A temperature control method and device for energy saving in data center

Abstract

The present invention belongs to the field of temperature control technology, and discloses a temperature control method and device for energy saving in a data center. The method determines at least one set of qualified temperature parameters for multiple distributed automation equipment in an SMT production line to meet the cooling capacity requirements in normal operation; multiple sets of temperature setting parameters for air conditioning systems and cooling water circulation systems in multiple distributed automation equipment are determined based on at least one set of qualified temperature parameters and the matching relationship between the setting parameter groups of the air conditioning system and the cooling water circulation system and the corresponding temperature parameter groups; the monitoring end periodically monitors the temperature parameter data of the data center in real time, and calculates the sum of the multiple sets of temperature setting parameters for the air conditioning system and the cooling water circulation system according to the neural network algorithm, performs screening, obtains the optimal value, and performs real-time regulation of the air conditioning system and the cooling water circulation system according to the optimal value. The present invention minimizes the total energy saving in the operation of distributed equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of temperature control, and in particular relates to a temperature control method and device for energy saving in a data center. Background Art

[0002] Data centers are a globally collaborative network of specific devices used to transmit, accelerate, display, calculate, and store data information on the Internet infrastructure. With the widespread application of data centers, artificial intelligence, network security, etc. have also emerged. Data centers usually consume a lot of electricity and generate a lot of heat. Cooling down the data center only through air conditioning systems cannot meet the real-time and effective energy-saving control requirements of the data center, and is not energy-saving and environmentally friendly.

[0003] Furthermore, the data center cooling system is responsible for providing cooling guarantee for IT equipment and environment in the data center. IT equipment (such as servers, storage, switches, routers, etc.) is in continuous operation, and the data center cooling system consumes a lot of energy. The data center cooling system generally has three cooling modes: mechanical compression cooling (only chiller cooling), partial natural cooling (cooling by chiller and outdoor natural cooling source at the same time) and full natural cooling (only outdoor natural cooling source cooling). In order to reduce the total energy consumption of the data center, the common energy-saving method in the industry is: under partial IT load, increase the chilled water supply temperature of the data center. Because by increasing the chilled water supply temperature, not only can the energy efficiency of the refrigeration equipment be improved when the chiller is running, and the power of the mechanical compression equipment can be reduced, but also the operation time of natural cooling or partial natural cooling can be increased to reduce the operation time of mechanical compression cooling, thereby reducing the total energy consumption of the data center. However, the energy-saving effect that can be achieved by increasing the chilled water temperature is limited and cannot meet higher energy-saving needs.

[0004] In addition, a data center refers to the infrastructure for IT equipment, including power supply, cooling, rack space, etc., among which IT equipment refers to servers, storage, switches, routers and other equipment. Generally, a data center cooling system has three cooling modes: mechanical compression cooling, partial natural cooling and full natural cooling. Mechanical compression cooling refers to the use of a compressor to compress the refrigerant to generate cooling; full natural cooling refers to a cooling method that does not use compressor compression cooling, but uses a natural cold source (such as the cold outside atmosphere) for heat exchange cooling; partial natural cooling refers to a cooling method that uses both compressor compression cooling and full natural cooling to cool at the same time.

[0005] In order to save electricity for data center operation and reduce electricity costs, the traditional temperature control method for data center energy saving is to increase the chilled water supply temperature under partial IT load. However, the energy saving effect brought by this method of increasing the chilled water supply temperature is limited, because after the temperature is raised to a certain level, if it is further increased, it will lead to the problem of not being able to meet the cooling needs of the data center.

[0006] Furthermore, industrial automation equipment is a general term for many automation products. Automation equipment automatically completes the tasks of the workflow according to the set instructions or programs without human intervention. Automation equipment is widely used in manufacturing, food production lines, and electronic and electrical packaging production lines. It also plays an important role in agriculture, logistics and other industries.

[0007] Most of the existing automation equipment adopts distributed technology. For example, the invention patent publication number CN 111045408 A, published on April 21, 2020, includes a host module, a data acquisition module, a control management module, a server, a data analysis module, a maintenance calculation module, a maintenance allocation module, a personnel calculation module and a registration and login module, as well as several hosts for controlling the automation equipment. How to achieve temperature control during the operation of these distributed devices to minimize the total energy saving and achieve the energy saving purpose is a problem that the existing technology needs to solve. Summary of the invention

[0008] In order to overcome the problems existing in the related art, the embodiments disclosed in the present invention provide a temperature control method and device for energy saving in a data center.

