A heat dissipation control method, device, equipment and medium

Abstract

The embodiment of the present application provides a heat dissipation control method, which comprises the following steps: collecting internal temperature data and environment temperature data of a target device, obtaining an air inlet temperature change rate and / or a predicted air inlet temperature of the target device according to the collected internal temperature data and environment temperature data; calculating a target hysteresis temperature according to the air inlet temperature change rate and / or the predicted air inlet temperature, and adjusting a hysteresis temperature of the target device to the target hysteresis temperature; determining a heat dissipation mode according to the target hysteresis temperature, and adjusting a fan rotating speed of the target device according to the heat dissipation mode when the air inlet temperature of the target device changes. The embodiment of the present application reduces reciprocating oscillation and fluctuation of the system fan rotating speed and the power body fan rotating speed of the target device caused by the air inlet temperature change, reduces heat dissipation energy consumption, and improves heat dissipation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of heat dissipation technology, and in particular to a heat dissipation control method, device, equipment and medium. Background Art

[0002] With the increasing advancement and development of computer network technology, electronic devices such as switches, servers, and personal computers (PCs) serve as core equipment in data center communication networks. Their overall performance and reliability directly affect the stability of the entire network system. During actual operation, these electronic devices continuously forward data and exchange traffic, which inevitably generates a large amount of heat. If the heat cannot be dissipated in a timely and effective manner, the equipment will inevitably overheat, thereby affecting its functional stability and even causing damage due to overheating. Currently, commonly used heat dissipation methods include natural air cooling, forced air cooling, and liquid cooling. Among air cooling methods, heat dissipation based on the switch air inlet temperature is a relatively mature, effective, and widely used method. However, this method still suffers from low heat dissipation efficiency, high energy consumption, or high cost in actual engineering applications. Therefore, there is an urgent need for an efficient, economical, and practical heat dissipation method to solve this problem. Summary of the Invention

[0003] In view of the above problems, the present invention proposes a heat dissipation control method, device, equipment and medium.

[0004] In a first aspect of the present invention, a heat dissipation control method is first provided, characterized in that the method comprises:

[0005] Collect internal temperature data and ambient temperature data of the target device;

[0006] determining a temperature change rate of an air inlet of the target device and / or predicting an air inlet temperature according to the internal temperature data and the ambient temperature data;

[0007] calculating a target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature, and adjusting the hysteresis temperature of the target device to the target hysteresis temperature;

[0008] A heat dissipation mode is determined according to the target hysteresis temperature, and when the air inlet temperature of the target device changes, a fan speed of the target device is adjusted according to the heat dissipation mode.

[0009] Optionally, determining the air inlet temperature change rate and / or predicting the air inlet temperature of the target device according to the internal temperature data and the ambient temperature data includes:

[0010] Obtaining air inlet temperature data of the target device according to an average value of the internal temperature and the ambient temperature;

[0011] The air inlet temperature of the target device is predicted based on the air inlet temperature data using an autoregressive integral moving average model to obtain a predicted air inlet temperature.

[0012] Optionally, the determining the air inlet temperature change rate and / or predicting the air inlet temperature of the target device based on the internal temperature data and the ambient temperature data further includes:

[0013] The air inlet temperature change rate is obtained according to the predicted air inlet temperature and the current air inlet temperature of the target device.

[0014] Optionally, calculating the target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature includes:

[0015] If the absolute value of the air inlet temperature change rate is greater than the absolute value of the preset temperature change rate standard value, calculating a first target hysteresis temperature according to the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value;

[0016] The calculation formula of the first target hysteresis temperature is:

[0017] h new =h*(1+|r|-|r d |)

[0018] Among them, h new represents the adjusted hysteresis temperature, h represents the current hysteresis temperature, r represents the temperature change rate, r d Indicates the standard value of temperature change rate;

[0019] If the absolute value of the air inlet temperature change rate is less than the product of the absolute value of the temperature change rate standard value and the preset change rate percentage, calculating the second target hysteresis temperature according to the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value;

[0020] The calculation formula of the second target hysteresis temperature is:

[0021] h new =h*(1-|r|+|r d |).

[0022] Optionally, the calculating the target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature further includes:

[0023] If the predicted inlet temperature is greater than the inlet temperature standard value, a third target hysteresis temperature is calculated according to the predicted inlet temperature and the inlet temperature standard value; the inlet temperature standard value is set according to the model of the target device;

[0024] wherein the calculation formula of the third target hysteresis temperature is:

[0025]

[0026] wherein T f represents the predicted inlet temperature, T d represents the inlet temperature standard value;

[0027] If the predicted inlet temperature is less than the product of the inlet temperature standard value and a preset inlet temperature percentage, a fourth target hysteresis temperature is calculated according to the predicted inlet temperature and the inlet temperature standard value;

[0028] wherein the calculation formula of the fourth target hysteresis temperature is:

[0029]

[0030] Optionally, the method further comprises:

[0031] If the output power of the target device is greater than a target device output power standard value, a fifth target hysteresis temperature is calculated according to the output power of the target device and the target device output power standard value; the target device output power standard value is set according to the model of the target device;

[0032] wherein the calculation formula of the fifth target hysteresis temperature is:

[0033]

[0034] wherein P represents the output power of the target device, P d represents the target device output power standard value;

[0035] If the output power of the target device is less than the product of the target device output power standard value and a preset target device output power percentage, a sixth target hysteresis temperature is calculated according to the output power of the target device and the target device output power standard value;

[0036] wherein the calculation formula of the sixth target hysteresis temperature is:

[0037]

[0038] Optionally, determining a heat dissipation mode according to the target hysteresis temperature, and adjusting a fan speed of the target device according to the heat dissipation mode when an air inlet temperature of the target device changes, includes:

[0039] Get the difference between the predicted air inlet temperature and the current air inlet temperature;

[0040] If the difference is greater than the target hysteresis temperature, obtaining a fan speed duty cycle of the target device based on the predicted air inlet temperature;

[0041] If the difference is less than or equal to the target hysteresis temperature, maintaining the fan speed duty cycle of the target device;

[0042] The fan speed duty cycle is set to the fan of the target device to adjust the fan speed of the target device.

[0043] In a second aspect of the present invention, a heat dissipation control device is provided, wherein the device comprises:

[0044] A data acquisition module is used to collect internal temperature data and ambient temperature data of the target device;

[0045] a data processing module, configured to determine a temperature change rate of an air inlet of the target device and / or predict an air inlet temperature based on the internal temperature data and the ambient temperature data;

[0046] a hysteresis temperature adjustment module, configured to calculate a target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature, and adjust the hysteresis temperature of the target device to the target hysteresis temperature;

[0047] The heat dissipation mode generating module is used to determine the heat dissipation mode according to the target hysteresis temperature, and adjust the fan speed of the target device according to the heat dissipation mode when the air inlet temperature of the target device changes.

[0048] In a third aspect of the implementation of the present invention, an electronic device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the heat dissipation control method as described above is implemented.

[0049] In a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the heat dissipation control method as described above is implemented.

