Cloud-based server heat dissipation method and system

Abstract

The invention relates to the technical field of server heat dissipation, in particular to a cloud-based server heat dissipation method and system, and the method comprises the following steps: monitoring the key operation parameters of a server in real time through a cloud platform, updating the state of a heat dissipation unit according to the heat dissipation demands monitored in real time, optimizing the heat dissipation efficiency, and obtaining the optimal configuration of the heat dissipation parameters. Through real-time monitoring and data-driven heat dissipation control, heat dissipation efficiency and energy consumption management are remarkably optimized, dynamic heat dissipation unit state updating and optimization are introduced, so that heat dissipation configuration can respond to real-time load and temperature changes of the server in real time, and by continuously adjusting feedback control logic including the feedback period and strength, the heat dissipation efficiency of the server is improved. The influence of the state of the heat dissipation unit can be simulated and predicted, the optimal configuration of the heat dissipation parameters is realized, the energy utilization of the server is optimized, the optimal matching between the heat dissipation control and the server load is ensured, the energy consumption is reduced, and meanwhile, the heat dissipation control efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of server heat dissipation, and in particular to a cloud-based server heat dissipation method and system. Background Art

[0002] Server cooling technology involves the use of different hardware devices to control and optimize the temperature of data centers, server rooms, and individual servers. Effective heat dissipation is essential to maintaining server performance, improving energy efficiency, and extending the life of hardware. Common cooling technologies include air cooling systems (such as fans and heat sinks), liquid cooling systems (such as water cooling or oil cooling), as well as phase change cooling and heat pipe technology.

[0003] Among them, the server cooling method is a technology that uses cloud computing resources to monitor and optimize the server's cooling process. It usually relies on a centrally managed software platform that can collect server temperature data in real time and analyze this data through cloud computing resources to adjust the working status of the cooling system or change the server's workload distribution. Its main purpose is to improve the energy efficiency of data centers, reduce operation and maintenance costs, and ensure that servers run at optimal temperatures to maintain performance and avoid failures caused by overheating.

[0004] Existing technologies rely on fixed cooling strategies and cannot be adjusted according to real-time data, resulting in the inability to provide sufficient cooling in time when the server load suddenly increases, increasing the risk of overheating. Especially when processing high-performance tasks, fixed cooling strategies lead to unnecessary energy waste or even hardware failures. In addition, the rigidity of existing technologies in the allocation of cooling resources makes it difficult to adapt to the diversified and dynamically changing needs of data centers, which not only affects the cooling effect, but also limits the optimization potential of data centers in energy efficiency and operation and maintenance costs, resulting in increased operation and maintenance costs and reduced server reliability. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a cloud-based server heat dissipation method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a cloud-based server heat dissipation method, comprising the following steps:

[0007] S1: Through the cloud platform, the key operating parameters of the server are monitored in real time. According to the real-time monitoring of the cooling demand, the cooling unit status is updated, the cooling efficiency is optimized, and the cooling parameter optimization configuration is obtained;

[0008] S2: Based on the heat dissipation parameter optimization configuration, the feedback control logic of the heat dissipation management is adjusted, including the feedback cycle and intensity, and the heat dissipation parameter settings of the server are optimized by simulating the influence of various heat dissipation unit states, and the adjusted heat dissipation settings are verified to obtain feedback control adjustment results;

[0009] S3: Based on the feedback control adjustment result, identify the deviation from the expected target of server performance, adjust the key parameters of heat dissipation control, refine the matching and response performance of heat dissipation control, and obtain a heat dissipation response optimization record;

[0010] S4: Based on the heat dissipation response optimization record, continuously monitor the heat dissipation effect of the server, adjust the heat dissipation unit to match the current load change of the server, and evaluate whether the server heat dissipation reaches the target efficiency and power consumption standards through the cloud platform, and generate a server heat dissipation log.

[0011] The present invention is improved in that the monitoring steps of the key operating parameters are specifically as follows:

[0012] S111: collect the temperature, power consumption, CPU and GPU load data of the server in real time through the cloud platform to obtain real-time operating parameters;

[0013] S112: Based on the real-time operating parameters, key parameters exceeding the threshold are screened, using the formula:

[0014] PQ=α Q ×T W +β Q ×P W +γ Q ×C W +δ Q ×G W

[0015] Perform weighted scoring PQ on the data to obtain a list of key monitored parameters, where T W , P W , C W and G W Represents temperature, power consumption, CPU load and GPU load data respectively, α Q , β Q , γ Q and δ Q is the corresponding weight coefficient.

[0016] The present invention is improved in that the step of obtaining the optimal configuration of the heat dissipation parameters is specifically as follows:

[0017] S121: obtaining heat dissipation demand analysis information by collecting temperature and power consumption indicators obtained from the server in real time, identifying heat dissipation parameters to be adjusted;

[0018] S122: Based on the heat dissipation demand analysis information, the heat dissipation unit status is updated using the formula:

[0019]

[0020] Adjust the heat dissipation efficiency and energy consumption to the target state to obtain the optimal configuration of heat dissipation parameters, where FE current Represents the current heat dissipation efficiency, FE opt represents the ideal heat dissipation efficiency, λ F is the adjustment factor, FP current Represents the current energy consumption, FP opt represents the target energy consumption, η F is the energy consumption adjustment factor.

[0021] The present invention is improved in that the adjustment steps of the feedback control logic are specifically as follows:

[0022] S211: Based on the heat dissipation parameter optimization configuration, analyzing the current operation status and performance index of the heat dissipation unit, and generating a data analysis record;

[0023] S212: Readjust the feedback control logic of the heat dissipation management according to the data analysis record, using the formula:

[0024]

[0025] Determine the current feedback cycle and feedback strength to obtain the optimized feedback control logic Control new , where k R is the adjustment factor, Delta temp is the temperature change, Threshold temp is the temperature change threshold, Control current is the current control setting;

[0026] S213: Implement the optimized feedback control logic, monitor the impact on heat dissipation efficiency, and verify the effectiveness of the new logic through current operating data to obtain verified feedback control logic.

[0027] The present invention is improved in that the step of obtaining the feedback control adjustment result is specifically as follows:

[0028] S221: Simulate the influence of the various heat dissipation unit states on the server temperature, determine the optimal heat dissipation parameters, including the operating frequency and cooling intensity of the heat dissipation unit, and obtain preliminary heat dissipation simulation data;

[0029] S222: Based on the preliminary heat dissipation simulation data, the formula is used:

[0030]

[0031] Adjust the server cooling parameters to get the optimized parameter configuration RC opt , where TC target is the target temperature, TC i is the temperature reached by the ith cooling unit in the simulation, n C is the total number of cooling units;

[0032] S223: Based on the optimized parameter configuration, perform an operation test, collect data to verify the heat dissipation effect, and obtain a feedback control adjustment result.

[0033] The present invention is improved in that the step of identifying the deviation from the expected target of server performance is specifically:

[0034] S311: Based on the feedback control adjustment result, collect the temperature, power consumption and operation index of the current server operation to generate a real-time operation data set;

[0035] S312: Based on the real-time operation data set, the expected target data of the server performance is compared, using the formula:

[0036]

[0037] Calculate the square sum of deviations DT of each performance indicator to obtain the performance deviation analysis results, where PN actual,i Indicates current performance data, PN target,i represents the target performance data, n T Indicates the number of performance indicators;

[0038] S313: According to the performance deviation analysis result, the key factors causing the performance not to meet the standard are evaluated to obtain a deviation identification result.

[0039] The present invention is improved in that the step of obtaining the heat dissipation response optimization record is specifically as follows:

[0040] S321: Adjust the key parameters of the heat dissipation control using the formula:

[0041] AR new =AR current +κ A ·(AT target -AT actual )

[0042] Automatically adjust to match server performance requirements and obtain heat dissipation performance data, among which AR new is the adjusted thermal response parameter, AR current is the current heat dissipation response parameter, AT target is the target temperature, AT actual is the current temperature;

[0043] S322: Based on the heat dissipation performance data, refine the matching and response performance of the heat dissipation control, verify the influence of the heat dissipation optimization, and obtain the heat dissipation response optimization record.

[0044] The present invention is improved in that the steps of obtaining the server heat dissipation log are specifically as follows:

[0045] S411: Based on the heat dissipation response optimization record, continuous monitoring is implemented to collect the current temperature of the server and the state of the heat dissipation unit, and the matching degree with the server load is calculated using the formula:

[0046]

[0047] Evaluate server cooling efficiency M efficiency , where AT target is the target temperature, AT actual is the current temperature, L current is the current load of the server, S unit is the current status of the cooling unit;

[0048] S412: Based on the heat dissipation efficiency of the server, the heat dissipation unit is adjusted to match the current load change of the server, and whether the heat dissipation of the server reaches the target efficiency and power consumption standard is evaluated through the cloud platform to obtain the server heat dissipation log.

[0049] A cloud-based server cooling system, the system comprising:

[0050] The real-time heat dissipation monitoring module monitors the key operating parameters of the server through the cloud platform, updates the status of the heat dissipation unit in real time according to the heat dissipation requirements, optimizes the heat dissipation efficiency and energy consumption management, and generates the optimal configuration of heat dissipation parameters;

[0051] The heat dissipation feedback adjustment module adjusts the feedback control logic of heat dissipation management, including feedback cycle and intensity, based on the heat dissipation parameter optimization configuration, optimizes the server heat dissipation parameter settings by simulating the influence of various heat dissipation unit states, verifies the adjustment effect, and generates feedback control adjustment results;

[0052] The performance matching adjustment module identifies the deviation from the expected target of server performance based on the feedback control adjustment result, adjusts the key parameters of the heat dissipation control, refines the matching and response performance of the heat dissipation control, and obtains a heat dissipation response optimization record;

[0053] The dynamic heat dissipation monitoring module continuously monitors the heat dissipation effect of the server based on the heat dissipation response optimization record, automatically adjusts the state of the heat dissipation unit according to the current server load change, and obtains server monitoring data;

[0054] The heat dissipation efficiency evaluation module evaluates whether the server heat dissipation reaches the target efficiency and power consumption standard based on the server monitoring data, optimizes the heat dissipation configuration, and matches the potential load changes to obtain the server heat dissipation log.

[0055] Compared with the prior art, the advantages and positive effects of the present invention are:

[0056] In the present invention, through real-time monitoring and data-driven heat dissipation control, the heat dissipation efficiency and energy consumption management are significantly optimized, and dynamic heat dissipation unit status update and optimization are introduced, so that the heat dissipation configuration can instantly respond to the real-time load and temperature changes of the server. By continuously adjusting the feedback control logic, including the feedback cycle and intensity, the influence of the heat dissipation unit status can be simulated and predicted, and the optimal configuration of the heat dissipation parameters can be achieved, thereby optimizing the energy utilization of the server, ensuring the best match between the heat dissipation control and the server load, reducing energy consumption, and improving the heat dissipation control efficiency. The continuous updating and application of the heat dissipation response optimization record enables the server heat dissipation to maintain optimal performance under different working conditions, reducing the risk of performance loss or hardware damage caused by insufficient heat dissipation. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flow chart of a cloud-based server heat dissipation method is proposed for the present invention;

[0058] Figure 2 It is a monitoring flow chart of key operating parameters in the present invention;

[0059] Figure 3 A flow chart for obtaining the optimal configuration of heat dissipation parameters in the present invention;

[0060] Figure 4 is a flow chart for adjusting the feedback control logic in the present invention;

[0061] Figure 5 A flow chart for obtaining feedback control adjustment results in the present invention;

[0062] Figure 6 A flowchart for identifying deviations from expected server performance targets in the present invention;

[0063] Figure 7 A flow chart for obtaining the heat dissipation response optimization record in the present invention;

[0064] Figure 8 This is a flow chart for obtaining the server heat dissipation log in the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0067] Example

[0068] See also Figure 1 The present invention provides a technical solution: a cloud-based server heat dissipation method, comprising the following steps:

[0069] S1: Through the cloud platform, the key operating parameters of the server are monitored in real time, including server temperature, power consumption, CPU and GPU load data. According to the real-time monitored cooling demand, the cooling unit status is updated, and the cooling efficiency is optimized to obtain the optimal configuration of cooling parameters; the cooling unit specifically refers to cooling components such as fans, heat sinks and coolants;

[0070] S2: Based on the optimized configuration of cooling parameters, the feedback control logic of cooling management is adjusted, including the feedback cycle and intensity. By simulating the impact of various cooling unit states, the cooling parameter settings of the server are optimized, and the adjusted cooling settings are verified to obtain the feedback control adjustment results.

[0071] S3: Based on the feedback control adjustment results, identify the deviation from the expected server performance target, adjust the key parameters of the heat dissipation control, refine the matching and response performance of the heat dissipation control, and obtain the heat dissipation response optimization record; the key parameters of the heat dissipation control include: fan speed, coolant flow, temperature threshold and operating load of the heat dissipation device;

[0072] S4: Based on the heat dissipation response optimization record, continuously monitor the server heat dissipation effect, adjust the heat dissipation unit, match the current load change of the server, and evaluate whether the server heat dissipation meets the target efficiency and power consumption standards through the cloud platform, and generate a server heat dissipation log.

[0073] The heat dissipation parameter optimization configuration includes temperature control standards, power thresholds, and response efficiency. The feedback control adjustment results are specifically the adjustment cycle, feedback strength, and effect prediction information. The heat dissipation response optimization records include difference analysis results, control parameter adjustment results, and matching evaluation results. The server heat dissipation log includes temperature log, power consumption record, and load change record.

[0074] See also Figure 2 , the monitoring steps of key operating parameters are as follows:

[0075] S111: collect the temperature, power consumption, CPU and GPU load data of the server in real time through the cloud platform to obtain real-time operating parameters;

[0076] By deploying a real-time monitoring system on the cloud platform, the server's temperature, power consumption, CPU and GPU load are continuously monitored. The real-time collected temperature data is obtained through the temperature sensor inside the server, and the power consumption is calculated through the current and voltage sensors to calculate the real-time power value. The CPU and GPU loads are provided with load data by the processor's performance monitoring unit PMU and the graphics processing unit's monitoring interface respectively. The monitoring system stores key data in the data set at specific time intervals. During the data collection process, outliers are eliminated and deviations caused by hardware errors or network delays are corrected to ensure the integrity and accuracy of the data and obtain a real-time operating parameter data set.

[0077] S112: Based on the real-time operating parameters, filter out the key parameters that exceed the threshold, using the formula:

[0078] PQ=α Q ×T W +β Q ×P W +γ Q ×C W +δ Q ×G W

[0079] Perform weighted scoring PQ on the data to obtain a list of key monitored parameters, where T W , P W , C W and G W Represents temperature, power consumption, CPU load and GPU load data respectively, α Q , β Q , γ Q and δ Q is the corresponding weight coefficient;

[0080] If the following data is available, the current temperature of the server is T W =70 degrees, power consumption P W =350W, CPU load C W=40%, GPU load G W =75%, the weight coefficient is set to α Q =0.25, β Q =0.30,γ Q =0.20,δ Q =0.25. The calculation process is:

[0081] PQ=0.25×70+0.30×350+0.20×40+0.25×75

[0082] PQ=17.5+105+8+18.75=149.25

[0083] The result shows that the score of 149.25 points reflects that the current status of the server is relatively critical and needs to be monitored. It can help technicians prioritize or adjust resources to ensure stable operation of the server.

[0084] See also Figure 3 , the specific steps for obtaining the optimal configuration of heat dissipation parameters are:

[0085] S121: by collecting temperature and power consumption indicators obtained from the server in real time, identifying heat dissipation parameters that need to be adjusted, and obtaining heat dissipation demand analysis information;

[0086] By real-time monitoring of the server, collecting temperature and power consumption data and performing data analysis, it is possible to identify cooling parameters that need to be adjusted. For example, if the temperature exceeds the set threshold or the power consumption increases abnormally, the parameters will be recorded and marked as key monitoring objects. Furthermore, the data will be used to generate cooling demand analysis information, which will provide decision support for the optimization of the cooling system.

[0087] S122: Based on the heat dissipation demand analysis information, the heat dissipation unit status is updated using the formula:

[0088]

[0089] Adjust the heat dissipation efficiency and energy consumption to the target state to obtain the optimal configuration of heat dissipation parameters, where FE current Represents the current heat dissipation efficiency, FE opt represents the ideal heat dissipation efficiency, λ F is the adjustment factor used to balance the transition between the current state and the ideal target, FP current Represents the current energy consumption, FP opt represents the target energy consumption, η F is the energy consumption adjustment factor;

[0090] If the following data is available, the current heat dissipation efficiency FE current =0.75, ideal heat dissipation efficiency FE opt=0.90, current energy consumption FP current =150W, target power consumption FP opt =100W, adjustment factor λ F =0.2 and energy consumption adjustment coefficient η F =0.05, substitute into the formula to calculate:

[0091]

[0092] FE new =0.15+0.72+0.075

[0093] FE new =0.945

[0094] The result shows that the current heat dissipation efficiency is 0.945, or 94.5%, indicating that after adjustment, the cooling system can manage heat more effectively while controlling energy consumption at a lower level, thereby optimizing overall performance.

[0095] See also Figure 4 , the adjustment steps of the feedback control logic are as follows:

[0096] S211: Analyze the operating status and performance indicators of the current cooling unit based on the cooling parameter optimization configuration, and generate a data analysis record;

[0097] Collect temperature fluctuation and power consumption data, analyze the information, identify key factors affecting cooling efficiency, such as cooling unit response time and power consumption pattern, and determine trends and outliers in the data, generate data analysis records, record the analysis results of all collected data, and propose performance improvement measures.

[0098] S212: Readjust the feedback control logic of the heat dissipation management according to the data analysis record, using the formula:

[0099]

[0100] Determine the current feedback cycle and feedback strength to obtain the optimized feedback control logic Control new , where k R is the adjustment factor, Delta temp is the temperature change, Threshold temp is the temperature change threshold, Control current is the current control setting;

[0101] The current temperature difference is Delta temp =10℃, the temperature threshold is Threshold temp =5℃, the current control setting is Control current=50, the adjustment factor is k R =0.5. The calculation process is as follows:

[0102]

[0103] Control new =0.5×2+50

[0104] Control new =1+50

[0105] Control new =51

[0106] This result shows that the optimized feedback control logic is 51. Compared with the current setting of 50, the subtle adjustment allows a more sensitive response to temperature changes, thereby effectively controlling the cooling performance, ensuring stable operation and saving energy.

[0107] S213: Implementing the optimized feedback control logic, monitoring the impact on the heat dissipation efficiency, and verifying the effectiveness of the new logic through current operation data to obtain the verified feedback control logic;

[0108] After implementing the current feedback control logic, the effectiveness of the adjusted control strategy is evaluated by continuously monitoring the heat dissipation efficiency and response, including comparing the energy consumption and working efficiency of the heat dissipation unit before and after the adjustment, and verifying it through actual operating data to ensure that the current feedback control logic can meet the latest heat dissipation requirements, and establish and confirm whether the updated feedback control has achieved the expected goals.

[0109] See also Figure 5 , the steps for obtaining the feedback control adjustment results are as follows:

[0110] S221: simulating the influence of various cooling unit states on the server temperature, determining the optimal cooling parameters, including the operating frequency and cooling intensity of the cooling unit, and obtaining preliminary cooling simulation data;

[0111] Simulate the impact of various cooling unit states on server temperature to determine the optimal cooling parameter configuration, which involves adjusting the operating frequency and cooling intensity. Complete the simulation through high-performance computing resources, analyze the data of each unit's impact on the overall temperature, ensure that each unit's configuration can maximize the cooling efficiency, collect simulation data to provide a basis for the next step of parameter optimization, and complete preliminary cooling simulation data.

[0112] S222: Based on preliminary heat dissipation simulation data, the formula is used:

[0113]

[0114] Adjust the server cooling parameters to get the optimized parameter configuration RCopt , where TC target is the target temperature, TC i is the temperature reached by the ith cooling unit in the simulation, n C is the total number of cooling units;

[0115] If the following data is available, the target temperature TC target is 35℃, the cooling unit temperature TC i is [34℃, 36℃, 37℃], the total number of cooling units is n C is 3, substitute it into the formula to calculate:

[0116]

[0117] RC opt =2

[0118] This result shows that the average square difference between each unit and the target temperature is 2, reflecting the deviation between the current cooling settings and the target settings. The optimized settings should reduce this deviation and improve the cooling efficiency.

[0119] S223: Based on the optimized parameter configuration, an operation test is performed to collect data to verify the heat dissipation effect, ensure that the new parameter setting can reach or exceed the predetermined heat dissipation performance standard under various operating conditions, and obtain feedback control adjustment results;

[0120] Based on the optimized cooling parameter configuration, actual operation tests are carried out to monitor the cooling efficiency and system response, collect operation data for analysis, verify the actual impact of the new cooling settings on temperature control, and confirm through data comparison whether the new parameter settings make the cooling performance reach or exceed the predetermined standards, so as to ensure stability and efficiency in actual operation and obtain feedback control adjustment results.

[0121] See also Figure 6 , the steps to identify deviations from the expected server performance goals are:

[0122] S311: Based on the feedback control adjustment result, collect the temperature, power consumption and operation index of the current server operation, and generate a real-time operation data set;

[0123] Based on the feedback control adjustment results, the monitoring of the server's actual performance data includes temperature, power consumption, and the operating efficiency of the CPU and GPU. This process involves real-time collection and organization of data to form a data set including real-time readings of each parameter. This data set is subsequently used to compare with the predetermined performance targets to analyze the actual operating status of the server.

[0124] S312: Based on the real-time running data set, the expected target data of the server performance is compared using the formula:

[0125]

[0126] Calculate the square sum of deviations DT of each performance indicator to obtain the performance deviation analysis results, where PN actual,i Indicates current performance data, PN target,i Represents the target performance data, n T Indicates the number of performance indicators;

[0127] If there are five performance indicators such as power consumption and CPU usage, and the actual data is:

[0128] PN actual ={65,55,85,90,75}

[0129] The target data is:

[0130] PN target ={60,50,80,85,70}

[0131] Then n T =5.

[0132] Calculate DT by substituting the actual and target values:

[0133] DT=(65-60) 2 +(55-50) 2 +(85-80) 2 +(90-85) 2 +(75-70) 2

[0134] DT=25+25+25+25+25=125

[0135] The result shows that the total squared deviation of the performance is 125, which reflects the overall difference between the current performance and the target performance and provides basic data for optimization and adjustment.

[0136] S313: Based on the performance deviation analysis results, evaluate the key factors that lead to substandard performance and obtain deviation identification results;

[0137] Through the performance deviation analysis results, a detailed evaluation is conducted on various factors that cause server performance to fail to meet standards, including but not limited to the impact of heat dissipation efficiency, power configuration, and other hardware parameters. The analysis is conducted based on the specific performance in the data set, and then the key technologies or configuration issues that cause the performance gap are determined, and accurate deviation identification results are obtained, providing a basis for subsequent optimization and adjustment.

[0138] See also Figure 7 , the specific steps for obtaining the heat dissipation response optimization record are:

[0139] S321: Adjust the key parameters of heat dissipation control using the formula:

[0140] AR new =AR current +κ A ·(AT target -AT actual )

[0141] Automatically adjust to match server performance requirements and obtain heat dissipation performance data, among which AR new is the adjusted thermal response parameter, AR current is the current heat dissipation response parameter, AT target is the target temperature, AT actual is the current temperature, κ A is the adjustment coefficient, which is used to determine the sensitivity and amplitude of the cooling parameter adjustment;

[0142] If the following data is available, AR current =30, AT target =75, AT actual =80,κ A =0.1, the current heat dissipation response parameter AR needs to be calculated new :

[0143] First calculate the temperature difference:

[0144] AT target -AT actual =75-80=-5

[0145] Then apply the formula to calculate AR new :

[0146] AR new =30+0.1·(-5)=30-0.5=29.5

[0147] When the actual temperature is higher than the target temperature, the heat dissipation response parameters will be appropriately reduced to increase the heat dissipation effect, thereby adjusting the actual temperature to near the target temperature, helping to keep the server at the optimal operating temperature and optimize performance and power efficiency.

[0148] S322: Based on the heat dissipation performance data, refine the matching and response performance of the heat dissipation control, verify the influence of the heat dissipation optimization, and obtain the heat dissipation response optimization record;

[0149] Based on the real-time monitoring of heat dissipation performance data, the adjustment strategy of the heat dissipation control system is refined, and the temperature and power consumption of each heat dissipation unit are recorded in real time through high-frequency data acquisition. At the same time, the data analysis algorithm is introduced to conduct preliminary screening and classification of the collected data, and sort out the key data affecting the heat dissipation performance, such as temperature peaks and energy consumption anomalies under specific working conditions. The data is compared with the preset heat dissipation performance target parameters, and the data points with large deviations are identified and analyzed. The reasons, such as aging of the heat dissipation unit, changes in ambient temperature or abnormal operation, are further analyzed. By simulating different heat dissipation schemes, the operating frequency and cooling intensity of the heat dissipation unit are adjusted, the heat dissipation parameter configuration is optimized, and a heat dissipation response optimization record is formed.

[0150] See also Figure 8 , the specific steps for obtaining the server cooling log are:

[0151] S411: Based on the heat dissipation response optimization record, continuous monitoring is implemented to collect the current temperature and heat dissipation unit status of the server, and the matching degree with the server load is calculated using the formula:

[0152]

[0153] Evaluate server cooling efficiency M efficiency , determine whether the cooling unit needs to be adjusted, where AT target is the target temperature, AT actual is the current temperature, L current is the current load of the server, S unit is the current status of the cooling unit;

[0154] If the following data is available, AT target =60℃, AT actual =70℃,L current = 80%, and S unit =20%, then substitute the calculation into the following:

[0155] Calculate the temperature difference ratio:

[0156]

[0157] Calculate the ratio of cooling unit to load and substitute into the formula:

[0158]

[0159] Solve the contents of the brackets:

[0160] M efficiency =-0.1667×(1+0.25)=-0.1667×1.25

[0161] The calculation results are:

[0162] M efficiency =-0.2084

[0163] The result shows that the current heat dissipation efficiency is -0.2084, which means that the current temperature exceeds the target temperature and the response of the heat dissipation unit fails to fully match the load demand, so the heat dissipation unit needs to be adjusted.

[0164] S412: Based on the heat dissipation efficiency of the server, the heat dissipation unit is adjusted to match the current load change of the server, and whether the heat dissipation of the server reaches the target efficiency and power consumption standard is evaluated through the cloud platform, and the heat dissipation log of the server is obtained;

[0165] Based on the server heat dissipation efficiency, according to the temperature data fed back in real-time monitoring and the operating status information of the heat dissipation unit, the server temperature change trends under different loads are compared, and various temperature and load correlation parameters are extracted, including the operating parameters of the heat dissipation unit under high load and low load scenarios, such as fan speed, coolant flow, etc. Finally, the gap between the current heat dissipation status and the target status is compared through the cloud platform, the efficiency difference in the heat dissipation process is evaluated, and the difference data is summarized to generate a server heat dissipation log.