[0009] The technical solution is as follows: A temperature control method for energy saving in a data center, comprising the steps of:

[0010] S1, determining at least one set of qualified temperature parameters required for multiple distributed automation equipment in the SMT production line to meet the normal operating cooling capacity;

[0011] S2, determining multiple groups of temperature setting data of air conditioning systems and cooling water circulation systems in multiple distributed automation devices according to a matching relationship between at least one group of qualified temperature parameters, air conditioning system parameters and cooling water circulation system parameters;

[0012] S3, the monitoring end periodically monitors the temperature parameter data of the data center, calculates the sum of multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system according to the neural network algorithm, and screens them to obtain the optimal value, and adjusts the air-conditioning system and the cooling water circulation system in real time according to the optimal value.

[0013] In step S2, multiple groups of temperature setting data for air-conditioning systems and cooling water circulation systems in multiple distributed automation equipment are determined, including: the settings of the air-conditioning system meet the temperature and total air supply per unit time for normal operation of multiple distributed automation equipment in the SMT production line, and the settings of the cooling water circulation system meet the temperature and total water supply per unit time for normal operation of multiple distributed automation equipment in the SMT production line.

[0014] In step S3, the monitoring end periodically monitors the temperature parameter data of the data center, including the steps of:

[0015] S301, collecting the operating temperature of each distributed automation equipment to obtain the operating status of each distributed automation equipment;

[0016] S302, adjusting each branch sub-air conditioning system and cooling water circulation system that is approaching a critical warning during operation.

[0017] In step S3, the sum of multiple groups of temperature setting parameters of the air conditioning system and the cooling water circulation system is calculated according to the neural network algorithm, including the steps of:

[0018] Step 1: Initialize multiple groups of temperature setting parameter samples, randomly assign and classify them, initialize the temperature setting parameters of the total calculation sub-air conditioning system and the cooling water circulation system, initialize the control rate of the temperature control factor, measure multiple groups of temperature setting parameters as the state encoding of the initial temperature control factor, repeat D times, and generate D initial multiple groups of temperature setting parameters;

[0019] Step 2: Evaluate multiple groups of temperature setting parameters based on the supply rate, calculate the supply rate of each dimension in each category, and use the top C feature numbers with the highest supply rate as the selected feature dimensions, and also as the screening weight of the temperature control factor;

[0020] Step 3: Summarize each temperature control factor and compare the experienced states and screening weight values;

[0021] Step 4, adjusting the control rate and state of the temperature control factor;

[0022] Step 5, calculating the sum of the mean values ​​of the temperature setting parameters of the sub-air conditioning system and the cooling water circulation system;

[0023] Step 6: Determine whether the algorithm termination condition is met. If so, end; if not, go to step 2.

[0024] In step 1, the control rate of the temperature control factor is initialized, including: the temperature control factor is encoded based on a limited joint encoding mechanism, using a real number encoding scheme based on the sum calculation center, and the encoding space consists of three parts: SUP, CEP, and CPV. SUP represents the real number encoding string of the feature subspace, CEP represents the real number encoding string of the class center, and CPV represents the change degree of the class center;

[0025] According to the value range, the quantized values ​​are encoded into strings, and the encoding length is shortened under the constraints; multiple groups of temperature setting parameters for the air-conditioning system and the cooling water circulation system are initialized, and the data with the largest feature dimension SUP_maxnumber and the largest number of classes CEP_maxnumber are randomly selected and encoded to form the sub-air-conditioning system and the cooling water circulation system temperature setting parameters, and the multiple groups of temperature setting parameters of the initial air-conditioning system and the cooling water circulation system preset by D_size are iterated to complete the initialization of the multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system.

