing, and recording real-time CLF; monitoring real-time outdoor ambient temperature and IT device power; under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value, training a machine learning model by using the extracted historical data to predict the machine room CLF; the current operation parameters of the air conditioner are taken as initial values, control parameters of a differential evolution algorithm are determined, and the optimal adjustable parameters of the air conditioner are obtained through calculation of the differential evolution algorithm; inputting the optimal adjustable parameters of the air conditioner to a CFD simulation platform, and calculating a simulation result; and issuing the adjustable parameters of the air conditioner to the data center edge platform under the condition that the simulation result accords with the allowable range.
Description
Technical Field
The disclosure relates to the technical field of machine room energy consumption management, in particular to an optimization control method, an optimization control system and a computer readable storage medium for air conditioner parameters.
Background
The data center refrigerating system has high coupling performance of each sensor, and complex and changeable operation modes, and almost no possibility of realizing the adaptation of all scenes by only depending on the logic programming control of a single automatic control system. The manual tuning method is also difficult to respond to the change of internal or external factors of the system in time, and multi-parameter simultaneous tuning cannot be achieved. In the face of such problems, the introduction of artificial intelligence technology is a new energy-saving approach. The energy consumption optimization of the data center is a long tail process, the whole process is always energy-saving, but the machine room is locally hot, so that an alarm condition is realized, or the water cooling unit is in a better mode, but a large amount of refrigeration redundancy is still realized in the end machine room. How to reasonably regulate and control the operation parameters of the air conditioner at the tail end of the data center according to the equipment performance and the environment arrangement is a problem to be solved at present.
Disclosure of Invention
One technical problem solved by the present disclosure is: an optimal control method for air conditioner parameters is provided to realize the optimization of the air conditioner parameters.
According to one aspect of the present disclosure, there is provided an optimal control method of air conditioner parameters, including: collecting data of a water-cooling data center machine room, processing the data, transmitting the processed data to a database for recording and storing, and recording a real-time refrigeration load factor (CLF), wherein the data comprises the following components: indoor and outdoor sensor data, power system data, and air conditioning system data; monitoring real-time outdoor environment temperature and internet technology IT equipment power; extracting historical data from the database under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value, and training a machine learning model by utilizing the historical data to predict a machine room CLF; the current operation parameters of the air conditioner are taken as initial values, control parameters of a differential evolution algorithm are determined, the trained machine learning model is taken as an objective function, and the optimal adjustable parameters of the air conditioner are obtained through calculation of the differential evolution algorithm; inputting the optimal adjustable parameters of the air conditioner to a Computational Fluid Dynamics (CFD) simulation platform, and calculating a simulation result; and sending the optimal adjustable parameters of the air conditioner to a data center edge platform under the condition that the simulation result accords with the allowable range so as to adjust the air conditioner.
In some embodiments, the control parameters of the differential evolution algorithm include: population scale M, generation number T and dimension D; the step of calculating the optimal adjustable parameters of the air conditioner through the differential evolution algorithm comprises the following steps: initializing a population according to current operation parameters of the air conditioner; when the current generation number T is less than or equal to T, performing mutation and crossover operation on the population through the objective function and the corresponding constraint condition, and calculating CLF of individuals in the temporary population; and selecting the population individuals with the smallest CLF, and continuing to execute the mutation and crossover operation until the current generation number T is greater than T so as to obtain the optimal air conditioning adjustable parameters of the population individuals.
In some embodiments, the constraints are:
X＝[x 11 ,x 12 ,...x 1D ,...,x n1 ,x n2 ,...x nD ,θ] T
X best ＝argmin(f(X))
wherein f (X) is the objective function, n is the total number of air conditioners in the machine room, and X .j The j-th air conditioner in the machine room can adjust parameters, j is more than or equal to 1 and less than or equal to D, j and n are positive integers,
is x .j Minimum value to be met, < >>
Is x ·j The maximum value that needs to be satisfied, θ, is the observed variable.
In some embodiments, the step of training a machine learning model to predict machine room CLF using the historical data comprises: training a machine learning model by using the historical data to obtain a power predicted value of each air conditioner; summing the power predicted values of all the air conditioners in the machine room to obtain a sum of the power predicted values of all the air conditioners; and calculating the predicted machine room CLF according to the sum of the power predicted values of all the air conditioners.
In some embodiments, the indoor and outdoor sensor data comprises: the temperature and humidity of a cold and hot channel of the machine room, the outdoor environment temperature and the outdoor environment humidity; the power system data includes: cabinet power and air conditioning power; the air conditioning system data includes air conditioning operating parameters including: air supply temperature, return air temperature, real-time rotating speed of a fan and real-time opening of an air conditioner water valve.
In some embodiments, the optimization control method further includes: acquiring air conditioner coordinates, cabinet coordinates and temperature sensor coordinates of a cold and hot channel before training a machine learning model by using the historical data; and determining the corresponding relation between the cabinet and the air conditioner according to the air conditioner coordinates, the cabinet coordinates and the temperature sensor coordinates of the cold and hot channels.
According to another aspect of the present disclosure, there is provided an optimal control system of air conditioner parameters, including: the acquisition module is used for acquiring data of a water-cooling data center machine room, transmitting the processed data to a database for recording and storing, and recording a real-time refrigeration load factor CLF, wherein the data comprises: indoor and outdoor sensor data, power system data, and air conditioning system data; the monitoring module is used for monitoring the real-time outdoor environment temperature and the power of the IT equipment of the Internet technology; the training module is used for extracting historical data from the database and training a machine learning model by utilizing the historical data to predict a machine room CLF under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value; the computing module is used for taking the current operation parameters of the air conditioner as initial values, determining control parameters of a differential evolution algorithm, taking the trained machine learning model as an objective function, and computing by the differential evolution algorithm to obtain optimal adjustable parameters of the air conditioner; the simulation module is used for inputting the optimal adjustable parameters of the air conditioner to a Computational Fluid Dynamics (CFD) simulation platform and calculating a simulation result; and the issuing module is used for issuing the optimal adjustable parameters of the air conditioner to the data center edge platform to adjust the air conditioner under the condition that the simulation result accords with the allowable range.
