Data center refrigeration regulation and control method and system based on deep learning

Abstract

The invention discloses a data center refrigeration regulation and control method and system based on deep learning, and relates to the technical field of refrigeration regulation and control, and the method comprises the steps: obtaining a high-temperature condensation point through an infrared thermal imager; a high-temperature condensation type and a refrigeration time interval are obtained based on the positions of the ventilation opening and the high-temperature condensation point; establishing a deep learning model, and performing real-time refrigeration regulation and control on the data center based on the high-temperature condensation type of the real-time condensation point; the method is used for solving the problems that in an existing data center refrigeration regulation and control method, the refrigeration process cannot be regulated and controlled based on the position with the high temperature in the data center, and when the data center is refrigerated, targeted refrigeration is not conducted on the area with the high temperature, and the refrigeration efficiency is poor. And when the refrigerating system refrigerates the data center, more resources are consumed, and the refrigerating efficiency is low.

Description

Technical Field

[0001] The present invention relates to the field of refrigeration control technology, and specifically to a data center refrigeration control method and control system based on deep learning. Background Art

[0002] Data center cooling regulation refers to the effective control of data center ambient temperature and humidity through various technologies and strategies, ensuring that IT equipment operates in a suitable environment, thereby safeguarding the stability and reliability of the data center. Cooling regulation is not only related to the stable operation of equipment, but also directly affects energy efficiency and environmental sustainability. The working principles of data center cooling regulation include airflow management, cooling components, and monitoring and maintenance.

[0003] Existing methods for data center cooling control usually obtain pre-cooling capacity in the data center based on a pre-cooling model, and obtain the thermal power consumption and cooling load corresponding to all equipment in the data center by analyzing the load and energy consumption of all equipment in the data center, and then generate a control strategy in combination with the temperature of the measuring point to achieve cooling control. Although this improved method can improve the response speed of the cooling system and the accuracy of cooling capacity distribution, it is unable to control the cooling process based on the location with higher temperature in the data center during cooling. As a result, even if the accuracy of cooling capacity distribution is improved when cooling the data center, it still cannot solve the problem that the cooling system consumes more resources and has lower cooling efficiency when cooling the data center due to the lack of targeted cooling of higher temperature areas. For example, in the patent application with publication number CN120111852A, a data center cooling system with second-level control is disclosed. Control method and system, this solution is to obtain the optimal strategy feedback by establishing a pre-cooling model, a load energy consumption prediction model and a cooling load conversion model, and realize model iterative optimization, and improve the response speed, cooling capacity distribution accuracy and overall energy efficiency of the cooling system through task-aware pre-cooling, component-level precise control and closed-loop feedback optimization. Other improvements for data center cooling control are usually based on simulation machine simulation cooling solutions, and improvements in cooling regulation efficiency are improved by screening refrigerators. However, they still cannot solve the problem that the cooling process cannot be controlled based on the higher temperature locations in the data center during cooling, resulting in the cooling system consuming more resources and having lower cooling efficiency when cooling the data center due to the lack of targeted cooling of higher temperature areas. In view of this, it is necessary to improve the existing data center cooling control method. Summary of the Invention

[0004] The present invention aims to solve, at least to a certain extent, one of the technical problems in the prior art. By proposing a data center refrigeration control method and control system based on deep learning, it is used to solve the problem that the existing data center refrigeration control methods are unable to control the refrigeration process based on the locations with higher temperatures in the data center. As a result, when cooling the data center, the higher temperature areas are not cooled in a targeted manner, causing the refrigeration system to consume more resources and have lower cooling efficiency when cooling the data center.

[0005] To achieve the above objectives, in a first aspect, the present application provides a data center cooling control method based on deep learning, comprising the following steps: When all equipment in the data center is operating normally, use an infrared thermal imager to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center; obtain multiple ventilation holes in the data center, and use the cooling control analysis method based on the locations of the multiple ventilation holes and the locations of the high-temperature condensation points to obtain the optimal cooling time and optimal cooling outlet for each high-temperature condensation point; Screening all high-temperature condensation points based on the preferred refrigeration port of each high-temperature condensation point, and obtaining multiple high-temperature condensation types and refrigeration time intervals for each high-temperature condensation type based on the screening results; Establish a deep learning model; store the refrigeration control analysis method in the deep learning model, and learn the process of obtaining high-temperature condensation types from high-temperature condensation points in the deep learning model; Using infrared thermal imaging cameras to obtain high-temperature condensation points in the data center in real time, when new high-temperature condensation points appear, the locations of the new high-temperature condensation points are recorded in the deep learning model, and the high-temperature condensation type corresponding to the new high-temperature condensation points is obtained based on the deep learning model; The high-temperature condensation point recently obtained by the infrared thermal imager is recorded as the real-time condensation point, and the data center is refrigerated in real time based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point.

