Temperature control method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of computers, in particular to a temperature control method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an estimated temperature of a heat dissipation part based on a pre-established physical model, and obtaining an actual temperature of the heat dissipation part based on the estimated temperature and the actual temperature of the heat dissipation part; judging whether parameters of a pre-established physical model meet preset updating conditions or not; if the parameters of the physical model meet preset updating conditions, the parameters of the pre-established physical model are updated, and based on the updated parameters, regulation and control parameters of a proportional integral differential controller are determined according to a preset objective function, so that the proportional integral differential controller controls the operating temperature of the server based on the regulation and control parameters. Therefore, the problems that in PID regulation and control of the server fan, parameter setting depends on artificial experience, efficiency is low, subjectivity is high, and power consumption, noise and heat dissipation performance cannot be effectively balanced in the prior art are solved, and effective control over the temperature, the power consumption and the noise of the server is achieved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a temperature control method, device, electronic device, and storage medium. Background Art

[0002] With the continuous improvement of server performance, its heat dissipation requirements are increasing day by day, and the fan control technology has become a key link to ensure the stable operation of the server. At present, the PID (Proportional-Integral-Derivative) controller is the main technical means for server heat dissipation control. It coordinates the regulation of the system temperature through proportional, integral, and derivative parameters. However, the parameter configuration depends on manual experience debugging, which has problems such as time-consuming, laborious, and strong subjectivity, and is prone to slow convergence, rotational speed fluctuations, and even the risk of component overheating. In addition, the existing PID control result evaluation system is based on theoretical indicators (such as overshoot and settling time), and it is difficult to adapt to the complex dynamic temperature change scenarios inside the server.

[0003] In related technologies, some solutions calculate the global heat dissipation parameters through weighted multi-component temperatures, which alleviates the problem of single heat dissipation strategy, but does not solve problems such as delay and overshoot; other methods introduce filtering algorithms to suppress overshoot, but do not solve the problems of single heat dissipation strategy, delays in rotational speed, temperature, etc., and disturbances during actual operation; there are also methods that combine fuzzy rule bases to correct PID parameters in real time, which improves multiple heat dissipation problems such as delay, overshoot, and single, but still lacks effective response to sudden disturbances during actual operation and urgently needs to be solved. Summary of the Invention

[0004] This application provides a temperature control method, device, electronic device, and storage medium to solve the problems in the PID regulation of server fans that parameter tuning depends on manual experience, is inefficient and subjective, and the existing technology cannot effectively balance power consumption, noise, and heat dissipation performance, and realizes effective control of server temperature, power consumption, and noise.

[0005] To achieve the above object, a temperature control method according to a first aspect embodiment of this application includes the following steps:

[0006] Obtain the actual temperature of the heat dissipation component;

[0007] Based on a pre-established physical model, obtain the estimated temperature of the heat dissipation component, and based on the estimated temperature and the actual temperature, determine whether the parameters of the pre-established physical model meet a preset update condition;

[0008] If the parameters of the physical model meet the preset update conditions, update the parameters of the pre-established physical model, and based on the updated parameters, determine the control parameters of the proportional-integral-derivative controller according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters.

[0009] According to the temperature control method provided by the embodiments of the present application, based on a pre-established physical model, the estimated temperature of the heat dissipation component is obtained, and based on the estimated temperature and the actual temperature of the heat dissipation component, when the parameters of the physical model meet the preset update conditions, the parameters of the pre-established physical model are updated, and based on the updated parameters, the control parameters of the proportional-integral-derivative controller are determined according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters. Thereby, the problems that in the PID regulation of the server fan, parameter tuning depends on manual experience, is inefficient and subjective, and the prior art cannot effectively balance power consumption, noise and heat dissipation performance are solved, and effective control of the server temperature, power consumption and noise is achieved.

[0010] To achieve the above object, an embodiment of the second aspect of the present application provides a temperature control device, including:

[0011] An acquisition module, configured to acquire the actual temperature of the heat dissipation component;

[0012] A processing module, configured to obtain the estimated temperature of the heat dissipation component based on a pre-established physical model, and based on the estimated temperature and the actual temperature, determine whether the parameters of the pre-established physical model meet the preset update conditions;

[0013] A control module, configured to update the parameters of the pre-established physical model if the parameters of the physical model meet the preset update conditions, and based on the updated parameters, determine the control parameters of the proportional-integral-derivative controller according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters.