In some embodiments, the control parameters of the differential evolution algorithm include: population scale M, generation number T and dimension D; the calculation module is used for initializing the population according to the current operation parameters of the air conditioner, when the current generation number T is less than or equal to T, the mutation and crossover operation is carried out on the population through the objective function and the corresponding constraint conditions, the CLF of the individuals in the temporary population is calculated, the individuals in the population with the smallest CLF are selected to continue to carry out the mutation and crossover operation until the current generation number T is less than or equal to T, and the optimal adjustable parameters of the air conditioner of the individuals in the population are obtained.
In some embodiments, the constraints are:
X＝[x 11 ,x 12 ,...x 1D ,...,x n1 ,x n2 ,...x nD ,θ] T
X best ＝arg min(f(X))
wherein f (X) is the objective function, n is the total number of air conditioners in the machine room, and X ·j The j-th air conditioner in the machine room can adjust parameters, j is more than or equal to 1 and less than or equal to D, j and n are positive integers,
is x ·j To meet the requirementsMinimum value (min.)>
Is x ·j The maximum value that needs to be satisfied, θ, is the observed variable.
In some embodiments, the training module is configured to train a machine learning model using the historical data to obtain a power prediction value for each air conditioner, sum the power prediction values for all air conditioners of the machine room to obtain a sum of the power prediction values for all air conditioners, and calculate a predicted machine room CLF from the sum of the power prediction values for all air conditioners.
In some embodiments, the indoor and outdoor sensor data comprises: the temperature and humidity of a cold and hot channel of the machine room, the outdoor environment temperature and the outdoor environment humidity; the power system data includes: cabinet power and air conditioning power; the air conditioning system data includes air conditioning operating parameters including: air supply temperature, return air temperature, real-time rotating speed of a fan and real-time opening of an air conditioner water valve.
In some embodiments, the optimization control system further comprises: the coordinate acquisition module is used for acquiring air conditioner coordinates, cabinet coordinates and temperature sensor coordinates of the cold and hot channels; and the corresponding relation determining module is used for determining the corresponding relation between the cabinet and the air conditioner according to the air conditioner coordinates, the cabinet coordinates and the temperature sensor coordinates of the cold and hot channels.
According to another aspect of the present disclosure, there is provided an optimal control system of air conditioner parameters, including: a memory; and a processor coupled to the memory, the processor configured to perform the method as described above based on instructions stored in the memory.
According to another aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method as described above.
In the method, data of a water-cooling data center room are collected, the data are transmitted to a database for recording and storage after being processed, and a real-time refrigeration load coefficient CLF is recorded, wherein the data comprise: indoor and outdoor sensor data, power system data, and air conditioning system data; monitoring real-time outdoor environment temperature and internet technology IT equipment power; extracting historical data from a database under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value, and training a machine learning model by utilizing the historical data to predict the machine room CLF; the current operation parameters of the air conditioner are taken as initial values, control parameters of a differential evolution algorithm are determined, a trained machine learning model is taken as an objective function, and optimal adjustable parameters of the air conditioner are obtained through calculation of the differential evolution algorithm; inputting the optimal adjustable parameters of the air conditioner to a CFD simulation platform, and calculating a simulation result; and under the condition that the simulation result accords with the allowable range, transmitting the optimal adjustable parameters of the air conditioner to the data center edge platform so as to adjust the air conditioner. The method can realize the optimization of the air conditioner parameters.
Other features of the present disclosure and its advantages will become apparent from the following detailed description of exemplary embodiments of the disclosure, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The disclosure may be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart illustrating a method of optimizing control of air conditioning parameters according to some embodiments of the present disclosure;
FIG. 2 is a flowchart illustrating an optimized control method of air conditioning parameters according to further embodiments of the present disclosure;
FIG. 3 is a flow chart illustrating a differential evolution algorithm according to some embodiments of the present disclosure;
FIG. 4 is a block diagram illustrating a configuration of an optimal control system for air conditioning parameters according to some embodiments of the present disclosure;
FIG. 5 is a block diagram illustrating a configuration of an optimal control system for air conditioning parameters according to further embodiments of the present disclosure;
FIG. 6 is a block diagram illustrating a configuration of an optimal control system for air conditioning parameters according to further embodiments of the present disclosure;
fig. 7 is a block diagram illustrating a configuration of an optimal control system of air conditioning parameters according to further embodiments of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
Fig. 1 is a flowchart illustrating an optimization control method of air conditioner parameters according to some embodiments of the present disclosure. As shown in fig. 1, the method includes steps S102 to S112.
In step S102, data of the water-cooled data center room is collected, the data is transferred to a database for recording and storing after being processed, and a real-time CLF (Cooling Load Factor, refrigeration load factor) is recorded, wherein the data includes: indoor and outdoor sensor data, power system data, and air conditioning system data.
Here, CLF is defined as a ratio of power consumption of refrigeration equipment to power consumption of IT equipment in a data center. For example, the CLF may be a ratio of refrigeration equipment power consumption to IT equipment power consumption in a data center. For example, the refrigeration equipment power consumption may be air conditioning power, and the IT equipment power consumption may be cabinet power.
In some embodiments, the indoor and outdoor sensor data comprises: temperature and humidity of a cold and hot channel of a machine room, outdoor environment temperature and outdoor environment humidity and the like. For example, the indoor and outdoor sensor data may also include chilled water supply temperature, etc.
In some embodiments, the power system data includes: cabinet power, air conditioning power, etc.
In some embodiments, the air conditioning system data includes air conditioning operating parameters. The air conditioner operating parameters may include: air supply temperature, return air temperature, real-time rotating speed of a fan, real-time opening of an air conditioner water valve and the like.
