CN120491791A - Server cooling control method and related equipment - Google Patents
Server cooling control method and related equipmentInfo
- Publication number
- CN120491791A CN120491791A CN202510978235.6A CN202510978235A CN120491791A CN 120491791 A CN120491791 A CN 120491791A CN 202510978235 A CN202510978235 A CN 202510978235A CN 120491791 A CN120491791 A CN 120491791A
- Authority
- CN
- China
- Prior art keywords
- flow rate
- temperature
- temperature difference
- heat
- current moment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Feedback Control In General (AREA)
Abstract
The application discloses a server cooling control method and related equipment, which relate to the technical field of computers, and can predict heat to be eliminated according to measured temperature and measured flow rate obtained by target equipment, and the cooling control is realized by combining the heat difference between the heat to be eliminated and the average heat to be eliminated and the temperature difference between the target temperature and the measured temperature at the current moment. The accuracy of cooling control can be ensured by the temperature difference between the target temperature and the measured temperature at the current moment, the heat difference between the heat to be eliminated and the average heat to be eliminated can realize the advance of cooling control, and the cooling effect is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a server cooling control method and related devices.
Background
In order to ensure the normal operation of the server, the server needs to be cooled by a cooling medium. Wherein the cooling medium may be a liquid or a gas, for example, water, or air.
In the related art, a temperature sensor may be provided on a component on which temperature overheating may occur on a server to detect the current temperature of the component. The flow rate of the cooling medium is dynamically adjusted according to the current temperature of the component. For example, the flow rate is increased when the current temperature is greater than a temperature threshold, and the flow rate is decreased when the current temperature is less than the temperature threshold. But this solution still has the problem of poor cooling.
Disclosure of Invention
The application provides a server cooling control method and related equipment, which at least solve the problem of poor cooling effect in the related technology.
The application provides a server cooling control method, which comprises the following steps:
Acquiring a measurement result sequence of a target component on a server at the current moment, wherein the measurement result sequence comprises one or more pieces of measurement result information, and the measurement result information comprises measurement moment, measurement temperature and measurement flow rate of a cooling medium, and the measurement moment is the current moment or the historical moment;
Predicting the heat to be eliminated required by the target component to reach the target temperature according to the measurement result sequence at the current moment, and determining the average heat to be eliminated according to the predicted heat to be eliminated at a plurality of moments;
calculating a temperature difference between the target temperature and the measured temperature at the current moment and a heat difference between the heat to be eliminated predicted at the current moment and the average heat to be eliminated;
And performing cooling control on the target component according to the temperature difference and the heat quantity difference.
The application also provides a server cooling control device, which comprises:
the measuring result acquisition module is used for acquiring a measuring result sequence of the target component on the server at the current moment, wherein the measuring result sequence comprises one or more pieces of measuring result information, and the measuring result information comprises measuring moment, measuring temperature and measuring flow rate of the cooling medium, and the measuring moment is the current moment or the historical moment.
And the prediction module is used for predicting the heat to be eliminated required by the target component to reach the target temperature according to the measurement result sequence at the current moment and determining the average heat to be eliminated according to the heat to be eliminated predicted at a plurality of moments.
The calculation module is used for calculating the temperature difference between the target temperature and the measured temperature at the current moment and the heat difference between the predicted heat to be eliminated at the current moment and the average heat to be eliminated.
And the cooling control module is used for carrying out cooling control on the target component according to the temperature difference and the heat quantity difference.
The application also provides an electronic device, comprising:
A memory for storing a computer program;
and a processor for implementing the steps of the server cooling control method as described above when executing the computer program.
The present application also provides a computer-readable storage medium having a computer program stored therein, wherein the computer program when executed by a processor implements the steps of the foregoing server cooling control method.
The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the server cooling control method as described above.
By the method, the heat to be eliminated can be predicted to realize cooling control by combining the heat difference between the heat to be eliminated and the average heat to be eliminated and the temperature difference between the target temperature and the measured temperature at the current moment. The accuracy of cooling control can be ensured by the temperature difference between the target temperature and the measured temperature at the current moment, the heat difference between the heat to be eliminated and the average heat to be eliminated can realize the advance of cooling control, and the cooling effect is improved.
Drawings
For a clearer description of embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described, it being apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating steps of a method for controlling cooling of a server according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating steps of another method for controlling cooling of a server according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of a server cooling control device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of another cooling control device for a server according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device provided by the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art without making any inventive effort are within the scope of the present application.
