Temperature control method, system, device and storage medium for computer host

Abstract

The present invention relates to the technical field of computer hosts, and discloses a temperature control method, system, device and storage medium of a computer host, wherein the method comprises obtaining the initial temperature, power parameter, number and initial speed of a cooling fan of the computer host; preprocessing the initial temperature and initial speed to obtain standardized data, and constructing a cooling effect prediction model; obtaining an initial cooling control strategy set according to the initial parameters and a preset initial strategy database; screening out an advanced cooling control strategy set through an intermediate evaluation matrix and associated feature analysis; performing temperature prediction on the strategies in the advanced cooling control strategy set based on the cooling effect prediction model to obtain an optimal cooling control strategy; performing error update on the optimal cooling control strategy to obtain a target cooling control strategy; adjusting the initial speed according to the target cooling control strategy to achieve temperature control. The present invention provides an automated computer host temperature control solution, which improves user experience and system performance.

Description

Technical Field

[0001] The present invention relates to the technical field of computer host, and in particular to a temperature control method, system, device and storage medium for a computer host. Background Art

[0002] At present, the computer host is the core component of the computer system, and its performance directly affects the performance of the entire computer, especially the host of a large computer system. The computer host mainly includes CPU, memory, motherboard, optical drive, chassis, power supply and radiator, etc. For the current computer host, its performance mainly depends on CPU and memory. All programs running on the computer are basically processed by the CPU, so the performance of the CPU has a decisive influence on the running speed of the computer; the second is the memory, that is, the memory bar. During the use of the computer, when a program is opened, the data of the program will be transferred to the memory, which serves as the working space of the CPU and provides a place for the CPU to read and write data quickly. When the program runs in the memory, the CPU will also process the program in it, so the performance of the memory also has a great influence on the running speed of the computer. The heat generated by the computer host during operation mainly comes from the high-speed operation of the CPU and memory. With the increase of usage time and the increase of workload, the heat generated by these components will cause the internal temperature of the host to rise. Excessive temperature will cause unstable operation of accessories, which is easy to cause data reading errors, hardware damage, and even system crashes. Excessive temperature will also reduce the computer's operating speed, shorten the service life of the hardware, may cause system instability, directly affect the stability of the PCIE interface, and lead to problems such as data transmission errors.

[0003] In one existing technology, a deep learning prediction algorithm is used to predict the heat dissipation performance of various resource cooling units in a data center computer room. A fixed speed is used to control fan heat dissipation based on the prediction results, thereby achieving equipment temperature management. However, due to the complexity and large amount of data on various resources in a data center computer room, this method has high requirements for implementation and the accuracy of the algorithm needs to be improved.

[0004] The existing technology adopts a fixed speed control solution, which cannot achieve the purpose of adjusting the fan speed according to the actual operating conditions, resulting in low temperature control efficiency. Summary of the invention

[0005] The present invention provides a temperature control method, system, electronic device and storage medium for a computer host, so as to realize accurate analysis of the heat dissipation effect of the computer host by collecting the operating parameters and environmental parameters of the computer host, thereby optimizing the heat dissipation control strategy and improving the heat dissipation efficiency of the computer host.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a temperature control method for a computer host, comprising:

[0007] Get the initial temperature, power parameters, number and initial speed of the cooling fan of the computer host;

[0008] According to the initial temperature and the initial rotation speed, standardized data is obtained through a preprocessing operation, and a heat dissipation effect prediction model is constructed based on the standardized data;

[0009] Based on the initial temperature, the power parameter, the number and the initial speed and a preset initial strategy database, an initial heat dissipation control strategy set is obtained;

[0010] Analyzing the initial heat dissipation control strategy set through the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set;

[0011] Based on the heat dissipation effect prediction model, temperature prediction is performed on the strategies in the advanced heat dissipation control strategy set to obtain the optimal heat dissipation control strategy;

[0012] Performing error update on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy;

[0013] According to the target heat dissipation control strategy, the initial rotation speed is adjusted to achieve temperature control of the computer host.

[0014] In an optional implementation, obtaining standardized data through a preprocessing operation according to the initial temperature and the initial rotation speed includes:

[0015] Performing a data filtering operation on the initial temperature and the initial rotation speed to obtain filtered data;

[0016] The data filtering operation is used to filter out temperature values ​​greater than a temperature threshold in the initial temperatures and rotation speeds less than or equal to 0 in the initial rotation speeds;

[0017] The filtered data is normalized to obtain standardized data.

[0018] In an optional implementation, the constructing a heat dissipation effect prediction model based on the standardized data includes:

[0019] Building a linear regression model based on the standardized data, training the linear regression model, and determining that the training is completed when the number of training times is greater than or equal to a preset maximum number of training times, thereby obtaining a heat dissipation effect prediction model;

[0020] The heat dissipation effect prediction model is used to obtain a corresponding temperature prediction range according to the initial temperature and the initial rotation speed.