In step S104, real-time outdoor ambient temperature and IT (Internet Technology ) device power are monitored.
Here, in monitoring the outdoor environment temperature and the IT device power, the amount of change in the outdoor environment temperature and the amount of change in the IT device power may be monitored. For example, an increase or decrease in the outdoor ambient temperature may be monitored, and an increase or decrease in the IT device power may also be monitored.
In this disclosure, the amount of change may be a change value or may be a change percentage. Here, the change value=the value after the change-the value before the change. For example, the change value of the outdoor environment temperature is a difference between a value after the change of the outdoor environment temperature and a value before the change of the outdoor environment temperature. For another example, the value of the change in the IT device power is a difference between a value after the change in the IT device power and a value before the change in the IT device power.
Percent change= (value after change-value before change)/value before change. For example, the percentage change in the outdoor environment temperature is a difference between a value after the change in the outdoor environment temperature and a value before the change in the outdoor environment temperature/a value before the change in the outdoor environment temperature. For another example, the value of the change in the IT device power is a difference between the value after the change in the IT device power and the value before the change in the IT device power/the value before the change in the IT device power.
In step S106, in the case where the variation of the outdoor ambient temperature is greater than or equal to the first set value, or the variation of the IT equipment power is greater than or equal to the second set value, historical data is extracted from the database, and a machine learning model is trained using the historical data to predict the machine room CLF.
In this step, when the variation of the outdoor ambient temperature is greater than or equal to the first set value, or the variation of the IT device power is greater than or equal to the second set value, the generation and the issuing of the energy-saving strategy may be triggered. In the generation process of the energy-saving strategy, historical data is extracted from the database, and a machine learning model is trained by utilizing the historical data so as to predict the machine room CLF.
Here, the first setting value and the second setting value may be set according to actual needs. For example, the first setting value is 5 ℃, the second setting value is 20%, that is, when the variation (e.g., variation value) of the outdoor environment temperature is greater than or equal to 5 ℃ (e.g., the increase of the outdoor environment temperature is greater than or equal to 5 ℃, or the decrease of the outdoor environment temperature is greater than or equal to 5 ℃), or the variation (e.g., variation percentage) of the IT device power is greater than or equal to 20%, the generation and the issuing of the energy saving strategy can be triggered. In the process of generating the energy-saving strategy, historical data is firstly extracted from the database, a machine learning model is trained by using the historical data to predict the machine room CLF, and other steps are carried out later.
In some embodiments, the step of training the machine learning model to predict the machine room CLF using the historical data includes: training a machine learning model by using the historical data to obtain a power prediction value of each air conditioner; summing the power predicted values of all the air conditioners in the machine room to obtain a sum of the power predicted values of all the air conditioners; and calculating the predicted machine room CLF according to the sum of the power predicted values of all the air conditioners.
Here, a section of history data is extracted from the database, and a machine learning model is trained to predict the machine room CLF after preprocessing, taking a decision tree model as an example. The history data is the data collected and stored in step S102, and for example, feature selection may include: the outdoor dry bulb temperature (namely outdoor environment temperature), the outdoor relative humidity (namely outdoor environment humidity), the chilled water supply temperature (terminal air conditioner), the total cabinet IT power corresponding to the air conditioner, the air conditioner fan power (rotating speed) set value, the air conditioner water valve opening set value and the air conditioner air supply (return) temperature set value. The machine learning model is trained by using the historical data, so that the air conditioner power at the next moment can be directly predicted, and the IT power consumption is basically unchanged, so that the IT power consumption at the previous time period (or moment) can be used as the IT power consumption at the next moment, and then all the predicted values of the air conditioner power of the machine room are summed, and the sum of the predicted values of the power of all the air conditioners is divided by the IT power consumption to calculate the predicted machine room CLF value.
In step S108, the current operation parameters of the air conditioner are taken as initial values, control parameters of the differential evolution algorithm are determined, the trained machine learning model is taken as an objective function, and the optimal adjustable parameters of the air conditioner are obtained through calculation of the differential evolution algorithm.
For example, the control parameters of the differential evolution algorithm include: population size M, generation number T, and dimension D. For example, the control parameters of the differential evolution algorithm may be set according to actual needs, thereby determining the control parameters.
In some embodiments, the step of calculating the optimal air conditioning adjustable parameter by a differential evolution algorithm comprises: initializing a population according to current operation parameters of the air conditioner; when the current generation number T is less than or equal to T, performing mutation and crossover operation on the population through an objective function and corresponding constraint conditions, and calculating CLF of the temporary population individuals; and selecting the individuals with the smallest CLF population, and continuing to execute mutation and crossover operation until the current generation number T is greater than T so as to obtain the optimal adjustable parameters of the air conditioner of the individuals with the population.
In some embodiments, the constraints are:
wherein f (X) is an objective function, n is the total number of air conditioners in the machine room, and X .j The j-th air conditioner in the machine room can adjust parameters, j is more than or equal to 1 and less than or equal to D, j and n are positive integers, 
Is x .j Minimum value to be met, < >>
Is x .j The maximum value that needs to be satisfied, θ, is the observed variable. For example, θ is the outdoor dry bulb temperature, the outdoor relative humidity, the chilled water supply temperature (end air conditioner) or the total of the IT power of the air conditioner corresponding cabinet, etc.
In step S110, the optimal air conditioner adjustable parameters are input to the CFD (Computational Fluid Dynamics ) simulation platform, and the simulation result is calculated.
Here, the CFD simulation platform is a simulation platform known to those skilled in the art, and will not be described in detail herein.
In step S112, if the simulation result meets the allowable range, the optimal air conditioner adjustable parameter is issued to the data center edge platform to adjust the air conditioner.