[0166] A cloud-based server cooling system, the system comprising:

[0167] The real-time heat dissipation monitoring module monitors the key operating parameters of the server through the cloud platform, updates the status of the heat dissipation unit in real time according to the heat dissipation requirements, optimizes the heat dissipation efficiency and energy consumption management, and generates the optimal configuration of heat dissipation parameters;

[0168] The heat dissipation feedback adjustment module adjusts the feedback control logic of heat dissipation management, including feedback cycle and intensity, based on the heat dissipation parameter optimization configuration. It optimizes the server heat dissipation parameter settings by simulating the influence of various heat dissipation unit states, verifies the adjustment effect, and generates feedback control adjustment results.

[0169] The performance matching adjustment module identifies the deviation from the expected server performance target based on the feedback control adjustment results, adjusts the key parameters of the heat dissipation control, refines the matching and response performance of the heat dissipation control, and obtains the heat dissipation response optimization record;

[0170] The dynamic heat dissipation monitoring module continuously monitors the heat dissipation effect of the server based on the heat dissipation response optimization record, automatically adjusts the state of the heat dissipation unit according to the current server load changes, and obtains server monitoring data;

[0171] The heat dissipation efficiency evaluation module evaluates whether the server heat dissipation meets the target efficiency and power consumption standards based on the server monitoring data, optimizes the heat dissipation configuration, and matches potential load changes to obtain the server heat dissipation log.

[0172] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A cloud-based server heat dissipation method, characterized in that: The following steps are involved: Through the cloud platform, the key operating parameters of the server are monitored in real time. According to the real-time monitoring of the cooling demand, the cooling unit status is updated, the cooling efficiency is optimized, and the cooling parameter optimization configuration is obtained; Based on the heat dissipation parameter optimization configuration, the feedback control logic of the heat dissipation management is adjusted, including the feedback cycle and intensity, and the heat dissipation parameter settings of the server are optimized by simulating the influence of various heat dissipation unit states, and the adjusted heat dissipation settings are verified to obtain feedback control adjustment results; Based on the feedback control adjustment result, the deviation from the expected target of server performance is identified, key parameters of heat dissipation control are adjusted, the matching and response performance of heat dissipation control are refined, and a heat dissipation response optimization record is obtained; Based on the heat dissipation response optimization record, the server heat dissipation effect is continuously monitored, the heat dissipation unit is adjusted to match the current load change of the server, and the cloud platform is used to evaluate whether the server heat dissipation meets the target efficiency and power consumption standards, and generate a server heat dissipation log.

2. The cloud-based server heat dissipation method according to claim 1, characterized in that: The monitoring steps of the key operating parameters are specifically as follows: Through the cloud platform, the server's temperature, power consumption, CPU and GPU load data are collected in real time to obtain real-time operating parameters; Based on the real-time operating parameters, key parameters exceeding the threshold are screened using the formula: PQ=a Q ×T W +b Q ×P W +g Q ×C W +d Q ×G W Perform weighted scoring PQ on the data to obtain a list of key monitored parameters, where T W , P W , C W and G W Represents temperature, power consumption, CPU load and GPU load data respectively, α Q , β Q , γ Q and δ Q is the corresponding weight coefficient.

3. The cloud-based server heat dissipation method according to claim 1, characterized in that: The steps for obtaining the heat dissipation parameter optimization configuration are specifically as follows: By collecting temperature and power consumption indicators obtained from the server in real time, identifying the heat dissipation parameters that need to be adjusted, and obtaining heat dissipation demand analysis information; Based on the heat dissipation demand analysis information, the heat dissipation unit status is updated using the formula: Adjust the heat dissipation efficiency and energy consumption to the target state to obtain the optimal configuration of heat dissipation parameters, where FE current Represents the current heat dissipation efficiency, FE opt represents the ideal heat dissipation efficiency, λ F is the adjustment factor, FP current Represents the current energy consumption, FP opt represents the target energy consumption, η F is the energy consumption adjustment factor.

4. The cloud-based server heat dissipation method according to claim 1, characterized in that: The adjustment steps of the feedback control logic are specifically as follows: Based on the optimized configuration of the heat dissipation parameters, analyzing the operating status and performance indicators of the current heat dissipation unit, and generating a data analysis record; According to the data analysis records, the feedback control logic of the heat dissipation management is readjusted, using the formula: Determine the current feedback cycle and feedback strength to obtain the optimized feedback control logic Control new , where k R is the adjustment factor, Delta temp is the temperature change, Threshold temp is the temperature change threshold, Control current is the current control setting; The optimized feedback control logic is implemented, the impact on the heat dissipation efficiency is monitored, and the effectiveness of the new logic is verified through current operating data to obtain a verified feedback control logic.

5. The cloud-based server heat dissipation method according to claim 1, characterized in that: The steps of obtaining the feedback control adjustment result are specifically as follows: Simulate the impact of the various cooling unit states on the server temperature, determine optimal cooling parameters, including the operating frequency and cooling intensity of the cooling unit, and obtain preliminary cooling simulation data; Based on the preliminary heat dissipation simulation data, the formula is adopted: Adjust the server cooling parameters to get the optimized parameter configuration RC opt , where TC target is the target temperature, TC i is the temperature reached by the ith cooling unit in the simulation, n C is the total number of cooling units; Based on the optimized parameter configuration, an operation test is performed, data is collected to verify the heat dissipation effect, and feedback control adjustment results are obtained.

6. The cloud-based server heat dissipation method according to claim 1, characterized in that: The steps for identifying the deviation from the expected target of server performance are specifically: Based on the feedback control adjustment result, collecting the temperature, power consumption and operation index of the current server operation to generate a real-time operation data set; Based on the real-time running data set, the expected target data of server performance is compared with the formula: Calculate the square sum of deviations DT of each performance indicator to obtain the performance deviation analysis results, where PN actual,i Indicates current performance data, PN target,i Represents the target performance data, n T Indicates the number of performance indicators; Based on the performance deviation analysis results, key factors leading to substandard performance are evaluated to obtain deviation identification results.

7. The cloud-based server heat dissipation method according to claim 1, characterized in that: The steps for obtaining the heat dissipation response optimization record are specifically as follows: To adjust the key parameters of the thermal control, the formula is used: AR new =AR current +κ A ·(AT target -AT actual ) Automatically adjust to match server performance requirements and obtain heat dissipation performance data, among which AR new is the adjusted thermal response parameter, AR current is the current heat dissipation response parameter, AT target is the target temperature, AT actual is the current temperature; Based on the heat dissipation performance data, the matching and response performance of the heat dissipation control are refined, the influence of the heat dissipation optimization is verified, and the heat dissipation response optimization record is obtained.

8. The cloud-based server heat dissipation method according to claim 1, characterized in that: The steps for obtaining the server heat dissipation log are specifically as follows: Based on the heat dissipation response optimization record, continuous monitoring is implemented to collect the current temperature and heat dissipation unit status of the server, and the matching degree with the server load is calculated using the formula: Evaluate server cooling efficiency M efficiency , where AT target is the target temperature, AT actual is the current temperature, L current is the current load of the server, S unit is the current status of the cooling unit; Based on the server heat dissipation efficiency, the heat dissipation unit is adjusted to match the current load change of the server, and the cloud platform is used to evaluate whether the server heat dissipation reaches the target efficiency and power consumption standard to obtain the server heat dissipation log.

9. A cloud-based server cooling system, characterized in that: According to the cloud-based server heat dissipation method according to any one of claims 1 to 8, the system comprises: The real-time heat dissipation monitoring module monitors the key operating parameters of the server through the cloud platform, updates the status of the heat dissipation unit in real time according to the heat dissipation requirements, optimizes the heat dissipation efficiency and energy consumption management, and generates the optimal configuration of heat dissipation parameters; The heat dissipation feedback adjustment module adjusts the feedback control logic of heat dissipation management, including feedback cycle and intensity, based on the heat dissipation parameter optimization configuration, optimizes the server heat dissipation parameter settings by simulating the influence of various heat dissipation unit states, verifies the adjustment effect, and generates feedback control adjustment results; The performance matching adjustment module identifies the deviation from the expected target of server performance based on the feedback control adjustment result, adjusts the key parameters of the heat dissipation control, refines the matching and response performance of the heat dissipation control, and obtains a heat dissipation response optimization record; The dynamic heat dissipation monitoring module continuously monitors the heat dissipation effect of the server based on the heat dissipation response optimization record, automatically adjusts the state of the heat dissipation unit according to the current server load change, and obtains server monitoring data; The heat dissipation efficiency evaluation module evaluates whether the server heat dissipation reaches the target efficiency and power consumption standard based on the server monitoring data, optimizes the heat dissipation configuration, and matches the potential load changes to obtain the server heat dissipation log.

Images