[0021] In an optional implementation, the initial heat dissipation control strategy set is analyzed by using the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set, including:

[0022] Generating a corresponding intermediate evaluation matrix for each strategy in the initial heat dissipation control strategy set;

[0023] Based on a preset acquisition frequency, acquiring the associated features of each of the intermediate evaluation matrices;

[0024] According to the intermediate evaluation matrix and the associated features, weights are assigned to the evaluation indicators in the intermediate evaluation matrix to obtain a comprehensive score for each heat dissipation control strategy in the intermediate evaluation matrix;

[0025] The heat dissipation control strategy with the comprehensive score greater than a preset score threshold is selected as the advanced heat dissipation control strategy set.

[0026] In an optional implementation, the weighting of the evaluation indicators in the intermediate evaluation matrix to obtain a comprehensive score of each heat dissipation control strategy in the intermediate evaluation matrix includes:

[0027] The calculation formula of the comprehensive score score_total is as follows:

[0028] ;

[0029] in, is the score of each indicator in each strategy in the initial heat dissipation control strategy set, is the weight of indicator i.

[0030] In an optional implementation, the performing temperature prediction on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain the optimal heat dissipation control strategy includes:

[0031] Obtaining the simulated actual temperature of the computer host and the simulated actual speed of the cooling fan under each cooling control strategy in the advanced cooling control strategy set;

[0032] Inputting the simulated actual temperature and the simulated actual speed into the heat dissipation effect prediction model to obtain a second predicted temperature;

[0033] Subtracting all the second predicted temperatures from the preset target temperature to obtain a temperature difference value corresponding to each second predicted temperature value;

[0034] A minimum difference value among all the temperature difference values ​​is determined, and a heat dissipation control strategy corresponding to the minimum difference value is determined as an optimal heat dissipation control strategy.

[0035] In an optional implementation, performing error updating on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy includes:

[0036] Based on the heat dissipation effect prediction model, performing temperature prediction on the optimal heat dissipation control strategy to obtain a third predicted temperature;

[0037] Acquire a low power consumption optimization strategy, and calculate a degree of fit between the low power consumption optimization strategy and the third predicted temperature;

[0038] Calculating a set of error result values ​​corresponding to the degree of fit, and generating an error association feature based on the set of error result values;

[0039] According to the error correlation characteristics, the optimal heat dissipation regulation strategy is updated to obtain a target heat dissipation regulation strategy.

[0040] In an optional implementation, the acquiring the low power consumption optimization strategy includes:

[0041] Get the operating temperature of the computer host at the lowest power and the operating speed of the cooling fan;

[0042] The operating speed corresponding to the temperature where the operating temperature does not exceed the preset maximum safety temperature and is not lower than the preset minimum safety temperature is selected as the speed included in the low power consumption optimization strategy.

[0043] In a second aspect, the present invention provides a temperature control system for a computer host, comprising:

[0044] The data acquisition module is used to obtain the initial temperature, power parameters, serial number and initial speed of the cooling fan of the computer host;

[0045] A data preprocessing module, configured to obtain standardized data through a preprocessing operation according to the initial temperature and the initial rotation speed, and to construct a heat dissipation effect prediction model based on the standardized data;

[0046] An initial strategy module, used to obtain an initial heat dissipation control strategy set based on the initial temperature, the power parameter, the number and the initial rotation speed and a preset initial strategy database;

[0047] An advanced strategy module, used to analyze the initial heat dissipation control strategy set through an intermediate evaluation matrix and associated features to obtain an advanced heat dissipation control strategy set;

[0048] An optimal strategy module, used to perform temperature prediction on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain an optimal heat dissipation control strategy;

[0049] A strategy updating module, used for performing error update on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy;

[0050] The fan control module is used to adjust the initial rotation speed according to the target heat dissipation control strategy to achieve temperature control of the computer host.

[0051] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned temperature control methods for a computer host when executing the computer program.

[0052] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the temperature control methods for the computer host described above.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention provides a temperature control method for a computer host, comprising obtaining an initial temperature, a power parameter, a number and an initial speed of a cooling fan of the computer host; obtaining standardized data through a preprocessing operation according to the initial temperature and the initial speed, and constructing a cooling effect prediction model based on the standardized data; obtaining an initial cooling control strategy set based on the initial temperature, the power parameter, the number and the initial speed and a preset initial strategy database; analyzing the initial cooling control strategy set through an intermediate evaluation matrix and associated features to obtain an advanced cooling control strategy set; performing temperature prediction on the strategies in the advanced cooling control strategy set based on the cooling effect prediction model to obtain an optimal cooling control strategy; performing error update on the optimal cooling control strategy to obtain a target cooling control strategy;

[0055] According to the target heat dissipation control strategy, the initial rotation speed is adjusted to achieve temperature control of the computer host.