[0026] In step three, the experienced states and screening weight values ​​are compared, including: the supply rate expressed by the sum of the subspaces using the characteristic dimension;

[0027] One The subspace class centered on , for each subclass To measure, For the A center point, For the subspace classes; the supply rate measurement evaluation function is as follows:

[0028] ,

[0029] In the formula, For the The subspace contains The supply rate measurement evaluation value under the number of characteristic dimensions, is the data point, For the Class, The data point dimension, The center point dimension, is the number of feature dimensions contained in the subspace, For Class The data point on Dimension and center point The smaller the distance of dimension, the smaller the value is. Pair The supply is large, The larger the value of Pair The supply is small;

[0030] calculate All feature dimension pairs in the class The supply and expression of , the expression is:

[0031] ,

[0032] In the formula, For calculation All feature dimension pairs in the class supply and is the maximum value of the feature dimension, For Class The data point on Dimension and center point The distance of the dimension is divided by the range of the supply space;

[0033] By all The sum of the screening weights of each class represents the screening weight of all temperature control factors, and the expression is:

[0034] ,

[0035] In the formula, For all The sum of the screening weights of each category represents the screening weights of all temperature control factors. is the number of subspaces.

[0036] Further, the neural network algorithm includes: initializing the state of each temperature control factor in the multiple sets of temperature setting parameters and control rate ;

[0037] In the formula, For the The state function of the temperature control factor of each subspace, express The temperature setting parameters of the group The state of the temperature control factor in each subspace; For the The temperature control rate of each subspace is for The temperature setting parameters of the group The temperature control rate of each subspace;

[0038] Current iteration number , give the loop restriction conditions, is the total number of iterations; when When the temperature control factors are summed up, according to the minimum distance principle, All vectors in A total calculation center In the class represented by is a normalized classification dataset;

[0039] Calculate the matching value of each temperature control factor, match the temperature control factors, select the matching data, update the current optimal solution of each temperature control factor, update the current optimal solution of multiple sets of temperature setting parameters of the air-conditioning system and the cooling water circulation system, and update the control rate and state of the temperature control factor; after the cycle is completed, calculate the indicators of the total calculation effect and output the total calculation result.

[0040] Furthermore, the expression for updating the control rate and state of the temperature control factor is:

[0041] ,

[0042] ,

[0043] In the formula, To update the control rate value of the temperature control factor, is the temperature control factor, is the first regulation rate function, is the second regulation rate function, For the The subspace in The setting of the dimension controls the speed. For The setting control speed between dimensions, is the temperature control coefficient, is the rate control coefficient, is the state control coefficient, For the The subspace in The regulation rate of the dimension, For the The subspace in After updating under the control rate constraint of the dimension The subspace in Dimension classification data status, For the The subspace in The categorical data status of the dimension; The reference value is 1 to M;

[0044] The reference value range of multiple groups of temperature setting parameters of the air conditioning system and cooling water circulation system is: 0.5-1.0℃;

[0045] Maximum control rate during dynamic transformation , Maximum state Take the maximum value of each dimension; is the maximum state, For the The maximum state function of the classified data state in the subspace;

[0046] The reference values ​​of multiple temperature setting parameters of the air conditioning system and the cooling water circulation system are set according to the actual environment, and the matching definitions are as follows:

[0047] ,

[0048] In the formula, Set the matching degree of parameters for multiple temperature groups of air conditioning system and cooling water circulation system. is the input function, To match the upper limit quantity, For affinity, is the similarity, Set the parameters for multiple groups of temperatures of the production line air conditioning system and cooling water circulation system. The ratio of the number of similar multiple groups of temperature setting parameters to the multiple groups of temperature setting parameters of the total production line air-conditioning system and cooling water circulation system. The higher the ratio, the smaller the number of matches.

[0049] In step 5, the mean sum of the temperature setting parameters of the sub-air conditioning system and the cooling water circulation system is calculated, and the expression is:

[0050] ,

[0051] In the formula, For the The subspace contains The sum of the updated mean values ​​under the number of feature dimensions, For the subspace, For the feature dimensions, For the Dimensions, For the The subspace contains The sum of the means under the number of feature dimensions, For the Updated mean of the classification dataset in the group temperature setting parameters.