It should be noted that in the description of the present application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "first," "second," and the like in this specification are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
During operation, overheating of parts of the server may occur, such as a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), and a power module. Overheating of these components can cause server operation anomalies, resulting in service outages. In order to ensure that the server operates normally, the server needs to be cooled by a server cooling technology, and the server cooling technology realizes cooling by conveying a cooling medium in the server, wherein the cooling medium can be liquid or gas, the liquid can be water or specified cooling liquid, and the gas is usually air.
Fig. 1 is a schematic diagram of an application scenario according to an embodiment of the present application. Referring to fig. 1, a cooling device is provided on a server, which can output a cooling medium to designated parts including a central processing unit, a graphic processor, and a power module.
In the related art, the flow rate of the cooling medium may be fixed or dynamically adjusted. For dynamic adjustment of the flow rate, the flow rate is continuously adjusted according to the actual measured current temperature. For example, the flow rate of the cooling medium may be increased while the current temperature is still greater than the preset threshold, or while the current temperature is still greater than the temperature at the previous time.
Of course, compared with a fixed flow rate, the dynamic flow rate adjustment has better energy saving effect and cooling effect. However, the above-mentioned dynamic flow rate adjustment can only be used for cooling control at the next moment according to the current temperature, and the cooling will be delayed, so that the cooling effect is still poor.
In order to solve the technical problems, the application predicts the heat to be eliminated according to the measured temperature and the measured flow rate, and realizes cooling control by combining the temperature difference between the heat to be eliminated and the average heat to be eliminated and the temperature difference between the target temperature and the measured temperature at the current moment. The accuracy of cooling control can be ensured by the temperature difference between the target temperature and the measured temperature at the current moment, the heat difference between the heat to be eliminated and the average heat to be eliminated can realize the advance of cooling control, and the cooling effect is improved.
The present application will be further described in detail below with reference to the drawings and detailed description for the purpose of enabling those skilled in the art to better understand the aspects of the present application.
Fig. 2 is a flowchart of steps of a server cooling control method according to an embodiment of the present application. Referring to fig. 2, the server cooling control method includes:
S201, acquiring a measurement result sequence of a target component on a server at the current moment, wherein the measurement result sequence comprises one or more pieces of measurement result information, and the measurement result information comprises measurement moment, measurement temperature and measurement flow rate of a cooling medium, and the measurement moment is the current moment or the historical moment.
Among other things, the target components here may be critical components on the server that overheat causing server operation anomalies, such as CPUs, GPUs, and power supplies.
For a target component, the measurement result sequence includes measurement result information of one or more measurement moments, and each measurement moment corresponds to one measurement result information. The measurement result information at the plurality of measurement times is arranged in the order of the measurement times, for example, in the ascending order of the measurement times, and the measurement result information at the preceding measurement time is arranged at the preceding position.
The embodiment of the application can acquire the measurement result sequence according to a certain time period, and the measurement result sequence acquired at each moment comprises N+1 measurement result information corresponding to the current moment and N historical moments before the current moment. For example, for an ascending time sequence: t_n+1, t_ N, t _n-1, & gt, t_2, t_1, t_0, at time t_0, the obtained measurement sequence may be R (t_n), R (t_n-1), & gt, R (t_1), R (t_0), at time t_1, the obtained measurement sequence may be R (t_n+1), R (t_n), & gt, R (t_2), R (t_1). Wherein, R (t_0) is measurement result information of the current time t_0, R (t_n), R (t_n-1),. And R (t_1) are measurement result information corresponding to N history times before the current time t_0, R (t_1) is measurement result information of the current time t_1, R (t_n+1), R (t_n),. And R (t_2) are measurement result information corresponding to N history times before the current time t_1.
The measurement result information can be obtained by measuring by a sensor, wherein the sensor comprises a temperature sensor and a flow rate sensor. The temperature sensor may be an NTC (Negative Temperature Coefficient ) thermistor whose resistance value decreases with increasing temperature, and the flow rate sensor may be a turbine flowmeter. The measured temperature is a temperature measured by a temperature sensor provided to the target member at the measurement time, and the measured flow rate is a flow rate of the cooling medium measured by a flow rate sensor at the measurement time.