In some embodiments, the allowed ranges may include a normal range of in-cabinet IT equipment operating temperatures and an ambient temperature range (e.g., an outdoor ambient temperature range). For example, the normal range of equipment operating temperatures and the range of ambient temperatures within the cabinet may be consulted by an expert.
For example, the normal range of in-cabinet IT equipment operating temperatures (i.e., room operating allowable temperatures) is 15 ℃ to 32 ℃. And discarding the current individual if the temperature in the simulation result of the simulation calculation exceeds the allowable temperature upper limit of the machine room. And if the temperature is in a healthy range (namely, in a range of the allowable temperature of the machine room operation), sending results of the simulated computer such as a machine room temperature cloud chart, an airflow chart and the like together with all the optimal control parameters of the air conditioner in the machine room to a data center edge platform. After the confirmation of the on-site operation and maintenance personnel, the system directly controls the terminal machine room to implement the strategy through an open air-conditioning protocol.
Thus, an optimized control method for air conditioning parameters according to some embodiments of the present disclosure is provided. The optimization control method comprises the following steps: collecting data of a water-cooling data center machine room, processing the data, transmitting the processed data to a database for recording and storing, and recording a real-time refrigeration load factor CLF, wherein the data comprises the following components: indoor and outdoor sensor data, power system data, and air conditioning system data; monitoring real-time outdoor environment temperature and internet technology IT equipment power; extracting historical data from a database under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value, and training a machine learning model by utilizing the historical data to predict the machine room CLF; the current operation parameters of the air conditioner are taken as initial values, control parameters of a differential evolution algorithm are determined, a trained machine learning model is taken as an objective function, and optimal adjustable parameters of the air conditioner are obtained through calculation of the differential evolution algorithm; inputting the optimal adjustable parameters of the air conditioner to a CFD simulation platform, and calculating a simulation result; and under the condition that the simulation result accords with the allowable range, transmitting the optimal adjustable parameters of the air conditioner to the data center edge platform so as to adjust the air conditioner. The method can realize the optimization of the air conditioner parameters.
In the prior art, the air conditioner parameter setting value is directly calculated and obtained according to a model, the input characteristics of the model are not comprehensively selected, and the output strategy cannot be ensured to be in a better level. In addition, the parameter strategy generated by the model is directly implemented, and hidden danger exists in the aspect of operation and maintenance safety of the machine room.
The method disclosed by the invention can reasonably regulate and control the operation parameters of the air conditioner at the tail end of the data center according to the equipment performance and the environmental arrangement on the premise of ensuring the operation safety of IT equipment. According to the method, the air conditioner can be timely adjusted when the load or the external temperature of the machine room changes, the machine room with unreasonable air conditioner cooling is adjusted, the refrigeration redundancy is reduced on the premise that the safety of the machine room is guaranteed, and finally the energy-saving purpose is achieved. The method can adapt to the data center machine room with different hardware facility conditions, and reduces the limitation of data.
In some embodiments, the optimization control method may further include: before training a machine learning model by using historical data, acquiring air conditioner coordinates, cabinet coordinates and temperature sensor coordinates of a cold and hot channel; and determining the corresponding relation between the cabinet and the air conditioner according to the air conditioner coordinates, the cabinet coordinates and the temperature sensor coordinates of the cold and hot channels. Thus, the corresponding relation between the cabinet and the precise air conditioner can be determined. To simplify the calculation, one cabinet may be made to correspond to one unique air conditioner.
Fig. 2 is a flowchart illustrating an optimization control method of air conditioner parameters according to further embodiments of the present disclosure.
Firstly, as shown in fig. 2, static and dynamic data are collected for the terminal machine room of the constructed water-cooled data center. The static and dynamic data includes the following:
indoor and outdoor sensor data: humiture of a cold and hot channel of a machine room and humiture of an outdoor environment;
power system data: cabinet power and air conditioning power;
precise air conditioning system data: the running state and the set value of the precise air conditioner comprise air supply temperature, real-time rotating speed of a fan, real-time opening of a water valve and the like.
And processing the acquired data, transmitting the processed data to a database for recording and storing, and recording the real-time CLF. And adjusting the set threshold value, and monitoring the outdoor environment temperature and the IT equipment power data. And triggering the energy-saving strategy to generate and issue under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value.
Next, as shown in fig. 2, coordinates of the terminal precise air conditioner, coordinates of the cabinet, and coordinates of the temperature sensor of the cold and hot channels are obtained, the euclidean distance is calculated by these coordinates, and then a corresponding relationship between the cabinet and the precise air conditioner is determined according to the euclidean distance, for example, in order to simplify the calculation, one cabinet corresponds to one unique air conditioner.
Next, as shown in fig. 2, the user selects an appropriate model from the model library based on the existing input information. For example, the model library may contain machine learning models such as multi-layer neural networks (e.g., DNN (Deep Neural Networks, deep neural network)), xgboost, lightGBM (Light Gradient Boosting Machine), and the like. And extracting a section of historical data from the database, and training a machine learning model to predict the machine room CLF after preprocessing, wherein a decision tree model is taken as an example. For example, feature selection includes: the temperature of the outdoor dry bulb, the outdoor relative humidity, the water supply temperature of chilled water (terminal air conditioner), the total power of the corresponding cabinet IT of the air conditioner, the set value of the power (rotating speed) of the fan of the air conditioner, the set value of the opening of the water valve of the air conditioner and the set value of the temperature of the air supply (return) air of the air conditioner. The model directly predicts the air conditioner power, and further sums all the predicted values of the air conditioner power of the machine room and calculates the predicted machine room CLF value. The parameter adjustment range can be confirmed according to the factory specification of the air conditioner.
Next, as shown in fig. 2, the current operation parameters of the precision air conditioner are taken as initial values. And calculating by a differential evolution algorithm to obtain the optimal adjustable parameters of the air conditioner.