[0052] Another object of the present invention is to provide a temperature control device for energy saving in a data center, which is implemented by the temperature control method for energy saving in a data center, and the device includes:

[0053] A qualified temperature parameter determination module, used to determine at least one set of qualified temperature parameters for multiple distributed automation equipment in the SMT production line to meet the cooling capacity requirements in normal operation;

[0054] A module for determining multiple groups of temperature setting parameters, for determining multiple groups of temperature setting parameters for air conditioning systems and cooling water circulation systems in multiple distributed automation devices according to at least one group of qualified temperature parameters and a matching relationship between the setting parameter groups of the air conditioning systems and cooling water circulation systems and the corresponding temperature parameter groups;

[0055] The neural network algorithm calculation module is used for the monitoring end to periodically monitor the temperature parameter data of the data center in real time, and calculate the sum of multiple groups of temperature setting parameters of the air conditioning system and the cooling water circulation system according to the neural network algorithm, screen and obtain the optimal value, and perform real-time regulation of the air conditioning system and the cooling water circulation system according to the optimal value.

[0056] Combined with all the above technical solutions, the beneficial effects of the present invention are as follows: the present invention can intelligently control the cabinet temperature of the data center through the air conditioning system and the cooling water circulation system of the distributed equipment according to the monitored environmental parameters, thereby realizing real-time and effective energy-saving control of the data center, and controlling the entire energy consumption within a reasonable range, which is worthy of promotion. The present invention can reduce the energy consumption of the data center, meet higher energy-saving requirements, and minimize the total energy saving in the operation of distributed equipment by effectively controlling the temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the principles of the present disclosure;

[0058] Figure 1 is a flow chart of a temperature control method for energy saving in a data center provided by an embodiment of the present invention;

[0059] Figure 2 The present invention provides a flowchart for calculating the sum of multiple groups of temperature setting parameters of an air-conditioning system and a cooling water circulation system according to a neural network algorithm, screening them, and obtaining an optimal value;

[0060] Figure 3 is a schematic diagram of a temperature control device for energy saving in a data center provided by an embodiment of the present invention;

[0061] In the figure: 1. Qualified temperature parameter determination module; 2. Multiple groups of temperature setting parameter determination module; 3. Neural network algorithm calculation module. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific implementation disclosed below. In the present invention, the real-time control hardware mechanism involving the air-conditioning system and the cooling water circulation system can be seen in the prior art A temperature control method and system for energy saving in a data center (Announcement No. CN111665881A, announcement date 20200915). This application focuses on the analysis of the total energy consumption of distributed automation equipment to achieve energy saving purposes.

[0063] Examples, such as Figure 1 As shown, the temperature control method for energy saving in a data center provided by an embodiment of the present invention comprises the following steps:

[0064] S1, determining at least one set of qualified temperature parameters required for multiple distributed automation equipment in the SMT production line to meet the normal operating cooling capacity;

[0065] S2, determining multiple groups of temperature setting data of air conditioning systems and cooling water circulation systems in multiple distributed automation devices according to a matching relationship between at least one group of qualified temperature parameters, air conditioning system parameters and cooling water circulation system parameters;

[0066] S3, the monitoring end periodically monitors the temperature parameter data of the data center, calculates the sum of multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system according to the neural network algorithm, and screens them to obtain the optimal value, and adjusts the air-conditioning system and the cooling water circulation system in real time according to the optimal value.

[0067] In step S2 of the embodiment of the present invention, the setting of the air conditioning system meets the temperature and total air supply per unit time for normal operation of multiple distributed automation equipment in the SMT production line, and the setting of the cooling water circulation system meets the temperature and total water supply per unit time for normal operation of multiple distributed automation equipment in the SMT production line.

[0068] Embodiment 2, as a preferred embodiment, as Figure 2 As shown, in step S3 of the embodiment of the present invention, the sum of multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system is calculated according to the neural network algorithm, and the screening is performed to obtain the optimal value, including the steps of:

[0069] S301, collecting the operating temperature of each distributed automation equipment to obtain the operating status of each distributed automation equipment;

[0070] S302, adjusting each branch sub-air conditioning system and cooling water circulation system that is approaching a critical warning during operation.

[0071] Combined with the neural network algorithm, the sum of the temperature setting parameters of each branch sub-air conditioning system and cooling water circulation system is calculated; the sum is screened to obtain the optimal value, and then the temperature setting parameters of each branch sub-air conditioning system and cooling water circulation system are adjusted.