[0056] In the present invention, the collection module first collects the operating parameters and environmental parameters such as the initial temperature, power parameters, number and initial speed of the cooling fan of the computer host in real time. Then, the data preprocessing module filters and normalizes these initial data to obtain standardized data. Then, the heat dissipation effect prediction model is constructed using these standardized data, which can predict the temperature changes under different heat dissipation strategies.

[0057] In addition, through the intermediate evaluation matrix and the analysis of the associated features, an advanced heat dissipation control strategy set is selected from the initial heat dissipation control strategy set, and these strategies are more in line with the actual heat dissipation requirements of the computer host. Further, the temperature of the advanced strategy set is predicted based on the heat dissipation effect prediction model to determine the optimal heat dissipation control strategy. After obtaining the optimal strategy, the system will perform an error update on it to obtain a more accurate target heat dissipation control strategy. Finally, the fan control module adjusts the speed of the cooling fan according to the target heat dissipation control strategy to achieve precise control of the temperature of the computer host. This method of dynamically adjusting the strategy not only improves the heat dissipation efficiency, but also ensures the stable operation of the computer host under different operating conditions, effectively prolongs the service life of the hardware, and reduces the risk of system instability caused by excessive temperature. Through this series of operations, the present invention provides users with an intelligent and automated computer host temperature control solution, which greatly improves the user experience and system performance.

[0058] The present invention provides a temperature control method, system, device and storage medium for a computer host, so as to realize accurate analysis of the heat dissipation effect of the computer host by collecting the operating parameters and environmental parameters of the computer host, thereby optimizing the heat dissipation control strategy and improving the heat dissipation efficiency of the computer host. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of a temperature control method of a computer host provided by an embodiment of the present invention;

[0060] Figure 2 The present invention is a schematic diagram of a temperature control system for a computer host provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Reference Figure 1 The first embodiment of the present invention provides a temperature control method for a computer host, comprising the following steps:

[0063] S11, obtaining the initial temperature, power parameters, number and initial speed of the cooling fan of the computer host;

[0064] S12, obtaining standardized data through a preprocessing operation according to the initial temperature and the initial rotation speed, and constructing a heat dissipation effect prediction model based on the standardized data;

[0065] S13, obtaining an initial heat dissipation control strategy set based on the initial temperature, the power parameter, the number and the initial rotation speed and a preset initial strategy database;

[0066] S14, analyzing the initial heat dissipation control strategy set through the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set;

[0067] S15, performing temperature prediction on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain an optimal heat dissipation control strategy;

[0068] S16, performing error update on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy;

[0069] S17, adjusting the initial rotation speed according to the target heat dissipation control strategy to achieve temperature control of the computer host.

[0070] In step S11, the initial temperature, power parameters, serial number and initial speed of the cooling fan of the computer host are obtained.

[0071] Among them, the initial temperature, power parameters, number and initial speed of the computer host are a set of environmental parameters of the computer host, among which the initial temperature and initial speed need to be adjusted according to the target optimization strategy to obtain the appropriate temperature and speed. The power parameter is the rate at which each component (such as the CPU) in the computer host consumes electrical energy. When the load of the computer host increases, it usually leads to an increase in power consumption, thereby generating more heat and causing the temperature to rise. These environmental parameters are collected by the acquisition and control platform. The acquisition and control platform includes communication equipment and control programs. The control program performs calculations and data processing, converts data into instruction sets, and controls the communication equipment to adjust the computer host. A heat dissipation effect prediction model is constructed based on these environmental parameters, and these environmental parameters are used as reference data for screening the initial, advanced, and optimal heat dissipation control strategy sets.

[0072] In step S12, standardized data is obtained through a preprocessing operation according to the initial temperature and the initial rotation speed, and a heat dissipation effect prediction model is constructed based on the standardized data.

[0073] It should be noted that the preprocessing operation includes data filtering and normalization operations. The initial temperature and initial speed are filtered to remove the temperature values ​​greater than the temperature threshold and the speed less than or equal to 0 in the initial speed, and the filtered data is obtained. The filtered data includes the temperature data sequence of the computer host and the speed data sequence of the cooling fan. Taking the temperature data sequence of the computer host in the filtered data as an example, the normalization operation is to subtract the mean of the temperature data sequence of the computer host from the temperature data of the computer host, and divide it by the standard deviation of the temperature data sequence of the computer host, and finally map the temperature range to between (0,1).

[0074] Furthermore, the construction of the heat dissipation effect prediction model based on the standardized data includes: constructing a linear regression model based on the standardized data, training the linear regression model, and when the number of training times is greater than or equal to a preset maximum number of training times, determining that the training is completed, and obtaining the heat dissipation effect prediction model; wherein the heat dissipation effect prediction model is used to obtain the corresponding temperature prediction range according to the initial temperature and the initial rotation speed.