In conventional approaches, the number and location of sensor distributions on the target part are fixed. However, this solution causes problems of too many or too few sensors, inaccurate measurement when the sensors are too few, and wasted sensors when the sensors are too many. In order to solve the problem, the application can dynamically adjust the sensor distribution to ensure the measurement accuracy as much as possible on the basis of saving the number of sensors. The method comprises the steps of obtaining the temperature change rate and the flow rate change rate of a target component, determining the sensor density on the target component according to the temperature change rate and the flow rate change rate of the target component, and finally adjusting the sensor distribution on the target component according to the sensor density.
In practical applications, a default number of sensors need to be set first to measure the temperature and the flow rate of the target component, so as to determine the temperature change rate and the flow rate change rate.
The temperature change rate is a temperature change amount per unit time, and can be calculated specifically from measured temperatures at a plurality of measurement times. For example, a ratio of a measured temperature difference at two measurement times, which may be adjacent measurement times or non-adjacent measurement times, to a time difference at two measurement times may be used as the temperature change rate. Of course, for more accuracy, the average value of the obtained temperature change rates at a plurality of measurement times may be used as the temperature change rate.
The flow rate change rate is a measured flow rate change amount per unit time length, and can be calculated specifically from the measured flow rates at a plurality of measurement times. For example, a ratio of a measured flow velocity difference at two measurement times to a time difference at two measurement times, which may be adjacent measurement times or non-adjacent measurement times, may be used as the flow velocity change rate. Of course, for more accuracy, the flow rate change rate may be obtained by an average value of the flow rate change rates obtained at a plurality of measurement timings.
When the above temperature change rate and flow rate change rate are obtained, the sensor density on the target member may be determined, and the sensor density may be the number of sensors per unit area. The sensor density may be positively correlated to the temperature change rate and the flow rate change rate, that is, the sensor density increases with an increase in the flow rate change rate when the temperature change rate is fixed, the sensor density decreases with a decrease in the flow rate change rate, and the sensor density increases with an increase in the temperature change rate when the flow rate change rate is fixed, and the sensor density decreases with a decrease in the temperature change rate.
In some possible embodiments, determining the sensor density on the target component based on the temperature change rate and the flow rate change rate of the target component includes first converting the temperature change rate of the target component to a temperature sensor density based on the temperature sensitivity coefficient, then converting the flow rate change rate of the target component to a flow rate sensor density based on the flow rate sensitivity coefficient, and finally determining the sensor density based on the temperature sensor density and the flow rate sensor density, the sensor density being positively correlated to the temperature sensor density and the flow rate sensor density. The application can respectively determine the density of the temperature sensor and the flow velocity sensor, and further can accurately estimate the total sensor density.
The temperature sensor density is positively related to the temperature change rate and the temperature sensitivity coefficient, the temperature sensor density is the number of temperature sensors in a unit area, and the flow rate sensor density is the number of flow rate sensors in a unit area.
In one example, the temperature sensor density may be a product of a temperature change rate and a temperature sensitivity coefficient, and the flow sensor density is a product of a flow rate change rate and a flow rate sensitivity coefficient. The temperature sensitivity coefficient is related to the material of the temperature sensor, and the flow rate sensitivity coefficient is related to the material of the flow rate sensor.
After the above-described temperature sensor density and flow rate sensor density are obtained, the sensor density can be determined. In a conventional algorithm, the temperature sensor density and the flow rate sensor density may be added as the sensor density.
In another embodiment, the above sensor density can be calculated by the following formula:
(1)
where D is the sensor density, k is the conversion coefficient, a is the temperature sensitivity coefficient, TR is the temperature change rate, b is the flow rate sensitivity coefficient, and FR is the flow rate change rate. a×tr is the temperature sensor density, and b×fr is the flow rate sensor density.
From the above formula (1), the sum of the temperature sensor density and the flow rate sensor density can be dynamically adjusted to serve as the sensor density.
When the sensor density is obtained, the number of sensors can be calculated according to the area of the target component and the sensor density, so that the sensors can be uniformly arranged on the target equipment according to the number of sensors. The sensor is connected to the main control platform through an I2C (Inter-INTEGRATED CIRCUIT, serial communication bus protocol) SPI (SERIAL PERIPHERAL INTERFACE, synchronous serial communication interface) interface to send the collected measurement result sequence to the main control platform to cause the main control platform to perform the method of the present application. A database may also be provided for temporarily storing the collected measurement sequences, so that the main control platform reads the measurement sequences from the database and performs the method of the present application.