[0072] Embodiment 3, as a further preferred embodiment, in step S302, the neural network algorithm calculates the sum of the temperature setting parameters of each branch sub-air conditioning system and the cooling water circulation system, and screens the sum to obtain the optimal value, including the steps of:

[0073] Step 1: Initialize multiple groups of temperature setting parameter samples, randomly assign and classify them, initialize the temperature setting parameters of the total calculation sub-air conditioning system and the cooling water circulation system, initialize the control rate of the temperature control factor, measure multiple groups of temperature setting parameters as the state encoding of the initial temperature control factor, repeat D times, and generate D initial multiple groups of temperature setting parameters;

[0074] Step 2: Evaluate multiple groups of temperature setting parameters based on the supply rate, calculate the supply rate of each dimension in each category, and use the top C feature numbers with the highest supply rate as the selected feature dimensions, and also as the screening weight of the temperature control factor;

[0075] Step 3: Summarize each temperature control factor and compare the experienced states and screening weight values;

[0076] Step 4, adjusting the control rate and state of the temperature control factor;

[0077] Step 5, calculating the sum of the mean values ​​of the temperature setting parameters of the sub-air conditioning system and the cooling water circulation system;

[0078] Step 6: Determine whether the algorithm termination condition is met. If so, end; if not, go to step 2.

[0079] Embodiment 4, as a further preferred embodiment, in Embodiment 3, the temperature control factor encoding in step 1 adopts a joint encoding mechanism based on limitation; the general encoding method focuses on the class center point space, and adopts a real number encoding scheme based on the sum calculation center; the encoding space consists of three parts SUP, CEP, CPV, where SUP represents the real number encoding string of the feature subspace, CEP represents the real number encoding string of the class center, and CPV represents the change degree of the class center;

[0080] According to the value range, the quantized values ​​are encoded into strings, and the encoding length is shortened under the constraints; multiple groups of temperature setting parameters for the air-conditioning system and the cooling water circulation system are initialized, and the data with the largest feature dimension SUP_maxnumber and the largest number of classes CEP_maxnumber are randomly selected and encoded to form the sub-air-conditioning system and the cooling water circulation system temperature setting parameters, and the multiple groups of temperature setting parameters of the initial air-conditioning system and the cooling water circulation system preset by D_size are iterated to complete the initialization of the multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system.

[0081] In step three, the experienced states and screening weight values ​​are compared, including: the supply rate expressed by the sum of the subspaces using the characteristic dimension;

[0082] One The subspace class centered on , for each subclass To measure, For the A center point, For the subspace classes; the supply rate measurement evaluation function is as follows:

[0083] ,

[0084] In the formula, For the The subspace contains The supply rate measurement evaluation value under the number of characteristic dimensions, is the data point, For the Class, The data point dimension, The center point dimension, is the number of feature dimensions contained in the subspace, For Class The data point on Dimension and center point The smaller the distance of dimension, the smaller the value is. Pair The supply is large, The larger the value of Pair The supply is small;

[0085] calculate All feature dimension pairs in the class The supply and expression of , the expression is:

[0086] ,

[0087] wherein, is for calculating the supply sum of all feature dimension pairs in class , is the maximum value of the feature dimension, is the class the distance between the dimension of the data point on and the dimension of the center point divided by the supply space range;

[0088] All The screening weights of all temperature control factors are represented by the sum of the screening weights of

[0089] ,

[0090] wherein, is the sum of the screening weights of all which represents the screening weights of all temperature control factors, is the number of subspaces.

[0091] Example 5, another possible implementation manner, in step S302, the neural network algorithm includes:

[0092] Initialize the state of each temperature control factor in multiple groups of temperature setting parameters and the regulation rate ; wherein, is the state function of the th subspace temperature control factor, represents the state of the th subspace temperature control factor in the group of temperature setting parameters; is the th subspace temperature regulation rate, is the th subspace temperature regulation rate in the

[0093] While (the current iteration number f < F); / / Give the loop limit condition

[0094] For i = 1 to the number of temperature control factors D / / The total sum calculation starts;

[0095] According to the minimum distance principle, all vectors in are assigned to a total sum calculation center represented by the class , is a normalized classification dataset;

[0096] Calculate the matching value of each temperature control factor;

[0097] Calculate the number of matches and match the temperature control factors;

[0098] Perform matching selection on the data;

[0099] Update the current optimal solution of each temperature control factor;

[0100] Update the current optimal solutions for multiple sets of temperature setting parameters of the air conditioning system and cooling water circulation system;

[0101] Update the control rate and status of the temperature control factor;

[0102] End for

[0103] end while / / end of loop

[0104] Calculate the total and calculate the effect of the index;

[0105] Output the total calculation result;

[0106] Finish.