Fig. 3 is a flow chart illustrating a differential evolution algorithm according to some embodiments of the present disclosure. The flow of the differential evolution algorithm is described in detail below in conjunction with fig. 3.
As shown in fig. 3, in step S302, determining differential evolution process control parameters includes: population size M, generation number T, dimension D.
In step S304, the population POP (0) is initialized according to the current value of the air conditioner operation parameter (e.g., fan rotation speed, water valve opening, etc. of the air conditioner).
In step S306, it is determined whether a termination condition is satisfied. If yes, the process advances to step S314; otherwise, the process advances to step S308.
For example, the termination condition is the generation number T > T.
In step S308, when the current generation number T is less than or equal to T, mutation and crossover operations are performed to generate a temporary population. Here, mutation and crossover operations are performed using known techniques to generate a temporary population.
In step S310, a temporary population fitness is calculated. For example, CLF of the temporary population is calculated.
In step S312, the individual with the smallest CLF is selected to perform CFD simulation to predict the heat dissipation effect of the machine room, for example, using the commercial data center modeling software 6SigmaDC. The optimizing target is the integral refrigeration efficiency (CLF) of the machine room, and the former model is taken as an objective function. In the parameter optimizing process, the constructed individual is the adjustable parameter variable of all air conditioners.
Objective function and constraint conditions:
X＝[x 11 ,x 12 ,...x 1D ,...,x n1 ,x n2 ,...x nD ,θ] T
X best ＝argmin(f(X))
here, argmin represents a variable value when the objective function f (X) is made to take a minimum value. "s.t." means subject to, limited to. X is x ·j The j-th adjustable setting parameter of a certain air conditioner in the machine room is as follows: the rated value of the rotating speed of the air conditioner fan, the minimum value of the rotating speed of the air conditioner fan, the maximum value of the opening degree of a water valve, the temperature of the air supply (return) and the like. θ represents the observed variables such as outdoor dry bulb temperature, outdoor relative humidity, chilled water supply temperature (end air conditioner), the total of IT power of the corresponding cabinet of the air conditioner, etc. f (X) represents the CLF prediction process.
In step S314, an optimal air conditioner operation parameter combination is output.
In step S316, the optimal individual is output.
Thus far, a differential evolution algorithm according to some embodiments of the present disclosure has been described.
Next, returning to fig. 2, the air conditioning control parameters contained in the outputted optimal individual are inputted into CFD simulation software. The normal range of equipment operating temperatures and the range of ambient temperatures within a given cabinet. For example, a given machine room operating allowable temperature is 15 ℃ to 32 ℃. If the temperature in the simulation calculation result exceeds the allowable temperature upper limit of the machine room, discarding the current individual, and re-executing the differential evolution algorithm. And if the temperature is in the allowable temperature range of the machine room, sending results such as a simulated computer machine room temperature cloud chart, an airflow chart and the like to a data center edge platform together with all air conditioner optimal control parameters in the machine room, and directly controlling the terminal machine room to implement a strategy by the system through an open air conditioner protocol after confirmation of on-site operation and maintenance personnel. For example, after checking the issued energy-saving strategy and simulation result, the on-site operation and maintenance expert can choose to confirm whether to execute or not, if confirm to execute, the strategy will directly control the air-conditioning parameters to the set values through the air-conditioning protocol.
Thus, there is provided an optimized control method of air conditioner parameters according to other embodiments of the present disclosure. In the method, data are collected, recorded and stored for a terminal machine room of a built water-cooling data center; utilizing the preprocessed characteristics to train a machine learning model to predict the machine room CLF; determining a normal range of equipment operating temperature and an environment temperature range in the cabinet; taking the current operation parameters of the precise air conditioner as initial values; determining control parameters of a differential evolution process, executing mutation and crossover operation, selecting an individual with the smallest CLF, and predicting the heat dissipation effect of a machine room through CFD simulation; and issuing and implementing the energy-saving strategy.
In some embodiments, data collection and monitoring may be performed simultaneously; the model library can provide machine learning model service; the model training and the database are interacted, the model prediction and the differential evolution algorithm optimizing are interacted, the parameter optimizing and the CFD modeling are interacted, and the final on-site strategy execution is confirmed. Modeling output is divided into two steps, wherein the first step is to output power of a single air conditioner, and the second step is to output integral refrigeration efficiency (CLF) of a machine room. And in the parameter optimizing process, the constructed individual is an adjustable parameter variable of all air conditioners, and a trained machine learning model is used as an objective function, namely, the optimizing target is the integral refrigeration efficiency (CLF) of the machine room.
Compared with the traditional non-artificial intelligent control method, the method disclosed by the invention can dynamically adapt to complex nonlinear environments. Not only master the service and temperature history of the machine room and the real-time state, but also adjust the air conditioner in time when the load or the external temperature of the machine room changes severely, and adjust the machine room with unreasonable air conditioner cooling, thereby finally realizing the purpose of energy conservation.
In the prior art, the operation parameters are often obtained directly by a model, and then the operation parameters are implemented to obtain the energy consumption index. The method directly models the energy consumption index, and the input source comprises indoor and outdoor data, a water cooling system and electric power data, so that the characteristic selection is comprehensive. The CLF can be used for evaluating the energy efficiency of a machine room, and the minimum CLF is selected in algorithm optimization, so that the purposes of saving energy, reducing consumption and reducing cooling cost can be achieved.
For the problem of differences in machine room environments and dynamic changes in a single machine room environment, the method of the present disclosure integrates machine learning models into a model library, e.g., at least 3 selectable models. The model library provided by the disclosure can adapt to data center machine rooms with different hardware facility conditions, reduces limitation from data, and improves practicability of a control method.
The method disclosed by the invention has the advantages that the heuristic algorithm is provided for parameter optimization based on the machine learning model, and the air conditioner parameter combination can be widely searched to jump out of local optimization.