After the measurement sequence is obtained, the measurement sequence may be preprocessed to improve the quality of the measurement sequence. Preprocessing may include, but is not limited to, outlier removal, data population.
Wherein the abnormal value removes measurement result information for removing the abnormality. Specifically, an average measured temperature, a measured temperature standard deviation, an average measured flow rate, and a measured flow rate standard deviation of a measured result sequence may be calculated, then for each measured result information, a measured temperature deviation between the measured temperature and the average measured temperature in the measured result information is calculated to take a ratio of the measured temperature deviation and the measured temperature standard deviation as an abnormality degree of the measured temperature, and a measured flow rate deviation between the measured flow rate and the average measured flow rate in the measured result information is calculated to take a ratio of the measured flow rate deviation and the measured flow rate standard deviation as an abnormality degree of the measured flow rate, and finally, the measured result information is deleted when the abnormality degree of the measured temperature and/or the abnormality degree of the measured flow rate is greater than or equal to a preset abnormality degree, and the measured result information is retained when both the abnormality degree of the measured temperature and the abnormality degree of the measured flow rate are less than the preset abnormality degree.
The data filling is used to fill in missing measured temperatures and/or measured flow rates in the sequence of measurements. The method can be realized by a linear interpolation algorithm, for example, an average value of two adjacent measurement temperatures of the missing measurement temperature is taken as the missing measurement temperature, and an average value of two adjacent measurement flow rates of the missing measurement flow rate is taken as the missing measurement flow rate.
S202, predicting the heat to be eliminated required by the target component to reach the target temperature according to the measurement result sequence at the current moment, and determining the average heat to be eliminated according to the heat to be eliminated predicted at a plurality of moments.
Wherein the target temperature is a temperature set for the target component, and the target component is in an optimal operation state when the temperature is less than or equal to the target temperature. The target temperatures for different target components may be different.
If the temperature of the target component is higher than the target temperature, it is necessary to remove excess heat from the target component by the cooling medium to bring the target component to the target temperature. The excessive heat to be eliminated by the cooling medium is the heat to be eliminated.
In practical application, a measurement result sequence is obtained at one moment, and can predict heat to be eliminated, and the measurement result sequence at one moment can be input into a pre-trained neural network model to predict the heat to be eliminated corresponding to the moment. Therefore, a plurality of measuring result sequences can be obtained at a plurality of moments, and a plurality of heat to be eliminated are obtained through prediction of the plurality of measuring result sequences. That is, one heat to be removed can be obtained at each time, so that the average value of the heat to be removed at a plurality of times can be taken as the average heat to be removed.
In some possible implementations, predicting the amount of heat to be removed required by the target component to reach the target temperature according to the measurement result sequence at the current time includes calculating statistical information according to the measurement result sequence at the current time to predict the amount of heat to be removed required by the target component to reach the target temperature according to the measurement result sequence at the current time and the statistical information. Therefore, on the basis of the change condition of the measurement result in a time period, the prediction of the heat to be eliminated is realized by combining the statistical information, and the prediction accuracy of the heat to be eliminated is improved.
Wherein the statistical information includes at least one of an average measured temperature, a maximum temperature difference, and a measured flow rate standard deviation.
The average measured temperature is an average value of measured temperatures at a plurality of measurement times in a measurement result sequence at the current time. Reference may be made in particular to the following formula:
(2)
Wherein AMT is the average measured temperature, n+1 is the length of the measurement result sequence at the current time, and MT (i) is the i-th measured temperature.
The maximum temperature difference is a difference between a maximum measured temperature and a minimum measured temperature in the measurement result sequence at the current time. Reference may be made in particular to the following formula:
(3)
Where MTM is the maximum temperature difference, max (MT (i)) is the maximum measured temperature, and min (MT (i)) is the minimum measured temperature.
The standard deviation of the measured flow rate is the standard deviation of a plurality of measured flows in a measurement result sequence at the current moment, and can be calculated by the following formula:
(4)
Wherein SDFV is the standard deviation of the measured flow rate, n+1 is the length of the measurement sequence at the current time, MF (i) is the i-th measured flow rate, AMF is the average value of the plurality of measured flow rates in the measurement sequence at the current time, that is, the average measured flow rate, which can be calculated by the following formula:
(5)
In one possible implementation, the sequence of measurements and statistical information at the current time may be input into a neural network model to obtain the heat to be removed required for the target component to reach the target temperature. Different target components may employ different neural network models in which target temperatures of the target components are recorded. Of course, different target components can share a set of neural network model, and when predicting a certain target component, the target temperature of the target component, the measurement result sequence at the current moment and the statistical information are required to be input into the neural network model together for prediction, so as to obtain the heat to be eliminated required by the target component to reach the target temperature. Therefore, the number of the neural network models can be reduced as much as possible, and the storage space is saved.