[0050] The embodiments of the present invention have the following advantages:

[0051] In an embodiment of the present invention, internal temperature data and ambient temperature data of a target device are collected; the target device's air inlet temperature change rate and / or predicted air inlet temperature are determined based on the internal temperature data and ambient temperature data; the target device's target hysteresis temperature is calculated based on the air inlet temperature change rate and / or predicted air inlet temperature, and the target device's hysteresis temperature is adjusted to the target hysteresis temperature; a heat dissipation mode is determined based on the target hysteresis temperature, and when the target device's air inlet temperature changes, the target device's fan speed is adjusted based on the heat dissipation mode. This significantly reduces the reciprocating oscillation and fluctuation in the speed of the target device's system fan and power supply fan caused by changes in the air inlet temperature, extends the service life of the target device's fan, and improves heat dissipation efficiency while reducing heat dissipation energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0053] Figure 1 This is a flowchart of a heat dissipation control method provided by one embodiment of the present invention;

[0054] Figure 2 is a schematic diagram of processing air inlet temperature provided by one embodiment of the present invention;

[0055] Figure 3 This is a principle block diagram of a heat dissipation control method provided by one embodiment of the present invention;

[0056] Figure 4 This is a flowchart of the steps for processing air inlet temperature data provided by one embodiment of the present invention;

[0057] Figure 5 This is a flowchart of steps for collecting air inlet temperature data provided by one embodiment of the present invention;

[0058] Figure 6 This is a flowchart of the steps for establishing an autoregressive integrated moving average model provided by one embodiment of the present invention;

[0059] Figure 7 This is a flow chart of the steps for dynamically adjusting the hysteresis temperature provided by one embodiment of the present invention;

[0060] Figure 8 This is a structural block diagram of a heat dissipation control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, each embodiment of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present invention, many technical details are provided to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in this application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with each other and referenced to each other under the premise that there is no contradiction.

[0062] In the first existing technical solution, the heat dissipation method based on air inlet temperature handles the following in practice: when the air inlet temperature rises, a heat dissipation strategy is generated to increase the speed of the switch system fans and the power supply fan; when the air inlet temperature drops, a heat dissipation strategy is generated to reduce the speed of the switch system fans and the power supply fan. A linear calculation formula is used to calculate the appropriate fan speed based on the air inlet temperature.

[0063] Although the existing technical solution 1 can respond to changes in the external ambient temperature or the switch air inlet temperature in a timely and rapid manner, it has an obvious disadvantage: when the external ambient temperature or the switch air inlet temperature jitters or fluctuates up and down in a short period of time, it will cause the speed of the switch system fan and the power supply body fan to rise and fall sharply and reciprocate, thereby affecting the stability of the cooling system. At the same time, frequent speed adjustment of the system fan and the power supply body fan in a short period of time will also accelerate the aging of the electronic components inside the fan, affecting the service life of the cooling components.

[0064] The existing technical solution 2 is further optimized based on the technical solution 1. Figure 2 As shown in the figure: When the air inlet temperature or the external ambient temperature rises, a cooling strategy is generated to increase the speed of the switch system fan and the power supply fan. However, when the switch air inlet temperature or the external ambient temperature drops, a new cooling strategy is not immediately generated to reduce the speed of the switch system fan and the power supply fan. Instead, a fixed hysteresis temperature (for example, 2 degrees Celsius, 4 degrees Celsius, etc.) is pre-set. When the switch temperature continues to drop and the drop exceeds the pre-set hysteresis temperature, a new cooling strategy is generated to reduce the speed of the switch system fan and the power supply fan.

[0065] The second technical solution of the prior art avoids, to a certain extent, the reciprocating oscillation and fluctuation of the fan speed caused by the drastic changes in the fan speed when the air inlet temperature or the external ambient temperature frequently rises and falls, and improves the heat dissipation efficiency to a certain extent. However, the second technical solution has an obvious disadvantage: when the air inlet temperature of the switch or the ambient temperature changes too little or too much, since its pre-set hysteresis temperature is a fixed value, it cannot change according to the dynamic changes of the air inlet temperature or the external ambient temperature. In some scenarios, it may lead to low heat dissipation efficiency or increased heat dissipation energy consumption.

[0066] In response to the fan speed oscillation and energy consumption problems in the heat dissipation method based on the switch air inlet temperature, this application proposes a heat dissipation control method, that is, when the switch air inlet temperature or the external ambient temperature fluctuates, the heat dissipation strategy is optimized by dynamically adjusting the hysteresis temperature, thereby achieving a dynamic balance between the switch's heat dissipation efficiency and energy consumption. However, this application is not limited to switches, and can also be applied to heat dissipation fields such as servers and personal PCs.

[0067] Reference Figure 1 , shows a flowchart of a heat dissipation control method provided by an embodiment of the present invention, which may specifically include the following steps:

[0068] Step 101: Collect internal temperature data and ambient temperature data of a target device.

[0069] The target device may include a switch, a server, a personal PC, etc. The embodiment of the present invention is described by taking a switch as an example.

[0070] Based on the position and direction of the air duct inside the switch, and the distribution of air duct sensors on the air duct inside the switch, two temperature sensors are selected as the internal temperature collection points of the switch air inlet, and at least one external temperature collection device of the switch is designed based on the position of the switch in the rack.

[0071] Specifically, to obtain a more accurate temperature reading at the switch's air inlet, multiple external temperature collection devices are installed based on the switch's position within the rack and its external shape. These devices collect the external ambient temperature in real time. Two temperature sensors are also located within the switch's internal air duct as inlet temperature collection points. One temperature sensor collects the temperature near the air inlet, while the other collects the temperature near the air outlet. The data collection frequency is determined based on actual needs, such as once every 10 seconds. Based on this frequency, the two temperature sensors and multiple temperature collection devices collect real-time data on the switch's internal air inlet and outlet temperatures, as well as the external ambient temperature.

[0072] Step 102: Determine the air inlet temperature change rate and / or predict the air inlet temperature of the target device according to the internal temperature data and the ambient temperature data.

[0073] Before determining the air inlet temperature change rate of the target device and predicting the air inlet temperature, the air inlet temperature data of the target device must be determined first.

[0074] Assume that the internal air duct temperature of the switch collected by the two temperature sensors is T M and T N , where T M Close to the air inlet, T N Close to the air outlet; Since there are multiple external temperature collection devices according to the location of the switch cabinet and the shape of the switch, the external environment temperature T O It can be obtained by the weighted average algorithm, specifically:

[0075]

[0076] Where n is the number of temperature collection devices outside the switch, T i Indicates the ambient temperature collected by multiple switch external temperature collection devices, w i Indicates the weights corresponding to the ambient temperatures collected by multiple switch external temperature collection devices.

[0077] Specifically, the weights corresponding to the ambient temperatures respectively collected by the multiple temperature sensors are determined according to the location of the switch.

[0078] The switch air inlet temperature T is:

[0079]

[0080] Among them, T M T is the internal air inlet temperature actually collected by the temperature sensor near the air inlet inside the switch. N Δt is the internal air outlet temperature actually collected by the temperature sensor near the air outlet inside the switch. M is the compensation temperature of the temperature sensor near the air inlet inside the switch, Δt N It is the compensation temperature of the temperature sensor near the air outlet inside the switch, and it is the external ambient temperature collected in real time by the temperature collection device outside the switch. O is the external ambient temperature.

