Server heat dissipation scheme screening method and system

Abstract

According to the server heat dissipation scheme screening method and system, quantification is carried out based on an evaluation model of the server heat dissipation schemes according to key performance indexes of the server heat dissipation schemes, a plurality of preliminarily screened server heat dissipation schemes are obtained, and then the server heat dissipation schemes are screened based on different expressions of servers in different use environments. And carrying out analogue simulation calculation on the heat dissipation schemes of the preliminarily screened servers one by one, carrying out matching degree analysis to obtain final scores of the heat dissipation schemes of the preliminarily screened servers, and determining the finally screened server heat dissipation scheme according to the final scores of the heat dissipation schemes of the preliminarily screened servers. According to the scheme of the invention, key performance indexes of the server are considered, and different expressions of the server in different use environments are also considered, so that the screening applicability is improved, the screening duration is shortened, the working time is saved, and the screening cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field related to servers, and particularly relates to a method and system for screening server cooling solutions. Background Art

[0002] The statements in this part only provide background technical information related to the present invention, and do not necessarily constitute prior art.

[0003] With the rapid development of digital information technologies such as big data, cloud computing, and 5G, servers, as the core support devices for these technologies, have continuously improved their performance and power consumption. However, high performance and high power consumption also bring severe cooling challenges. A large amount of heat is generated during the operation of the server. If it cannot be dissipated in a timely and effective manner, it will lead to an increase in the server temperature, which in turn will cause a decline in performance, a reduction in stability, and even hardware damage and system failures.

[0004] Currently, common cooling methods on the market include: air cooling, water cooling, phase change heat exchange, etc., with a wide variety and diverse technologies. Facing multiple cooling technologies and solutions, how to screen out the most suitable cooling solution for a specific server application scenario has become a key issue. Therefore, developing a scientific and efficient method for screening server cooling solutions has become an urgent problem to be solved. Summary of the Invention

[0005] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a method and system for screening server cooling solutions, which not only considers the key performance indicators of the server, but also takes into account the different performances of the server in different usage environments, improves the applicability of the screening, reduces the screening duration, saves working time, and reduces the screening cost.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for screening server cooling solutions, including:

[0008] Obtaining the key performance indicators of each server cooling solution;

[0009] According to the key performance indicators of each server cooling solution, calling a preset evaluation index model of the server cooling solution to obtain the predicted evaluation index values of each server cooling solution;

[0010] According to the predicted evaluation index values of each server cooling solution, screening through a preset first screening requirement to screen out several preliminarily screened server cooling solutions;

[0011] According to different usage environments of the servers, the heat dissipation solutions of each preliminary screening server are simulated and calculated one by one, and a matching degree analysis is carried out to obtain the final scores of the heat dissipation solutions of each preliminary screening server.

[0012] According to the final scores of the heat dissipation solutions of each preliminary screening server, screening is carried out through a preset second screening requirement to screen out the final server heat dissipation solution.

[0013] In a second aspect, the present invention provides a server heat dissipation solution screening system, including:

[0014] An acquisition module, which is configured to: acquire the key performance indicators of each server heat dissipation solution;

[0015] A predicted evaluation index value module, which is configured to: according to the key performance indicators of each server heat dissipation solution, call a preset evaluation model of the server heat dissipation solution to obtain the predicted evaluation index values of each server heat dissipation solution;

[0016] A preliminary screening module, which is configured to: according to the predicted evaluation index values of each server heat dissipation solution, screen through a preset first screening requirement to screen out several preliminary screening server heat dissipation solutions;

[0017] A calculated evaluation index value module, which is configured to: according to different usage environments of the servers, simulate and calculate each preliminary screening server heat dissipation solution one by one, and carry out a matching degree analysis to obtain the final scores of each preliminary screening server heat dissipation solution;

[0018] A final screening module, which is configured to: according to the final scores of each preliminary screening server heat dissipation solution, screen through a preset second screening requirement to screen out the final server heat dissipation solution.

[0019] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in the first aspect is completed.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by the processor, the method described in the first aspect is completed.

[0021] In a fifth aspect, the present invention provides a computer program product, including a computer program. When the computer program is executed by the processor, the method described in the first aspect is implemented.

[0022] The above one or more technical solutions have the following beneficial effects:

[0023] In the present invention, according to the key performance indicators of the server heat dissipation solution, it is quantified based on the evaluation model of the server heat dissipation solution to obtain several initially screened server heat dissipation solutions. Then, based on the different performances of the server in different usage environments, each initially screened server heat dissipation solution is subjected to simulation calculation one by one, and the matching degree analysis is carried out to obtain the final score of each initially screened server heat dissipation solution. Furthermore, according to the final scores of each initially screened server heat dissipation solution, the finally selected server heat dissipation solution is determined. The solution of the present invention not only considers the key performance indicators of the server, but also considers the differences in the performance of the server under different usage environments, improves the applicability of the screening, reduces the screening duration, saves working time, and reduces the screening cost.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0026] Figure 1 is a flowchart of a method for screening a server heat dissipation solution in Embodiment 1 of the present invention;

[0027] Figure 2 is a block diagram of a method for screening a server heat dissipation solution in Embodiment 1 of the present invention;

[0028] Figure 3 is a schematic diagram of a server hardware system in Embodiment 1 of the present invention;

[0029] In the figure, 1. storage box cover, 2. storage box body, 3. front cabinet door, 4. left cabinet door, 5. KVM, 6. rear cabinet door, 7. server power cord, 8. right cabinet door, 9. data acquisition line, 10. low-temperature pipeline, 11. high-temperature pipeline, 12. data collector, 13. cabinet bracket, 14. external cooling device, 15. phase change immersion server, 16. single-phase immersion server, 17. water-cooled server, 18. air-cooled server. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0032] In the case of no conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0033] Embodiment 1

[0034] This embodiment discloses a method for screening server cooling solutions, including:

[0035] Obtain the key performance indicators of each server cooling solution;

[0036] According to the key performance indicators of each server cooling solution, call the preset evaluation model of the server cooling solution to obtain the predicted evaluation index values of each server cooling solution;

[0037] According to the predicted evaluation index values of each server cooling solution, screen through the preset first screening requirements to screen out several initially screened server cooling solutions;

[0038] According to the different usage environments of the servers, simulate each initially screened server cooling solution one by one and conduct a matching degree analysis to obtain the final scores of each initially screened server cooling solution;

[0039] According to the final scores of each initially screened server cooling solution, screen through the preset second screening requirements to screen out the final server cooling solution.

[0040] As Figure 3 shown, the hardware of this embodiment mainly includes: a cabinet, a server group, an external cooling system, and a data acquisition system.

[0041] Among them, the cabinet is the main support structure of the system, including the front cabinet door 3, the left cabinet door 4, the rear cabinet door 6, the right cabinet door 8 and the cabinet bracket 13; the server group consists of 4 servers with different heat dissipation methods, including a phase change immersion server 15, a single-phase immersion server 16, a water-cooled server 17 and an air-cooled server 18. Except for the different heat dissipation methods, the models of other components such as the motherboard, memory, CPU and graphics card of each server host are exactly the same. The motherboard is MSI-Z790-P, the CPU is Intel-i9-13900K, the memory is Acer-16G×2-DDR5-6000MHz, and the solid state drive is WDC-SN770-1T. It supports external access through the Internet and also supports the transfer of relevant data through data lines; the external cooling system provides a storage location for the external cooling device or its own cooling device for the server host, including the storage box cover 1, the storage box body 2, the external cooling device 14, the low-temperature pipeline 10 and the high-temperature pipeline 11; the data acquisition system collects various types of data, realizes the collation, display and storage of data, and displays the numerical values of temperature, heat dissipation efficiency and energy consumption in real time, including measurement sensors for parameters such as temperature, flow rate, power, and pressure, data acquisition lines 9, data acquisition devices 12, etc.

[0042] The following Figure 1 - Figure 2 will describe in detail a method for screening server heat dissipation solutions proposed in this embodiment, specifically including:

[0043] Step 1: Obtain the key performance indicators of each server heat dissipation solution.

[0044] Specifically, the key performance indicators of the server heat dissipation solution include: temperature, noise, power, etc.

[0045] Step 2: According to the key performance indicators of each server heat dissipation solution, call the preset evaluation index model of the server heat dissipation solution to obtain the predicted evaluation index values of each server heat dissipation solution.

[0046] In this embodiment, the construction of the preset evaluation model of the server heat dissipation solution is specifically as follows:

[0047] Obtain historical server heat dissipation solutions and their corresponding key performance indicators;

[0048] Calculate the preliminary scores of historical server heat dissipation solutions;

[0049] Use the key performance indicators and preliminary scores of historical server heat dissipation solutions as training data to train the random forest model, and use the trained random forest model as the preset evaluation model of the server heat dissipation solution.

[0050] Specifically, the preliminary score F of the server cooling solution is calculated based on performance indicators such as the server energy consumption, server performance utilization, service temperature control, and server noise level. F When calculating, its specific calculation formula is as follows:

[0051] F F = aF PUE + bF UR + cF TC + dF NL

[0052] In the formula, a, b, c, and d are weighted calculation coefficients; F PUE is the score of the server energy consumption; F UR is the score of the server performance utilization; F TC is the score of the server temperature control; F NL is the score of the server noise level.

[0053] The determination process of the weighted calculation coefficients a, b, c, and d is as follows:

[0054] a + b + c + d = 1

[0055]

[0056]

[0057] The number of weighted calculation coefficients is determined by the number of performance indicators to be considered. Each performance indicator has a unique corresponding weighted calculation coefficient. The specific value of each weighted calculation coefficient is determined by the proportion of the corresponding indicator in the overall server. The proportion of the indicator in the overall server depends on the importance of the indicator to the server. The value of the weighted calculation coefficient is reserved to two decimal places, and the sum of all weighted calculation coefficients is 1.

[0058] The calculation formula for the score F of the server energy consumption is as follows: PUE In the formula, W

[0059]

[0060] is the total energy consumption of the server; W TEC is the energy consumption of the IT equipment. IT

[0061] When calculating the score F of the server performance utilization UR the utilization of performance such as CPU, GPU, memory, and storage is considered. Its specific calculation formula is as follows:

[0062] F UR = a1f CPU + b1f GPU + c1f MU+d1f DU

[0063] wherein, a1, b1, c1, and d1 are all weighted calculation coefficients; f CPU is the CPU utilization rate score; f GPU is the graphics card utilization rate score; f MU is the memory utilization rate score; f DU is the storage utilization rate score.

[0064] The determination process of the weighted calculation coefficients a1, b1, c1, and d1 is as follows:

[0065] a1 + b1 + c1 + d1 = 1

[0066]

[0067]

[0068] The number of weighted calculation coefficients is determined by the number of performance indicators to be considered. Each performance indicator has a uniquely corresponding weighted calculation coefficient. The specific value of each weighted calculation coefficient is determined by the proportion of the corresponding indicator in the overall server. The proportion of the indicator in the overall server depends on the importance of the indicator to the server. The value of the weighted calculation coefficient is reserved to two decimal places, and the sum of all weighted calculation coefficients is 1.

[0069] When calculating the CPU utilization rate score f CPU , the graphics card utilization rate score f GPU , the memory utilization rate score f MU , and the storage utilization rate score f DU and other performance scores, the usage situation of the server's relevant performance can be retrieved, and the proportion of the used resources to the total resources can be checked for scoring.

[0070]

[0071] Exemplarily, the preliminary scores F F corresponding to air-cooled, water-cooled, water-cooled, single-phase immersion, and phase-change immersion are shown in Table 1, and the performance utilization rate scores F UR are shown in Table 2.

[0072] Table 1 Preliminary scores F of four heat dissipation schemes F

[0073]

[0074]

[0075] Table 2 Server performance utilization rate scores F of four heat dissipation schemes UR

[0076]

[0077] It can be found from Table 1 and Table 2 that in terms of the server energy consumption, phase change immersion > single-phase immersion > water cooling > air cooling. The phase change immersion scheme has the best energy consumption situation and the highest energy utilization rate. In terms of the server performance utilization rate, water cooling > phase change immersion > single-phase immersion > air cooling. The water cooling scheme has the highest performance utilization rate, mainly affected by the CPU performance. In terms of temperature control, water cooling > air cooling > single-phase immersion > phase change immersion. The water cooling scheme has the best temperature control effect. In terms of noise level, phase change immersion > single-phase immersion > water cooling > air cooling. The phase change immersion scheme has the lowest noise. In the preliminary score F F , water-cooled servers > phase change immersion servers > single-phase immersion servers > air-cooled servers. The water cooling scheme has the highest preliminary score.

[0078] Through the above scheme, the preliminary scores F of the historical server heat dissipation schemes in the same usage environment are obtained F , and the key performance indicators and preliminary score F of the historical server heat dissipation schemes F are used as training data to train the random forest model, and the trained random forest model is used as the evaluation model for the preset server heat dissipation scheme.

[0079] Step 3: According to the predicted evaluation index values of each server heat dissipation scheme, screen through the preset first screening requirements to screen out several initially screened server heat dissipation schemes.

[0080] Specifically, screen out the predicted evaluation index values of each server heat dissipation scheme that exceed the set threshold to screen out several initially screened server heat dissipation schemes.

[0081] Step 4: According to the different usage environments of the servers, perform simulation calculations and matching analyses on each initially screened server heat dissipation scheme one by one to obtain the calculated evaluation index values of each initially screened server heat dissipation scheme.

[0082] In this embodiment, according to the different usage environments of the servers, perform simulation and matching analyses on each initially screened server heat dissipation scheme one by one to obtain the final scores of each initially screened server heat dissipation scheme, specifically:

[0083] Establish simulation with different usage environment conditions according to each initially screened server heat dissipation scheme, and respectively assign different weighting coefficients according to the matching degree of each server heat dissipation scheme with different usage environments and the consumption or cost situation of each server heat dissipation scheme in different usage environments; calculate the final score of each scheme according to the correction coefficient of each initially screened server heat dissipation scheme. The higher the matching degree, the higher the corresponding weight, and the lower the consumption or cost, the higher the corresponding weight.

[0084] When calculating the scoring correction coefficient x, screening factors such as heat dissipation, energy consumption, cost, and demand are considered, and its specific calculation formula is as follows:

[0085]

[0086] In the formula, a2, b2, c2, and d2 are all weighted calculation coefficients; f HD is the scoring of the heat dissipation effect of the scheme; f EC is the scoring of the energy consumption situation of the scheme; f C is the scoring of the cost of the scheme; f R is the scoring of the demand matching of the scheme.

[0087] The determination process of the weighted calculation coefficients a2, b2, c2, and d2 is as follows:

[0088] a2 + b2 + c2 + d2 = 1

[0089]

[0090] The number of weighted calculation coefficients is determined by the number of performance indicators to be considered. Each performance indicator has a unique corresponding weighted calculation coefficient. The specific value of each weighted calculation coefficient is determined by the proportion of the corresponding indicator in the overall server. The proportion of the indicator in the overall server depends on the importance of the indicator to the server. The value of the weighted calculation coefficient is reserved to two decimal places, and the sum of all weighted calculation coefficients is 1.

[0091] When calculating the scoring of indicators such as the heat dissipation effect scoring f HD , the energy consumption situation scoring f EC , the cost scoring f C and the demand matching scoring f R of the scheme, data such as the server heat dissipation situation, energy consumption situation, cost, and model of the evaluated scheme can be retrieved, and compared with the heat dissipation, energy consumption, cost, and demand in the ideal state to obtain the corresponding values.

[0092]

[0093] Among them, if the current heat dissipation effect is better than the ideal heat dissipation effect, the heat dissipation effect scoring f 0D of the scheme will be greater than 100 points, otherwise it will be less than 100 points; if the current energy consumption is lower than the ideal energy consumption, the energy consumption situation scoring f EC of the scheme will be greater than 100 points, otherwise it will be less than 100 points; if the current cost is lower than the ideal cost, the cost scoring f C of the scheme will be greater than 100 points, otherwise it will be less than 100 points; if the satisfied demand is more than all demands, the demand matching scoring f R of the scheme will be greater than 100 points, otherwise it will be less than 100 points.

[0094] Specifically, for each preliminary screening server cooling solution, a corresponding scoring correction coefficient x is generated, and it is multiplied by the preliminary score F F to obtain the final score F E and the cooling solutions are sorted according to the scores from high to low;

[0095] The final score F E is calculated as follows:

[0096] F E = xF F

[0097] where x is the scoring correction coefficient; F F is the preliminary score.

[0098] Step 5: According to the final scores of each preliminary screening server cooling solution, perform screening through a preset second screening requirement to screen out the final server cooling solution.

[0099] Specifically: Perform screening through a preset second screening requirement to screen out several second screening server cooling solutions;

[0100] According to the final scores, rank the several second screening server cooling solutions screened out, and select the solution with a higher rank as the final server cooling solution.

[0101] In all the above scores, the full score is 100 points. Scores below 60 points are unqualified, scores from 60 to 69 points are qualified, scores from 70 to 79 points are medium, scores from 80 to 89 points are good, scores from 90 to 95 points are excellent, and scores from 95 to 100 points are very excellent. If any score of a cooling solution is lower than 60 points, the solution is directly eliminated.

[0102] Exemplarily, the final scores F corresponding to air cooling, water cooling, water cooling, single-phase immersion, and phase change immersion E are shown in Table 3, and the scoring correction coefficient x is shown in Table 4.

[0103] Table 3 Final scores F of four cooling solutions E

[0104] Heat dissipation method Correction factor Preliminary score Final score Air-cooled 0.918 85.53 78.51654 Water-cooled 0.979 92.07 90.13653 Single-phase immersion 0.926 89.86 83.21036 Phase-change immersion 0.946 90.8 85.8968

[0105] Table 4 Scoring correction coefficient x

[0106]

[0107] It can be found from Table 3 and Table 4 that in terms of heat dissipation effect, water-cooled > phase-change immersion > single-phase immersion > air-cooled, and the water-cooled solution has the best heat dissipation; in terms of energy consumption, phase-change immersion > single-phase immersion > water-cooled > air-cooled, and the phase-change immersion solution has the lowest energy consumption; in terms of cost, air-cooled > water-cooled > single-phase immersion > phase-change immersion, and the air-cooled solution has the lowest cost; in terms of demand matching degree, water-cooled > phase-change immersion > single-phase immersion > air-cooled, and the water-cooled solution has the highest demand matching degree; in terms of the correction coefficient x, water-cooled > phase-change immersion > single-phase immersion > water-cooled, and the water-cooled solution has the highest correction coefficient; in terms of the final score F E , water-cooled > phase-change immersion > single-phase immersion > air-cooled, and the final score F of the water-cooled solution E is the highest.

[0108] It can be found from Table 1, Table 2, Table 3 and Table 4 that for home desktop servers, among the four heat dissipation solutions, the air-cooled solution has a low cost and has certain advantages in temperature control; the water-cooled solution has high performance utilization, good temperature control effect, good heat dissipation effect, and strong demand matching; the single-phase immersion solution has certain advantages in noise and energy consumption control; the phase-change immersion solution has low energy consumption and low noise, and has certain advantages in heat dissipation and demand matching. Considering comprehensively, the most suitable solution for home desktop servers is the water-cooled heat dissipation solution.

[0109] Embodiment 2

[0110] The purpose of this embodiment is to provide a server heat dissipation solution screening system, including:

[0111] An acquisition module, which is configured to: acquire the key performance indicators of each server heat dissipation solution;

[0112] A predicted evaluation index value module, which is configured to: call a preset evaluation model of the server heat dissipation solution according to the key performance indicators of each server heat dissipation solution, and obtain the predicted evaluation index values of each server heat dissipation solution;

[0113] A preliminary screening module, which is configured to: screen according to the predicted evaluation index values of each server heat dissipation solution through a preset first screening requirement, and screen out several preliminary screened server heat dissipation solutions;

[0114] A calculated evaluation index value module, which is configured to: perform simulation calculation on each preliminary screened server heat dissipation solution one by one according to different usage environments of the server, and perform matching degree analysis to obtain the final scores of each preliminary screened server heat dissipation solution;

[0115] A final screening module, which is configured to: screen according to the final scores of each preliminary screened server heat dissipation solution through a preset second screening requirement, and screen out the final server heat dissipation solution.

[0116] In more embodiments, there is also provided:

[0117] An electronic device includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in Embodiment 1 is completed. For the sake of brevity, it will not be elaborated here.

[0118] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0119] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0120] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method described in Embodiment 1 is completed.

[0121] The method in Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0122] A computer program product includes a computer program. When the computer program is executed by the processor, the method described in Embodiment 1 is implemented.

[0123] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which are executed in a device on a target real or virtual processor to perform the processes / methods described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or divided as needed among the program modules. The machine-executable instructions for the program modules can be executed within a local or distributed device. In a distributed device, the program modules can be located in local and remote storage media.

[0124] The computer program code for implementing the method of the present invention can be written in one or more programming languages. This computer program code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program code is executed by the computer or other programmable data processing device, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the computer, partially on the computer, as a stand-alone software package, partially on the computer and partially on a remote computer, or entirely on a remote computer or server.

[0125] In the context of the present invention, the computer program code or related data can be carried by any suitable carrier so that a device, apparatus, or processor can perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals can include electrical, optical, radio, sound, or other forms of propagated signals, such as carrier waves, infrared signals, etc.

[0126] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with this embodiment can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0127] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that based on the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A method for screening server heat dissipation solutions, characterized in that: include: Obtain key performance indicators of each server cooling solution; According to the key performance indicators of each server cooling solution, the preset evaluation indicator of the server cooling solution is called to calculate the random forest model to obtain the predicted evaluation indicator value of each server cooling solution; According to the predicted evaluation index value of each server cooling solution, a number of preliminary screening server cooling solutions are screened out through the preset first screening requirements; According to the different usage environments of the servers, each of the initially screened server cooling solutions is simulated and calculated one by one, and a matching analysis is performed to obtain the final score of each initially screened server cooling solution; According to the final scores of the initially screened server cooling solutions, the preset second screening requirements are used to screen out the final server cooling solutions.

2. A server heat dissipation solution screening method as claimed in claim 1, characterized in that: The key performance indicators of the server heat dissipation solution include: temperature, power and noise.

3. A server heat dissipation solution screening method as claimed in claim 1, characterized in that: The construction of the evaluation model of the preset server heat dissipation solution is specifically as follows: Obtain historical server cooling solutions and corresponding key performance indicators; Calculate preliminary scores for historical server cooling solutions; The key performance indicators of historical server cooling solutions and preliminary scores are used as training data to train the random forest model, and the trained random forest model is used as the evaluation model of the preset server cooling solution.

4. A server heat dissipation solution screening method as claimed in claim 1, characterized in that: The second screening requirements include server heat dissipation effect, server energy consumption, server solution cost and server solution demand matching.

5. A server heat dissipation solution screening method according to any one of claims 1 to 4, characterized in that: According to the different usage environments of the servers, each of the initially screened server cooling solutions is simulated and calculated and the matching degree is analyzed one by one to obtain the final score of each initially screened server cooling solution, which is as follows: Simulate and calculate the cooling solutions of each initially screened server in different preset usage environments one by one, and perform matching analysis. Calculate the correction coefficient of each initially screened server cooling solution based on different screening conditions such as heat dissipation, energy consumption, cost and demand; According to the correction coefficient of each initially screened server cooling solution and the corresponding predicted evaluation index value of each initially screened server cooling solution, the final score of each initially screened server cooling solution is calculated.

6. A server heat dissipation solution screening method as claimed in claim 5, characterized in that: According to the final scores of the initially screened server cooling solutions, the preset second screening requirements are used to screen out the final server cooling solutions, which are as follows: According to the final scores of the cooling solutions of the initially screened servers, the cooling solutions of the initially screened servers are ranked; According to the sorting results, the server cooling solution with the highest value is selected as the final server cooling solution.

7. A server heat dissipation solution screening system, characterized in that: include: An acquisition module is configured to: acquire key performance indicators of each server cooling solution; The prediction evaluation index value module is configured to: call a preset evaluation model of the server cooling scheme according to the key performance indicators of each server cooling scheme to obtain the prediction evaluation index value of each server cooling scheme; A preliminary screening module is configured to: screen a number of preliminary screening server cooling solutions according to the predicted evaluation index value of each server cooling solution through a preset first screening requirement; The evaluation index value calculation module is configured to: simulate and calculate each of the preliminarily screened server cooling solutions one by one according to different server usage environments, and perform matching analysis to obtain the final score of each preliminarily screened server cooling solution; The final screening module is configured to: screen the final server cooling solutions according to the final scores of the initially screened server cooling solutions through the preset second screening requirements, and screen out the final server cooling solutions.

8. An electronic device, characterized in that: The method comprises a memory and a processor and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the method described in any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images