[0014] According to the temperature control device provided by the embodiments of the present application, based on a pre-established physical model, the estimated temperature of the heat dissipation component is obtained, and based on the estimated temperature and the actual temperature of the heat dissipation component, when the parameters of the physical model meet the preset update conditions, the parameters of the pre-established physical model are updated, and based on the updated parameters, the control parameters of the proportional-integral-derivative controller are determined according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters. Thereby, the problems that in the PID regulation of the server fan, parameter tuning depends on manual experience, is inefficient and subjective, and the prior art cannot effectively balance power consumption, noise and heat dissipation performance are solved, and effective control of the server temperature, power consumption and noise is achieved.

[0015] To achieve the above object, an embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the temperature control method as described in the above embodiment.

[0016] To achieve the above object, an embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the temperature control method as described in the above embodiment.

[0017] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0018] To more clearly illustrate the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 FIG. is a flowchart of a temperature control method provided according to an embodiment of the present application;

[0020] Figure 2 FIG. is a flowchart of a temperature control method according to an embodiment of the present application;

[0021] Figure 3 FIG. is a schematic block diagram of a temperature control device provided according to an embodiment of the present application;

[0022] Figure 4 FIG. is a schematic structural diagram of an electronic device provided according to an embodiment of the present application.

[0023] Reference numerals: 10 - Abnormal diagnosis device of the basic input / output system, 100 - Judgment module, 200 - Processing module, 300 - Diagnosis module; 401 - Memory, 402 - Processor, 403 - Communication interface. Detailed Embodiments

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present application.

[0025] It should be noted that in the description of this application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. The terms "first", "second", etc. in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0026] In order to enable those skilled in the art of this technology to better understand the solution of this application, the following further detailed description of this application will be given in conjunction with the accompanying drawings and specific embodiments.

[0027] Those skilled in the art can understand that traditional engineering tuning schemes such as Ziegler-Nichols are inefficient and inaccurate, and the PID tuning scheme of intelligent computing algorithms is relatively complex and has requirements for the usage scenario and hardware devices, which brings great difficulties to actual deployment and use. In addition, the prior art has not solved how to construct the mathematical relationship between PID parameters and the system heat dissipation performance, and how to evaluate and adjust the PID control result, or the process is too vague, mainly focusing on the fuzzy development of single factors or rules, and the practical value is not high.

[0028] Based on this and the problems mentioned in the background technology that the parameter tuning in the PID control of the server fan relies on manual experience, is inefficient and subjective, and the prior art cannot effectively balance power consumption, noise and heat dissipation performance, this application proposes a simple, reliable and easy-to-deploy PID adaptive tuning scheme, establishes a system model and identification, sets initial parameters, and realizes the adaptive tuning of PID parameters according to the optimization objective function and multi-objective optimization strategy. Thus, the problems that the parameter tuning in the PID control of the server fan relies on manual experience, is inefficient and subjective, and the prior art cannot effectively balance power consumption, noise and heat dissipation performance are solved, and online stable and reliable PID self-tuning can be realized, and effective control of the server temperature, power consumption and noise is achieved.

[0029] Specifically, Figure 1 is a flowchart of the temperature control method according to an embodiment of this application.

[0030] As Figure 1 shown, the temperature control method includes the following steps:

[0031] In step S101, obtain the actual temperature of the heat dissipation component.

[0032] Among them, the heat dissipation component refers to the core heat - generating components that need to be cooled in the server, such as the CPU (Central Processing Unit), GPU (Graphics Processing Unit), power module, etc., which are not specifically limited herein.

[0033] Specifically, in the embodiments of the present application, the actual temperature of the heat dissipation component can be obtained by an internally - built temperature sensor. The types of temperature sensors can include thermistors, thermocouples, etc., which are not specifically limited herein.

[0034] In step S102, based on the pre - established physical model, the estimated temperature of the heat dissipation component is obtained, and based on the estimated temperature and the actual temperature, it is determined whether the parameters of the pre - established physical model meet the preset update conditions.

[0035] Specifically, the temperature control system of the server is determined as a first - order inertial lag system for analysis. The pre - established physical model is:

[0036]

[0037] Wherein, T is the estimated temperature of the heat dissipation component, p is the PWM (Pulse Width Modulation) value input by the cooling fan, K is the first parameter, Q is the second parameter, L is the third parameter, and e is the natural constant.