[0075] Among them, the heat dissipation effect prediction model is a prediction model obtained after training a linear regression model built based on standardized data. The temperature and corresponding speed values ​​after normalization processing are input into the prediction model. The output value represents the temperature prediction range under different speeds. The output value is further used as the basis for constructing the heat dissipation control strategy.

[0076] In step S13, an initial heat dissipation control strategy set is obtained based on the initial temperature, the power parameter, the number and the initial rotation speed and a preset initial strategy database.

[0077] It is worth noting that the initial strategy database is established during the design and testing phase of the computer host. It contains a series of preset thermal control strategies based on historical operating data, user feedback, and simulation test results. This database is dynamically updated to include the latest strategies and optimization measures. Each strategy is associated with a specific power and temperature range in the database, and the corresponding fan speed setting is recommended. These strategies are carefully designed to cope with different operating conditions and cooling requirements.

[0078] For example, for a computer host running at high power, the strategy will recommend a higher fan speed to improve heat dissipation efficiency; for a host running at low power, a lower speed will be recommended to reduce noise and energy consumption. Search the initial strategy database for the strategy that best matches the current computer host status. The initial strategy database contains fields such as initial temperature, power parameter, initial speed, target temperature, target power parameter, CPU temperature, and recommended speed. That is, if one of the strategies is adopted, the initial speed is adjusted to the recommended speed, and then the initial temperature is adjusted to the target temperature to achieve temperature control. Combine the collected data into a feature vector F_Vector=[number, initial temperature, power parameter, initial speed], assign weights to the initial temperature parameters and power parameters in each feature vector, calculate the score of each strategy based on the weight, set the score threshold, and obtain the initial control strategy for the computer host with the number. The initial control strategy contains multiple strategies with scores greater than the score threshold. The score of each strategy is expressed by the following formula:

[0079] ;

[0080] Among them, the initial temperature of the current host is , the current host power parameters are ; The initial temperature of each strategy in the initial strategy database is , the power parameter of each strategy in the initial strategy database is .

[0081] In step S14, the initial heat dissipation control strategy set is analyzed by using the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set, including:

[0082] Generating a corresponding intermediate evaluation matrix for each strategy in the initial heat dissipation control strategy set;

[0083] Based on a preset acquisition frequency, acquiring the associated features of each of the intermediate evaluation matrices;

[0084] According to the serial number of the computer host and the corresponding associated features, an advanced heat dissipation regulation and control strategy set is obtained by matching the initial heat dissipation regulation and control strategy set.

[0085] It is worth noting that the associated features include power, CPU temperature, and cooling fan speed. Different cooling control strategies in the initial cooling control strategy set are evaluated based on these indicators. The rows in the intermediate evaluation matrix represent different cooling control strategies, the columns represent different evaluation indicators, and the values ​​of the matrix represent the scores of the indicators under a certain strategy. Since there may be differences in dimensions and magnitudes between different indicators, the data needs to be standardized. This process involves converting the original data into dimensionless relative values ​​so that they can be compared and calculated on the same scale. The score calculation formula for each indicator under each strategy is as follows:

[0086] ;

[0087] Among them, s is the standardized data obtained after standardization processing, min and max are the preset safety minimum value and safety maximum value of each indicator respectively.

[0088] Finally, by calculating and analyzing the data in the matrix, weights are assigned to these indicators to obtain a comprehensive score for each heat dissipation control strategy, and heat dissipation control strategies with a comprehensive score greater than the preset score threshold are selected as the advanced heat dissipation control strategy set. The calculation formula for the comprehensive score score_total is as follows:

[0089] ;

[0090] in, is the score of each indicator in each strategy in the initial heat dissipation control strategy set, is the weight of indicator i.

[0091] In step S15, temperature prediction is performed on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain the optimal heat dissipation control strategy, including:

[0092] Obtaining the simulated actual temperature of the computer host and the simulated actual speed of the cooling fan under each cooling control strategy in the advanced cooling control strategy set;

[0093] Inputting the simulated actual temperature and the simulated actual speed into the heat dissipation effect prediction model to obtain a second predicted temperature;

[0094] Subtracting all the second predicted temperatures from the preset target temperature to obtain a temperature difference value corresponding to each second predicted temperature value;

[0095] A minimum difference value among all the temperature difference values ​​is determined, and a heat dissipation control strategy corresponding to the minimum difference value is determined as an optimal heat dissipation control strategy.

[0096] For example, taking the optimal heat dissipation control strategy decision of a host as an example, after obtaining multiple advanced heat dissipation control strategies, the simulated actual temperature of the computer host and the simulated actual speed of the cooling fan under each advanced heat dissipation control strategy are obtained, and the simulated actual temperature and the simulated actual speed are input into the heat dissipation effect prediction model to obtain the second predicted temperature. All the second predicted temperatures are subtracted from the preset target temperature to obtain the temperature difference value corresponding to each second predicted temperature value. The minimum difference value among all the temperature difference values ​​is determined, and the heat dissipation control strategy corresponding to the minimum difference value is determined as the optimal heat dissipation control strategy.