[0107] The expression of the control rate and state of the updated temperature control factor is:

[0108] ,

[0109] ,

[0110] In the formula, To update the control rate value of the temperature control factor, is the temperature control factor, is the first regulation rate function, is the second regulation rate function, For the The subspace in The setting of the dimension controls the speed. For The setting control speed between dimensions, is the temperature control coefficient, is the rate control coefficient, is the state control coefficient, For the The subspace in The regulation rate of the dimension, For the The subspace in The updated first The subspace in Dimension classification data status, For the The subspace in The categorical data status of the dimension;

[0111] The reference value range of multiple groups of temperature setting parameters of the air conditioning system and cooling water circulation system is: 0.5-1.0℃;

[0112] The reference value is 1 to M;

[0113] During dynamic transformation, the maximum control rate , Maximum state Take the maximum value of each dimension; is the maximum state, For the The maximum state function of the classified data state in the subspace;

[0114] The reference values ​​of multiple temperature setting parameters of the air conditioning system and the cooling water circulation system are set according to the actual environment, and the matching definitions are as follows:

[0115] ,

[0116] In the formula, Set the matching degree of parameters for multiple temperature groups of air conditioning system and cooling water circulation system. is the input function, To match the upper limit quantity, For affinity, is the similarity, Set the parameters for multiple groups of temperatures of the production line air conditioning system and cooling water circulation system. The ratio of the number of similar multiple groups of temperature setting parameters to the multiple groups of temperature setting parameters of the total production line air-conditioning system and cooling water circulation system. The higher the ratio, the smaller the number of matches.

[0117] Example 6, another possible implementation method, in step 5, the mean sum of the temperature setting parameters of the sub-air conditioning system and the cooling water circulation system is calculated, and the expression is:

[0118] ,

[0119] In the formula, For the The subspace contains The sum of the updated mean values ​​under the number of feature dimensions, For the subspace, For the feature dimensions, For the Dimensions, For the The subspace contains The sum of the means under the number of feature dimensions, For the Updated mean of the classification dataset in the group temperature setting parameters.

[0120] Embodiment 7, as Figure 3 As shown, an embodiment of the present invention provides a temperature control device for energy saving in a data center, comprising:

[0121] The qualified temperature parameter determination module 1 is used to determine at least one set of qualified temperature parameters for multiple distributed automation equipment in the SMT production line to meet the cooling capacity requirements in normal operation;

[0122] A module 2 for determining multiple groups of temperature setting parameters, for determining multiple groups of temperature setting parameters for air conditioning systems and cooling water circulation systems in multiple distributed automation devices according to at least one group of qualified temperature parameters and a matching relationship between the setting parameter groups of the air conditioning systems and cooling water circulation systems and the corresponding temperature parameter groups;

[0123] The neural network algorithm calculation module 3 is used for the monitoring end to periodically monitor the temperature parameter data of the data center in real time, and calculate the sum of multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system according to the neural network algorithm, screen them, and obtain the optimal value. According to the optimal value, the air-conditioning system and the cooling water circulation system are adjusted in real time.

[0124] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0125] Since the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present invention, their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0126] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment.

[0127] An embodiment of the present invention further provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0128] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0129] An embodiment of the present invention further provides an information data processing terminal, which, when executed on an electronic device, provides a user input interface to implement the steps in the above method embodiments. The information data processing terminal is not limited to mobile phones, computers, and switches.

[0130] An embodiment of the present invention further provides a server, which is used to provide a user input interface to implement the steps in the above method embodiments when executed on an electronic device.

[0131] An embodiment of the present invention provides a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0132] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0133] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the protection scope of the present invention.