[0038] The pre - established physical model in the embodiments of the present application can characterize the physical characteristics of the server temperature change system to the greatest extent.

[0039] Further, the current PWM value p input by the cooling fan is read through a sensor or a controller. Combining the current PWM value input by the cooling fan with the first parameter K, the second parameter Q, and the third parameter L of the currently pre - established physical model, the current estimated temperature of the heat dissipation component can be calculated.

[0040] Further, in some embodiments, based on the estimated temperature and the actual temperature, determining whether the parameters of the pre - established physical model meet the preset update conditions includes: calculating the difference between the estimated temperature and the actual temperature; determining whether the estimated temperature is less than the actual temperature, or whether the difference is greater than the first preset threshold; if the estimated temperature is less than the actual temperature, or the difference is greater than the first preset threshold, it is determined that the parameters of the pre - established physical model meet the preset update conditions.

[0041] Among them, the first preset temperature can be a threshold preset by those skilled in the art, which can be a threshold obtained through a limited number of experiments, or a threshold obtained through computer simulation, which is not specifically limited herein.

[0042] Specifically, calculate the difference between the estimated temperature and the actual temperature, and determine whether the estimated temperature is less than the actual temperature, or whether the difference between the estimated temperature and the actual temperature is greater than a first preset threshold. If the estimated temperature is less than the actual temperature, it indicates that the heat dissipation capacity of the system is insufficient, such as insufficient fan speed or decreased heat sink efficiency, and the adjustment parameters need to be updated immediately to avoid the risk of overheating. If the difference between the estimated temperature and the actual temperature is greater than the first preset threshold, it means that the current parameters can no longer accurately describe the dynamic characteristics of the system. At this time, the parameters of the pre-established physical model also need to be updated and adjusted.

[0043] For example, when the server switches from low load to high load, the CPU temperature rises rapidly, resulting in the estimated temperature being less than the actual temperature. At this time, it is determined that the parameters of the pre-established physical model meet the preset update conditions.

[0044] Further, assuming that the first preset threshold is 10 °C, the current estimated temperature of the heat dissipation component is 71 °C, and the actual temperature of the heat dissipation component is 60 °C, it is determined that the parameters of the pre-established physical model meet the preset update conditions.

[0045] Thus, by judging whether the physical model parameters need to be updated based on the comparison between the estimated temperature and the actual temperature, the performance of the server temperature control system can be significantly improved, ensuring that the system can maintain stability and efficiency under various operating conditions.

[0046] In addition, if the estimated temperature is greater than or equal to the actual temperature, and the difference between the estimated temperature and the actual temperature is less than or equal to the first preset threshold, it means that the current parameters of the pre-established physical model can basically accurately reflect the actual heat dissipation situation of the heat dissipation component, and parameter update is not required. At this time, it is determined that the parameters of the pre-established physical model do not meet the preset update conditions.

[0047] For example, assume that at the current k moment, the PWM input of the actual system is p k , the actual temperature of the heat dissipation component is T k , and the current estimated temperature T k ′ of the heat dissipation component calculated according to the first-order inertial lag model (i.e., the pre-established physical model). Then, if the following conditions are met: T k ′ ≥T k , and T k ′ -T kIf it is ≤10, it indicates that the current transfer function can basically represent the current actual operation of the machine. At this time, it is determined that the parameters of the pre-established physical model do not meet the preset update conditions, and continuous iterative update of parameter identification may not be performed. Otherwise, it is determined that the parameters of the pre-established physical model meet the preset update conditions, and further iterative update must be performed on the basis of the previous model parameters.

[0048] Further, in some embodiments, the temperature control method further includes: obtaining the previous moment pulse width modulation value and the current moment pulse width modulation value of the cooling fan in the temperature control system; if it is determined that the change value of the pulse width modulation value is greater than the second preset threshold based on the current moment pulse width modulation value and the previous moment pulse width modulation value, it is determined that the parameters of the pre-established physical model meet the preset update conditions.

[0049] Wherein, the second preset threshold can be a threshold preset by those skilled in the art, such as 10%, which is not specifically limited herein.

[0050] Specifically, at the initial stage of system operation, the system records the matrix of the estimated temperature T of the heat dissipation component and the PWM value p input by the cooling fan. When the instantaneous change of the PWM value exceeds the second preset threshold, for example, when the PWM value input by the cooling fan has a step change exceeding 10%, it is determined that the parameters of the pre-established physical model meet the preset update conditions, that is, the parameters of the pre-established physical model need to be updated.