[0097] In step S16, the optimal heat dissipation control strategy is error updated to obtain a target heat dissipation control strategy, including:

[0098] Based on the heat dissipation effect prediction model, performing temperature prediction on the optimal heat dissipation control strategy to obtain a third predicted temperature;

[0099] Acquire a low power consumption optimization strategy, and calculate a degree of fit between the low power consumption optimization strategy and the third predicted temperature;

[0100] Calculating a set of error result values ​​corresponding to the degree of fit, and generating an error association feature based on the set of error result values;

[0101] According to the error correlation characteristics, the optimal heat dissipation regulation strategy is updated to obtain a target heat dissipation regulation strategy.

[0102] For example, taking the update of the optimal heat dissipation control strategy of a host as an example, firstly, the heat dissipation effect prediction model is used to predict the temperature of the optimal heat dissipation control strategy to obtain the third predicted temperature. A PID (proportional-integral-differential) controller is set. The PID controller is a common feedback loop control system that adjusts the control command according to the error of the control object to achieve system stability and optimization. In the present invention, the proportional gain (kp) of the PID controller is dynamically adjusted according to the real-time ambient temperature to achieve precise control of the speed of the cooling fan. Using the determination coefficient ( ) Calculate the degree of fit between the low power optimization strategy temperature and the third predicted temperature. The coefficient of determination is a statistical indicator that measures the degree of fit between the model prediction value and the actual observed value. In this example, it is used to evaluate the degree of match between the current heat dissipation strategy and the low power optimization strategy. Set a fit threshold. If the current fit is greater than the fit threshold, it means that the closer the third predicted temperature is to the low power optimization strategy temperature, the less the need to update the optimal heat dissipation control strategy, and it is already the target heat dissipation control strategy.

[0103] If the current degree of fit is less than the degree of fit threshold, the system will enter the error processing process. At this time, a set of error result values ​​will be generated. The corresponding error-related features include power, CPU temperature, and cooling fan speed. The error result value set is the error value of these three features. These error values ​​are important indicators for evaluating the performance of the current cooling strategy. They point out the gap between the current strategy and the ideal state. In this case, it is necessary to adjust the parameters of the PID controller, such as increasing the proportional gain (kp) to quickly respond to temperature changes, or adjusting the integral term (ki) to eliminate steady-state errors. These adjustments help improve the response speed and stability of the system, ensuring that the computer host can maintain a safe and efficient temperature range under various working conditions. Regularly review and optimize the parameters of the PID controller to adapt to different working conditions and ambient temperature changes.

[0104] In one embodiment, the low power consumption optimization strategy is obtained, including: obtaining the operating temperature of the computer host at the lowest power and the operating speed of the cooling fan; selecting the operating speed corresponding to the operating temperature which is not higher than the preset maximum safety temperature and not lower than the preset minimum safety temperature as the speed included in the low power consumption optimization strategy.

[0105] In step S17, the initial rotation speed is adjusted according to the target heat dissipation control strategy to achieve temperature control of the computer host.

[0106] It should be noted that in the process of implementing the target heat dissipation control strategy, the control interface is responsible for sending adjustment instructions to the cooling fan, and the adjustment instructions include the target speed to be achieved, and these instructions are transmitted to the cooling fan through a digital communication protocol. After receiving the adjustment instructions, the cooling fan will adjust the fan speed through its built-in motor control circuit to ensure that its speed matches the target speed. The motor control circuit includes sensors, microcontrollers and power electronic devices, which work together to ensure that the speed of the cooling fan can be smoothly and accurately adjusted to the target value. While adjusting the fan speed, the system will continuously monitor the temperature changes of the computer host and dynamically adjust the cooling fan speed according to the feedback temperature information.

[0107] In order to better illustrate the beneficial effects of the embodiments of the present invention, the working process of the present invention is described below with a practical example.