[0081] It should be noted that after the air outside the switch enters the switch through the air inlet, it is affected by the heat-generating components in the air duct (such as the heat-generating power supply, heat-generating optical module, and some other heat-generating electronic components). The actual temperature is higher than the external ambient temperature. Therefore, a compensation temperature is required to make it closer to the external ambient temperature.

[0082] Generally, the compensation temperature is determined based on the following two methods:

[0083] (1) Select a value based on actual engineering experience;

[0084] This approach relies heavily on long-term engineering practice and accumulated experience. Through extensive experimental data and field testing, a typical value for the temperature difference between the inside and outside of a switch under specific conditions can be determined.

[0085] (2) Divide the temperature into sections and calculate the temperature difference between the inside and outside of the switch as the compensation temperature.

[0086] Divide the temperature range into several segments (for example, 10-20°C, 20-30°C, 30-40°C, etc.). In each temperature segment, collect temperature data from inside and outside the switch. Calculate the average difference between the internal and external temperatures of the switch in each temperature segment, and use the statistically obtained difference as the compensation temperature for that temperature segment.

[0087] After determining the air inlet temperature data of the switch, the air inlet temperature can be predicted using an Autoregressive Integrated Moving Average Model (ARIMA).

[0088] Autoregressive Integrated Moving Average Model (ARIMA), where Autoregressive (AR) is the autoregressive part that represents the relationship between the current value and the past value; Integrated (I) is the integral part that represents the difference processing of the time series to make it smooth; Moving Average (MA) is the moving average part that represents the relationship between the current value and the past error term.

[0089] The main parameters in the ARIMA model include the autoregressive order p, the difference order d, and the moving average order q, which is usually expressed as ARIMA(p, d, q) and can be expressed by the following formula:

[0090]

[0091] Among them, T t is the switch air inlet temperature at time t, Tt-i is the temperature sequence of the switch inlet at the past i moments, θ j and are the sliding average coefficient and autoregressive coefficient of the ARIMA model, respectively. m and n are the orders of the autoregressive and sliding average parts, namely p and q; α t represents a residual sequence with mean zero.

[0092] like Figure 6 FIG. 1 is a flowchart of steps for establishing an autoregressive integrated moving average model according to an embodiment of the present invention. The specific steps are as follows:

[0093] 1. Determine model parameters

[0094] Based on the time series data, that is, the collected air inlet temperature data, the autocorrelation function (ACF) and partial autocorrelation function (PACF) graphs are drawn. By observing the ACF graph and the PACF graph, in the PACF graph, the position of the first significant non-zero lag is usually considered to be a reasonable estimate of the autoregressive order p; in the ACF graph, the position of the first significant non-zero lag is usually considered to be a reasonable estimate of the sliding average order q.

[0095] Perform a difference operation on the original time series, that is, the collected air inlet temperature data, until the time series becomes stationary. Record the number of differences required to convert the time series data into a stationary series, which is the value of the difference order d. A stationary series refers to a series whose mean and variance do not change over time. The ADF (Augmented Dickey-Fuller Test) or other stationarity test methods can be used to confirm whether the time series is stationary.

[0096] Draw the ACF and PACF diagrams for the time series after differentiation to determine the autoregressive order p and the sliding average order q.

[0097] 2. Parameter selection

[0098] The Akaike information criterion (AIC) or the Bayesian Information Criterion (BIC) was used to select the optimal model parameters.

[0099] AIC and BIC are both statistics for model selection, in the range of p, q and d determined initially, multiple ARIMA models are constructed, the AIC value or BIC value of each constructed ARIMA model is calculated, and the model with the minimum AIC value or BIC value is selected as the optimal model, that is, the optimal model parameters are determined.

[0100] 3. Model establishment

[0101] The determined optimal model parameters p, q and d are used to establish an ARIMA model.

[0102] 4. Model fitting

[0103] The collected inlet temperature data are used for model fitting, and the collected inlet temperature data are substituted into the formula of the established ARIMA model.

[0104] At this point, the fitted ARIMA model can be used to predict the temperature of the air inlet of the switch.

[0105] Specifically, the ARIMA model is used to predict the temperature, and the predicted temperature is denoted as T f .

[0106] Further, the predicted inlet temperature minus the current inlet temperature is used to obtain the difference between the predicted inlet temperature and the current inlet temperature, and the difference is divided by the current inlet temperature and multiplied by 100 to obtain the temperature change rate r, that is, the temperature change rate at the next time. Wherein, the temperature change rate is less than 0, indicating that the temperature of the air inlet of the switch is in a downward trend.

[0107] The temperature predicted by the ARIMA model is denoted as T f , and the current inlet temperature is denoted as T t , then the temperature change rate r is:

[0108]

[0109] Wherein, T f is the predicted inlet temperature, T t is the current inlet temperature, and r is the temperature change rate.

[0110] Step 103, calculating the target hysteresis temperature of the target device according to the inlet temperature change rate and / or the predicted inlet temperature, and adjusting the hysteresis temperature of the target device to the target hysteresis temperature.

[0111] The hysteresis temperature can be understood as the amplitude of temperature change. For example, if the hysteresis temperature is 2°C, when the temperature starts to drop from a high temperature (for example, 40°C), the temperature at time t1 is 39°C, and 40°C-39°C < 2°C, then the speed will not be adjusted at time t1; the temperature at time t2 is 38°C, and 40°C-38°C = 2°C, then the speed will not be adjusted at time t2; the temperature at time t3 is 37.5°C, and 40°C-37.5°C > 2°C, then the speed will start at time t3.

[0112] By analogy, the next time the speed is adjusted should be when (37.5°C - a certain temperature) > 2°C.

[0113] Set the initial hysteresis temperature of the switch's air inlet temperature.

[0114] 1. If the temperature change rate |r|>|r d |, then appropriately increase the hysteresis temperature to reduce unnecessary strategy adjustments, reduce the speed regulation oscillation period, and improve heat dissipation efficiency; if the temperature change rate |r|<|r d |*p r , then the hysteresis temperature needs to be appropriately lowered to quickly respond to temperature changes; if the temperature change rate |r d |*p r ≤|r|≤|r d |, then the hysteresis temperature is not adjusted at this time and the hysteresis temperature is kept unchanged. d Indicates the standard value of temperature change rate, which can be set according to measured data and experience; p r Indicates the percentage of change rate. This value can be determined based on engineering experience or through a large amount of statistical analysis. It varies for different models and different computer room environments.

[0115] 2. If the switch predicts the air inlet temperature T f >T d , then the hysteresis temperature should be appropriately increased to improve the heat dissipation efficiency; if the predicted air inlet temperature T f <T d *p T , then appropriately reduce the hysteresis temperature to reduce heat dissipation energy consumption; if the switch inlet temperature T d *p T ≤T f ≤T d , at this time, the hysteresis temperature is not adjusted and the hysteresis temperature is kept unchanged. d Indicates the standard value of the switch air inlet temperature, which can be set according to different switch models; p T Indicates the percentage of air inlet temperature, which is determined in the same way as p r same.