In one embodiment, predicting the heat to be removed required by the target component to reach the target temperature according to the measurement result sequence and the statistical information of the current moment includes stitching the measurement result sequence and the statistical information into a feature vector of the target component, and inputting the feature vector into a Long Short-Term Memory network model (LSTM) to obtain the heat to be removed required by the target component to reach the target temperature. Therefore, the change condition of the measurement result information in the measurement result sequence can be accurately extracted through the long-term and short-term memory network model, and the method is favorable for accurately predicting the heat to be eliminated.
In some implementations, when multiple target components share the long-short-term memory network model described above, or when there is a change in the target temperature of the target component, it is also desirable to stitch the target temperature into the feature vector. The positions of the target temperature, the measurement result sequence and the statistical information in the feature vector can be flexibly set, and the position sequence is not limited by the embodiment of the application. For example, the feature vector includes a sequence of measurement results, statistical information, and a target temperature. Therefore, no matter the target temperatures of a plurality of target components are different or the target temperature of the same target component is changed, the long-term and short-term memory network does not need to be adjusted, and the training times and the cost are reduced.
The predictive process of heat to be removed can be expressed by the following formula:
(6)
wherein y (t) is the predicted heat to be eliminated at the time t, wy is the weight matrix of the output layer of the long-short-period memory network model, h (t) is the hidden state of the hidden layer for the output of the measurement result sequence at the time t, by is the bias term of the output layer of the long-short-period memory network model, f () is the activation function of the long-short-period memory network model, wh is the weight matrix of the hidden layer, h (t-1) is the hidden state of the hidden layer for the output of the measurement result sequence at the time t-1, X (t) is the feature vector of the measurement result sequence at the time t, and Bh is the bias term of the hidden layer.
And S203, calculating a temperature difference between the target temperature and the measured temperature at the current moment and a heat difference between the predicted heat to be eliminated at the current moment and the average heat to be eliminated.
The temperature difference may be a difference obtained by subtracting the measured temperature from the target temperature, and the heat difference is a difference obtained by subtracting the average heat to be eliminated from the heat to be eliminated.
And S204, cooling control is carried out on the target component according to the temperature difference and the heat quantity difference.
In one possible implementation, the target flow rate of the cooling medium may be increased when the temperature difference is greater than a preset temperature difference, and the target flow rate of the cooling medium may be decreased when the temperature difference is less than the preset temperature difference.
Accordingly, the target flow rate of the cooling medium may be increased when the heat difference is greater than the preset heat difference, and the target flow rate of the cooling medium may be decreased when the heat difference is less than the preset heat difference.
In some possible implementations, cooling control of the target component according to the temperature difference and the heat difference includes determining a target flow rate of the cooling medium according to the temperature difference and the heat difference to control cooling of the target component based on the target flow rate. In this way, the cooling control can be accurately realized according to the target flow rate. The main control platform in the embodiment of the application is also connected to the cooling device to control the flow rate of the cooling device to be a target flow rate.
In some possible implementations, the target flow rate is positively correlated with the temperature difference, the heat difference, that is, the greater the temperature difference, the greater the target flow rate, the smaller the heat difference, the smaller the target flow rate, when the temperature difference is smaller, so that the target flow rate can be dynamically increased or decreased according to the relationship. For example, a map may be set to query the target flow rate corresponding to the temperature difference and the heat difference, or calculate the target flow rate according to a functional relation between the temperature difference, the heat difference, and the target flow rate.
In one possible implementation manner, the method for determining the target flow rate of the cooling medium according to the temperature difference and the heat difference specifically includes the steps of firstly converting the temperature difference into a first predicted flow rate, converting the heat difference into a second predicted flow rate, and determining the target flow rate of the cooling medium according to the first predicted flow rate and the second predicted flow rate. The temperature difference and the heat quantity are respectively and independently converted, so that the independence of the temperature difference and the heat quantity can be fully considered, the target flow rate can be obtained, and the accuracy of the target flow rate can be improved.