[0108] When the computer host starts, the acquisition module, as the first line of defense of the system, starts working in real time to collect current environmental data and operating data. These data include the temperature of the computer host, the temperature of the core component CPU, power parameters, host number, and the speed of the cooling fan. For example, the system records that the temperature of the computer host is 35°C, the CPU temperature is 45°C, the power parameter is 150W, the host number is Host_01, and the speed of the cooling fan is 1200 RPM. These parameters are monitored in real time because they directly affect the heat dissipation performance of the computer host. After collecting these key parameters, these parameters are matched to obtain the target heat dissipation control strategy that best suits the current conditions. The computer host adjusts the speed of the cooling fan according to the target heat dissipation control strategy. After determining the target heat dissipation control strategy, the system sends adjustment instructions to the cooling fan through the control interface. These instructions include the target speed to be achieved so that the cooling fan can be adjusted according to the actual heat dissipation requirements of the computer host. This adjustment is dynamic, which means that the system will continuously adjust the fan speed according to real-time data to adapt to the changing heat dissipation requirements. For example, if the CPU temperature is close to the critical value, the system will increase the fan speed to improve the heat dissipation efficiency. After the strategy is implemented, the system will continue to monitor the temperature data of the computer host in real time to ensure that the temperature is maintained within a preset safe range. If the temperature exceeds this range, the system will immediately adjust the heat dissipation strategy to cope with the temperature change. The system of the present invention can not only respond to real-time data, but also learn from past regulation effects to optimize future decisions. The system will regularly review and analyze historical data to identify patterns and trends in temperature changes, thereby predicting future heat dissipation needs. Through continuous learning and adjustment, the system can predict and regulate temperature more and more accurately, thereby providing more stable and efficient heat dissipation performance. This temperature control technology is particularly important for computer hosts that need to run for a long time at high loads, such as data centers, gaming PCs, professional workstations, etc. These devices usually need to handle complex graphics and data processing tasks, which generate a lot of heat. Through the temperature control method of the present invention, it can be ensured that these high-performance devices will not overheat during long-term operation, thereby maintaining optimal performance and stability.

[0109] In summary, the present invention provides a temperature control method for a computer host, comprising obtaining an initial temperature, power parameter, number and initial speed of a cooling fan of the computer host; obtaining standardized data through a preprocessing operation according to the initial temperature and the initial speed, and constructing a cooling effect prediction model based on the standardized data; obtaining an initial cooling control strategy set based on the initial temperature, the power parameter, the number and the initial speed and a preset initial strategy database; analyzing the initial cooling control strategy set through an intermediate evaluation matrix and associated features to obtain an advanced cooling control strategy set; performing temperature prediction on the strategies in the advanced cooling control strategy set based on the cooling effect prediction model to obtain an optimal cooling control strategy; performing error update on the optimal cooling control strategy to obtain a target cooling control strategy; adjusting the initial speed according to the target cooling control strategy to achieve temperature control of the computer host.

[0110] In the present invention, the collection module first collects the operating parameters and environmental parameters such as the initial temperature, power parameters, number and initial speed of the cooling fan of the computer host in real time. Then, the data preprocessing module filters and normalizes these initial data to obtain standardized data. Then, the heat dissipation effect prediction model is constructed using these standardized data, which can predict the temperature changes under different heat dissipation strategies.

[0111] In addition, through the intermediate evaluation matrix and the analysis of the associated features, an advanced heat dissipation control strategy set is selected from the initial heat dissipation control strategy set, and these strategies are more in line with the actual heat dissipation requirements of the computer host. Further, the temperature of the advanced strategy set is predicted based on the heat dissipation effect prediction model to determine the optimal heat dissipation control strategy. After obtaining the optimal strategy, the system will perform an error update on it to obtain a more accurate target heat dissipation control strategy. Finally, the fan control module adjusts the speed of the cooling fan according to the target heat dissipation control strategy to achieve precise control of the temperature of the computer host. This method of dynamically adjusting the strategy not only improves the heat dissipation efficiency, but also ensures the stable operation of the computer host under different operating conditions, effectively prolongs the service life of the hardware, and reduces the risk of system instability caused by excessive temperature. Through this series of operations, the present invention provides users with an intelligent and automated computer host temperature control solution, which greatly improves the user experience and system performance.

[0112] The present invention provides a temperature control method, system, device and storage medium for a computer host, so as to realize accurate analysis of the heat dissipation effect of the computer host by collecting the operating parameters and environmental parameters of the computer host, thereby optimizing the heat dissipation control strategy and improving the heat dissipation efficiency of the computer host.

[0113] Reference Figure 2The second embodiment of the present invention provides a temperature control system for a computer host, comprising:

[0114] The data acquisition module is used to obtain the initial temperature, power parameters, serial number and initial speed of the cooling fan of the computer host;

[0115] A data preprocessing module, configured to obtain standardized data through a preprocessing operation according to the initial temperature and the initial rotation speed, and to construct a heat dissipation effect prediction model based on the standardized data;

[0116] An initial strategy module, used to obtain an initial heat dissipation control strategy set based on the initial temperature, the power parameter, the number and the initial rotation speed and a preset initial strategy database;

[0117] An advanced strategy module, used to analyze the initial heat dissipation control strategy set through an intermediate evaluation matrix and associated features to obtain an advanced heat dissipation control strategy set;

[0118] An optimal strategy module, used to perform temperature prediction on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain an optimal heat dissipation control strategy;

[0119] A strategy updating module, used for performing error update on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy;

[0120] The fan control module is used to adjust the initial rotation speed according to the target heat dissipation control strategy to achieve temperature control of the computer host.