[0116] 3. If the switch output power P>P d, then appropriately increase the hysteresis temperature to improve the heat dissipation efficiency; if the switch output power P <P d *P p , then appropriately reduce the hysteresis temperature to reduce energy consumption. If the switch output power P d *P p ≤P≤P d , at this time, the hysteresis temperature is not adjusted and the hysteresis temperature is kept unchanged. d Indicates the standard value of the switch output power, which can be set according to the switch model; P p Indicates a percentage, which is determined in the same way as p r same.

[0117] 4. If all system fans are in place and working normally, the hysteresis temperature should be appropriately lowered to reduce heat dissipation energy consumption. If the number of system fans in place is less than 50% or the number of faulty fans is less than 50%, the hysteresis temperature should be appropriately increased to improve heat dissipation efficiency.

[0118] 5. If the CPU usage of the switch exceeds 70%, the hysteresis temperature should be appropriately increased to improve heat dissipation efficiency; if the CPU usage of the switch is less than 40%, the hysteresis temperature should be appropriately lowered to reduce heat dissipation energy consumption.

[0119] It should be noted that the switch output power, system fan status, and switch CPU utilization can all be monitored in real time. Switch output power is related to the power module. SNMP (Simple Network Management Protocol) can be used to obtain power module power information. Fan status information and CPU utilization data can also be obtained through SNMP. This application does not impose any restrictions.

[0120] like Figure 7 FIG. 1 is a flowchart of a step of dynamically adjusting the hysteresis temperature according to an embodiment of the present invention. In this embodiment, p r Take 50%, p T Take 90%, P p Take 80%, the specific process is as follows:

[0121] 1. Determine whether the temperature change rate is greater than the standard value. If so, increase the hysteresis temperature and end the process. If not, determine whether the temperature change rate is less than the standard value multiplied by 50%;

[0122] 2. If the temperature change rate is less than the standard value multiplied by 50%, the hysteresis temperature is lowered and the process ends; if not, determine whether the predicted air inlet temperature is greater than the standard value;

[0123] 3. If the predicted air inlet temperature is greater than the standard value, the hysteresis temperature is increased and the process ends; if not, it is determined whether the predicted air inlet temperature is less than the standard value multiplied by 90%;

[0124] 4. If the predicted air inlet temperature is less than the standard value multiplied by 90%, the hysteresis temperature is lowered and the process ends. If not, determine whether the switch output power is greater than the standard value.

[0125] 5. If the switch output power is greater than the standard value, the hysteresis temperature is increased and the process ends; if not, the switch output power is determined to be less than the standard value multiplied by 80%;

[0126] 6. If the switch output power is less than the standard value multiplied by 80%, the hysteresis temperature is lowered and the process ends. If not, determine whether all the switch fans are functioning normally.

[0127] 7. If all fans on the switch are functioning normally, the hysteresis temperature is lowered and the process ends. If not, the normal fan power is determined to be below 50%.

[0128] 8. If the normal fan utilization rate is less than 50%, the hysteresis temperature is increased and the process ends. If not, the CPU utilization rate of the switch is determined to be greater than 70%.

[0129] 9. If the CPU usage of the switch is greater than 70%, the hysteresis temperature is increased and the process ends. If not, the process determines whether the CPU usage of the switch is less than 40%.

[0130] 10. If the CPU usage of the switch is less than 40%, reduce the hysteresis temperature; if not, end the process.

[0131] Step 104 : determining a heat dissipation mode according to the target hysteresis temperature, and adjusting a fan speed of the target device according to the heat dissipation mode when the air inlet temperature of the target device changes.

[0132] The cooling strategy can be simply understood as the fan speed value and alarm information. The fan speed is the key factor in controlling the heat dissipation of the switch. By adjusting the fan speed, the temperature of the switch can be effectively controlled to prevent overheating. The alarm information can be set by setting the alarm threshold to promptly notify the administrator when the switch temperature is abnormal or the fan fails so that appropriate measures can be taken.

[0133] The relationship between the fan's PWM value and temperature T can be expressed using a linear equation:

[0134] PWM=k*T+b

[0135] Among them, PWM is the fan speed duty cycle, that is, the fan speed, T is the air inlet temperature, and k and b are two constants.

[0136] At different temperatures T, the PWM value of the fan is recorded. At least two data points are required to determine the two constants of the linear equation.

[0137] After determining the linear equation between the fan's PWM value and temperature T, the difference between the predicted inlet temperature and the current inlet temperature is calculated. Then, a check is made to see if this difference is greater than the target hysteresis temperature. If so, the predicted inlet temperature is substituted into the linear equation to calculate a new PWM value. If the difference is less than or equal to the hysteresis temperature, the original PWM value is maintained.

[0138] You can use the driver software to set the fan speed value in the cooling policy, that is, the PWM value, to the switch fan to adjust the fan speed.

[0139] By using the switch's external temperature acquisition device and the switch's internal temperature sensor to obtain the switch's air inlet temperature, the ARIMA model is used to predict the air inlet temperature and temperature change rate. Combined with the switch's power, system fan operating status, CPU occupancy and other operating conditions, the switch's air inlet hysteresis temperature is dynamically adjusted. A cooling strategy is then generated and issued to the switch's system fan and power supply fan. This significantly reduces the reciprocating oscillation and fluctuation in the switch system fan and power supply fan speed caused by lower air inlet temperature, extending the service life of the switch fan and improving heat dissipation efficiency while reducing heat dissipation energy consumption.

[0140] This application can also be applied to heat dissipation fields such as servers and personal PCs. The air inlet temperature is collected by the air inlet duct temperature sensor, and the hysteresis temperature is dynamically adjusted according to the temperature change trend and the actual working status inside the server or personal PC, so that the fan speed is maintained at a relatively ideal speed, thereby achieving the goal of improving heat dissipation efficiency, reducing noise and heat dissipation energy consumption.

[0141] When predicting future air inlet temperatures based on collected air inlet temperature data, a deep learning model, LSTM (Long-Short Term Memory), can also be used for prediction. The LSTM is trained using historical data, and the model's performance is evaluated using a validation set to improve prediction accuracy.

[0142] Furthermore, in some embodiments of the present invention, step 102 further includes the following steps:

[0143] S1021: Obtain air inlet temperature data of the target device according to an average value of the internal temperature and the ambient temperature.

[0144] Taking a switch as an example, based on the switch's internal air duct location, air duct direction, and air duct sensor distribution, a temperature sensor is selected on the switch's internal air inlet duct as the switch's internal temperature collection point.

[0145] Specifically, temperature sensors are usually selected in the following two locations:

[0146] 1. PDB_Temp (Power Distribution Board Temperature), typically located near the power distribution board (PDB), monitors the temperature near the PDB, indirectly reflecting the air inlet temperature. Since the PDB is typically close to the air inlet, its temperature can serve as a reference point for the air inlet temperature.

[0147] 2. Inlet_Temp (Inlet Temperature), located directly at the air inlet, is the most direct inlet temperature collection point. This sensor can accurately obtain the air inlet temperature data.

[0148] Selecting PDB_Temp and Inlet_Temp as the internal temperature collection points for the air inlet ensures both the reliability of an indirect reference and the accuracy of direct measurement. This selection is widely used in engineering practice and effectively monitors the air inlet temperature of switches, ensuring stable system operation.

[0149] The data collection frequency is determined according to actual needs. In this embodiment, the internal air inlet temperature can be collected once every 10 seconds through the first temperature sensor, which is recorded as T M .