Wherein the target flow rate may be a weighted sum of the first predicted flow rate and the second predicted flow rate. The weighting coefficients of the first predicted flow rate and the second predicted flow rate can be flexibly set to adjust the influence degree of the first predicted flow rate and the second predicted flow rate on the target flow rate.
The first predicted flow rate is predicted by taking the product of the first conversion coefficient and the temperature difference at the current moment as a first sub-flow rate and/or determining a second sub-flow rate through the temperature difference at the current moment and the temperature differences at a plurality of historical moments before the current moment, and further determining the first predicted flow rate according to the first sub-flow rate and/or the second sub-flow rate. It can be seen that the first predicted flow rate may be determined in accordance with one or a combination of both, helping to improve its accuracy.
The second sub-flow rate not only considers the temperature difference at the current moment, but also comprehensively considers the temperature difference at the historical moment, namely, the temperature difference in a period of time is predicted, so that the accuracy of the first predicted flow rate can be improved, and the misprediction caused by occasional floating of the temperature difference is avoided.
The second sub-flow rate can be determined by firstly updating a temperature difference integral term of the previous moment through a temperature difference of the current moment to obtain the temperature difference integral term of the current moment, then determining the temperature difference change rate of the current moment according to the temperature difference of the current moment and the temperature difference of the previous moment, and finally determining the second sub-flow rate according to the temperature difference of the current moment, the temperature difference integral term of the current moment and the temperature difference change rate of the current moment.
The temperature difference integral term is just related to the temperature difference integral term of the last moment, and the temperature difference integral term is used for indicating the accumulation condition of the temperature difference and can be also understood as the accumulated temperature difference. The expression can be represented by the following formula:
(7)
Wherein I (t) is the temperature difference integral of the current time t, I (t-1) is the temperature difference integral of the previous time t-1, e (t) is the temperature difference of the current time t, and ITL is the sampling time interval, i.e. the time difference between t and t-1.
The above-mentioned temperature difference change rate is used to indicate the change speed of the temperature difference, and may be defined as the ratio of the difference between the temperature difference at the current time and the temperature difference at the previous time to the sampling time interval, specifically may be expressed by the following formula:
(8)
wherein D (t) is the temperature difference change rate at the current time t, and e (t-1) is the temperature difference at the previous time t-1.
After determining the temperature difference integral term, the temperature difference change rate, and the temperature difference described above, a second sub-flow rate may be determined from the temperature difference integral term, the temperature difference change rate, and the temperature difference, the second sub-flow rate being positively correlated to the temperature difference integral term, the temperature difference change rate, and the temperature difference. Therefore, the temperature difference at the current moment, the temperature difference at the historical moment and the temperature difference change rate can be comprehensively considered by the second sub-flow rate, and the accuracy of the second sub-flow rate can be improved.
In one implementation, the temperature difference integral term, the temperature difference rate of change, and the temperature difference may be added, or weighted, as the second sub-flow rate.
In another implementation, determining the second sub-flow rate based on the temperature difference at the current time, the temperature difference integral term at the current time, and the temperature difference rate of change at the current time includes weighting the temperature difference at the current time, the temperature difference integral term, and the temperature difference rate of change to obtain a control parameter to map the control parameter to the second sub-flow rate based on the maximum flow rate, the second sub-flow rate being directly related to the maximum flow rate and being directly related to the control parameter. Therefore, the second sub-flow rate can be accurately controlled within the maximum flow rate, and the rationality of the second sub-flow rate is ensured.
The above control parameters can be expressed by the following formula:
(9)
Wherein U (t) is a control parameter of the current time t, kp, ki and Kd are weights of the temperature difference, the temperature difference integral term and the temperature difference change rate respectively, and the weights can be flexibly adjusted.
In one example, the second sub-flow rate may be a product of the maximum flow rate and the control parameter, or a ratio of the product of the maximum flow rate and the control parameter to a flow rate mapping coefficient, for example, as follows:
(10)
where V2 (t) is the second sub-flow rate at the current time t and Vmax is the maximum flow rate. B is a flow rate map coefficient, and may be flexibly set according to the value range of U (t) such that U (t)/B is between 0 and 1, for example, when the maximum value of U (t) is 100, B may be set to 100.
In one embodiment of the present application, the determining the first predicted flow rate according to the first sub-flow rate and/or the second sub-flow rate includes the following three cases:
in the first case, the first sub-flow rate is taken as the first predicted flow rate.