The method can further comprise CFD simulation and operation and maintenance personnel on-site confirmation functions, the energy-saving strategy can be confirmed manually before being executed, the temperature of the machine room is ensured to be in a safe range by utilizing an artificial intelligence technology, and cooling power consumption is minimized.
In the method disclosed by the disclosure, the machine room energy consumption is predicted and perceived based on an artificial intelligence method, the operation parameters of the precise air conditioner are optimized, the CFD modeling visualization model is utilized to optimize the result, the on-site personnel confirms by one key, and the workload of operation and maintenance personnel is greatly reduced. The energy-saving method is high in safety and practicability.
Fig. 4 is a block diagram illustrating a configuration of an optimal control system of air conditioning parameters according to some embodiments of the present disclosure. As shown in fig. 4, the system includes an acquisition module 402, a monitoring module 404, a training module 406, a calculation module 408, a simulation module 410, and a delivery module 412.
The collection module 402 is configured to collect data of a water-cooled data center room, process the data, transmit the processed data to a database, record and store the processed data, and record a real-time CLF, where the data includes: indoor and outdoor sensor data, power system data, and air conditioning system data.
In some embodiments, the indoor and outdoor sensor data comprises: the temperature and humidity of the cold and hot channels of the machine room, the outdoor environment temperature and the outdoor environment humidity.
In some embodiments, the power system data includes: cabinet power and air conditioning power.
In some embodiments, the air conditioning system data includes air conditioning operating parameters including: air supply temperature, return air temperature, real-time rotating speed of a fan and real-time opening of an air conditioner water valve.
The monitoring module 404 is used to monitor real-time outdoor ambient temperature and IT equipment power.
The training module 406 is configured to extract historical data from the database and train the machine learning model to predict the machine room CLF using the historical data when the change in the outdoor ambient temperature is greater than or equal to a first set value or the change in the IT equipment power is greater than or equal to a second set value.
In some embodiments, the training module 406 may be configured to train a machine learning model using the historical data to obtain a power prediction value for each air conditioner, sum the power prediction values for all air conditioners of the machine room to obtain a sum of the power prediction values for all air conditioners, and calculate a predicted machine room CLF from the sum of the power prediction values for all air conditioners.
The calculation module 408 is configured to take a current operation parameter of the air conditioner as an initial value, determine a control parameter of the differential evolutionary algorithm, and calculate an optimal adjustable parameter of the air conditioner through the differential evolutionary algorithm by using the trained machine learning model as an objective function.
In some embodiments, the control parameters of the differential evolution algorithm include: population size M, generation number T, and dimension D.
In some embodiments, the calculation module 408 may be configured to initialize a population according to a current operating parameter of the air conditioner, perform mutation and crossover operations on the population through an objective function and corresponding constraint conditions when a current generation number T is less than or equal to T, calculate CLFs of individuals of the temporary population, select individuals of the population with the smallest CLF, and continue performing mutation and crossover operations until the current generation number T is greater than T, so as to obtain an optimal adjustable parameter of the air conditioner of the individuals of the population.
In some embodiments, the constraints are:
X＝[x 11 ,x 12 ,...x 1D ,...,x n1 ,x n2 ,...x nD ,θ] T
X best ＝arg min(f(X))
wherein f (X) is an objective function, n is the total number of air conditioners in the machine room, and X ·j The j-th air conditioner in the machine room can adjust parameters, j is more than or equal to 1 and less than or equal to D, j and n are positive integers,
is x ·j Minimum value to be met, < >>
Is x ·j The maximum value that needs to be satisfied, θ, is the observed variable.
The simulation module 410 is configured to input the optimal air conditioner adjustable parameter to the CFD simulation platform, and calculate a simulation result.
The issuing module 412 is configured to issue the optimal air conditioner adjustable parameter to the data center edge platform to adjust the air conditioner if the simulation result meets the allowable range.
Thus far, an optimal control system for air conditioning parameters according to some embodiments of the present disclosure is provided. The system can reasonably regulate and control the operation parameters of the air conditioner at the tail end of the data center according to the equipment performance and the environment arrangement on the premise of ensuring the operation safety of IT equipment.
Fig. 5 is a block diagram illustrating a configuration of an optimal control system of air conditioning parameters according to further embodiments of the present disclosure. As shown in fig. 5, the system includes an acquisition module 402, a monitoring module 404, a training module 406, a calculation module 408, a simulation module 410, and a delivery module 412.
In some embodiments, as shown in fig. 5, the system may further include a coordinate acquisition module 514. The coordinate acquisition module 514 is used for acquiring air conditioner coordinates, cabinet coordinates and temperature sensor coordinates of the cold and hot channels.
In some embodiments, as shown in fig. 5, the system may further include a correspondence determination module 516. The correspondence determining module 516 is configured to determine a correspondence between the cabinet and the air conditioner according to the air conditioner coordinates, the cabinet coordinates, and the temperature sensor coordinates of the cold and hot channels.
Fig. 6 is a block diagram illustrating a configuration of an optimal control system of air conditioning parameters according to further embodiments of the present disclosure. The optimization control system includes a memory 610 and a processor 620. Wherein:
The memory 610 may be a magnetic disk, flash memory, or any other non-volatile storage medium. The memory is used to store instructions in at least one of the corresponding embodiments of fig. 1-3.
In some embodiments, the optimization control system 700 may also include a memory 710 and a processor 720, as shown in FIG. 7. Processor 720 is coupled to memory 710 through BUS 730. The optimization control system 700 may also be coupled to external storage 750 via storage interface 740 to invoke external data, and may also be coupled to a network or another computer system (not shown) via network interface 760, not described in detail herein.
In this embodiment, the optimization of the air conditioning parameters may be achieved by storing the data instructions in the memory and processing the instructions by the processor.