[0006] Furthermore, when all equipment in the data center is operating normally, an infrared thermal imager is used to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center, including: Establish a spatial rectangular coordinate system, which is recorded as the spatial analysis coordinate system, where the units of the X axis, Y axis and Z axis of the spatial analysis coordinate system are all meters; Based on the design drawings of the data center and the dimensional data of all equipment in the data center, a proportional model of the interior of the data center is established in the first quadrant of the spatial analysis coordinate system and recorded as a data three-dimensional model, where the dimensional data includes height data, width data, and length data.

[0007] Furthermore, when all equipment in the data center is operating normally, using an infrared thermal imager to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center also includes: When all equipment in the data center is operating normally, use an infrared thermal imager to measure the temperature inside the data center every kmin. After the temperature measurement, the location with the highest temperature in the data center is obtained and marked as a high-temperature location. All high-temperature locations detected by the infrared thermal imager in the data center during the day are obtained and marked in the data 3D model. Obtain the temperature corresponding to the high-temperature position in the temperature detection when all high-temperature positions are marked, and record it as the high-temperature temperature of the high-temperature position; record all high-temperature positions whose high-temperature temperatures are greater than the maximum temperature threshold as high-temperature condensation points, where the maximum temperature threshold is the maximum value of the normal temperature range in the data center.

[0008] Furthermore, obtaining multiple ventilation openings in the data center and using a cooling control analysis method based on the locations of the multiple ventilation openings and the location of the high-temperature condensation point to obtain the optimal cooling time and optimal cooling opening for each high-temperature condensation point includes: In the data 3D model: obtain multiple ventilation holes in the data center and record them as ventilation holes TF1 to ventilation holes TF c Based on the equipment usage specifications of the data center, obtain the maximum and minimum number of all ventilation openings that can be opened simultaneously, denoted as m and n, respectively, where m and n are positive integers less than or equal to c and greater than or equal to 1; Get all the corresponding opening conditions of the ventilation openings in the data center, from n, n+1, etc. to m, and record them as ventilation opening conditions TK1 to ventilation opening conditions TF. p ; The positions of all high-temperature condensation points are obtained and the optimal refrigeration time and optimal refrigeration port for each high-temperature condensation point are obtained using the refrigeration control analysis method.

[0009] Furthermore, the refrigeration control analysis method includes: For any high-temperature condensation point A: When the temperature of the high-temperature condensation point A detected by the infrared thermal imager is equal to the high temperature of the high-temperature condensation point A, the cooling system in the data center is started and based on the ventilation opening condition TK q Open the ventilation vents in the data center, use an infrared thermal imager to obtain the temperature at the location of the high-temperature condensation point A in real time, and start a timer, where q is a positive integer less than or equal to p and greater than or equal to 1; When the temperature of the high-temperature condensation point A in the infrared thermal imager is less than or equal to the maximum temperature threshold, the timer is turned off, and the time of the timer is recorded as the cooling time.

[0010] Furthermore, the refrigeration control analysis method also includes: When the temperature of high-temperature condensation point A is equal to the high temperature of high-temperature condensation point A, the cooling time corresponding to all ventilation opening conditions is obtained, and the minimum cooling time is recorded as the preferred cooling time of high-temperature condensation point A, and all open vents in the ventilation opening condition corresponding to the minimum cooling time are recorded as the preferred cooling vents of high-temperature condensation point A; Obtain the optimal cooling time and optimal cooling port corresponding to all high-temperature condensation points.

[0011] Furthermore, all high-temperature condensation points are screened based on the preferred cooling port of each high-temperature condensation point, and multiple high-temperature condensation types and cooling time intervals of each high-temperature condensation type are obtained based on the screening results, including: For any high-temperature condensation point A: the high-temperature condensation points other than the high-temperature condensation point A whose preferred cooling ports are exactly the same as the preferred cooling ports of the high-temperature condensation point A are recorded as the same type of condensation points as the high-temperature condensation point A, and the high-temperature condensation point A and the high-temperature condensation point A are recorded as the same high-temperature condensation type; Obtain multiple high-temperature condensation types corresponding to all high-temperature condensation points; for any high-temperature condensation type, record the closed interval consisting of the minimum and maximum values ​​in the preferred cooling time of all high-temperature condensation points corresponding to the high-temperature condensation type as the cooling time interval of the high-temperature condensation type.

[0012] Furthermore, the high-temperature condensation point recently acquired by the infrared thermal imager is recorded as a real-time condensation point. Based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point, real-time cooling control of the data center is performed, including: When the real-time condensation point is obtained, the cooling system in the data center is started, and the preferred cooling ports of all high-temperature condensation points corresponding to the high-temperature condensation type of the real-time condensation point are started; Keep the cooling system startup time and all open vents open longer than T1.