In the second case, the second sub-flow rate is taken as the second predicted flow rate.
In the third case, the first sub-flow rate and the second sub-flow rate are weighted to obtain a first predicted flow rate. The weighting coefficients of the first sub-flow velocity and the second sub-flow velocity can be flexibly set to adjust the influence degree of the first sub-flow velocity and the second sub-flow velocity on the final first predicted flow velocity, and the two prediction algorithms can be compatible, so that the accuracy of the first predicted flow velocity is improved.
In one embodiment of the present application, the heat difference is converted into the second predicted flow rate, and the product of the second conversion coefficient and the heat difference may be used as the second predicted flow rate. Therefore, the second conversion coefficient can be preset, conversion can be realized through simple multiplication operation, and the operation complexity is low.
It can be seen that the first predicted flow rate may be a weighting of the first sub-flow rate and/or the second sub-flow rate, and the second predicted flow rate.
In summary, the application can combine the predicted heat difference to perform cooling control on the basis of the temperature difference, can perform cooling control in advance, and improves the cooling control effect. In addition, the sensor distribution can be dynamically adjusted to ensure the measurement accuracy as much as possible on the basis of saving the sensors.
After each cooling control, before the next cooling control time is reached after a control period, the weights corresponding to the first conversion coefficient, the second conversion coefficient, the temperature difference when calculating the control parameter, the temperature difference integral term and the temperature difference change rate, and the weights of the first sub-flow rate and the second sub-flow rate used for calculating the first predicted flow rate may be dynamically adjusted. So that the next cooling control is performed using the adjusted parameters, which contributes to improving the dynamics of the cooling control.
Fig. 3 is a flowchart illustrating steps of another method for controlling cooling of a server according to an embodiment of the present application. Referring to fig. 3, the server cooling control method includes:
S301, converting the temperature change rate of the target component on the server into the temperature sensor density according to the temperature sensitivity coefficient, and converting the flow rate change rate of the target component into the flow rate sensor density according to the flow rate sensitivity coefficient.
S302, determining the sensor density according to the temperature sensor density and the flow velocity sensor density, and adjusting the sensor distribution on the target component according to the sensor density.
The sensor comprises a temperature sensor and a flow rate sensor, wherein the sensor density is positively related to the temperature sensor density and the flow rate sensor density, and the sensor density is positively related to the temperature change rate and the flow rate change rate.
S303, acquiring a measurement result sequence of the target component on the server at the current moment.
The measurement result sequence comprises one or more pieces of measurement result information, wherein the measurement result information comprises measurement time, measurement temperature and measurement flow rate of the cooling medium, and the measurement time is current time or historical time.
And S304, calculating statistical information according to the measurement result sequence at the current moment, and splicing the measurement result sequence and the statistical information into a feature vector of the target component.
Wherein the statistical information includes at least one of an average measured temperature, a maximum temperature difference, and a measured flow rate standard deviation.
And S305, inputting the characteristic vector into the long-short-term memory network model to obtain the heat to be eliminated required by the target component to reach the target temperature, and determining the average heat to be eliminated according to the predicted heat to be eliminated at a plurality of moments.
S306, calculating a temperature difference between the target temperature and the measured temperature at the current moment and a heat difference between the predicted heat to be eliminated at the current moment and the average heat to be eliminated.
And S307, taking the product of the first conversion coefficient and the temperature difference at the current moment as a first sub-flow rate.
And S308, updating a temperature difference integral term of the previous moment through the temperature difference of the current moment to obtain the temperature difference integral term of the current moment, and determining the temperature difference change rate of the current moment according to the temperature difference of the current moment and the temperature difference of the previous moment.
And S309, weighting the temperature difference, the temperature difference integral term and the temperature difference change rate at the current moment to obtain a control parameter, and mapping the control parameter into a second sub-flow rate according to the maximum flow rate.
Wherein the second sub-flow rate is positively correlated to the maximum flow rate and is positively correlated to the control parameter.
And S310, weighting the first sub-flow rate and the second sub-flow rate to obtain a first predicted flow rate, and taking the product of the second conversion coefficient and the heat difference as a second predicted flow rate.
And S311, determining a target flow rate of the cooling medium according to the first predicted flow rate and the second predicted flow rate so as to perform cooling control on the target component based on the target flow rate.