[0051] Thus, by monitoring the drastic fluctuation of the PWM value, the sudden change of the system heat dissipation demand or environmental disturbance is indirectly reflected, which is convenient for timely adjusting the model to maintain the prediction accuracy.

[0052] In step S103, if the parameters of the physical model meet the preset update conditions, the parameters of the pre-established physical model are updated, and based on the updated parameters, the control parameters of the proportional integral differential controller are determined according to the preset objective function, so that the proportional integral differential controller controls the operating temperature of the server based on the control parameters.

[0053] Further, in some embodiments, updating the parameters of the pre-established physical model includes: obtaining an initial parameter matrix, an initial covariance matrix, and a forgetting factor; updating the parameters of the pre-established physical model according to the preset recursive least squares method based on the initial parameter matrix, the initial covariance matrix, and the forgetting factor to obtain the updated parameters.

[0054] Among them, the forgetting factor is a number between 0 and 1, which is used to adjust the weight of the algorithm for old data. The closer the forgetting factor is to 1, the smaller the weight of the old data, and the faster the algorithm can adapt to new data changes. The closer the forgetting factor is to 0, the greater the weight of the old data, and the more stable the algorithm can be, but it may not be sensitive enough to new data changes.

[0055] Specifically, when the parameters of the physical model meet the preset update conditions, the system will use the recursive least squares method to update the first parameter K, the second parameter Q, and the third parameter L in real time, and thus the latest transfer function model of the server system can be obtained. In the embodiment of the present application, the initial parameter matrix is set to zero, that is, the initial parameter vector θ(0) is all 0, and the initial covariance matrix P(0)=δI, where δ = 5000, and I is a 3x3 identity matrix. The initial forgetting factor σ can be defined as 1, and other inferences are performed according to the recursive operation of the recursive least squares method. And for subsequent iterative updates, the forgetting factor σ can be defined between [0.5, 0.98], and it is recommended not to define it as the initial value of 1 or a value close to 1.

[0056] Further, whenever new PWM values and corresponding heat dissipation component temperature values are obtained, these data are substituted into the recurrence formula. Using the initial parameter matrix, the initial covariance matrix, and the forgetting factor as the starting point of the recurrence, iterative calculations are started. In each step of the recurrence, the parameter estimation value and the covariance matrix are adjusted according to the new data, so as to update the parameters of the physical model.

[0057] Through the above technical means, through the recursive least squares method, the physical model parameters can be updated in real time to adapt to the changes of the server heat dissipation system, and the accuracy and prediction ability of the physical model are improved.

[0058] Further, in some embodiments, before determining the control parameters of the proportional-integral-derivative controller according to the preset objective function based on the updated parameters, it further includes: obtaining the current load and the current heat dissipation safety requirement of the server; based on the current load and the current heat dissipation safety requirement, determining the temperature weight coefficient, the power consumption weight coefficient, and the rotational speed fluctuation noise coefficient in the heat dissipation control process; and obtaining the preset objective function based on the temperature weight coefficient, the power consumption weight coefficient, and the rotational speed fluctuation noise coefficient.

[0059] Specifically, the current load of the server reflects the usage of the server's computing resources. In the embodiments of the present application, the current load situation of the server can be obtained based on indicators such as CPU usage rate, memory usage rate, network traffic, and disk I / O. The current heat dissipation safety requirement of the server mainly reflects the operating state of the server's heat dissipation system and the temperature of the heat dissipation components to ensure that the server does not fail due to overheating. In the embodiments of the present application, the current heat dissipation safety requirement of the server can be comprehensively obtained based on the real-time temperature of the server's heat dissipation components, the status of the heat dissipation fans (such as the rotation speed and operating state of the heat dissipation fans), and the ambient temperature.

[0060] Further, the embodiments of the present application consider the impacts of temperature, power consumption, and rotational speed fluctuation noise during the heat dissipation regulation process, and propose three weight coefficients, namely the temperature weight coefficient α related to heat dissipation safety, the comprehensive power consumption weight coefficient β, and the rotational speed fluctuation noise weight coefficient γ. Based on the temperature weight coefficient, the power consumption weight coefficient, and the rotational speed fluctuation noise coefficient, the following preset objective function is obtained:

[0061]

[0062] Where J is the preset objective function, α is the temperature weight coefficient, u is the temperature error, that is, the difference between the actual output value and the set value, β is the power consumption weight coefficient, R is the rotational speed of the current fan, γ is the rotational speed fluctuation noise weight coefficient, and t is time.