[0013] Furthermore, the high-temperature condensation point recently acquired by the infrared thermal imager is recorded as a real-time condensation point, and the real-time cooling control of the data center based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point also includes: When the startup time of the cooling system in the data center and the opening time of all opened vents are less than or equal to T2 and the temperature of the real-time condensation point is less than or equal to the maximum temperature threshold, the cooling system in the data center is shut down; When the startup time of the cooling system in the data center and the opening time of all opened vents are greater than T2 and the temperature of the real-time condensation point is greater than the maximum temperature threshold, a temperature control abnormality report is performed, where T1 is the minimum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point, and T2 is the maximum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point.

[0014] Secondly, this application also provides a data center refrigeration control system based on deep learning, including a high-temperature refrigeration analysis module, a high-temperature type screening module, and a deep real-time control module; The high-temperature cooling analysis module is used to detect the temperature of the data center using an infrared thermal imager when all equipment in the data center is operating normally, and obtain multiple high-temperature condensation points in the data center; obtain multiple ventilation holes in the data center, and use the cooling control analysis method based on the locations of the multiple ventilation holes and the locations of the high-temperature condensation points to obtain the optimal cooling time and optimal cooling outlet for each high-temperature condensation point; The high-temperature type screening module screens all high-temperature condensation points based on the preferred refrigeration port of each high-temperature condensation point, and obtains multiple high-temperature condensation types and the refrigeration time interval of each high-temperature condensation type based on the screening results; The deep real-time control module is used to establish a deep learning model; the refrigeration control analysis method is stored in the deep learning model, and the process of obtaining the high-temperature condensation type from the high-temperature condensation point is learned in the deep learning model; Using infrared thermal imaging cameras to obtain high-temperature condensation points in the data center in real time, when new high-temperature condensation points appear, the locations of the new high-temperature condensation points are recorded in the deep learning model, and the high-temperature condensation type corresponding to the new high-temperature condensation points is obtained based on the deep learning model; The high-temperature condensation point recently obtained by the infrared thermal imager is recorded as the real-time condensation point, and the data center is refrigerated in real time based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point.