[0121] Preferably, the data preprocessing module includes:

[0122] A filtering operation unit, used for performing a data filtering operation on the initial temperature and the initial rotational speed to obtain filtered data; the data filtering operation is used for filtering out temperature values ​​greater than a temperature threshold value in the initial temperature and rotational speeds less than or equal to 0 in the initial rotational speed;

[0123] The normalization operation unit is used to perform a normalization operation on the filtered data to obtain standardized data.

[0124] Preferably, the advanced strategy module includes:

[0125] An intermediate evaluation matrix generating unit, used to generate a corresponding intermediate evaluation matrix for each strategy in the initial heat dissipation control strategy set;

[0126] A correlation feature acquisition unit, used for acquiring the correlation feature of each of the intermediate evaluation matrices based on a preset acquisition frequency;

[0127] A weight allocation unit, used to allocate weights to the evaluation indicators in the intermediate evaluation matrix according to the intermediate evaluation matrix and the associated features, so as to obtain a comprehensive score for each heat dissipation control strategy in the intermediate evaluation matrix;

[0128] The advanced strategy selection unit is used to select the heat dissipation control strategy with a comprehensive score greater than a preset score threshold as an advanced heat dissipation control strategy set.

[0129] Preferably, the optimal strategy module includes:

[0130] A simulation data acquisition unit, used to acquire the simulated actual temperature of the computer host and the simulated actual speed of the cooling fan under each cooling control strategy in the advanced cooling control strategy set;

[0131] A second temperature prediction unit, used for inputting the simulated actual temperature and the simulated actual speed into the heat dissipation effect prediction model to obtain a second predicted temperature;

[0132] A temperature difference calculation unit, used for subtracting all the second predicted temperatures from a preset target temperature to obtain a temperature difference value corresponding to each second predicted temperature value;

[0133] The optimal strategy determination unit is used to determine the minimum difference value among all the temperature difference values, and determine the heat dissipation control strategy corresponding to the minimum difference value as the optimal heat dissipation control strategy.

[0134] Preferably, the policy update module includes:

[0135] A third temperature prediction unit, configured to perform temperature prediction on the optimal heat dissipation control strategy based on the heat dissipation effect prediction model to obtain a third predicted temperature;

[0136] A low power consumption optimization strategy acquisition unit, used for acquiring a low power consumption optimization strategy;

[0137] an error correlation feature generating unit, configured to calculate a degree of fit between the low power consumption optimization strategy and the third predicted temperature, calculate a set of error result values ​​corresponding to the degree of fit, and generate an error correlation feature based on the set of error result values;

[0138] A strategy updating unit is used to update the optimal heat dissipation control strategy according to the error correlation characteristics to obtain a target heat dissipation control strategy.

[0139] It should be noted that a temperature control system for a computer host provided in an embodiment of the present invention is used to execute all process steps of a temperature control method for a computer host in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated.

[0140] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the temperature control method of the computer host described above are implemented, for example Figure 1 Step S11 is shown.

[0141] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0142] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0143] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0144] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0145] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0146] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0147] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A temperature control method for a computer host, characterized in that: include: Get the initial temperature, power parameters, number and initial speed of the cooling fan of the computer host; According to the initial temperature and the initial rotation speed, standardized data is obtained through a preprocessing operation, and a heat dissipation effect prediction model is constructed based on the standardized data; Based on the initial temperature, the power parameter, the number and the initial speed and a preset initial strategy database, an initial heat dissipation control strategy set is obtained; Analyzing the initial heat dissipation control strategy set through the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set; Based on the heat dissipation effect prediction model, temperature prediction is performed on the strategies in the advanced heat dissipation control strategy set to obtain the optimal heat dissipation control strategy; Performing error update on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy; According to the target heat dissipation control strategy, the initial rotation speed is adjusted to achieve temperature control of the computer host; The initial heat dissipation control strategy set is analyzed by using the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set, including: Generating a corresponding intermediate evaluation matrix for each strategy in the initial heat dissipation control strategy set; Based on a preset acquisition frequency, acquiring the associated features of each of the intermediate evaluation matrices; According to the intermediate evaluation matrix and the associated features, weights are assigned to the evaluation indicators in the intermediate evaluation matrix to obtain a comprehensive score for each heat dissipation control strategy in the intermediate evaluation matrix; Selecting the heat dissipation control strategy whose comprehensive score is greater than a preset score threshold as an advanced heat dissipation control strategy set; Among them, the associated features include power, CPU temperature, and cooling fan speed; the rows in the middle evaluation matrix represent different cooling control strategies, the columns represent different evaluation indicators, and the values ​​of the matrix represent the scores of the indicators under a certain strategy.

2. The temperature control method of a computer host according to claim 1, characterized in that: The step of obtaining standardized data through a preprocessing operation according to the initial temperature and the initial rotation speed includes: Performing a data filtering operation on the initial temperature and the initial rotation speed to obtain filtered data; The data filtering operation is used to filter out temperature values ​​greater than a temperature threshold in the initial temperatures and rotation speeds less than or equal to 0 in the initial rotation speeds; The filtered data is normalized to obtain standardized data.