In other embodiments, the present disclosure also provides a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method in at least one corresponding embodiment of fig. 1-3. It will be apparent to those skilled in the art that embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Thus far, the present disclosure has been described in detail. In order to avoid obscuring the concepts of the present disclosure, some details known in the art are not described. How to implement the solutions disclosed herein will be fully apparent to those skilled in the art from the above description.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (14)
1. An optimization control method of air conditioner parameters comprises the following steps:
Collecting data of a water-cooling data center machine room, processing the data, transmitting the processed data to a database for recording and storing, and recording a real-time refrigeration load factor (CLF), wherein the data comprises the following components: indoor and outdoor sensor data, power system data, and air conditioning system data;
monitoring real-time outdoor environment temperature and internet technology IT equipment power;
extracting historical data from the database under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value, and training a machine learning model by utilizing the historical data to predict a machine room CLF;
the current operation parameters of the air conditioner are taken as initial values, control parameters of a differential evolution algorithm are determined, the trained machine learning model is taken as an objective function, and the optimal adjustable parameters of the air conditioner are obtained through calculation of the differential evolution algorithm;
inputting the optimal adjustable parameters of the air conditioner to a Computational Fluid Dynamics (CFD) simulation platform, and calculating a simulation result; and
and under the condition that the simulation result accords with the allowable range, sending the optimal adjustable parameters of the air conditioner to a data center edge platform so as to adjust the air conditioner.
2. The optimal control method according to claim 1, wherein,
the control parameters of the differential evolution algorithm comprise: population scale M, generation number T and dimension D;
the step of calculating the optimal adjustable parameters of the air conditioner through the differential evolution algorithm comprises the following steps:
initializing a population according to current operation parameters of the air conditioner;
when the current generation number T is less than or equal to T, performing mutation and crossover operation on the population through the objective function and the corresponding constraint condition, and calculating CLF of individuals in the temporary population;
and selecting the population individuals with the smallest CLF, and continuing to execute the mutation and crossover operation until the current generation number T is greater than T so as to obtain the optimal air conditioning adjustable parameters of the population individuals.
3. The optimization control method according to claim 2, wherein the constraint condition is:
X＝[x 11 ,x 12 ,...x 1D ,...,x n1 ,x n2 ,...x nD ,θ] T
X best ＝argmin(f(X))
wherein f (X) is the objective function, n is the total number of air conditioners in the machine room, and X .j The j-th air conditioner in the machine room can adjust parameters, j is more than or equal to 1 and less than or equal to D, j and n are positive integers,
is x .j Minimum value to be met, < >>
Is x .j The maximum value that needs to be satisfied, θ, is the observed variable.
4. The optimal control method according to claim 1, wherein training a machine learning model to predict a machine room CLF using the history data comprises:
Training a machine learning model by using the historical data to obtain a power predicted value of each air conditioner;
summing the power predicted values of all the air conditioners in the machine room to obtain a sum of the power predicted values of all the air conditioners; and
and calculating the predicted machine room CLF according to the sum of the power predicted values of all the air conditioners.
5. The optimal control method according to claim 1, wherein,
the indoor and outdoor sensor data includes: the temperature and humidity of a cold and hot channel of the machine room, the outdoor environment temperature and the outdoor environment humidity;
the power system data includes: cabinet power and air conditioning power;
the air conditioning system data includes air conditioning operating parameters including: air supply temperature, return air temperature, real-time rotating speed of a fan and real-time opening of an air conditioner water valve.
6. The optimization control method according to claim 1, further comprising:
acquiring air conditioner coordinates, cabinet coordinates and temperature sensor coordinates of a cold and hot channel before training a machine learning model by using the historical data; and
and determining the corresponding relation between the cabinet and the air conditioner according to the air conditioner coordinates, the cabinet coordinates and the temperature sensor coordinates of the cold and hot channels.
7. An optimal control system for air conditioning parameters, comprising:
The acquisition module is used for acquiring data of the water-cooling data center machine room, transmitting the processed data to the database for recording and storing, and recording real-time CLF, wherein the data comprises: indoor and outdoor sensor data, power system data, and air conditioning system data;
the monitoring module is used for monitoring the real-time outdoor environment temperature and the IT equipment power;
the training module is used for extracting historical data from the database and training a machine learning model by utilizing the historical data to predict a machine room CLF under the condition that the variation of the outdoor environment temperature is larger than or equal to a first set value or the variation of the IT equipment power is larger than or equal to a second set value;
the computing module is used for taking the current operation parameters of the air conditioner as initial values, determining control parameters of a differential evolution algorithm, taking the trained machine learning model as an objective function, and computing by the differential evolution algorithm to obtain optimal adjustable parameters of the air conditioner;
the simulation module is used for inputting the optimal adjustable parameters of the air conditioner to the CFD simulation platform and calculating a simulation result; and
and the issuing module is used for issuing the optimal adjustable parameters of the air conditioner to the data center edge platform so as to adjust the air conditioner under the condition that the simulation result accords with the allowable range.
8. The optimal control system according to claim 7, wherein,
the control parameters of the differential evolution algorithm comprise: population scale M, generation number T and dimension D;
the calculation module is used for initializing the population according to the current operation parameters of the air conditioner, when the current generation number T is less than or equal to T, the mutation and crossover operation is carried out on the population through the objective function and the corresponding constraint conditions, the CLF of the individuals in the temporary population is calculated, the individuals in the population with the smallest CLF are selected to continue to carry out the mutation and crossover operation until the current generation number T is less than or equal to T, and the optimal adjustable parameters of the air conditioner of the individuals in the population are obtained.
9. The optimal control system of claim 8, wherein the constraints are:
X＝[x 11 ,x 12 ,...x 1D ,...,x n1 ,x n2 ,...x nD ,θ] T
X best ＝argmin(f(X))
wherein f (X) is the objective function, n is the total number of air conditioners in the machine room, and X ·j The j-th air conditioner in the machine room can adjust parameters, j is more than or equal to 1 and less than or equal to D, j and n are positive integers,
is x ·j Minimum value to be met, < >>
Is x ·j The maximum value that needs to be satisfied, θ, is the observed variable.