[0063] Therefore, in view of the problem that the PID regulation process in the current prior art does not comprehensively consider the fan power consumption and fluctuation noise, the embodiments of the present application propose an optimized objective function, which can comprehensively evaluate and optimize the temperature, power consumption, and rotational speed fluctuation noise.

[0064] Further, in some embodiments, when the current load is greater than the preset load value, or the current heat dissipation safety requirement is greater than the preset safety requirement, the temperature weight coefficient is greater than the power consumption weight coefficient, and the temperature weight coefficient is greater than the rotational speed fluctuation noise coefficient.

[0065] Specifically, the embodiments of the present application comprehensively consider the temperature weight coefficient α related to heat dissipation safety, the comprehensive power consumption weight coefficient β, and the rotational speed fluctuation noise weight coefficient γ, and need to make different adjustments in different scenarios, mainly including the following two situations:

[0066] ① In high-load periods or scenarios with high requirements for heat dissipation safety, priority is given to heat dissipation consideration: the temperature weight coefficient α is greater than the power consumption weight coefficient β, and the temperature weight coefficient α is greater than the rotational speed fluctuation noise weight coefficient γ;

[0067] ②In low-load periods or scenarios where server silence and power consumption are more emphasized, the priority is given to silence and energy conservation: the temperature weight coefficient α is less than the power consumption weight coefficient β, and the temperature weight coefficient α is less than the rotational speed fluctuation noise weight coefficient γ.

[0068] Therefore, the embodiments of the present application propose a multi-objective optimization strategy for different scenarios, define the comparison criteria for power consumption, noise, and heat dissipation requirements according to different scenario requirements, and provide a more advantageous custom selection for PID self-tuning.

[0069] Furthermore, when the temperature load of the heat dissipation component suddenly increases and causes the temperature to rise, first determine whether the current physical model parameters can cover the operating conditions of the current actual machine. When the current physical model does not need to be updated (that is, the estimated temperature of the physical model is greater than or equal to the actual temperature, and the difference between the estimated temperature and the actual temperature is less than or equal to the first preset threshold, and the change value of the pulse width modulation value is less than or equal to the second preset threshold), then determine the first parameter K, the second parameter Q, and the third parameter L of the current physical model, and solve for the PID control parameters corresponding to the minimum value of the preset objective function value J, and use this PID control parameter as the final PID control parameter, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the final PID control parameter.

[0070] Furthermore, after the current physical model meets the preset update conditions and the parameters of the physical model are updated, according to the first parameter K, the second parameter Q, and the third parameter L of the updated physical model, re-solve for the PID control parameters corresponding to the minimum value of the preset objective function value J, and use this PID control parameter as the final PID control parameter, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the final PID control parameter.

[0071] To facilitate those skilled in the art to more clearly and intuitively understand the temperature control method proposed by the present application, the following will be combined with Figure 2 for a detailed description.

[0072] Specifically, as Figure 2 shown, first, a system summary model is established, second, system model parameter identification is performed, and then an optimization strategy is determined; then the objective function is calculated, and finally the optimal PID parameters are solved, and the model parameters are re-identified through the PWM step signal for real-time control of the fan speed to achieve a multi-objective balance of temperature stability, power consumption reduction, and noise suppression.

[0073] Thus, according to the overall solution method for optimizing power consumption and noise in server fan heat dissipation regulation proposed in the embodiments of the present application, aiming at the problem that it is difficult to accurately deduce the transfer function of the server and thus PID automatic tuning cannot be achieved, the present invention uses a fuzzy first-order inertial lag system as a judgment criterion and proposes an objective function formula that can balance the temperature error, power consumption, and fan rotation fluctuation noise, providing an implementation solution for the self-tuning of the server PID fan regulation.