3. The temperature control method of a computer host according to claim 1, characterized in that: The step of constructing a heat dissipation effect prediction model based on the standardized data includes: Building a linear regression model based on the standardized data, training the linear regression model, and determining that the training is completed when the number of training times is greater than or equal to a preset maximum number of training times, thereby obtaining a heat dissipation effect prediction model; The heat dissipation effect prediction model is used to obtain a corresponding temperature prediction range according to the initial temperature and the initial rotation speed.

4. The temperature control method of a computer host according to claim 1, characterized in that: The weighting of the evaluation indicators in the intermediate evaluation matrix to obtain a comprehensive score of each heat dissipation control strategy in the intermediate evaluation matrix includes: The calculation formula of the comprehensive score score_total is as follows: ； in, is the score of each indicator in each strategy in the initial heat dissipation control strategy set, is the weight of indicator i.

5. The temperature control method of a computer host according to claim 1, characterized in that: The step of performing temperature prediction on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain the optimal heat dissipation control strategy includes: Obtaining the simulated actual temperature of the computer host and the simulated actual speed of the cooling fan under each cooling control strategy in the advanced cooling control strategy set; Inputting the simulated actual temperature and the simulated actual speed into the heat dissipation effect prediction model to obtain a second predicted temperature; Subtracting all the second predicted temperatures from the preset target temperature to obtain a temperature difference value corresponding to each of the second predicted temperatures; A minimum difference value among all the temperature difference values ​​is determined, and a heat dissipation control strategy corresponding to the minimum difference value is determined as an optimal heat dissipation control strategy.

6. The temperature control method of a computer host according to claim 1, characterized in that: The error updating of the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy includes: Based on the heat dissipation effect prediction model, performing temperature prediction on the optimal heat dissipation control strategy to obtain a third predicted temperature; Acquire a low power consumption optimization strategy, and calculate a degree of fit between the low power consumption optimization strategy and the third predicted temperature; Calculating a set of error result values ​​corresponding to the degree of fit, and generating an error association feature based on the set of error result values; According to the error correlation characteristics, the optimal heat dissipation regulation strategy is updated to obtain a target heat dissipation regulation strategy.

7. The temperature control method of a computer host according to claim 6, characterized in that: The obtaining of the low power consumption optimization strategy comprises: Get the operating temperature of the computer host at the lowest power and the operating speed of the cooling fan; The operating speed corresponding to the temperature where the operating temperature does not exceed the preset maximum safety temperature and is not lower than the preset minimum safety temperature is selected as the speed included in the low power consumption optimization strategy.

8. A temperature control system for a computer host, characterized in that: include: The data acquisition module is used to obtain the initial temperature, power parameters, serial number and initial speed of the cooling fan of the computer host; A data preprocessing module, configured to obtain standardized data through a preprocessing operation according to the initial temperature and the initial rotation speed, and to construct a heat dissipation effect prediction model based on the standardized data; An initial strategy module, used to obtain an initial heat dissipation control strategy set based on the initial temperature, the power parameter, the number and the initial rotation speed and a preset initial strategy database; An advanced strategy module, used to analyze the initial heat dissipation control strategy set through an intermediate evaluation matrix and associated features to obtain an advanced heat dissipation control strategy set; An optimal strategy module, used to perform temperature prediction on the strategies in the advanced heat dissipation control strategy set based on the heat dissipation effect prediction model to obtain an optimal heat dissipation control strategy; A strategy updating module, used for performing error update on the optimal heat dissipation control strategy to obtain a target heat dissipation control strategy; A fan control module, used to adjust the initial rotation speed according to the target heat dissipation control strategy to achieve temperature control of the computer host; The initial heat dissipation control strategy set is analyzed by using the intermediate evaluation matrix and the associated features to obtain an advanced heat dissipation control strategy set, including: Generating a corresponding intermediate evaluation matrix for each strategy in the initial heat dissipation control strategy set; Based on a preset acquisition frequency, acquiring the associated features of each of the intermediate evaluation matrices; According to the intermediate evaluation matrix and the associated features, weights are assigned to the evaluation indicators in the intermediate evaluation matrix to obtain a comprehensive score for each heat dissipation control strategy in the intermediate evaluation matrix; Selecting the heat dissipation control strategy whose comprehensive score is greater than a preset score threshold as an advanced heat dissipation control strategy set; Among them, the associated features include power, CPU temperature, and cooling fan speed; the rows in the middle evaluation matrix represent different cooling control strategies, the columns represent different evaluation indicators, and the values ​​of the matrix represent the scores of the indicators under a certain strategy.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the temperature control method of the computer host according to any one of claims 1 to 7.

Images