[0015] The present invention has the following beneficial effects: The present invention first uses an infrared thermal imager to obtain multiple high-temperature condensation points in a data center; and uses a refrigeration control analysis method based on the locations of multiple ventilation openings and the locations of the high-temperature condensation points in the data center to obtain the optimal cooling time and optimal cooling port for each high-temperature condensation point. This has the advantage that by obtaining the high-temperature condensation points, several locations in the data center with higher temperatures during normal operation can be obtained. By obtaining the optimal cooling time and optimal cooling port for each high-temperature condensation point based on the locations of the ventilation openings and the locations of the high-temperature condensation points, the fastest cooling efficiency time for each high-temperature condensation point and the opening state of the ventilation openings in the refrigeration center when the cooling efficiency is the fastest can be obtained when the refrigeration system in the data center is operating. This allows for targeted cooling of higher-temperature areas in the control center based on the real-time condensation points during subsequent real-time refrigeration control, thereby reducing cooling resource consumption and improving cooling efficiency. The present application also screens all high-temperature condensation points based on the preferred cooling port of each high-temperature condensation point, and obtains multiple high-temperature condensation types and the cooling time interval of each high-temperature condensation type based on the screening results; finally, a deep learning model is established, and when there is a new high-temperature condensation point, the high-temperature condensation type corresponding to the new high-temperature condensation point is obtained based on the deep learning model; the high-temperature condensation point newly obtained by the infrared thermal imager is recorded as a real-time condensation point, and the data center is subjected to real-time cooling control based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point. The advantage of this is that by obtaining the cooling time interval, the cooling effect can be tested based on the cooling time interval after each cooling control, so that the staff can be notified in time to handle it when a cooling abnormality occurs; by establishing a deep learning model, the efficiency of obtaining the high-temperature condensation type corresponding to the high-temperature condensation point after obtaining the new high-temperature condensation point can be improved, and the corresponding cooling time interval and the preferred cooling port can be obtained in time for efficient cooling control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a functional block diagram of the system of the present invention; Figure 2 is a flow chart of the steps of the method of the present invention; Figure 3 is a flow chart of the steps of the refrigeration control analysis method of the present invention; Figure 4 Schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] Example 1, please refer to Figure 1 As shown, the present application provides a data center refrigeration control system based on deep learning, including a high-temperature refrigeration analysis module, a high-temperature type screening module, and a deep real-time control module; The high-temperature cooling analysis module is used to detect the temperature of the data center using an infrared thermal imager when all equipment in the data center is operating normally, and obtain multiple high-temperature condensation points in the data center; obtain multiple ventilation holes in the data center, and use the cooling control analysis method based on the locations of the multiple ventilation holes and the locations of the high-temperature condensation points to obtain the optimal cooling time and optimal cooling outlet for each high-temperature condensation point; The high-temperature refrigeration analysis module includes a high-temperature condensation point analysis unit, which is equipped with a high-temperature condensation point analysis strategy. The high-temperature condensation point analysis strategy includes: Establish a spatial rectangular coordinate system, which is recorded as the spatial analysis coordinate system, where the units of the X axis, Y axis and Z axis of the spatial analysis coordinate system are all meters; Based on the design drawings of the data center and the dimensional data of all equipment in the data center, a proportional model of the interior of the data center is established in the first quadrant of the spatial analysis coordinate system and recorded as a three-dimensional data model. The dimensional data includes height data, width data, and length data. When all equipment in the data center is operating normally, use an infrared thermal imager to measure the temperature inside the data center every kmin. After the temperature measurement, the location with the highest temperature in the data center is obtained and marked as a high-temperature location. All high-temperature locations detected by the infrared thermal imager in the data center during the day are obtained and marked in the data 3D model. In the specific implementation process, the value of k can be set according to the temperature detection interval allowed when the infrared thermal imager is actually used. To ensure more comprehensive temperature detection in the data center, the value of k should be as small as possible. In this embodiment, the value of k is set to 10; that is, the infrared thermal imager is used to detect the temperature inside the data center every 10 minutes. Obtain the temperature corresponding to the high-temperature location in the temperature detection when all high-temperature locations are marked, and record it as the high-temperature temperature of the high-temperature location; record all high-temperature locations with high-temperature temperatures greater than the maximum temperature threshold as high-temperature condensation points, where the maximum temperature threshold is the maximum value of the normal temperature range in the data center; In the specific implementation process, the maximum temperature threshold can be set according to the operating status of the equipment in the data center and the maximum temperature it can withstand. For example, during a data analysis, it was found that the ambient temperature of the servers in the data center should be maintained at 22°C to 26°C when they are operating normally. In this case, the maximum temperature threshold can be set to 26°C. In the data 3D model: obtain multiple ventilation holes in the data center and record them as ventilation holes TF1 to ventilation holes TF c Based on the equipment usage specifications of the data center, obtain the maximum and minimum number of all ventilation openings that can be opened simultaneously, denoted as m and n, respectively, where m and n are positive integers less than or equal to c and greater than or equal to 1; In the specific implementation process, by marking the position of the vents in the data three-dimensional model, it is convenient to process the data in the data three-dimensional model during subsequent analysis, so as to improve the efficiency of obtaining the optimal cooling vents; Get all the corresponding opening conditions of the ventilation openings in the data center, from n, n+1, etc. to m, and record them as ventilation opening conditions TK1 to ventilation opening conditions TF. p ; In a specific implementation process, for example, during a data analysis, if three ventilation vents in a data center are allowed to be opened at the same time, and four ventilation vents are allowed to be opened at the same time, then all situations corresponding to the situation when three ventilation vents in the data center are opened at the same time, and all situations corresponding to the situation when four ventilation vents are opened at the same time can be recorded as ventilation opening situations respectively; Obtain the locations of all high-temperature condensation points and use the refrigeration control analysis method to obtain the optimal refrigeration time and optimal refrigeration port for each high-temperature condensation point; Refrigeration control analysis methods include: See Figure 3 As shown, for any high-temperature condensation point A: when the temperature of the high-temperature condensation point A detected by the infrared thermal imager is equal to the high temperature of the high-temperature condensation point A, the cooling system in the data center is started and based on the ventilation opening condition TK q Open the ventilation vents in the data center, use an infrared thermal imager to obtain the temperature at the location of the high-temperature condensation point A in real time, and start a timer, where q is a positive integer less than or equal to p and greater than or equal to 1; When the temperature of the high-temperature condensation point A in the infrared thermal imager is less than or equal to the maximum temperature threshold, the timer is turned off and the time of the timer is recorded as the cooling time; When the temperature of high-temperature condensation point A is equal to the high temperature of high-temperature condensation point A, the cooling time corresponding to all ventilation opening conditions is obtained, and the minimum cooling time is recorded as the preferred cooling time of high-temperature condensation point A, and all open vents in the ventilation opening condition corresponding to the minimum cooling time are recorded as the preferred cooling vents of high-temperature condensation point A; In a specific implementation process, for example, in a data analysis, the number of ventilation opening conditions is 7. The time for the temperature of the high-temperature condensation point A to change from a high temperature to less than or equal to the maximum temperature threshold under the 7 ventilation opening conditions is 1 minute, 1.5 minutes, 1.1 minutes, 0.9 minutes, 1.2 minutes, 1.3 minutes and 2 minutes respectively. Then, all the opened vents in the ventilation opening condition corresponding to 0.9 minutes can be recorded as the preferred cooling vents of the high-temperature condensation point A, thereby obtaining the opening condition of the ventilator with the fastest cooling efficiency for the high-temperature condensation point A. Obtain the optimal cooling time and optimal cooling port corresponding to all high-temperature condensation points.