Claims

1. A temperature control method for energy saving in a data center, characterized in that: The method comprises the steps of: S1, determining at least one set of qualified temperature parameters required for multiple distributed automation equipment in the SMT production line to meet the normal operating cooling capacity; S2, determining multiple groups of temperature setting data of air conditioning systems and cooling water circulation systems in multiple distributed automation devices according to a matching relationship between at least one group of qualified temperature parameters, air conditioning system parameters and cooling water circulation system parameters; S3, the monitoring end periodically monitors the temperature parameter data of the data center, calculates the sum of multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system according to the neural network algorithm, and screens and obtains the optimal value, and adjusts the air-conditioning system and the cooling water circulation system in real time according to the optimal value; In step S3, the sum of multiple groups of temperature setting parameters of the air conditioning system and the cooling water circulation system is calculated according to the neural network algorithm, including the steps of: Step 1: Initialize multiple groups of temperature setting parameter samples, randomly assign and classify them, initialize the temperature setting parameters of the total calculation sub-air conditioning system and the cooling water circulation system, initialize the control rate of the temperature control factor, measure multiple groups of temperature setting parameters as the state encoding of the initial temperature control factor, repeat D times, and generate D initial multiple groups of temperature setting parameters; Step 2: Evaluate multiple groups of temperature setting parameters based on the supply rate, calculate the supply rate of each dimension in each category, and use the top C feature numbers with the highest supply rate as the selected feature dimensions, and also as the screening weight of the temperature control factor; Step 3: Summarize each temperature control factor and compare the experienced states and screening weight values; Step 4, adjusting the control rate and state of the temperature control factor; Step 5, calculating the sum of the mean values ​​of the temperature setting parameters of the sub-air conditioning system and the cooling water circulation system; Step 6: Determine whether the algorithm termination condition is met, if so, terminate; If not, go to step 2; In step 1, the control rate of the temperature control factor is initialized, including: the temperature control factor is encoded based on a limited joint encoding mechanism, using a real number encoding scheme based on the sum calculation center, and the encoding space consists of three parts: SUP, CEP, and CPV. SUP represents the real number encoding string of the feature subspace, CEP represents the real number encoding string of the class center, and CPV represents the change degree of the class center; According to the value range, the quantized values ​​are encoded into strings, and the encoding length is shortened under the constraints; multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system are initialized, and the data with the largest feature dimension SUP_maxnumber and the largest number of classes CEP_maxnumber are randomly selected and encoded to form the temperature setting parameters of the sub-air-conditioning system and the cooling water circulation system, and the multiple groups of temperature setting parameters of the initial air-conditioning system and the cooling water circulation system preset by D_size are iterated to complete the initialization of multiple groups of temperature setting parameters of the air-conditioning system and the cooling water circulation system; In step 3, the experienced states and screening weight values ​​are compared, including: the supply rate expressed by the sum of the subspaces using the characteristic dimension, One The subspace class centered on , for each subclass To measure, For the A center point, For the subspace classes; the supply rate measurement evaluation function is: ， In the formula, For the The subspace contains The supply rate measurement evaluation value under the number of characteristic dimensions, is the data point, For the Class, The data point dimension, The center point dimension, is the number of feature dimensions contained in the subspace, For Class The data point on Dimension and center point The smaller the distance of dimension, the greater the dimension. Pair The supply is large, The larger the value of Pair The supply is small; calculate All feature dimension pairs in the class The supply and expression of , the expression is: ， In the formula, For calculation All feature dimension pairs in the class supply and is the maximum value of the feature dimension, For Class The data point on Dimension and center point The distance of the dimension is divided by the range of the supply space; By all The sum of the screening weights of each class represents the screening weights of all temperature control factors, and the expression is: ， In the formula, For all The sum of the screening weights of each category represents the screening weights of all temperature control factors. is the number of subspaces; Neural network algorithm, including: initializing the state of each temperature control factor in multiple sets of temperature setting parameters and control rate ; For the The state function of the temperature control factor of each subspace, express The temperature setting parameters of the group The state of the temperature control factor in each subspace; For the The temperature control rate of each subspace is for The temperature setting parameters of the group The temperature control rate of each subspace; Current iteration number , give the loop restriction conditions, is the total number of iterations; when When the temperature control factors are summed up, according to the minimum distance principle, All vectors in A total calculation center In the class represented by is a normalized classification dataset; Calculate the matching value of each temperature control factor, match the temperature control factors, select the matching data, update the current optimal solution of each temperature control factor, update the current optimal solution of multiple sets of temperature setting parameters of the air-conditioning system and the cooling water circulation system, and update the control rate and state of the temperature control factor; after the cycle is completed, calculate the indicators of the total calculation effect and output the total calculation result.