[0074] According to the temperature control method proposed in the embodiments of the present application, based on a pre-established physical model, the estimated temperature of the heat dissipation component is obtained, and based on the estimated temperature and the actual temperature of the heat dissipation component, when the parameters of the physical model meet the preset update conditions, the parameters of the pre-established physical model are updated, and based on the updated parameters, the control parameters of the proportional-integral-derivative controller are determined according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters. Thus, the problems that parameter tuning in server fan PID regulation relies on manual experience, has low efficiency and strong subjectivity, and the prior art cannot effectively balance power consumption, noise, and heat dissipation performance are solved, and effective control of the server temperature, power consumption, and noise is achieved.

[0075] Next, the temperature control device proposed in the embodiments of the present application is described with reference to the accompanying drawings.

[0076] Figure 3 It is a block diagram of the temperature control device according to an embodiment of the present application.

[0077] As Figure 3 shown, the temperature control device 10 includes: an acquisition module 100, a processing module 200, and a control module 300.

[0078] Among them, the acquisition module 100 is used to acquire the actual temperature of the heat dissipation component; the processing module 200 is used to obtain the estimated temperature of the heat dissipation component based on a pre-established physical model, and based on the estimated temperature and the actual temperature, determine whether the parameters of the pre-established physical model meet the preset update conditions; the control module 300 is used to update the parameters of the pre-established physical model if the parameters of the physical model meet the preset update conditions, and based on the updated parameters, determine the control parameters of the proportional-integral-derivative controller according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters.

[0079] Further, in some embodiments, the processing module 200 is used to: calculate the difference between the estimated temperature and the actual temperature; determine whether the estimated temperature is less than the actual temperature, or whether the difference is greater than a first preset threshold; if the estimated temperature is less than the actual temperature, or the difference is greater than the first preset threshold, it is determined that the parameters of the pre-established physical model meet the preset update conditions.

[0080] Further, in some embodiments, the pre-established physical model is:

[0081]

[0082] Wherein, T is the estimated temperature of the heat dissipation component, p is the PWM value input by the cooling fan, K is the first parameter, Q is the second parameter, L is the third parameter, and e is the natural constant.

[0083] Further, in some embodiments, the control module 300 is configured to: obtain an initial parameter matrix, an initial covariance matrix, and a forgetting factor; update the parameters of the pre-established physical model based on the initial parameter matrix, the initial covariance matrix, and the forgetting factor according to a preset recursive least squares method to obtain updated parameters.

[0084] Further, in some embodiments, before determining the control parameters of the proportional-integral-derivative controller according to a preset objective function based on the updated parameters, the control module 300 is further configured to: obtain the current load and the current heat dissipation safety requirement of the server; determine a temperature weight coefficient, a power consumption weight coefficient, and a rotational speed fluctuation noise coefficient during the heat dissipation control process based on the current load and the current heat dissipation safety requirement; and obtain a preset objective function based on the temperature weight coefficient, the power consumption weight coefficient, and the rotational speed fluctuation noise coefficient.

[0085] Further, in some embodiments, when the current load is greater than a preset load value, or the current heat dissipation safety requirement is greater than a preset safety requirement, the temperature weight coefficient is greater than the power consumption weight coefficient, and the temperature weight coefficient is greater than the rotational speed fluctuation noise coefficient.

[0086] Further, in some embodiments, the temperature control device 10 is further configured to: obtain the pulse width modulation value at the previous moment and the pulse width modulation value at the current moment of the cooling fan in the temperature control system; and determine that the parameters of the pre-established physical model meet the preset update condition if it is determined that the change value of the pulse width modulation value is greater than a second preset threshold based on the pulse width modulation value at the current moment and the pulse width modulation value at the previous moment.

[0087] It should be noted that the foregoing explanation of the embodiments of the temperature control method is also applicable to the temperature control device of this embodiment, and will not be elaborated here.

[0088] The temperature control device proposed according to the embodiments of the present application obtains the estimated temperature of the heat dissipation component based on a pre-established physical model, and based on the estimated temperature and the actual temperature of the heat dissipation component, when the parameters of the physical model meet the preset update conditions, updates the parameters of the pre-established physical model, and based on the updated parameters, determines the control parameters of the proportional-integral-derivative controller according to the preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters. Thus, it solves the problems that the parameter tuning in the PID control of the server fan depends on manual experience, has low efficiency and strong subjectivity, and the prior art cannot effectively balance power consumption, noise and heat dissipation performance, and realizes the effective control of the server temperature, power consumption and noise.

[0089] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

[0090] A memory 401, a processor 402, and a computer program stored on the memory 401 and executable on the processor 402.

[0091] When the processor 402 executes the program, it implements the temperature control method provided in the above embodiment.

[0092] Further, the electronic device further includes:

[0093] A communication interface 403 for communication between the memory 401 and the processor 402.

[0094] The memory 401 is used to store a computer program executable on the processor 402.

[0095] The memory 401 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0096] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be interconnected through a bus and communicate with each other. The bus may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 4It is represented only by a thick line, but it does not mean that there is only one bus or one type of bus.

[0097] Optionally, in a specific implementation, if the memory 401, the processor 402, and the communication interface 403 are integrated on a single chip, the memory 401, the processor 402, and the communication interface 403 can communicate with each other through an internal interface.

[0098] The processor 402 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0099] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above temperature control method is implemented.

[0100] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0101] The above has introduced in detail a method for diagnosing anomalies in a basic input / output system provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A temperature control method, characterized in that, Including the following steps: Obtain the actual temperature of the heat dissipation component; Based on a pre-established physical model, obtain the estimated temperature of the heat dissipation component, and based on the estimated temperature and the actual temperature, determine whether the parameters of the pre-established physical model meet a preset update condition; If the parameters of the physical model meet the preset update condition, update the parameters of the pre-established physical model, and based on the updated parameters, determine the control parameters of the proportional-integral-derivative controller according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the control parameters.

2. The method according to claim 1, characterized in that, The determining whether the parameters of the pre-established physical model meet the preset update condition based on the estimated temperature and the actual temperature includes: Calculate the difference between the estimated temperature and the actual temperature; Determine whether the estimated temperature is less than the actual temperature, or whether the difference is greater than a first preset threshold; If the estimated temperature is less than the actual temperature, or the difference is greater than the first preset threshold, determine that the parameters of the pre-established physical model meet the preset update condition.

3. The method according to claim 1 or 2, characterized in that, The pre-established physical model is: where T is the estimated temperature of the heat dissipation component, p is the PWM value input by the cooling fan, K is the first parameter, Q is the second parameter, L is the third parameter, and e is the natural constant.

4. The method according to claim 1, characterized in that, The updating the parameters of the pre-established physical model includes: Obtain an initial parameter matrix, an initial covariance matrix, and a forgetting factor; Based on the initial parameter matrix, the initial covariance matrix, and the forgetting factor, update the parameters of the pre-established physical model according to a preset recursive least squares method to obtain the updated parameters.

5. The method according to claim 1, characterized in that Before determining the control parameters of the proportional-integral-derivative controller according to the preset objective function based on the updated parameters, it further includes: Obtain the current load and the current heat dissipation safety requirement of the server; Based on the current load and the current heat dissipation safety requirement, determine the temperature weight coefficient, the power consumption weight coefficient, and the rotational speed fluctuation noise coefficient during the heat dissipation control process; Based on the temperature weight coefficient, the power consumption weight coefficient, and the rotational speed fluctuation noise coefficient, obtain the preset objective function.

6. The method according to claim 5, wherein When the current load is greater than a preset load value, or the current heat dissipation safety requirement is greater than a preset safety requirement, the temperature weight coefficient is greater than the power consumption weight coefficient, and the temperature weight coefficient is greater than the rotational speed fluctuation noise coefficient.

7. The method according to claim 1, characterized in that, It further includes: Obtain the previous moment pulse width modulation value and the current moment pulse width modulation value of the cooling fan in the temperature control system; If it is determined that the change value of the pulse width modulation value is greater than a second preset threshold based on the current moment pulse width modulation value and the previous moment pulse width modulation value, determine that the parameters of the pre-established physical model meet the preset update condition.

8. A temperature control device, characterized in that, It includes: An obtaining module, configured to obtain the actual temperature of the heat dissipation component; A processing module, configured to obtain an estimated temperature of the heat dissipation component based on a pre-established physical model, and determine whether parameters of the pre-established physical model meet a preset update condition based on the estimated temperature and the actual temperature; A control module, configured to update the parameters of the pre-established physical model if the parameters of the physical model meet the preset update condition, and determine regulation parameters of a proportional-integral-derivative controller based on the updated parameters according to a preset objective function, so that the proportional-integral-derivative controller controls the operating temperature of the server based on the regulation parameters.

9. An electronic device, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the temperature control method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor for implementing the temperature control method according to any one of claims 1-7.

Images