[0019] The high-temperature type screening module screens all high-temperature condensation points based on the preferred refrigeration port of each high-temperature condensation point, and obtains multiple high-temperature condensation types and the refrigeration time interval of each high-temperature condensation type based on the screening results; The high temperature type screening module includes a high temperature condensation point screening unit, which is equipped with a high temperature condensation point screening strategy. The high temperature condensation point screening strategy includes: For any high-temperature condensation point A: the high-temperature condensation points other than the high-temperature condensation point A whose preferred cooling ports are exactly the same as the preferred cooling ports of the high-temperature condensation point A are recorded as the same type of condensation points as the high-temperature condensation point A, and the high-temperature condensation point A and the high-temperature condensation point A are recorded as the same high-temperature condensation type; In the specific implementation process, the high-temperature condensation points are analyzed to obtain the high-temperature condensation type, which can be classified based on the preferred cooling port. This is conducive to directly obtaining the corresponding high-temperature condensation type through the high-temperature condensation points based on the deep learning model in subsequent analysis, so as to more quickly obtain the corresponding preferred cooling port, thereby improving cooling efficiency; Obtain multiple high-temperature condensation types corresponding to all high-temperature condensation points; for any high-temperature condensation type, record the closed interval formed by the minimum and maximum values ​​of the preferred cooling times of all high-temperature condensation points corresponding to the high-temperature condensation type as the cooling time interval of the high-temperature condensation type; During the specific implementation process, for example, the preferred cooling times for all high-temperature condensation points in a high-temperature condensation type are 1min, 1.5min, 1.1min and 2min respectively, then the cooling time interval can be set to [1min, 2min]. This means that when the vents are opened based on this high-temperature condensation type, it takes at least 2 minutes to reduce the temperature of all areas in the data center to below the maximum temperature threshold. Therefore, during actual cooling, if there are still areas with temperatures greater than the maximum temperature threshold 2 minutes after the vents are opened based on this high-temperature condensation type, it means that there is an abnormality in the cooling system and the cooling abnormality should be reported.

[0020] The deep real-time control module is used to establish a deep learning model; the refrigeration control analysis method is stored in the deep learning model, and the process of obtaining the high-temperature condensation type from the high-temperature condensation point is learned in the deep learning model; Using infrared thermal imaging cameras to obtain high-temperature condensation points in the data center in real time, when new high-temperature condensation points appear, the locations of the new high-temperature condensation points are recorded in the deep learning model, and the high-temperature condensation type corresponding to the new high-temperature condensation points is obtained based on the deep learning model; The most recently acquired high-temperature condensation point by the infrared thermal imager is recorded as the real-time condensation point. The data center is then refrigerated in real time based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point. The deep real-time control module includes a real-time cooling control unit, which is configured with a real-time cooling control strategy. The real-time cooling control strategy includes: When the real-time condensation point is obtained, the cooling system in the data center is started, and the preferred cooling ports of all high-temperature condensation points corresponding to the high-temperature condensation type of the real-time condensation point are started; Keep the cooling system startup time and all open vents open longer than T1. When the startup time of the cooling system in the data center and the opening time of all opened vents are less than or equal to T2 and the temperature of the real-time condensation point is less than or equal to the maximum temperature threshold, the cooling system in the data center is shut down; When the startup time of the cooling system in the data center and the opening time of all opened vents are greater than T2 and the temperature of the real-time condensation point is greater than the maximum temperature threshold, a temperature control abnormality report is performed, where T1 is the minimum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point, and T2 is the maximum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point.

[0021] Example 2, please refer to Figure 2 As shown, this application also provides a data center cooling control method based on deep learning, including the following steps: Step S1: When all equipment in the data center is operating normally, use an infrared thermal imager to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center; obtain multiple ventilation openings in the data center, and use a cooling control analysis method to obtain the optimal cooling time and optimal cooling opening for each high-temperature condensation point based on the locations of the multiple ventilation openings and the locations of the high-temperature condensation points; Step S1 includes: Step S101, establishing a spatial rectangular coordinate system, which is recorded as a spatial analysis coordinate system, wherein the units of the X axis, Y axis and Z axis of the spatial analysis coordinate system are all meters; Step S102: Based on the design drawings of the data center and the dimensional data of all equipment in the data center, a proportional model of the interior of the data center is created in the first quadrant of the spatial analysis coordinate system, and recorded as a three-dimensional data model, wherein the dimensional data includes height data, width data, and length data; Step S103: When all equipment in the data center is operating normally, use an infrared thermal imager to measure the temperature inside the data center every kmin. The location with the highest temperature in the data center after the temperature measurement is obtained and marked as a high-temperature location. All high-temperature locations detected by the infrared thermal imager in the data center during the day are obtained and marked in the data 3D model. Step S104: Obtain the temperature corresponding to the high-temperature location in the temperature detection when all high-temperature locations are marked, and record it as the high-temperature temperature of the high-temperature location; record all high-temperature locations whose high-temperature temperature is greater than a maximum temperature threshold as high-temperature condensation points, where the maximum temperature threshold is the maximum value of the normal temperature range in the data center; Step S105: In the data three-dimensional model, obtain multiple ventilation holes in the data center and record them as ventilation holes TF1 to ventilation holes TF c Based on the equipment usage specifications of the data center, obtain the maximum and minimum number of all ventilation openings that can be opened simultaneously, denoted as m and n, respectively, where m and n are positive integers less than or equal to c and greater than or equal to 1; Step S106: Obtain all corresponding opening conditions of the ventilation openings in the data center, from n, n+1, etc. to m, and record them as ventilation opening conditions TK1 to ventilation opening conditions TF. p ; Step S107: Obtain the positions of all high-temperature condensation points and use a refrigeration control analysis method to obtain the optimal refrigeration time and optimal refrigeration port for each high-temperature condensation point.

[0022] The cooling control analysis method includes: step S1071, for any high temperature condensation point A: when the temperature of the high temperature condensation point A detected by the infrared thermal imager is equal to the high temperature of the high temperature condensation point A, the cooling system in the data center is started and based on the ventilation opening condition TK q Open the ventilation vents in the data center, use an infrared thermal imager to obtain the temperature at the location of the high-temperature condensation point A in real time, and start a timer, where q is a positive integer less than or equal to p and greater than or equal to 1; Step S1072: When the temperature of the high-temperature condensation point A in the infrared thermal imager is less than or equal to the maximum temperature threshold, the timer is turned off, and the time of the timer is recorded as the cooling time; Step S1073: Obtain the cooling time corresponding to all ventilation opening conditions when the temperature of high-temperature condensation point A is equal to the high temperature of high-temperature condensation point A, record the minimum cooling time as the preferred cooling time for high-temperature condensation point A, and record all open vents in the ventilation opening condition corresponding to the minimum cooling time as the preferred cooling vents for high-temperature condensation point A; Step S1074, obtaining the preferred cooling time and the preferred cooling port corresponding to all high-temperature condensation points.

[0023] Step S2: screening all high-temperature condensation points based on the preferred refrigeration port of each high-temperature condensation point, and obtaining multiple high-temperature condensation types and refrigeration time intervals for each high-temperature condensation type based on the screening results; Step S2 includes: Step 201, for any high-temperature condensation point A: record the high-temperature condensation points other than the high-temperature condensation point A whose preferred cooling ports are identical to the preferred cooling ports of the high-temperature condensation point A as similar condensation points to the high-temperature condensation point A, and record the high-temperature condensation point A and the high-temperature condensation point A as the same high-temperature condensation type; Step 202: Obtain multiple high-temperature condensation types corresponding to all high-temperature condensation points. For any high-temperature condensation type, record the closed interval consisting of the minimum and maximum values ​​in the preferred cooling time of all high-temperature condensation points corresponding to the high-temperature condensation type as the cooling time interval of the high-temperature condensation type.

[0024] Step S3, establishing a deep learning model; storing the refrigeration control analysis method in the deep learning model, and learning the process of obtaining the high-temperature condensation type from the high-temperature condensation point in the deep learning model; Using infrared thermal imaging cameras to obtain high-temperature condensation points in the data center in real time, when new high-temperature condensation points appear, the locations of the new high-temperature condensation points are recorded in the deep learning model, and the high-temperature condensation type corresponding to the new high-temperature condensation points is obtained based on the deep learning model; The most recently acquired high-temperature condensation point by the infrared thermal imager is recorded as the real-time condensation point. The data center is then refrigerated in real time based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point. Step S3 includes: Step S301, when a real-time condensation point is obtained, starting the cooling system in the data center and starting the preferred cooling ports of all high-temperature condensation points corresponding to the high-temperature condensation type of the real-time condensation point; Step S302, maintaining the startup time of the cooling system in the data center and the opening time of all opened vents greater than T1; Step S303: When the startup time of the cooling system in the data center and the opening time of all opened vents are less than or equal to T2 and the temperature of the real-time condensation point is less than or equal to the maximum temperature threshold, shut down the cooling system in the data center; Step S304: When the startup time of the cooling system in the data center and the opening time of all opened vents are greater than T2 and the temperature of the real-time condensation point is greater than the maximum temperature threshold, a temperature control abnormality report is performed, where T1 is the minimum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point, and T2 is the maximum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point.

[0025] Example 3, please refer to Figure 4 As shown, Figure 4 A schematic diagram of an electronic device is provided, which may include a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps of a data center cooling control method based on deep learning are executed to implement the following functions: first, an infrared thermal imager is used to obtain multiple high-temperature condensation points in the data center; based on the locations of multiple ventilation openings and the locations of the high-temperature condensation points in the data center, a cooling control analysis method is used to obtain a preferred cooling time and a preferred cooling port for each high-temperature condensation point; then, all high-temperature condensation points are screened based on the preferred cooling port of each high-temperature condensation point, and multiple high-temperature condensation types and cooling time intervals for each high-temperature condensation type are obtained based on the screening results; finally, a deep learning model is established, and when a new high-temperature condensation point is found, the high-temperature condensation type corresponding to the new high-temperature condensation point is obtained based on the deep learning model; the high-temperature condensation point newly obtained by the infrared thermal imager is recorded as a real-time condensation point, and real-time cooling control of the data center is performed based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point.

[0026] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0027] Example 4. The present application also provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the data center cooling control method based on deep learning are executed to achieve the following functions: first, an infrared thermal imager is used to obtain multiple high-temperature condensation points in the data center; based on the locations of multiple ventilation holes and the locations of high-temperature condensation points in the data center, a cooling control analysis method is used to obtain the preferred cooling time and preferred cooling port for each high-temperature condensation point; then, all high-temperature condensation points are screened based on the preferred cooling port of each high-temperature condensation point, and multiple high-temperature condensation types and cooling time intervals for each high-temperature condensation type are obtained based on the screening results; finally, a deep learning model is established, and when there is a new high-temperature condensation point, the high-temperature condensation type corresponding to the new high-temperature condensation point is obtained based on the deep learning model; the high-temperature condensation point newly obtained by the infrared thermal imager is recorded as a real-time condensation point, and the data center is subjected to real-time cooling control based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point.

[0028] Through the description of the above embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the essence of the above technical solutions or the portion that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various embodiments or certain portions of the embodiments.

[0029] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0030] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data center cooling control method based on deep learning, characterized in that: The steps include: When all equipment in the data center is operating normally, use an infrared thermal imager to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center; obtain multiple ventilation holes in the data center, and use the cooling control analysis method based on the locations of the multiple ventilation holes and the locations of the high-temperature condensation points to obtain the optimal cooling time and optimal cooling outlet for each high-temperature condensation point; Screening all high-temperature condensation points based on the preferred refrigeration port of each high-temperature condensation point, and obtaining multiple high-temperature condensation types and refrigeration time intervals for each high-temperature condensation type based on the screening results; Building deep learning models; The refrigeration control analysis method is stored in the deep learning model, and the process of obtaining the high-temperature condensation type from the high-temperature condensation point is learned in the deep learning model; Using infrared thermal imaging cameras to obtain high-temperature condensation points in the data center in real time, when new high-temperature condensation points appear, the locations of the new high-temperature condensation points are recorded in the deep learning model, and the high-temperature condensation type corresponding to the new high-temperature condensation points is obtained based on the deep learning model; The high-temperature condensation point recently obtained by the infrared thermal imager is recorded as the real-time condensation point, and the data center is refrigerated in real time based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point.

2. The data center cooling control method based on deep learning according to claim 1 is characterized in that: When all equipment in the data center is operating normally, use an infrared thermal imager to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center, including: Establish a spatial rectangular coordinate system, which is recorded as the spatial analysis coordinate system, where the units of the X axis, Y axis and Z axis of the spatial analysis coordinate system are all meters; Based on the design drawings of the data center and the dimensional data of all equipment in the data center, a proportional model of the interior of the data center is established in the first quadrant of the spatial analysis coordinate system and recorded as a data three-dimensional model, where the dimensional data includes height data, width data, and length data.

3. The data center cooling control method based on deep learning according to claim 2 is characterized in that: When all equipment in the data center is operating normally, use an infrared thermal imager to detect the temperature of the data center and obtain multiple high-temperature condensation points in the data center, including: When all equipment in the data center is operating normally, use an infrared thermal imager to measure the temperature inside the data center every kmin. After the temperature measurement, the location with the highest temperature in the data center is obtained and marked as a high-temperature location. All high-temperature locations detected by the infrared thermal imager in the data center during the day are obtained and marked in the data 3D model. Obtain the temperature corresponding to the high-temperature position in the temperature detection when all high-temperature positions are marked, and record it as the high-temperature temperature of the high-temperature position; record all high-temperature positions whose high-temperature temperatures are greater than the maximum temperature threshold as high-temperature condensation points, where the maximum temperature threshold is the maximum value of the normal temperature range in the data center.

4. The data center cooling control method based on deep learning according to claim 3 is characterized in that: Obtaining multiple ventilation openings in the data center and using a cooling control analysis method based on the locations of the multiple ventilation openings and the locations of high-temperature condensation points to obtain an optimal cooling time and optimal cooling opening for each high-temperature condensation point includes: In the data 3D model: obtain multiple ventilation holes in the data center and record them as ventilation holes TF1 to ventilation holes TF c Based on the equipment usage specifications of the data center, obtain the maximum and minimum number of all ventilation openings that can be opened simultaneously, denoted as m and n, respectively, where m and n are positive integers less than or equal to c and greater than or equal to 1; Get all the corresponding opening conditions of the ventilation openings in the data center, from n, n+1, etc. to m, and record them as ventilation opening conditions TK1 to ventilation opening conditions TF. p ; The positions of all high-temperature condensation points are obtained and the optimal refrigeration time and optimal refrigeration port for each high-temperature condensation point are obtained using the refrigeration control analysis method.

5. The data center cooling control method based on deep learning according to claim 4 is characterized in that: Refrigeration control analysis methods include: For any high-temperature condensation point A: When the temperature of the high-temperature condensation point A detected by the infrared thermal imager is equal to the high temperature of the high-temperature condensation point A, the cooling system in the data center is started and based on the ventilation opening condition TK q Open the ventilation vents in the data center, use an infrared thermal imager to obtain the temperature at the location of the high-temperature condensation point A in real time, and start a timer, where q is a positive integer less than or equal to p and greater than or equal to 1; When the temperature of the high-temperature condensation point A in the infrared thermal imager is less than or equal to the maximum temperature threshold, the timer is turned off, and the time of the timer is recorded as the cooling time.

6. The data center cooling control method based on deep learning according to claim 5 is characterized in that: Refrigeration control analysis also includes: When the temperature of high-temperature condensation point A is equal to the high temperature of high-temperature condensation point A, the cooling time corresponding to all ventilation opening conditions is obtained, and the minimum cooling time is recorded as the preferred cooling time of high-temperature condensation point A, and all open vents in the ventilation opening condition corresponding to the minimum cooling time are recorded as the preferred cooling vents of high-temperature condensation point A; Obtain the optimal cooling time and optimal cooling port corresponding to all high-temperature condensation points.

7. The data center cooling control method based on deep learning according to claim 6 is characterized in that: All high-temperature condensation points are screened based on the preferred cooling port of each high-temperature condensation point, and multiple high-temperature condensation types and cooling time intervals of each high-temperature condensation type are obtained based on the screening results, including: For any high-temperature condensation point A: the high-temperature condensation points other than the high-temperature condensation point A whose preferred cooling ports are exactly the same as the preferred cooling ports of the high-temperature condensation point A are recorded as the same type of condensation points as the high-temperature condensation point A, and the high-temperature condensation point A and the high-temperature condensation point A are recorded as the same high-temperature condensation type; Obtain multiple high-temperature condensation types corresponding to all high-temperature condensation points; for any high-temperature condensation type, record the closed interval consisting of the minimum and maximum values ​​in the preferred cooling time of all high-temperature condensation points corresponding to the high-temperature condensation type as the cooling time interval of the high-temperature condensation type.

8. The data center cooling control method based on deep learning according to claim 7 is characterized in that: The most recently acquired high-temperature condensation point by the infrared thermal imager is recorded as the real-time condensation point. Based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point, the data center is subjected to real-time cooling control, including: When the real-time condensation point is obtained, the cooling system in the data center is started, and the preferred cooling ports of all high-temperature condensation points corresponding to the high-temperature condensation type of the real-time condensation point are started; Keep the cooling system startup time and all open vents open longer than T1.

9. The data center cooling control method based on deep learning according to claim 8, characterized in that: The high-temperature condensation point recently acquired by the infrared thermal imager is recorded as the real-time condensation point. Based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point, the real-time cooling control of the data center also includes: When the startup time of the cooling system in the data center and the opening time of all opened vents are less than or equal to T2 and the temperature of the real-time condensation point is less than or equal to the maximum temperature threshold, the cooling system in the data center is shut down; When the startup time of the cooling system in the data center and the opening time of all opened vents are greater than T2 and the temperature of the real-time condensation point is greater than the maximum temperature threshold, a temperature control abnormality report is performed, where T1 is the minimum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point, and T2 is the maximum value in the cooling time interval of the high-temperature condensation type of the real-time condensation point.

10. A data center refrigeration control system based on deep learning, used to implement the data center refrigeration control method based on deep learning according to any one of claims 1 to 9, characterized in that: Including high temperature refrigeration analysis module, high temperature type screening module and deep real-time control module; The high-temperature cooling analysis module is used to detect the temperature of the data center using an infrared thermal imager when all equipment in the data center is operating normally, and obtain multiple high-temperature condensation points in the data center; obtain multiple ventilation holes in the data center, and use the cooling control analysis method based on the locations of the multiple ventilation holes and the locations of the high-temperature condensation points to obtain the optimal cooling time and optimal cooling outlet for each high-temperature condensation point; The high-temperature type screening module screens all high-temperature condensation points based on the preferred refrigeration port of each high-temperature condensation point, and obtains multiple high-temperature condensation types and the refrigeration time interval of each high-temperature condensation type based on the screening results; The deep real-time control module is used to build deep learning models; The refrigeration control analysis method is stored in the deep learning model, and the process of obtaining the high-temperature condensation type from the high-temperature condensation point is learned in the deep learning model; Using infrared thermal imaging cameras to obtain high-temperature condensation points in the data center in real time, when new high-temperature condensation points appear, the locations of the new high-temperature condensation points are recorded in the deep learning model, and the high-temperature condensation type corresponding to the new high-temperature condensation points is obtained based on the deep learning model; The high-temperature condensation point recently obtained by the infrared thermal imager is recorded as the real-time condensation point, and the data center is refrigerated in real time based on the cooling time interval corresponding to the high-temperature condensation type of the real-time condensation point.

Images