2. The temperature control method for data center energy saving according to claim 1, characterized in that: In step S2, multiple groups of temperature setting data for air-conditioning systems and cooling water circulation systems in multiple distributed automation equipment are determined, including: the settings of the air-conditioning system meet the temperature and total air supply per unit time for normal operation of multiple distributed automation equipment in the SMT production line, and the settings of the cooling water circulation system meet the temperature and total water supply per unit time for normal operation of multiple distributed automation equipment in the SMT production line.

3. The temperature control method for energy saving in a data center according to claim 1, characterized in that: In step S3, the monitoring end periodically monitors the temperature parameter data of the data center, including the steps of: S301, collecting the operating temperature of each distributed automation equipment to obtain the operating status of each distributed automation equipment; S302, adjusting each branch sub-air conditioning system and cooling water circulation system that is approaching a critical warning during operation.

4. The temperature control method for energy saving in a data center according to claim 1, characterized in that: The expression for updating the control rate and state of the temperature control factor is: ， ， In the formula, To update the control rate value of the temperature control factor, is the temperature control factor, is the first regulation rate function, is the second regulation rate function, For the Subspace in The setting of the dimension controls the speed. For The setting control speed between dimensions, is the temperature control coefficient, is the rate control coefficient, is the state control coefficient, For the The subspace in The regulation rate of the dimension, For the The subspace in After updating under the control rate constraint of the dimension The subspace in Dimension classification data status, For the The subspace in The categorical data status of the dimension; The reference value is 1 to M; The reference value range of multiple temperature setting parameters of the air conditioning system and cooling water circulation system is: 0.5-1.0℃; During dynamic transformation, the maximum control rate , Maximum state Take the maximum value of each dimension; is the maximum state, For the The maximum state function of the classified data state in the subspace; The reference values ​​of multiple temperature setting parameters for the air conditioning system and cooling water circulation system are set according to the actual environment, and the matching definitions are as follows: ， In the formula, Set the matching degree of parameters for multiple temperature groups of air conditioning system and cooling water circulation system. is the input function, To match the upper limit quantity, For affinity, is the similarity, Set the parameters for multiple groups of temperatures of the production line air conditioning system and cooling water circulation system. The ratio of the number of similar multiple groups of temperature setting parameters to the multiple groups of temperature setting parameters of the total production line air-conditioning system and cooling water circulation system. The higher the ratio, the smaller the number of matches.

5. The temperature control method for energy saving in a data center according to claim 1, characterized in that: In step 5, the mean sum of the temperature setting parameters of the sub-air conditioning system and the cooling water circulation system is calculated, and the expression is: ， In the formula, For the The subspace contains The sum of the updated mean values ​​under the number of feature dimensions, For the subspace, For the feature dimensions, For the Dimensions, For the The subspace contains The sum of the means under the number of feature dimensions, For the Updated mean of the classification dataset in the group temperature setting parameters.

6. A temperature control device for energy saving in a data center, characterized in that: The device is implemented by the temperature control method for energy saving in a data center according to any one of claims 1 to 5, and the device comprises: A qualified temperature parameter determination module (1) is used to determine at least one set of qualified temperature parameters for a plurality of distributed automation devices in an SMT production line to meet the cooling capacity requirements during normal operation; A multiple-group temperature setting parameter determination module (2) is used to determine multiple groups of temperature setting parameters for air conditioning systems and cooling water circulation systems in multiple distributed automation devices based on at least one group of qualified temperature parameters and a matching relationship between the setting parameter groups of the air conditioning systems and cooling water circulation systems and the corresponding temperature parameter groups; The neural network algorithm calculation module (3) is used for the monitoring end to periodically monitor the temperature parameter data of the data center in real time, and calculate the sum of multiple groups of temperature setting parameters of the air conditioning system and the cooling water circulation system according to the neural network algorithm, screen them, obtain the optimal value, and perform real-time regulation of the air conditioning system and the cooling water circulation system according to the optimal value.

Images