[0150] Then, based on the internal air duct position, air duct wind direction, and air duct sensor distribution of the switch, a temperature sensor is selected on the air outlet duct inside the switch as the internal temperature collection point of the switch outlet.

[0151] Similarly, the second temperature sensor is set to collect the internal air outlet temperature every 10 seconds, which is recorded as T N .

[0152] Then, at least one switch external temperature collection device is designed based on the position of the switch in the rack.

[0153] Specifically, in order to obtain a more accurate temperature of the switch air inlet, at least one temperature collection device is designed at the external air inlet of the switch, that is, at a position outside the switch close to the switch air inlet, and the ambient temperature is also collected every 10 seconds.

[0154] Since there are multiple external temperature collection devices according to the location of the switch cabinet and the shape of the switch, the external environment temperature T O It can be obtained by weighted average algorithm:

[0155]

[0156] Where n is the number of temperature collection devices outside the switch, T i Indicates the ambient temperature collected by multiple switch external temperature collection devices, w i Indicates the weights corresponding to the ambient temperatures collected by the multiple switch external temperature collection devices. Specifically, in this embodiment, n=10.

[0157] Furthermore, the internal air inlet temperature collected by the first temperature sensor is T M , the preset compensation temperature of the first temperature sensor is Δt M , then the first internal air inlet temperature is: T M +Δt M .

[0158] The internal air outlet temperature collected by the second temperature sensor is T N , the preset compensation temperature of the second temperature sensor is Δt N , then the second internal temperature is: T M +Δt N .

[0159] The air inlet temperature T of the switch is:

[0160]

[0161] Among them, T M is the internal air inlet temperature collected by the first temperature sensor, T N is the internal air outlet temperature collected by the second temperature sensor, Δt M is the preset compensation temperature of the first temperature sensor, Δt N is the preset compensation temperature of the second temperature sensor, T O is the external ambient temperature.

[0162] S1022 : Predicting the air inlet temperature of the target device using an autoregressive integral moving average model based on the air inlet temperature data to obtain a predicted air inlet temperature.

[0163] Specifically, the obtained air inlet temperature data is stored in a database or file, and noise and abnormal values ​​in the stored air inlet temperature data are cleared to ensure data quality. The data processing method can be selected according to actual needs and is not limited in this application.

[0164] The ACF and PACF diagrams are drawn based on the processed time series data (inlet temperature data). By observing the ACF and PACF diagrams, the position of the first significant non-zero lag in the PACF diagram is usually considered to be a reasonable estimate of the autoregressive order p; in the ACF diagram, the position of the first significant non-zero lag is usually considered to be a reasonable estimate of the sliding average order q.

[0165] Perform a differential operation on the original time series, that is, the collected air inlet temperature data, until the time series is stable. Record the number of differentials required to convert the time series data into a stable series, which is the value of the differential order d.

[0166] Draw the ACF and PACF diagrams for the time series after differentiation to determine the autoregressive order p and the sliding average order q.

[0167] Use AIC or BIC to select the optimal model parameters.

[0168] The ARIMA model is established based on the determined autoregressive order p, moving average order q and difference order d.

[0169] Then, the ARIMA model is used to predict the temperature, and the predicted air inlet temperature data is T f .

[0170] Furthermore, in some embodiments of the present invention, step 102 further includes the following steps:

[0171] S102-1: Obtain an air inlet temperature change rate according to the predicted air inlet temperature and the current air inlet temperature of the target device.

[0172] Specifically, the temperature predicted by the ARIMA model is denoted as T f , the current air inlet temperature is recorded as T t , then the temperature change rate r is:

[0173]

[0174] Among them, T f To predict the air inlet temperature, record T t is the current air inlet temperature, and r is the temperature change rate.

[0175] Furthermore, in some embodiments of the present invention, step 103 further includes the following steps:

[0176] S1031, if the absolute value of the air inlet temperature change rate is greater than the absolute value of a preset temperature change rate standard value, calculating a first target hysteresis temperature according to the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value;

[0177] The calculation formula of the first target hysteresis temperature is:

[0178] h new =h*(1+|r|-|r d |)

[0179] Among them, h newrepresents the adjusted hysteresis temperature, h represents the current hysteresis temperature, r represents the temperature change rate, r d Indicates the standard value of temperature change rate.

[0180] Specifically, if the temperature change rate |r|>|r d |, at this time, the first target hysteresis temperature is calculated based on the absolute value of the temperature change rate and the absolute value of the preset temperature change rate standard value:

[0181] h new =h*(1+|r|-|r d |)

[0182] Among them, h new represents the adjusted hysteresis temperature, h represents the current hysteresis temperature, r represents the temperature change rate, r d Indicates the standard value of temperature change rate, which can be set based on measured data and experience.

[0183] The hysteresis temperature of the target device is adjusted to the first target hysteresis temperature, that is, the hysteresis temperature of the target device is increased, unnecessary policy adjustments are reduced, the speed regulation oscillation period is shortened, and heat dissipation efficiency is improved.

[0184] S1032, if the absolute value of the air inlet temperature change rate is less than the product of the absolute value of the temperature change rate standard value and the preset change rate percentage, calculating a second target hysteresis temperature based on the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value;

[0185] The calculation formula of the second target hysteresis temperature is:

[0186] h new =h*(1-|r|+|r d |).

[0187] Specifically, if the temperature change rate |r| < |r d |*p r At this time, the second target hysteresis temperature is calculated based on the absolute value of the temperature change rate and the absolute value of the preset temperature change rate standard value:

[0188] h new =h*(1-|r|+|r d |)

[0189] Then, the hysteresis temperature of the target device is adjusted to the second target hysteresis temperature, that is, the hysteresis temperature is lowered, which can quickly respond to temperature changes. r Indicates the percentage of change rate. This value can be determined based on engineering experience or through a large amount of statistical analysis. Different models and different computer room environments have differences. In the embodiment of the present invention, p r50% is preferable.

[0190] It should be noted that if the temperature change rate |r d |*p r ≤|r|≤|r d |, then the hysteresis temperature is not adjusted at this time, and the hysteresis temperature is maintained unchanged.

[0191] Further, in some embodiments of the present application, step 103 further comprises the following steps:

[0192] S103-1, if the predicted inlet temperature is greater than the inlet temperature standard value, calculating a third target hysteresis temperature according to the predicted inlet temperature and the inlet temperature standard value; the inlet temperature standard value is set according to the model of the target device;

[0193] wherein the calculation formula of the third target hysteresis temperature is:

[0194]

[0195] wherein T f represents the predicted inlet temperature, T d represents the inlet temperature standard value.

[0196] Specifically, if the predicted inlet temperature T f >T d , a third target hysteresis temperature is calculated according to the predicted inlet temperature and the inlet temperature standard value:

[0197]

[0198] wherein T f represents the predicted inlet temperature, T d represents the inlet temperature standard value, which can be set according to the model of different target devices.

[0199] Further, the hysteresis temperature of the target device is adjusted to the third target hysteresis temperature, i.e. the hysteresis temperature is increased, and the heat dissipation efficiency is further improved.