10. The optimal control system according to claim 7, wherein,
the training module is used for training a machine learning model by utilizing the historical data to obtain a power predicted value of each air conditioner, summing the power predicted values of all the air conditioners in the machine room to obtain a sum of the power predicted values of all the air conditioners, and calculating a predicted machine room CLF according to the sum of the power predicted values of all the air conditioners.
11. The optimal control system according to claim 7, wherein,
the indoor and outdoor sensor data includes: the temperature and humidity of a cold and hot channel of the machine room, the outdoor environment temperature and the outdoor environment humidity;
the power system data includes: cabinet power and air conditioning power;
the air conditioning system data includes air conditioning operating parameters including: air supply temperature, return air temperature, real-time rotating speed of a fan and real-time opening of an air conditioner water valve.
12. The optimal control system of claim 7, further comprising:
the coordinate acquisition module is used for acquiring air conditioner coordinates, cabinet coordinates and temperature sensor coordinates of the cold and hot channels; and
and the corresponding relation determining module is used for determining the corresponding relation between the cabinet and the air conditioner according to the air conditioner coordinates, the cabinet coordinates and the temperature sensor coordinates of the cold and hot channels.
13. An optimal control system for air conditioning parameters, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of any of claims 1-6 based on instructions stored in the memory.
14. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111550594.XA CN116266253A (en) | 2021-12-17 | 2021-12-17 | Optimization control method, system and computer readable storage medium for air conditioner parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111550594.XA CN116266253A (en) | 2021-12-17 | 2021-12-17 | Optimization control method, system and computer readable storage medium for air conditioner parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116266253A true CN116266253A (en) | 2023-06-20 |
Family
ID=86743584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111550594.XA Pending CN116266253A (en) | 2021-12-17 | 2021-12-17 | Optimization control method, system and computer readable storage medium for air conditioner parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116266253A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116382377A (en) * | 2023-05-12 | 2023-07-04 | 安徽中科新源半导体科技有限公司 | Multi-split control method and system for temperature control of base station cabinet |
| CN116989505A (en) * | 2023-09-27 | 2023-11-03 | 浙江德塔森特数据技术有限公司 | Control method and control device for detecting and supplementing data cabinet air conditioner refrigerants |
| 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 |
| CN117970986A (en) * | 2024-04-01 | 2024-05-03 | 广东热矩智能科技有限公司 | Temperature and humidity control method, device and medium of cold and hot system |
-
2021
- 2021-12-17 CN CN202111550594.XA patent/CN116266253A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116382377A (en) * | 2023-05-12 | 2023-07-04 | 安徽中科新源半导体科技有限公司 | Multi-split control method and system for temperature control of base station cabinet |
| CN116382377B (en) * | 2023-05-12 | 2023-10-24 | 安徽中科新源半导体科技有限公司 | Multi-split control method and system for temperature control of base station cabinet |
| CN116989505A (en) * | 2023-09-27 | 2023-11-03 | 浙江德塔森特数据技术有限公司 | Control method and control device for detecting and supplementing data cabinet air conditioner refrigerants |
| CN116989505B (en) * | 2023-09-27 | 2023-12-26 | 浙江德塔森特数据技术有限公司 | Control method and control device for detecting and supplementing data cabinet air conditioner refrigerants |
| 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 |
| CN117606109B (en) * | 2024-01-22 | 2024-05-24 | 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 |
| CN117970986A (en) * | 2024-04-01 | 2024-05-03 | 广东热矩智能科技有限公司 | Temperature and humidity control method, device and medium of cold and hot system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116266253A (en) | Optimization control method, system and computer readable storage medium for air conditioner parameters | |
| CN108386971B (en) | Energy-saving automatic control system of central air conditioner | |
| Lu et al. | Global optimization for overall HVAC systems––Part II problem solution and simulations | |
| CN110410942B (en) | Energy-saving optimization control method and system for cold and heat source machine room | |
| US5918200A (en) | State estimating apparatus | |
| CN102283283B (en) | Intelligentized superficial geothermal energy low-temperature grain storage system | |
| CN113739365A (en) | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium | |
| CN112415924A (en) | Energy-saving optimization method and system for air conditioning system | |
| CN114383299B (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| CN109028446A (en) | A kind of refrigerating plant room control method based on equipment overall performance model | |
| CN110220288A (en) | Central air-conditioning system intelligent optimized control method and device based on big data cloud platform | |
| CN112413762B (en) | Parameter optimization method and system for cooling water system of refrigerating room | |
| CN115776795A (en) | Data center air conditioning system diagnosis method and device | |
| CN113778215A (en) | Method for realizing data center PUE prediction and consumption reduction strategy based on big data | |
| CN115789957A (en) | Energy supply regulation and control method, device, equipment and storage medium | |
| Wang et al. | A decentralized swarm intelligence algorithm for global optimization of HVAC system | |
| CN101672510B (en) | Method for simulating and monitoring optimal operation of air-conditioning system | |
| CN111043720B (en) | Low-cost robustness adjustment strategy making method of refrigeration system under load uncertainty | |
| CN116562111A (en) | Data center energy saving method, device, system and storage medium | |
| Yu et al. | A Combined Neural and Genetic Algorithm Model for Data Center Temperature Control. | |
| CN103528294B (en) | A kind of efficiency processing method of refrigeration system and system | |
| CN112944599A (en) | Multi-parameter coupling control method and device of air conditioning system | |
| CN115398159A (en) | System with automatic cooler antisurge and method of operating a cooler to avoid future surge events | |
| Lin et al. | Optimizing for Large Time Delay Systems by BP Neural Network and Evolutionary Algorithm Improving. | |
| CN115978736B (en) | Self-adaptive prediction wind-water linkage control method for subway station air conditioning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |