Automatic temperature control method and system for data center power supply and electronic equipment

By using stress and resonance detectors in the immersed server system to detect the degree of server expansion, combined with parameter adjustment of the coolant delivery components, the problems of complexity and high cost of data center heat dissipation are solved, and precise temperature control and energy consumption optimization are achieved.

CN120669784APending Publication Date: 2025-09-19SHENZHEN TAOP IND CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510816152.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-18
Publication Date
2025-09-19

AI Technical Summary

Technical Problem

Existing data centers are not intelligent enough, especially when it comes to the cooling needs of high-performance devices. Liquid cooling technology has problems of complexity and high cost.

Method used

By using stress detectors and resonance detectors in the immersion server system to detect the expansion degree of the server, combined with the working parameters of the coolant delivery component, precise adjustment of the coolant temperature and flow rate can be achieved, avoiding the deployment of a large number of temperature sensors.

Benefits of technology

It achieves precise temperature control and energy consumption optimization of servers, reduces costs and failure rates, and improves the intelligence level of data centers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120669784A_ABST
    Figure CN120669784A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of server cooling, and provides an automatic temperature control method and system for a data center power supply and electronic equipment. The data center power supply automatic temperature control method comprises the following steps: obtaining the expansion degree of a server; determining the real-time temperature of the server based on the expansion degree of the server; based on the real-time temperature of the server, working parameters of the cooling liquid conveying assembly are determined; and according to the working parameters of the cooling liquid conveying assembly, working of the cooling liquid conveying assembly is controlled so as to adjust the temperature and the flowing speed of the cooling liquid. According to the automatic temperature control method for the data center power supply, the physical characteristic of thermal expansion of the server is utilized to indirectly measure the temperature, and the real-time temperature of the server can be detected without deploying a large number of temperature sensors in a complex liquid cooling environment. Meanwhile, the temperature change is reflected through the expansion degree, then the working parameters of the cooling liquid conveying assembly are adjusted in real time, precise temperature control and energy consumption optimization are achieved, and the intelligent degree of the data center is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of server cooling technology, and in particular to a method, system, and electronic equipment for automatic temperature control of a data center power supply. Background Art

[0002] Data centers are primarily composed of servers, power supplies, and other components. Servers are specialized computers or systems that provide services to other devices or programs (clients), typically featuring high performance, high stability, and long-term operational capabilities. With the rise of big data, cloud computing, and artificial intelligence, the computing power demands of data centers and computing servers are increasing, and the power consumption of high-performance devices is also rising, with a single chip reaching over 400W. To meet these cooling requirements, liquid cooling technology is currently used to dissipate heat from servers, such as immersion server systems, which immerse the server and power supply in coolant to enhance cooling.

[0003] The intelligence level of data centers in related technologies needs to be improved. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the related art. To this end, the present application proposes a data center power supply automatic temperature control method, system and electronic equipment.

[0005] According to the first aspect of the present application, a data center power supply automatic temperature control method is applied to an immersion server system, the immersion server system comprising a housing, a server, and a cooling liquid delivery assembly, the housing forming an installation cavity for accommodating cooling liquid, the server being installed in the installation cavity, the server being at least partially immersed in the cooling liquid, the housing forming a liquid inlet communicating with the installation cavity and a liquid outlet communicating with the installation cavity, the output end of the cooling liquid delivery assembly being connected to the liquid inlet, and the input end of the cooling liquid delivery assembly being connected to the liquid outlet; the data center power supply automatic temperature control method comprising:

[0006] Obtaining the expansion level of the server;

[0007] determining a real-time temperature of the server based on the expansion degree of the server;

[0008] determining operating parameters of the coolant delivery assembly based on the real-time temperature of the server;

[0009] According to the working parameters of the coolant delivery component, the operation of the coolant delivery component is controlled to adjust the temperature and flow rate of the coolant.

[0010] According to one embodiment of the present application, the immersive server system further includes a rigid sleeve and a stress detector, wherein the rigid sleeve is sleeved on the outside of the server, and the stress detector is arranged on the side of the rigid sleeve facing away from the server, and the stress detector is used to detect the stress of the rigid sleeve to determine the degree of expansion of the server based on the stress of the rigid sleeve.

[0011] According to one embodiment of the present application, the step of obtaining the expansion degree of the server includes:

[0012] Based on the detection data of the stress detector, the expansion degree of the server is determined.

[0013] According to one embodiment of the present application, the immersive server system further includes a rigid sleeve and a resonance detector, wherein the rigid sleeve is sleeved on the outside of the server, and the resonance detector is arranged on the side of the rigid sleeve facing away from the server, and the resonance detector is used to detect the offset of the resonance peak of the rigid sleeve to determine the degree of expansion of the server based on the offset of the resonance peak of the rigid sleeve.

[0014] According to one embodiment of the present application, the step of obtaining the expansion degree of the server includes:

[0015] Based on the detection data of the resonance detector, the expansion degree of the server is determined.

[0016] A data center power supply automatic temperature control system according to an embodiment of the second aspect of the present application includes:

[0017] An acquisition module, configured to acquire the expansion degree of the server;

[0018] a first determining module, configured to determine a real-time temperature of the server based on the expansion degree of the server;

[0019] A second module is configured to determine operating parameters of the coolant delivery assembly based on the real-time temperature of the server;

[0020] The control module is used to control the operation of the coolant delivery component according to the operating parameters of the coolant delivery component to adjust the temperature and flow rate of the coolant.

[0021] According to the immersion server system of the third aspect embodiment of the present application, it includes a box, a server and a cooling liquid delivery component, the box is formed with an installation cavity, the installation cavity is used to accommodate cooling liquid, the server is installed in the installation cavity, the server is at least partially immersed in the cooling liquid, the box is formed with a liquid inlet communicating with the installation cavity and a liquid outlet communicating with the installation cavity, the output end of the cooling liquid delivery component is connected to the liquid inlet, and the input end of the cooling liquid delivery component is connected to the liquid outlet.

[0022] According to the electronic device of the fourth embodiment of the present application, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned data center power automatic temperature control method is implemented.

[0023] According to the non-transitory computer-readable storage medium of the fifth embodiment of the present application, the non-transitory computer-readable storage medium includes a computer program, and when the computer program is executed by the processor, it implements the above-mentioned data center power supply automatic temperature control method.

[0024] According to the computer program product of the sixth aspect of the present application, the computer program product includes a computer program, and when the computer program is executed by the processor, it implements the above-mentioned data center power supply automatic temperature control method.

[0025] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 This is a flow chart of the data center power automatic temperature control method provided by the present invention;

[0028] Figure 2 It is a structural diagram of the data center power automatic temperature control system provided by the present invention;

[0029] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention;

[0030] Figure 4 It is a structural diagram of the immersion server system provided by the present invention;

[0031] Figure 5 This is one of the structural diagrams of the server power supply provided by the present invention;

[0032] Figure 6 It is a partial structural diagram of the immersion server system provided by the present invention;

[0033] Figure 7 This is the second structural diagram of the server power supply provided by the present invention;

[0034] Figure 8 This is the third structural diagram of the server power supply provided by the present invention. DETAILED DESCRIPTION

[0035] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0036] The embodiments of the present application provide an embodiment of a method for automatic temperature control of a data center power supply. It should be noted that although a logical sequence is shown in the flow chart, under certain data, the steps shown or described may be completed in an order different from that shown here.

[0037] Before introducing the data center power automatic temperature control method of the embodiment of the present application, the application scenario of the data center power automatic temperature control method is first explained. The data center power automatic temperature control method of the present application can be applied to smart terminals such as smart phones, tablets and computers, and can also be applied to servers. This application does not make any special limitations here, as long as it can carry and implement the data center power automatic temperature control method of the present application.

[0038] The following description will be made by applying the data center power automatic temperature control method to a server side. However, it should be understood that the data center power automatic temperature control method is not limited to being applied only to a server side.

[0039] The following combination Figures 1 to 8 The present invention describes a data center power automatic temperature control method, system, and electronic equipment.

[0040] According to the embodiment of the first aspect of the present application, Figure 1 and Figure 4As shown, a data center power supply automatic temperature control method is applied to an immersion server system, the immersion server system comprising a housing 1, a server 2 and a coolant delivery assembly 5, the housing 1 forming an installation cavity 11, the installation cavity 11 being used to accommodate coolant, the server 2 being installed in the installation cavity 11, the server 2 being at least partially immersed in the coolant, the housing 1 forming a liquid inlet communicating with the installation cavity 11 and a liquid outlet communicating with the installation cavity 11, the output end of the coolant delivery assembly 5 being connected to the liquid inlet, and the input end of the coolant delivery assembly 5 being connected to the liquid outlet; the data center power supply automatic temperature control method comprising:

[0041] Step 101: Obtain the expansion degree of the server 2;

[0042] It is understood that server 2 generates thermal expansion during operation due to heat generation, and the degree of expansion is positively correlated with temperature. Deformation sensors (such as strain gauges or fiber optic deformation sensors) or displacement detection devices (such as laser rangefinders) installed on the server 2 housing or key components (such as the CPU or power module) can monitor the deformation or displacement of the server 2 housing or internal structure in real time to obtain expansion data.

[0043] Step 102: Determine the real-time temperature of the server 2 based on the expansion degree of the server 2;

[0044] It can be understood that an expansion degree-temperature mapping relationship model (such as a lookup table or mathematical model) is established in advance through experiments or simulations, and the expansion degree detected in step 101 is input into the model and directly converted into the corresponding real-time temperature of the server 2, thereby avoiding the complexity of arranging temperature sensors inside the coolant or server 2, and can reflect the comprehensive temperature of the server 2 as a whole or in a local hot spot area.

[0045] For example, the temperature of the coolant can be adjusted by controlling the refrigeration unit (such as a compressor, a heat exchanger) of the coolant delivery component 5 .

[0046] For example, the flow rate of the coolant can be adjusted by adjusting the rotation speed or valve opening of the coolant pump of the coolant delivery component 5 .

[0047] Step 103: determining the operating parameters of the coolant delivery component 5 based on the real-time temperature of the server 2;

[0048] It is understood that the operating parameters of the coolant delivery assembly 5 include the coolant temperature and flow rate. Different coolant temperatures and flow rates result in different cooling effects. When the real-time temperatures of the servers 2 vary, the coolant temperature and flow rate required to maintain the server 2 within the standard temperature range also vary. Therefore, the operating parameters of the coolant delivery assembly 5 can be determined based on the real-time temperatures of the servers 2.

[0049] Step 104 : Control the operation of the coolant delivery component 5 according to the operating parameters of the coolant delivery component 5 to adjust the temperature and flow rate of the coolant.

[0050] According to the data center power supply automatic temperature control method of the embodiment of the present application, the expansion degree of the server 2 is first obtained, and then the real-time temperature of the server 2 is determined based on the expansion degree of the server 2. According to the real-time temperature of the server 2, the working parameters of the coolant delivery component 5 can be determined. Finally, according to the working parameters of the coolant delivery component 5, the operation of the coolant delivery component 5 is controlled to adjust the temperature and flow rate of the coolant. In other words, the present application uses the physical characteristics of the thermal expansion of the server 2 itself to indirectly measure the temperature. It is unnecessary to deploy a large number of temperature sensors in a complex liquid cooling environment to detect the real-time temperature of the server 2, which is beneficial to reducing costs and failure rates. At the same time, the temperature change is reflected by the expansion degree, and the working parameters of the coolant delivery component 5 are adjusted in real time to achieve precise temperature control and energy consumption optimization, thereby improving the intelligence level of the data center.

[0051] In one embodiment of the present application, Figure 7 As shown, the immersion server system also includes a rigid sleeve 01 and a stress detector 02. The rigid sleeve 01 is sleeved on the outside of the server 2, and the stress detector 02 is arranged on the side of the rigid sleeve 01 away from the server 2. The stress detector 02 is used to detect the stress of the rigid sleeve 01 to determine the expansion degree of the server 2 based on the stress of the rigid sleeve 01.

[0052] It can be understood that when the server 2 expands, it will generate a force on the rigid sleeve 01, thereby causing the rigid sleeve 01 to generate stress. Therefore, the stress of the rigid sleeve 01 is detected by the stress detector 02, and then the expansion degree of the server 2 can be determined by the stress, thereby realizing the detection of the expansion degree of the server 2.

[0053] Specifically, the step of obtaining the expansion degree of the server 2 includes:

[0054] Based on the detection data of the stress detector 02 , the expansion degree of the server 2 is determined.

[0055] In one embodiment of the present application, Figure 8 As shown, the immersion server system further includes a rigid sleeve 01 and a resonance detector 03. The rigid sleeve 01 is sleeved on the outside of the server 2, and the resonance detector 03 is arranged on the side of the rigid sleeve 01 away from the server 2. The resonance detector 03 is used to detect the offset of the resonance peak of the rigid sleeve 01, so as to determine the expansion degree of the server 2 according to the offset of the resonance peak of the rigid sleeve 01.

[0056] It is understandable that when the server 2 expands, it will generate a force on the rigid sleeve 01, causing the rigid sleeve 01 to deform under the force, and then the offset of the resonance peak of the rigid sleeve 01 will also change. Therefore, the offset of the resonance peak of the rigid sleeve 01 is detected by the resonance detector 03, and then the expansion degree of the server 2 can be determined by the offset of the resonance peak, thereby realizing the detection of the expansion degree of the server 2.

[0057] It is understood that when rigid sleeve 01 is placed on the outer wall of server 2, the shift of the resonance peak of rigid sleeve 01 will change when the state of server 2 changes due to the contact between rigid sleeve 01 and the outer wall of server 2. In other words, the state of server 2 is correlated with the shift of the resonance peak of rigid sleeve 01. The present application detects the shift of the resonance peak of rigid sleeve 01 using resonance detector 03. Based on the shift of the resonance peak of rigid sleeve 01, the degree of expansion of server 2 can be determined. This eliminates the need for a large number of detection sensors to detect the degree of expansion of server 2, reducing the complexity and cost of detecting server 2.

[0058] For example, a mapping relationship between the expansion degree of the server 2 and the shift of the resonance peak of the rigid set 01 can be established in advance. When the shift of the resonance peak of the rigid set 01 is obtained, the expansion degree of the server 2 can be determined according to the mapping relationship.

[0059] In some embodiments, the resonance detector 03 is, for example, a resonator.

[0060] Specifically, the step of obtaining the expansion degree of the server 2 includes:

[0061] Based on the detection data of the resonance detector 03 , the expansion degree of the server 2 is determined.

[0062] In one embodiment of the present application, Figure 1 and Figure 4As shown, the data center power supply automatic temperature control method is applied to an immersion server system, which includes a server power supply 3, which is installed in an installation cavity 11 and at least partially immersed in a coolant. The server power supply 3 is connected to a server 2 and is used to power the server 2. The data center power supply automatic temperature control method also includes:

[0063] Determine the real-time power required by server 2 based on the operating mode of server 2;

[0064] It's understandable that Server 2's operating mode (e.g., low load, high load, standby, etc.) directly affects its power consumption. For example, during AI training or big data computing, Server 2 is in high load mode, resulting in higher power consumption; while during idle mode, power consumption is lower. Server 2's real-time power requirements can be determined by monitoring its operating status (e.g., CPU / GPU utilization, task queues, etc.) or by using a pre-set power-mode mapping table.

[0065] Determine the heat generation of server power supply 3 based on the real-time required power;

[0066] It is understandable that the heat generation of the server power supply 3 is related to its power supply efficiency, and the power supply power of the server power supply 3 is related to the real-time required power, so the heat generation of the server power supply 3 can be determined according to the real-time required power.

[0067] Determine the operating parameters of the coolant delivery component 5 based on the heat generated by the server power supply 3;

[0068] It is understood that the operating parameters of the coolant delivery assembly 5 include the flow rate and temperature of the coolant to ensure that the heat dissipation efficiency matches the heat output. The optimal parameters can be determined using a lookup table or a calculation model (such as a thermodynamic formula).

[0069] Based on the operating parameters of the coolant delivery component 5 , the operation of the coolant delivery component 5 is controlled.

[0070] It is understandable that according to the calculated working parameters, the speed of the liquid pump of the coolant delivery component 5 and the power of the coolant delivery component 5 are adjusted so that the coolant flows through the server power supply 3 at an appropriate flow rate and temperature to achieve precise heat dissipation.

[0071] According to the data center power automatic temperature control method of the embodiment of the present application, the real-time power required by server 2 is determined according to the working mode of server 2. The heat generation of server power supply 3 can be determined according to the real-time power required. The working parameters of the coolant delivery component 5, such as the flow rate and temperature of the coolant, can be determined according to the heat generation of server power supply 3. That is, the working parameters of the coolant delivery component 5 are inferred from the heat generation. Then, the operation of the coolant delivery component 5 is controlled according to the working parameters, so that the coolant can cool the server power supply 3 and control the temperature of the server power supply 3 within the standard range. By intelligently adjusting the flow rate and temperature of the coolant, efficient heat dissipation control of the server power supply 3 is achieved, thereby improving the degree of intelligence. In addition, the heat dissipation strategy is dynamically adjusted according to the load of server 2 to avoid overcooling or insufficient heat dissipation. The operating intensity of the coolant delivery component 5 is reduced at low loads, thereby reducing unnecessary energy waste.

[0072] In one embodiment of the present application, Figure 4 As shown, the immersion server system further includes an impurity filtering component 7; after the step of controlling the operation of the cooling liquid delivery component 5, the following steps are included:

[0073] It is determined that the impurity content in the coolant exceeds the standard value, and the impurity filtering component 7 is controlled to filter the coolant.

[0074] It is understood that after controlling the operation of the coolant delivery assembly 5 based on the operating parameters of the coolant delivery assembly 5, the impurity content in the coolant is detected. When it is determined that the impurity content in the coolant exceeds the standard value, it indicates that the impurity content is excessive, which will cause the cooling effect of the coolant to decrease. Therefore, the impurity filter assembly 7 is controlled to filter the coolant to reduce the impurity content in the coolant and ensure the cooling effect of the coolant. In other words, this embodiment adds the impurity filter assembly 7 to monitor and filter impurities in the coolant to ensure the long-term stable operation of the heat dissipation system.

[0075] In some examples, an optical sensor (such as a turbidity sensor), a conductivity sensor, or a particle detector may be used to monitor the impurity content (such as metal debris, oxides, dust, etc.) in the coolant in real time.

[0076] Specifically, the immersion server system also includes a switching valve, the inlet of the switching valve is connected to the output end of the coolant delivery component 5, the first outlet of the switching valve is connected to the liquid inlet through a pipeline, and the impurity filter component 7 is connected between the second outlet and the liquid inlet of the switching valve. By controlling the switching valve, the switching valve can be switched between a first state and a second state. In the first state, the switching valve connects the output end of the coolant delivery component 5 and the pipeline, and the coolant does not pass through the impurity filter component 7. In the second state, the switching valve connects the output end of the coolant delivery component 5 and the impurity filter component 7, and the coolant passes through the impurity filter component 7 and then flows into the installation cavity 11.

[0077] In some examples, the impurity filtering component 7 is, for example, a centrifugal separator or a magnetic filter. It should be noted that the impurity filtering component 7 can select a suitable filter element according to the type of impurities, and is not particularly limited here.

[0078] In one embodiment of the present application, the step of determining that the impurity content in the coolant exceeds a standard value includes:

[0079] Get the current temperature value of server power supply 3;

[0080] Get the total heat generated by server power supply 3 within a preset time period;

[0081] After a preset time, obtain the subsequent temperature value of the server power supply 3;

[0082] Determine cooling efficiency based on current temperature value, total heat generation, and subsequent temperature values;

[0083] When the cooling efficiency is lower than a preset efficiency, it is determined that the impurity content in the coolant exceeds a standard value.

[0084] It can be understood that when determining whether the impurity content in the coolant exceeds the standard value, the current temperature value of the server power supply 3 can be obtained first, and then the total heat generation of the server power supply 3 within the preset time period can be obtained. After the preset time period, the temperature of the server power supply 3 is obtained again, and the current temperature value is compared with the subsequent temperature values ​​to determine the temperature change of the server power supply 3. Combined with the total heat generation, it can be determined how much heat of the server power supply 3 the coolant has taken away within the preset time period, and then the cooling efficiency can be determined.

[0085] The cooling efficiency is compared with a preset efficiency. If the cooling efficiency is lower than the preset efficiency, it indicates that the impurity content in the coolant exceeds the standard, resulting in a decrease in cooling efficiency. This indicates that the impurity content in the coolant exceeds the standard value. In other words, this embodiment indirectly determines whether the coolant's cooling efficiency has decreased due to impurity accumulation by analyzing the relationship between the heat output and temperature changes of the server power supply 3, thereby triggering a filtering operation. This avoids reliance on costly sensors and improves system reliability and cost-effectiveness.

[0086] Exemplarily, the current temperature value (T1) of the server power supply 3 is first obtained: at time point t1, the surface or internal temperature of the server power supply 3 is measured by a temperature sensor (such as a surface-mount NTC or infrared sensor), which is recorded as T1.

[0087] Then calculate the total heat generation (Q) within the preset time period (Δt): During the time period Δt (e.g., 5 minutes), continuously monitor the real-time power P(t) of server 2 and calculate the total heat generation within this period based on the conversion efficiency η of the server power supply 3:

[0088] Then, a subsequent temperature value (T2) after a preset time period is obtained: at time point t2 = t1 + Δt, the temperature of the server power supply 3 is measured again, which is recorded as T2.

[0089] Finally, calculate the cooling efficiency (E): where C is the heat capacity of server power supply 3 (which can be obtained through experimental calibration or manufacturer parameters). If E ≤ a threshold (e.g., 0.8), impurities in the coolant have reduced its heat dissipation capacity, triggering filtration.

[0090] In one embodiment of the present application, Figure 6 As shown, the immersion server system further includes a connecting pipe 101, a rigid member 102, and a resonance detection member 103. The connecting pipe 101 connects the liquid outlet and the input end of the coolant delivery assembly 5. The rigid member 102 is sleeved on the outer wall of the connecting pipe 101. The resonance detection member 103 is provided on the side of the rigid member 102 away from the connecting pipe 101. The resonance detection member 103 is used to detect the shift of the resonance peak of the rigid member 102. The step of determining whether the impurity content in the coolant exceeds the standard value includes:

[0091] Obtaining a shift value of a resonance peak of the rigid member 102;

[0092] Based on the shift value of the resonance peak, the impurity content of the coolant in the connecting pipe 101 is determined.

[0093] It is understandable that since the impurity content in the coolant will affect the offset value of the resonance peak of the rigid part 102, the impurity content in the coolant can be judged in real time by monitoring the changes in the resonance characteristics of the connecting pipe 101, thereby achieving more accurate and faster impurity detection.

[0094] It is understood that an initial calibration of the resonance peak can be performed in advance: when the coolant is pure (free of impurities), the rigid member 102 will generate an inherent resonance frequency f0 due to the flow of liquid in the connecting tube 101 (which can be pre-determined through experiments or simulations). The impurity content of the coolant is then sequentially varied, and the offset value of the resonance peak of the rigid member 102 is obtained. A mapping relationship between the impurity content and the offset value of the resonance peak of the rigid member 102 is then established, allowing the impurity content of the coolant in the connecting tube 101 to be directly determined based on the offset value of the resonance peak of the rigid member 102.

[0095] It should be noted that when the coolant contains impurities (such as particles, bubbles or oil), the density, viscosity or flow state of the liquid will change, causing the vibration characteristics of the connecting pipe 101 to change.

[0096] In one embodiment of the present application, Figure 4 As shown, the impurity filter assembly 7 includes an impurity filter box 71 and an impurity filter pump 72. The input end of the impurity filter pump 72 is connected to the liquid outlet, the output end of the impurity filter pump 72 is connected to the inlet of the filter box 1, and the outlet of the filter box 1 is connected to the liquid inlet. The impurity filter pump 72 is used to drive the coolant to flow between the installation cavity 11 and the impurity filter box 71. The steps of controlling the impurity filter assembly 7 to filter the coolant include:

[0097] Determine the predicted required power of server 2 based on the workload of server 2;

[0098] Determining that during the target time period, the predicted required power of server 2 is lower than the preset power;

[0099] During the target time period, the impurity filtering pump 72 is controlled to drive the coolant to flow to the impurity filtering box 71 .

[0100] It is understandable that the coolant in the installation cavity 11 can be pumped into the impurity filtering box 71 by the impurity filtering pump 72 for filtration, and then the filtered coolant is transported back to the installation cavity 11 .

[0101] When controlling the impurity filter component 7 to filter the coolant, first determine the preset required power of the server 2 according to the work task of the server 2, and determine the time period when the preset required power is lower than the preset power as the target time period. Then, control the impurity filter pump 72 to drive the coolant to flow to the impurity filter box 71 during the target time period to filter the coolant.

[0102] When the coolant is filtered, the flow rate of the coolant will be reduced or the coolant level in the installation cavity 11 will drop. However, this embodiment determines the preset required power of the server 2 and sets the filtering time period to a time period when the required power of the server 2 is low. At this time, the heat generation of the server 2 is low. Even if the flow rate of the coolant is low or the coolant level in the installation cavity 11 drops, the heat dissipation requirements of the server 2 can be met, thereby avoiding the situation where the temperature of the server 2 is too high due to filtering the coolant.

[0103] In one embodiment of the present application, an online viscosity sensor and a temperature sensor are provided at the liquid inlet, the online viscosity sensor is used to detect the viscosity of the coolant, and the temperature sensor is used to detect the temperature of the coolant; after the step of controlling the operation of the coolant delivery component 5, the following steps are also included:

[0104] determining that the real-time viscosity of the coolant exceeds a preset viscosity, and determining that the real-time temperature of the coolant exceeds a preset temperature;

[0105] The rotation speed of the pump of the coolant delivery assembly 5 is controlled to be increased.

[0106] It is understandable that the viscosity of the coolant changes with temperature and affects the heat dissipation efficiency. In this embodiment, an online viscosity sensor is installed in the coolant circuit and combined with the temperature sensor to collect data. When high temperature and high viscosity are detected, the speed of the pump of the coolant delivery component 5 is automatically increased by 15% to 20% to ensure stable flow, which is beneficial to improving heat dissipation efficiency and reducing pump energy consumption.

[0107] In one embodiment of the present application, Figure 1 and Figure 4 As shown, the immersion server system includes a server 2, a server power supply 3 and a spray cooling component 4. The server 2 and the server power supply 3 are both installed in the installation cavity 11. The spray cooling component 4 is provided on the outer wall of the box 1 and is used to spray and cool the box 1. The data center power supply automatic temperature control method also includes:

[0108] Acquire a first temperature value of the server power supply 3 and a second temperature value of the outer wall of the box 1;

[0109] For example, the following data can be collected in real time by a temperature sensor:

[0110] A first temperature value of the server power supply 3 (such as the internal temperature of the power supply module); and

[0111] The second temperature value of the outer wall of box 1 (such as the temperature of the metal shell of box 1)

[0112] Determining that the first temperature value is greater than a first threshold value, and determining that the second temperature value is greater than a second threshold value;

[0113] The spray cooling component 4 is controlled to spray and cool the box body 1 .

[0114] It is understandable that when the immersion server system is installed outdoors, it may be exposed to sunlight, which may cause the temperature of the outer wall of the box body 1 to be too high, thereby affecting the heat dissipation of the server power supply 3. Therefore, when the first temperature value is greater than the first threshold value and the second temperature value is greater than the second threshold value, the spray cooling component 4 is controlled to spray and cool the outer wall of the box body 1 to reduce the temperature of the outer wall of the box body 1, so that the heat of the server power supply 3 can be effectively dissipated to the outside through the outer wall of the box body 1.

[0115] According to the data center power supply automatic temperature control method of the embodiment of the present application, by obtaining the temperature of the server power supply 3 and the temperature of the outer wall of the box body 1, it is determined whether the temperature of the server power supply 3 and the temperature of the outer wall of the box body 1 are too high. When it is determined that the temperature of the server power supply 3 and the temperature of the outer wall of the box body 1 are both too high, it means that the server power supply 3 needs to be cooled at this time, and the temperature of the outer wall of the box body 1 is too high, which is not conducive to the heat dissipation of the server power supply 3. Therefore, the spray cooling component 4 is controlled to spray and cool the box body 1 to reduce the temperature of the outer wall of the box body 1 and the temperature of the server power supply 3, ensuring that the server 2 and the server power supply 3 can operate stably. In other words, by providing the spray cooling component 4, the present application improves the heat dissipation capacity of the immersion server system, can avoid the excessive temperature of the outer wall of the box body 1 affecting the heat dissipation of the server 2 and the server power supply 3, and ensures that the server 2 and the server power supply 3 can operate stably.

[0116] It is understandable that this application utilizes a dual temperature determination mechanism. If the temperature of server power supply 3 is too high, it indicates insufficient heat dissipation within the server power supply 3, possibly due to excessive load or internal cooling failure. If the temperature of the outer wall of enclosure 1 is too high, it indicates that the ambient heat load has affected the internal temperature of enclosure 1, exacerbating the heat dissipation pressure on the power supply. When both temperatures exceed the specified limits, spraying is initiated simultaneously, avoiding unnecessary spraying caused by a single temperature fluctuation (such as a brief high power supply load), thus conserving cooling resources.

[0117] In one embodiment of the present application, the immersion server system further includes a fan connected to the outer wall of the box 1, and the fan is used to drive the flow of gas at the outer wall of the box 1; after the step of controlling the spray cooling component 4 to spray and cool the box 1, the following steps are included:

[0118] After the spray cooling component 4 works for a preset time, the first temperature value of the server power supply 3 is obtained again;

[0119] If the first temperature value obtained again is still greater than the first threshold, the fan is controlled to start working.

[0120] It can be understood that after spraying the outer wall of the box body 1 for a preset period of time, the temperature of the server power supply 3 is detected again to determine whether the first temperature value of the server power supply 3 is still greater than the first threshold value. If it is greater than, it means that the heat dissipation speed is insufficient at this time, so the fan can be controlled to drive the gas flow at the outer wall of the box body 1, accelerate the evaporation rate of water at the outer wall of the box body 1, and thereby improve the cooling effect.

[0121] In one embodiment of the present application, the control method further includes:

[0122] Determine a standard heating rate of server power supply 3 based on the operating data of server 2;

[0123] When the ambient temperature is greater than the third threshold and the actual heating rate of the server power supply 3 is greater than the standard heating rate, the spray cooling component 4 is controlled to spray and cool the cabinet 1 .

[0124] It is understood that the operating data of the server 2 (such as CPU / GPU load, memory usage, network traffic, etc.) is monitored in real time, and based on historical data or a preset model, the standard heating rate of the server power supply 3 (i.e., the temperature rising trend under a typical workload) is calculated. The external ambient temperature of the cabinet 1 is obtained through an ambient temperature sensor and compared with a preset third threshold (such as 35°C).

[0125] When the ambient temperature exceeds the third threshold, it indicates a harsh external thermal environment. If the actual temperature rise rate of the server power supply 3 exceeds the standard temperature rise rate, this indicates abnormal power supply heat dissipation or an unexpected load. This means that the ambient temperature is affecting the heat dissipation of the server power supply 3. This controls the spray cooling assembly 4 to spray the outer wall of the enclosure 1, reducing the impact of the ambient temperature on the heat dissipation of the server power supply 3 and suppressing an excessive temperature rise in the server power supply 3.

[0126] It is understandable that by introducing the ambient temperature threshold, unnecessary spraying in low-temperature environments (such as at night or in cold regions) can be avoided. At the same time, when the temperature of the server power supply 3 has not yet reached the first threshold but the temperature rise trend is abnormal, spraying can be started in advance to prevent temperature runaway, which is particularly suitable for intermittent high-load scenarios (such as bursts of traffic in immersive server systems during emergency communications).

[0127] For example, when an immersive server system is performing large-scale data forwarding tasks in hot weather, the CPU load suddenly increases to 90%, and the power supply temperature rises at a rate of 2°C / min (the standard rate is 1°C / min). The system immediately triggers a spray cooling system to prevent the power supply from overheating.

[0128] In one embodiment of the present application, the immersion server system further includes a heat conducting member, and the server 2 and the server power supply 3 are both connected to the inner wall surface of the box 1 through the heat conducting member, and the box 1 is made of a heat dissipating material.

[0129] It is understood that connecting server 2 to the inner wall of enclosure 1 via the heat conducting member allows the heat generated by server 2 to be directly transferred to enclosure 1 via the heat conducting member and then dissipated to the outside through enclosure 1, thereby improving the heat dissipation effect of server 2. Connecting server power supply 3 to the inner wall of enclosure 1 via the heat conducting member allows the heat generated by server power supply 3 to be directly transferred to enclosure 1 via the heat conducting member and then dissipated to the outside through enclosure 1, thereby improving the heat dissipation effect of server power supply 3.

[0130] In one embodiment of the present application, a receiving groove 12 is formed on the top wall of the box body 1 , and the receiving groove 12 is used to receive the spray cooling assembly 4 .

[0131] It can be understood that by accommodating the spray cooling component 4 in the accommodating groove 12, the space utilization of the box body 1 is improved, and the situation in which the spray cooling component 4 protrudes from the box body 1 when not in use can be avoided.

[0132] In one embodiment of the present application, Figure 4 As shown, the spray cooling assembly 4 includes a spray part 41 and a lifting part 42. The lifting part 42 is arranged in the receiving tank 12. The spray part 41 is connected to the lifting part 42. The lifting part 42 is used to drive the spray part 41 to rise and fall, so that the spray part 41 rises and falls relative to the receiving tank 12.

[0133] It is understood that the lifting member 42 drives the spray member to rise and fall, so that the spray member 41 can switch between two states: being located within the receiving groove 12 and protruding from the receiving groove 12. When the spray member 41 is needed to spray the box 1, the lifting member 42 drives the spray member 41 upward, so that the spray member 41 can effectively spray the box 1, thereby improving the intelligence of the immersion server system.

[0134] In some examples, the spraying member 41 is, for example, a nozzle connected to a water tank or an external water storage member of the vehicle via a water pipe, and a water pump is provided at the water pipe so that the nozzle can spray and cool the box 1. The lifting member 42 is, for example, a cylinder lifting structure.

[0135] In one embodiment of the present application, the immersion server system also includes an air-conditioning refrigeration circuit, which is used to cool the cab. At least part of the air-conditioning refrigeration circuit is located in the installation cavity 11, so that the air-conditioning refrigeration circuit can be used to cool the server 2 and the server power supply 3.

[0136] It is understood that vehicles are generally equipped with air conditioning systems that cool the vehicle's cab through an air conditioning refrigeration circuit. In this application, a portion of the air conditioning refrigeration circuit is disposed within the installation cavity 11, so that the air conditioning refrigeration circuit can also cool the server 2 and server power supply 3 within the installation cavity 11, thereby reducing the temperature of the server 2 and server power supply 3 and improving the heat dissipation capacity of the immersion server system.

[0137] It should be noted that the air conditioning refrigeration circuit is a mature refrigeration structure in the relevant technology and will not be described in detail here.

[0138] In one embodiment of the present application, the immersion server system further includes an air conditioning refrigeration circuit, refrigeration piping, a control valve, and a heat exchanger. The air conditioning refrigeration circuit is used to cool the cab. The air conditioning refrigeration circuit includes a compressor, a condenser, an expansion valve, and an evaporator connected in sequence.

[0139] The first end of the control valve is connected between the expansion valve and the evaporator, the second end of the control valve is connected to the first end of the refrigeration pipeline, the control valve is used to control the connection and disconnection between the first end of the refrigeration pipeline and the output end of the expansion valve, and the second end of the refrigeration pipeline is connected to the output end of the evaporator;

[0140] The server 2 and the server power supply 3 are connected to the refrigeration pipeline through a heat exchanger.

[0141] It is understandable that by connecting the first end of the refrigeration line and the output end of the expansion valve through the control valve, the refrigerant in the air conditioning refrigeration circuit can flow into the refrigeration line and then flow through the second end of the refrigeration line to the output end of the evaporator, forming a flow cycle. In other words, part of the refrigerant can flow into the refrigeration line to cool the refrigeration line, and the refrigeration line is connected to the server 2 and the server power supply 3 through the heat exchange element. The heat of the server 2 and the server power supply 3 will be transferred to the heat exchange element, and the refrigeration line can cool the heat exchange element, thereby cooling the server 2 and the server power supply 3, realizing the reuse of the air conditioning refrigeration circuit and improving the heat dissipation capacity of the immersion server system.

[0142] As you can understand, when the temperature of server 2 and / or server power supply 3 exceeds the specified temperature, the control valve opens, diverting some of the expanded low-temperature refrigerant to the refrigeration line. After passing through the heat exchanger, the cooling medium absorbs heat from server 2 and then returns to the evaporator output to participate in the main circuit circulation.

[0143] In one embodiment of the present application, after the step of controlling the spray cooling component 4 to spray and cool the box 1, the following steps are included:

[0144] determining that the first temperature value is still greater than the first threshold;

[0145] The control valve is controlled to connect the refrigeration pipeline and the output end of the expansion valve, so that part of the refrigerant medium of the air-conditioning refrigeration circuit flows into the refrigeration pipeline.

[0146] It can be understood that after controlling the spray cooling component 4 to spray and cool the box 1, if the first temperature value of the server power supply 3 is still greater than the first threshold value, the control valve is controlled to connect the refrigeration pipeline and the output end of the expansion valve, so that part of the refrigerant medium of the air-conditioning refrigeration circuit flows into the refrigeration pipeline, and the air-conditioning refrigeration circuit is used to cool the server power supply 3, so as to effectively reduce the temperature of the server power supply 3 and ensure that the server power supply 3 can work stably.

[0147] In one embodiment of the present application, Figure 1 and Figure 4 As shown, the data center power supply automatic temperature control method is applied to an immersion server system, the immersion server system also includes a server 2, the server 2 and the server power supply 3 are both installed in the installation cavity 11, and the server 2 and the server power supply 3 are at least partially immersed in the coolant; the data center power supply automatic temperature control method also includes:

[0148] Determine the real-time power required by server 2 based on the operating mode of server 2;

[0149] It is understood that based on the working mode of server 2, the working task of server 2 can be determined, and further, the real-time power required by server 2 to complete the corresponding working task can be determined. Specifically, the current real-time power required is calculated based on the power consumption curve or preset mapping table corresponding to the working mode (for example, the power in high-performance mode is 400W, and the power in standby mode is 50W).

[0150] Exemplarily, the working mode of the server 2 (such as CPU / GPU full load, idle state, etc.) is acquired in real time through built-in sensors or system management software (such as IPMI, BMC).

[0151] Determine the target temperature and target flow rate based on the real-time required power;

[0152] It is understandable that based on thermodynamic formulas, combined with the allowable operating temperature of the server power supply 3 and the chip, the target temperature of the coolant can be reversed. For example, the coolant temperature needs to be lowered (e.g., 25°C) at high power, and can be appropriately increased (e.g., 35°C) at low power. The minimum required flow rate of the coolant can be determined by using a fluid heat dissipation efficiency model (e.g., Newton's law of cooling) combined with the heat generation corresponding to the real-time power. For example, a flow rate of 2 m / s is required at 400 W power, and this can be reduced to 0.5 m / s at 50 W power.

[0153] Based on the target temperature and the target flow rate, the coolant delivery component 5 is controlled to adjust the temperature and the flow rate of the coolant.

[0154] For example, a heat exchanger (such as a semiconductor refrigeration plate or a chiller) connected to the coolant delivery component 5 can be controlled to adjust the coolant inlet temperature to a target value.

[0155] For example, the coolant circulation speed can be adjusted to the target flow rate by a variable frequency pump or a flow valve to ensure an optimal match between heat dissipation efficiency and pump power consumption.

[0156] According to the data center power automatic temperature control method of the embodiment of the present application, the real-time power required by the server 2 can be determined according to the working mode of the server 2, and the heat generated by the server 2 can be determined according to the real-time power required, and the target temperature and target flow rate of the cooling liquid can be determined according to the heat generated, so that the cooling liquid can effectively control the temperature of the server 2. Therefore, the cooling liquid delivery component 5 is controlled according to the target temperature and target flow rate, and the real-time temperature of the cooling liquid is adjusted to the target temperature, and the real-time flow rate of the cooling liquid is adjusted to the target flow rate. In other words, the present application can adjust the temperature and flow rate of the cooling liquid in real time according to the working mode of the server 2, so that the temperature and flow rate of the cooling liquid match the heat generated by the server 2, and then the cooling liquid can prevent the temperature of the server 2 from being too high, ensuring that the server 2 can work stably, and improving the intelligence level of the immersion server system.

[0157] It is understood that this application dynamically adjusts the coolant temperature and flow rate to match the heat dissipation requirements of server 2 by monitoring the operating mode of server 2 in real time. Specifically, server 2's operating mode (e.g., high-load computing, low-load standby, etc.) determines its real-time power consumption, which in turn affects heat generation. By calculating the real-time required power, the optimal coolant temperature and flow rate can be derived, thereby precisely controlling the coolant delivery component 5 (e.g., pump, heat exchanger, etc.), achieving a balance between efficient heat dissipation and optimized energy consumption.

[0158] In one embodiment of the present application, after the step of controlling the cooling liquid delivery component 5 to adjust the temperature and flow rate of the cooling liquid, the data center power automatic temperature control method includes:

[0159] Determine the predicted required power of server 2 based on the workload of server 2;

[0160] Determine the predicted heat generation of server 2 and server power supply 3 based on the predicted required power of server 2;

[0161] If the predicted heat generation is greater than the current heat generation, the coolant delivery component 5 is controlled to adjust the temperature of the coolant based on the predicted heat generation.

[0162] As you can understand, this embodiment employs a predictive temperature control mechanism. By analyzing the workload of server 2 (e.g., upcoming high-performance computing, batch data processing, etc.), it predicts changes in its power and heat generation in advance. If a significant increase in heat generation is predicted, the coolant temperature is lowered in advance to avoid a sudden temperature increase in server 2 or the power supply due to delayed cooling. This maintains system operation within a safe temperature range, improves stability, and reduces the impact of temperature fluctuations on the hardware.

[0163] Specifically, the task load information (such as CPU / GPU occupancy, memory bandwidth requirements, etc.) for a period of time in the future (such as the next 5-10 seconds) is obtained through the server 2 operating system, task scheduler (such as Kubernetes, SLURM) or AI prediction model. According to historical data or task feature library (such as deep learning training tasks usually correspond to 300W+ power), the predicted power is directly matched. Based on the predicted power, the predicted heat production can be determined. If the predicted heat production is greater than the current heat production, the coolant temperature can be lowered in advance to avoid temperature overshoot caused by traditional "hysteresis regulation" and reduce hardware thermal stress. At the same time, task prediction and real-time data are combined to achieve smooth temperature control transition and improve system stability.

[0164] In one embodiment of the present application, after the step of controlling the cooling liquid delivery component 5 to adjust the temperature and flow rate of the cooling liquid, the data center power automatic temperature control method includes:

[0165] Based on the real-time power requirement of server 2, determine the actual heat generation of server 2 and server power supply 3;

[0166] If the actual heat generation is lower than the preset value, the depth of the server 2 and the server power supply 3 immersed in the coolant is controlled and adjusted based on the actual heat generation.

[0167] It is understood that when the actual heat generation of server 2 and the power supply is low, adjusting the immersion depth (e.g., partially exposing them to the coolant) can reduce coolant flow resistance and pump power consumption while still ensuring effective heat dissipation. When heat generation is high, maintaining full immersion maximizes heat dissipation efficiency.

[0168] For example, when the actual heat generation is lower than a preset value, the server 2 or non-critical heat-generating components of the power supply (such as the power module housing and part of the PCB) can be partially lifted using an electric lifting mechanism or a buoyancy adjustment device (such as an inflatable airbag) to reduce the submerged volume (e.g., from 100% submersion to 50%). If the heat generation rises back to or above the preset value, the full submersion state is restored.

[0169] In some examples, the immersion server system also includes a coolant holding tank and a liquid pump located outside the box 1. The liquid pump is connected to the holding chamber. The liquid pump can extract the coolant in the holding chamber into the coolant holding tank, or can transport the coolant in the coolant holding tank into the holding chamber, thereby adjusting the height of the coolant in the holding chamber and adjusting the height of the server 2 and the server power supply 3 immersed in the coolant.

[0170] In one embodiment of the present application, Figure 4 As shown, the immersion server system further includes an ejector 6, which is movably mounted in the mounting cavity 11;

[0171] After the step of controlling the coolant delivery component 5 to adjust the temperature and flow rate of the coolant, the data center power automatic temperature control method includes:

[0172] Get the actual temperature at different locations of server power supply 3;

[0173] Determining that an actual temperature at one location of the server power supply 3 is higher than an actual temperature at another location of the server power supply 3;

[0174] The ejector 6 is controlled to increase the flow rate of the cooling liquid at one location of the server power supply 3 .

[0175] It can be understood that by monitoring the temperature distribution at different positions of the power supply, identifying the hot spot area (such as near the high-power MOSFET or transformer), and controlling the movable ejector 6 to directionally enhance the coolant flow rate in the area, precise local heat dissipation can be achieved, avoiding the temperature unevenness problem caused by traditional uniform heat dissipation methods, and quickly suppressing the hot spot temperature to prevent power supply components from failing due to local high temperature.

[0176] For example, temperature sensors (such as NTC thermistors or infrared temperature measurement modules) can be placed near key heat-generating components of the power supply (such as input / output filter capacitors, switching transistors, inductors, etc.). Alternatively, data from each sensor can be collected using multiple ADCs to generate a temperature distribution map of the power supply (for example, position A is 65°C, position B is 50°C, and position C is 70°C).

[0177] In some examples, the ejector 6 comprises a rotatable nozzle and a microcentrifugal pump, driven by a servo motor (e.g., an XYZ three-axis guide) within the mounting cavity 11. Based on the hotspot coordinates (e.g., position C), the ejector 6 is controlled to move above the target area, the nozzle angle is adjusted, and the pump speed is increased so that the coolant impacts the hotspot surface at a high velocity (e.g., 3 m / s). For example, if the temperature at position C reaches 70°C, the ejector 6 is moved directly above it, and the flow rate is increased from 1 m / s to 3 m / s, continuing until the temperature drops below 65°C.

[0178] In one embodiment of the present application, Figure 5 As shown, the server power supply 3 includes a power supply body 31, a steel belt 32, and a stress detection member 33. The steel belt 32 is sleeved on the outer wall of the power supply body 31. The stress detection members 33 are provided at different positions on the side of the steel belt 32 facing away from the power supply body 31. The steps of obtaining the actual temperature at different positions of the server power supply 3 include:

[0179] Based on the detection data of different stress detection components 33 , the actual temperatures at different positions of the server power supply 3 are determined.

[0180] It is understandable that since the server power supply 3 is in an immersion cooling environment, traditional temperature sensors may be disturbed by the flow of coolant or limited by the installation space. This solution utilizes the thermal stress-temperature correlation and provides stress detection parts 33 at different positions of the steel belt 32. By detecting the stress changes in the steel belt 32 caused by the thermal expansion of the power supply body 31, the temperature distribution at different positions of the power supply is indirectly inferred, thereby realizing non-contact temperature monitoring.

[0181] It is understandable that a stepped power load (such as 100W→400W) can be applied to the power supply in advance in a laboratory environment, and the microstrain value (με) of each stress detection component 33 and the actual temperature measured by the infrared thermal imager can be recorded synchronously to establish a strain-temperature mapping table, so as to facilitate the subsequent direct determination of the temperature of the server power supply 3 based on the detection data of the stress detection component 33.

[0182] According to an embodiment of the third aspect of the present application, Figure 4 As shown, the immersion server system includes a box 1, a server 2 and a cooling liquid delivery component 5, the box 1 is formed with an installation cavity 11, the installation cavity 11 is used to accommodate cooling liquid, the server 2 is installed in the installation cavity 11, and the server 2 is at least partially immersed in the cooling liquid, the box 1 is formed with a liquid inlet communicating with the installation cavity 11 and a liquid outlet communicating with the installation cavity 11, the output end of the cooling liquid delivery component 5 is connected to the liquid inlet, and the input end of the cooling liquid delivery component 5 is connected to the liquid outlet.

[0183] Specifically, the immersive server system also includes a rigid sleeve 01 and a stress detector 02. The rigid sleeve 01 is sleeved on the outside of the server 2, and the stress detector 02 is arranged on the side of the rigid sleeve 01 away from the server 2. The stress detector 02 is used to detect the stress of the rigid sleeve 01 to determine the expansion degree of the server 2 based on the stress of the rigid sleeve 01.

[0184] Specifically, the immersive server system also includes a rigid sleeve 01 and a resonance detector 03. The rigid sleeve 01 is sleeved on the outside of the server 2, and the resonance detector 03 is arranged on the side of the rigid sleeve 01 away from the server 2. The resonance detector 03 is used to detect the offset of the resonance peak of the rigid sleeve 01 to determine the expansion degree of the server 2 based on the offset of the resonance peak of the rigid sleeve 01.

[0185] According to the embodiment of the second aspect of the present application, the data center power supply automatic temperature control system and the data center power supply automatic temperature control method correspond to each other. Figure 2 As shown, the data center power automatic temperature control system includes:

[0186] An acquisition module 201 is configured to acquire the expansion degree of the server 2;

[0187] A first determining module 202 is configured to determine a real-time temperature of the server 2 based on the expansion degree of the server 2;

[0188] The second module 203 is used to determine the operating parameters of the coolant delivery component 5 based on the real-time temperature of the server 2;

[0189] The control module 204 is used to control the operation of the coolant delivery component 5 according to the operating parameters of the coolant delivery component 5 to adjust the temperature and flow rate of the coolant.

[0190] According to an embodiment of the fourth aspect of the present application, Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the data center power automatic temperature control method, which includes:

[0191] Obtaining the expansion degree of the server 2;

[0192] determining a real-time temperature of the server 2 based on the expansion degree of the server 2;

[0193] Determining the operating parameters of the coolant delivery component 5 based on the real-time temperature of the server 2;

[0194] According to the working parameters of the coolant delivery component 5, the operation of the coolant delivery component 5 is controlled to adjust the temperature and flow rate of the coolant.

[0195] In addition, the logic instructions in the above-mentioned memory 330 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 prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server 222, or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0196] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the data center power supply automatic temperature control method provided by the above methods. The method includes:

[0197] Obtaining the expansion degree of the server 2;

[0198] determining a real-time temperature of the server 2 based on the expansion degree of the server 2;

[0199] Determining the operating parameters of the coolant delivery component 5 based on the real-time temperature of the server 2;

[0200] According to the working parameters of the coolant delivery component 5, the operation of the coolant delivery component 5 is controlled to adjust the temperature and flow rate of the coolant.

[0201] According to an embodiment of the fifth aspect of the present application, the present application further includes a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for automatically controlling the temperature of a data center power supply provided above is implemented. The method includes:

[0202] Obtaining the expansion degree of the server 2;

[0203] determining a real-time temperature of the server 2 based on the expansion degree of the server 2;

[0204] Determining the operating parameters of the coolant delivery component 5 based on the real-time temperature of the server 2;

[0205] According to the working parameters of the coolant delivery component 5, the operation of the coolant delivery component 5 is controlled to adjust the temperature and flow rate of the coolant.

[0206] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0207] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or certain parts of the embodiment.

[0208] Finally, it should be noted that the above embodiments are intended only to illustrate the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the embodiments, those skilled in the art will appreciate that various combinations, modifications, or equivalent substitutions of the technical solutions of the present application do not depart from the spirit and scope of the technical solutions of the present application and are intended to be encompassed by the claims of the present application.

Claims

1. A data center power supply automatic temperature control method, applied to an immersion server system, characterized in that: The immersion server system includes a housing, a server, and a coolant delivery assembly. The housing is formed with an installation cavity for accommodating coolant. The server is installed in the installation cavity and is at least partially immersed in the coolant. The housing is formed with a liquid inlet and a liquid outlet communicating with the installation cavity. The output end of the coolant delivery assembly is connected to the liquid inlet, and the input end of the coolant delivery assembly is connected to the liquid outlet. The data center power supply automatic temperature control method includes: Obtaining the expansion level of the server; determining a real-time temperature of the server based on the expansion degree of the server; determining operating parameters of the coolant delivery assembly based on the real-time temperature of the server; According to the working parameters of the coolant delivery component, the operation of the coolant delivery component is controlled to adjust the temperature and flow rate of the coolant.

2. The data center power automatic temperature control method according to claim 1, characterized in that: The submerged server system also includes a rigid sleeve and a stress detector. The rigid sleeve is sleeved on the outside of the server, and the stress detector is arranged on the side of the rigid sleeve facing away from the server. The stress detector is used to detect the stress of the rigid sleeve to determine the expansion degree of the server based on the stress of the rigid sleeve.

3. The data center power automatic temperature control method according to claim 2, characterized in that: The step of obtaining the expansion degree of the server includes: Based on the detection data of the stress detector, the expansion degree of the server is determined.

4. The data center power automatic temperature control method according to claim 1, characterized in that: The immersion server system also includes a rigid sleeve and a resonance detector. The rigid sleeve is sleeved on the outside of the server, and the resonance detector is arranged on the side of the rigid sleeve facing away from the server. The resonance detector is used to detect the offset of the resonance peak of the rigid sleeve to determine the expansion degree of the server based on the offset of the resonance peak of the rigid sleeve.

5. The data center power supply automatic temperature control method according to claim 3, characterized in that: The step of obtaining the expansion degree of the server includes: Based on the detection data of the resonance detector, the expansion degree of the server is determined.

6. A data center power supply automatic temperature control system, characterized in that: include: An acquisition module, configured to acquire the expansion degree of the server; a first determining module, configured to determine a real-time temperature of the server based on the expansion degree of the server; A second module is configured to determine operating parameters of the coolant delivery assembly based on the real-time temperature of the server; The control module is used to control the operation of the coolant delivery component according to the operating parameters of the coolant delivery component to adjust the temperature and flow rate of the coolant.

7. An immersion server system, characterized in that: The invention comprises a box, a server and a coolant delivery component, wherein the box is formed with an installation cavity, the installation cavity is used to accommodate coolant, the server is installed in the installation cavity, and the server is at least partially immersed in the coolant, the box is formed with a liquid inlet communicating with the installation cavity and a liquid outlet communicating with the installation cavity, the output end of the coolant delivery component is connected to the liquid inlet, and the input end of the coolant delivery component is connected to the liquid outlet.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the data center power supply automatic temperature control method according to any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium comprising a computer program, characterized in that: When the computer program is executed by a processor, the data center power supply automatic temperature control method according to any one of claims 1 to 5 is implemented.