[0200] S103-2, if the predicted inlet temperature is less than the product of the inlet temperature standard value and a preset inlet temperature percentage, calculating a fourth target hysteresis temperature according to the predicted inlet temperature and the inlet temperature standard value;

[0201] wherein the calculation formula of the fourth target hysteresis temperature is:

[0202]

[0203] Specifically, if the predicted inlet temperature T f <T d*p T , the fourth target hysteresis temperature is calculated based on the predicted air inlet temperature and the standard value of the air inlet temperature:

[0204]

[0205] Then, the hysteresis temperature of the target device is adjusted to the fourth target hysteresis temperature, that is, the hysteresis temperature is lowered, thereby reducing the heat dissipation energy consumption. T Indicates the percentage of air inlet temperature, which is determined in the same way as p r In the embodiment of the present invention, p T 90% is acceptable.

[0206] It should be noted that if the switch air inlet temperature T d *p T ≤T f ≤T d At this time, the hysteresis temperature is not adjusted and is maintained unchanged.

[0207] Furthermore, in some embodiments of the present invention, the following steps are also included:

[0208] S1, if the output power of the target device is greater than the target device output power standard value, calculating a fifth target hysteresis temperature value according to the output power of the target device and the target device output power standard value; the target device output power standard value is set according to the model of the target device;

[0209] The calculation formula of the fifth target hysteresis temperature is:

[0210]

[0211] Where P represents the output power of the target device, P d Indicates the target device's output power standard value.

[0212] Specifically, taking a switch as an example, if the switch output power P>P d , the fifth target hysteresis temperature is calculated based on the output power of the switch and the standard value of the switch output power:

[0213]

[0214] Where P represents the output power of the switch, P d Indicates the standard value of the switch output power, which can be set according to the switch model.

[0215] Furthermore, the hysteresis temperature of the switch is adjusted to the fifth target hysteresis temperature, that is, the hysteresis temperature is increased, thereby improving the heat dissipation efficiency.

[0216] S2, if the output power of the target device is less than the product of the target device output power standard value and a preset target device output power percentage, calculating a sixth target hysteresis temperature according to the output power of the target device and the target device output power standard value;

[0217] wherein the calculation formula of the sixth target hysteresis temperature is:

[0218]

[0219] Specifically, if the switch output power P < P d *P p , the sixth target hysteresis temperature is calculated according to the output power of the switch and the switch output power standard value:

[0220]

[0221] Further, the hysteresis temperature of the switch is adjusted to the sixth target hysteresis temperature, i.e. the hysteresis temperature is reduced, and thus the energy consumption is reduced. Wherein P p represents a percentage, and its determination manner is the same as p r In the embodiment of the present application, 80% can be taken.

[0222] It should be noted that if the switch output power P d *P p ≤ P ≤ P d , the hysteresis temperature is not adjusted, and the hysteresis temperature is maintained unchanged.

[0223] In the embodiment of the present application, the hysteresis temperature can also be adjusted according to the fan working state of the target device and the CPU occupancy rate.

[0224] Specifically, taking the switch as an example, if all the system fans of the switch are in place and the working state is normal, the hysteresis temperature is appropriately reduced to reduce the heat dissipation energy consumption.

[0225] If the number of system fans in place is less than 50% or the number of faulty fans is less than 50%, the hysteresis temperature is appropriately increased to improve the heat dissipation efficiency.

[0226] If the CPU occupancy rate of the switch exceeds 70%, the hysteresis temperature is appropriately increased to improve the heat dissipation efficiency.

[0227] If the CPU occupancy rate of the switch is less than 40%, the hysteresis temperature is appropriately reduced to reduce the heat dissipation energy consumption.

[0228] It's important to note that after raising the hysteresis temperature, the fan speed remains high as the temperature drops within the specified range. This high fan speed dissipates more heat, ensuring high heat dissipation efficiency. However, after lowering the hysteresis temperature, the fan speed decreases slightly with each temperature drop, resulting in slower fan speeds and lower energy consumption.

[0229] Furthermore, in some embodiments of the present invention, step 104 further includes the following steps:

[0230] S1041: Obtain the difference between the predicted air inlet temperature and the current air inlet temperature.

[0231] Specifically, the predicted air inlet temperature T f Subtract the current air inlet temperature T t Get the difference.

[0232] S1042: If the difference is greater than the target hysteresis temperature, obtain a fan speed duty cycle of the target device based on the predicted air inlet temperature.

[0233] Specifically, if the difference between the predicted air inlet temperature and the current air inlet temperature is greater than the target hysteresis temperature, the predicted air inlet temperature is substituted into the linear equation of the fan's PWM value and temperature T to calculate a new fan speed duty cycle, i.e., the fan speed value.

[0234] The linear equation between the fan's PWM value and temperature T can be expressed as:

[0235] PWM=k*T+b

[0236] Among them, PWM is the fan speed duty cycle, that is, the fan speed, T is the air inlet temperature, and k and b are two constants.

[0237] By recording the fan's PWM values ​​at different temperatures, we can determine the two constants k and b in the linear equation. At least two data points must be collected to determine the two constants in the linear equation.

[0238] S1043: If the difference is less than or equal to the target hysteresis temperature, maintain the fan speed duty cycle of the target device.

[0239] Specifically, if the difference between the predicted air inlet temperature and the current air inlet temperature is smaller than the hysteresis temperature, the original PWM value is maintained.

[0240] S1044: Set the fan speed duty cycle of the switch to the fan of the target device to adjust the fan speed of the target device.

[0241] Specifically, the fan speed value in the latest heat dissipation strategy, ie, the PWM value, is set to the fan of the target device through the driver software to adjust the fan speed.

[0242] Through the above operation, the target device inlet temperature is dynamically adjusted in combination with the target device load, system fan working state, CPU occupancy and other working states, and then a heat dissipation strategy is generated and issued to the target device system fan and the power body fan, so that the reciprocating oscillation and fluctuation of the target device system fan and the power body fan caused by the reduction of the inlet temperature is greatly reduced, the service life of the target device fan is prolonged, the heat dissipation efficiency is improved while the heat dissipation energy consumption is reduced.

[0243] Further, in the embodiment of the present application, as shown in Figure 3 , a principle block diagram of a heat dissipation control method is provided, taking a switch as an example, and the specific principle is as follows:

[0244] The present application mainly consists of five modules, i.e. a temperature monitoring module, a data processing module, a dynamic adjustment module, a strategy generation module and a strategy execution module.

[0245] The temperature monitoring module is mainly responsible for monitoring and collecting the inlet temperature, the outlet temperature and the external environment temperature of the switch, at least one external temperature collection device of the switch can be designed according to the position of the switch, or the internal temperature sensor of the switch can be used as the temperature data collection point according to the internal air duct direction of the switch, that is, the temperature monitoring module can be realized by the external independent temperature collection device of the switch, or can be provided by the function of the switch itself.

[0246] The data processing module analyzes and calculates the inlet temperature change rate in real time according to the collected temperature data, and predicts the temperature change trend.

[0247] The dynamic adjustment module dynamically adjusts the hysteresis temperature according to the inlet temperature change rate and the change trend in combination with the actual running working state of the switch.

[0248] The strategy generation module calculates the target rotating speed of the switch system fan and the power body fan according to the real-time value of the inlet temperature and the hysteresis temperature in combination with the speed regulation calculation method.

[0249] The strategy execution module issues the latest heat dissipation strategy to the switch system fan and the power body fan, and finally completes the fan rotating speed adjustment.

[0250] Further, in the embodiment of the present application, as shown in Figure 4 , a step flow chart for processing the inlet temperature data is also provided, and the specific steps are as follows:

[0251] 1. Temperature data collection.

[0252] 2. Autoregressive integrated moving average model modeling, determining model parameters according to inlet temperature data, and establishing an ARIMA model according to model parameters.

[0253] 3. Temperature change rate calculation, the temperature change rate of the air inlet is obtained according to the percentage of the difference between the predicted air inlet temperature and the current air inlet temperature and the current air inlet temperature.

[0254] Further, in the embodiment of the present application, as shown in Figure 5 , a step flow chart for collecting air inlet temperature data is also provided, and the specific steps are as follows:

[0255] 1. Set the sampling frequency, determine the data collection frequency according to the actual needs, and in the embodiment of the present application, it can be set to collect once every 10 seconds.

[0256] 2. Select the sensor, select two temperature sensors in the air inlet duct inside the target device, and design at least one temperature collection device at the air inlet position outside the target device.

[0257] 3. Data storage, store the collected data into a database or a file for subsequent processing and analysis.

[0258] 4. Data cleaning, remove noise and outliers in the stored data to ensure data quality, and the data processing method can be selected according to the actual needs.

[0259] In the embodiment of the present application, by collecting the internal temperature data and the environmental temperature data of the target device, the temperature change rate of the air inlet of the target device and / or the predicted air inlet temperature are determined according to the internal temperature data and the environmental temperature data; the target hysteresis temperature of the target device is calculated according to the temperature change rate of the air inlet and / or the predicted air inlet temperature, and the hysteresis temperature of the target device is adjusted to the target hysteresis temperature; the target hysteresis temperature is determined according to the heat dissipation mode, and when the air inlet temperature of the target device changes, the fan speed of the target device is adjusted according to the heat dissipation mode. Greatly reduces the reciprocating oscillation and fluctuation of the system fan and the power supply body fan speed of the target device caused by the change of the air inlet temperature, prolongs the service life of the fan of the target device, reduces the heat dissipation energy consumption while improving the heat dissipation efficiency.

[0260] It should be noted that for the method embodiment, in order to simply describe, it is expressed as a series of action combinations, but those skilled in the art should know that the embodiment of the present application is not limited by the described action sequence, because according to the embodiment of the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the involved actions are not necessarily required by the embodiment of the present application.

[0261] Referring to Figure 8 , a structural block diagram of a heat dissipation control device provided by an embodiment of the present application is shown, which can specifically include the following modules:

[0262] The data acquisition module 201 is used to collect the internal temperature data and the ambient temperature data of the target device;

[0263] A data processing module 202 is configured to determine a temperature change rate of an air inlet of the target device and / or predict an air inlet temperature based on the internal temperature data and the ambient temperature data;

[0264] a hysteresis temperature adjustment module 203 for calculating a target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature, and adjusting the hysteresis temperature of the target device to the target hysteresis temperature;

[0265] The heat dissipation mode generating module 204 is configured to determine a heat dissipation mode according to the target hysteresis temperature, and adjust the fan speed of the target device according to the heat dissipation mode when the air inlet temperature of the target device changes.

[0266] Optionally, the data processing module 202 includes:

[0267] An air inlet temperature data acquisition module, configured to obtain the air inlet temperature data of the target device based on the average value of the internal temperature and the ambient temperature;

[0268] A predicted air inlet temperature acquisition module is used to predict the air inlet temperature of the target device based on the air inlet temperature data using an autoregressive integral moving average model to obtain a predicted air inlet temperature;

[0269] Optionally, the data processing module 202 further includes:

[0270] The temperature change rate acquisition module is used to obtain the air inlet temperature change rate according to the predicted air inlet temperature and the current air inlet temperature of the target device.

[0271] Optionally, the hysteresis temperature adjustment module 203 includes:

[0272] a first target hysteresis temperature calculation module, configured to calculate a first target hysteresis temperature based on the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value if the absolute value of the air inlet temperature change rate is greater than the absolute value of the preset temperature change rate standard value;

[0273] The calculation formula of the first target hysteresis temperature is:

[0274] h new =h*(1+|r|-|r d |)

[0275] Among them, h newrepresents the adjusted hysteresis temperature, h represents the current hysteresis temperature, r represents the temperature change rate, r d represents the temperature change rate standard value;

[0276] The second target hysteresis temperature calculation module is configured to calculate a second target hysteresis temperature according to the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value if the absolute value of the air inlet temperature change rate is less than the product of the absolute value of the temperature change rate standard value and a preset change rate percentage.

[0277] The calculation formula of the second target hysteresis temperature is:

[0278] h new = h * (1 - |r| + |r d ).

[0279] Optionally, the hysteresis temperature adjustment module 203 further comprises:

[0280] The third target hysteresis temperature calculation module is configured to calculate a third target hysteresis temperature according to the predicted air inlet temperature and the air inlet temperature standard value if the predicted air inlet temperature is greater than an air inlet temperature standard value; the air inlet temperature standard value is set according to the model of the target device.

[0281] The calculation formula of the third target hysteresis temperature is:

[0282]

[0283] wherein T f represents the predicted air inlet temperature, T d represents the air inlet temperature standard value.

[0284] The fourth target hysteresis temperature calculation module is configured to calculate a fourth target hysteresis temperature according to the predicted air inlet temperature and the air inlet temperature standard value if the predicted air inlet temperature is less than the product of the air inlet temperature standard value and a preset air inlet temperature percentage.

[0285] The calculation formula of the fourth target hysteresis temperature is:

[0286]

[0287] Optionally, the device further comprises:

[0288] The fifth target hysteresis temperature calculation module is configured to calculate a fifth target hysteresis temperature according to the output power of the target device and a target device output power standard value if the output power of the target device is greater than the target device output power standard value; the target device output power standard value is set according to the model of the target device.

[0289] The calculation formula of the fifth target hysteresis temperature is:

[0290]

[0291] Where P represents the output power of the target device, P d Indicates the target device output power standard value;

[0292] a sixth target hysteresis temperature calculation module, configured to calculate a sixth target hysteresis temperature based on the output power of the target device and the target device output power standard value if the output power of the target device is less than the product of the target device output power standard value and a preset target device output power percentage;

[0293] The calculation formula of the sixth target hysteresis temperature is:

[0294]

[0295] Optionally, the heat dissipation mode generating module 204 includes:

[0296] A difference acquisition module is used to obtain the difference between the predicted air inlet temperature and the current air inlet temperature;

[0297] a first difference judgment module, configured to obtain a fan speed duty cycle of the target device based on the predicted air inlet temperature if the difference is greater than the target hysteresis temperature;

[0298] a second difference judgment module, configured to maintain the fan speed duty cycle of the target device if the difference is less than or equal to the target hysteresis temperature;

[0299] The speed adjustment module is used to set the fan speed duty cycle to the fan of the target device to adjust the fan speed of the target device.

[0300] In an embodiment of the present invention, internal temperature data and ambient temperature data of a target device are collected; the target device's air inlet temperature change rate and / or predicted air inlet temperature are determined based on the internal temperature data and ambient temperature data; the target device's target hysteresis temperature is calculated based on the air inlet temperature change rate and / or predicted air inlet temperature, and the target device's hysteresis temperature is adjusted to the target hysteresis temperature; a heat dissipation mode is determined based on the target hysteresis temperature, and when the target device's air inlet temperature changes, the target device's fan speed is adjusted based on the heat dissipation mode. This significantly reduces the reciprocating oscillation and fluctuation in the speed of the target device's system fan and power supply fan caused by changes in the air inlet temperature, extends the service life of the target device's fan, and improves heat dissipation efficiency while reducing heat dissipation energy consumption.

[0301] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the above heat dissipation control method is implemented.

[0302] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above heat dissipation control method is implemented.

[0303] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0304] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0305] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0306] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0307] These computer program instructions can also be loaded into a computer or other programmable data processing terminal device, so that a series of operational steps are performed on the computer or other programmable terminal device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide a process for implementing the functions specified in the flowchart Figure 1 one or more flows and / or blocks Figure 1 one or more blocks or steps of the functions specified in the flowchart

[0308] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to cover all changes and modifications falling within the scope of the embodiments of the present application.

[0309] Finally, it should be noted that the relational terms herein, such as first and second, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, so that a process, method, article, or terminal device including a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or terminal device. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or terminal device including the above element.

[0310] The above provides a heat dissipation control method, device, equipment and medium, and the principle and implementation manner of the present application are described by specific examples. Although the embodiments of the present application are described above, the above description and definition are only for facilitating the understanding of the embodiments of the present application, and are not used to limit the present application. Any modification and change made without departing from the spirit and scope of the present application is within the protection scope of the present application. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A heat dissipation control method, characterized in that: The method comprises: Collect internal temperature data and ambient temperature data of the target device; determining a temperature change rate of an air inlet of the target device and / or predicting an air inlet temperature according to the internal temperature data and the ambient temperature data; calculating a target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature, and adjusting the hysteresis temperature of the target device to the target hysteresis temperature; determining a heat dissipation mode according to the target hysteresis temperature, and adjusting a fan speed of the target device according to the heat dissipation mode when an air inlet temperature of the target device changes; Calculating the target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature includes: If the absolute value of the air inlet temperature change rate is greater than the absolute value of the preset temperature change rate standard value, a first target hysteresis temperature is calculated based on the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value; wherein the calculation formula of the first target hysteresis temperature is: in, represents the adjusted hysteresis temperature, Indicates the current hysteresis temperature. represents the rate of temperature change, Indicates the standard value of temperature change rate; If the absolute value of the air inlet temperature change rate is less than the product of the absolute value of the temperature change rate standard value and the preset change rate percentage, calculating the second target hysteresis temperature according to the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value; The calculation formula of the second target hysteresis temperature is: 。 2. The method according to claim 1, characterized in that The determining the air inlet temperature change rate and / or predicting the air inlet temperature of the target device according to the internal temperature data and the ambient temperature data includes: Obtaining air inlet temperature data of the target device according to an average value of the internal temperature and the ambient temperature; The air inlet temperature of the target device is predicted based on the air inlet temperature data using an autoregressive integral moving average model to obtain a predicted air inlet temperature.

3. The method according to claim 2, characterized in that The determining of the air inlet temperature change rate and / or the predicted air inlet temperature of the target device according to the internal temperature data and the ambient temperature data further includes: The air inlet temperature change rate is obtained according to the predicted air inlet temperature and the current air inlet temperature of the target device.

4. The method according to claim 1, wherein The calculating the target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature further includes: If the predicted air inlet temperature is greater than the standard air inlet temperature value, calculating a third target hysteresis temperature based on the predicted air inlet temperature and the standard air inlet temperature value; the standard air inlet temperature value is set according to the model of the target device; The calculation formula of the third target hysteresis temperature is: in, Indicates the predicted air inlet temperature, Indicates the standard value of air inlet temperature; If the predicted air inlet temperature is less than the product of the air inlet temperature standard value and the preset air inlet temperature percentage, calculating a fourth target hysteresis temperature based on the predicted air inlet temperature and the air inlet temperature standard value; The calculation formula of the fourth target hysteresis temperature is: 。 5. The method according to claim 1, wherein The method further comprises: If the output power of the target device is greater than the target device output power standard value, calculating a fifth target hysteresis temperature value according to the output power of the target device and the target device output power standard value; the target device output power standard value is set according to the model of the target device; The calculation formula of the fifth target hysteresis temperature is: Where P represents the output power of the target device, Indicates the target device output power standard value; If the output power of the target device is less than the product of the target device output power standard value and the preset target device output power percentage, calculating a sixth target hysteresis temperature according to the output power of the target device and the target device output power standard value; The calculation formula of the sixth target hysteresis temperature is: 。 6. The method according to claim 1 or 2, wherein determining a heat dissipation mode according to the target hysteresis temperature and adjusting a fan speed of the target device according to the heat dissipation mode when an air inlet temperature of the target device changes comprises: Obtaining a difference between the predicted air inlet temperature and the current air inlet temperature; If the difference is greater than the target hysteresis temperature, obtaining a fan speed duty cycle of the target device based on the predicted air inlet temperature; If the difference is less than or equal to the target hysteresis temperature, maintaining the fan speed duty cycle of the target device; The fan speed duty cycle of the switch is set to the fan of the target device to adjust the fan speed of the target device.

7. A heat dissipation control device, characterized in that: The device comprises: A data acquisition module is used to collect internal temperature data and ambient temperature data of the target device; a data processing module, configured to determine a temperature change rate of an air inlet of the target device and / or predict an air inlet temperature based on the internal temperature data and the ambient temperature data; a hysteresis temperature adjustment module, configured to calculate a target hysteresis temperature of the target device according to the air inlet temperature change rate and / or the predicted air inlet temperature, and adjust the hysteresis temperature of the target device to the target hysteresis temperature; a heat dissipation mode generating module, configured to determine a heat dissipation mode according to the target hysteresis temperature, and adjust a fan speed of the target device according to the heat dissipation mode when the air inlet temperature of the target device changes; The hysteresis temperature adjustment module includes: A first target hysteresis temperature adjustment module is configured to calculate a first target hysteresis temperature based on the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value if the absolute value of the air inlet temperature change rate is greater than the absolute value of the preset temperature change rate standard value; wherein the calculation formula for the first target hysteresis temperature is: in, represents the adjusted hysteresis temperature, Indicates the current hysteresis temperature. represents the rate of temperature change, Indicates the standard value of temperature change rate; a second target hysteresis temperature adjustment module, configured to calculate a second target hysteresis temperature based on the absolute value of the air inlet temperature change rate and the absolute value of the preset temperature change rate standard value if the absolute value of the air inlet temperature change rate is less than the product of the absolute value of the temperature change rate standard value and the preset change rate percentage; The calculation formula of the second target hysteresis temperature is: 。 8. An electronic device, characterized in that: The heat dissipation control method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the heat dissipation control method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the heat dissipation control method according to any one of claims 1 to 6 is implemented.

Images