The steps S301 to S311 may specifically refer to the server cooling control method shown in fig. 2, and are not described herein.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment.
Fig. 4 is a schematic structural diagram of a server cooling control device according to an embodiment of the present application. As shown in fig. 4, an embodiment of the present application further provides a server cooling control apparatus 400, including:
The measurement result obtaining module 401 is configured to obtain a measurement result sequence of the target component at the current time on the server, where the measurement result sequence includes one or more measurement result information, and the measurement result information includes a measurement time, a measurement temperature, and a measurement flow rate of the cooling medium, and the measurement time is the current time or the history time.
The prediction module 402 is configured to predict an amount of heat to be removed required for the target component to reach the target temperature according to the measurement result sequence at the current time, and determine an average amount of heat to be removed according to the amounts of heat to be removed predicted at the multiple times.
A calculating module 403, configured to calculate a temperature difference between the target temperature and the measured temperature at the current time, and a difference between the predicted heat to be removed and the average heat to be removed at the current time.
The cooling control module 404 is configured to perform cooling control on the target component according to the temperature difference and the heat quantity difference.
In some possible implementations, the cooling control module 404 is further configured to:
and performing cooling control on the target component based on the target flow rate.
In some possible implementations, the cooling control module 404 is further configured to:
the method includes converting a temperature difference to a first predicted flow rate, converting a heat difference to a second predicted flow rate, and determining a target flow rate of the cooling medium based on the first predicted flow rate and the second predicted flow rate.
In some possible implementations, the cooling control module 404 is further configured to:
Taking the product of the first conversion coefficient and the temperature difference at the current moment as a first sub-flow rate, and/or determining a second sub-flow rate through the temperature difference at the current moment and the temperature differences at a plurality of historical moments before the current moment; the first predicted flow rate is determined based on the first sub-flow rate and/or the second sub-flow rate.
In some possible implementations, the cooling control module 404 is further configured to:
The temperature difference integral term of the previous moment is updated through the temperature difference of the current moment to obtain the temperature difference integral term of the current moment, the temperature difference change rate of the current moment is determined according to the temperature difference of the current moment and the temperature difference of the previous moment, and the second sub-flow rate is determined according to the temperature difference of the current moment, the temperature difference integral term of the current moment and the temperature difference change rate of the current moment.
In some possible implementations, the cooling control module 404 is further configured to:
and mapping the control parameter into a second sub-flow rate according to the maximum flow rate, wherein the second sub-flow rate is positively related to the maximum flow rate and is positively related to the control parameter.
In some possible implementations, the cooling control module 404 is further configured to:
and weighting the first sub-flow rate and the second sub-flow rate to obtain a first predicted flow rate.
In some possible implementations, the cooling control module 404 is further configured to:
And taking the product of the second conversion coefficient and the heat difference as a second predicted flow rate.
In some possible implementations, the prediction module 402 is further configured to:
And calculating statistical information according to the measurement result sequence at the current moment, wherein the statistical information comprises at least one of average measured temperature, maximum temperature difference and standard deviation of measured flow rate, and predicting the heat to be eliminated required by the target component to reach the target temperature according to the measurement result sequence at the current moment and the statistical information.
In some possible implementations, the prediction module 402 is further configured to:
And inputting the feature vector into a long-term and short-term memory network model to obtain the heat to be eliminated required by the target component to reach the target temperature.
In some possible implementations, referring to fig. 5, the apparatus further includes:
a change rate acquisition module 405 for acquiring a temperature change rate and a flow rate change rate of the target component.
A density determination module 406 for determining a sensor density on the target component based on the rate of change of temperature and the rate of change of flow of the target component, the sensor density being positively correlated to the rate of change of temperature and the rate of change of flow.
The sensor adjustment module 407 is configured to adjust a sensor distribution on the target component according to a sensor density, where the sensor includes a temperature sensor and a flow rate sensor.
In some possible implementations, the density determination module 406 is further to:
the temperature change rate of the target component is converted into a temperature sensor density according to the temperature sensitivity coefficient, the flow rate change rate of the target component is converted into a flow rate sensor density according to the flow rate sensitivity coefficient, the sensor density is determined according to the temperature sensor density and the flow rate sensor density, and the sensor density is positively related to the temperature sensor density and the flow rate sensor density.
The description of the features in the embodiment corresponding to the server cooling control device may be referred to the related description of the embodiment corresponding to the server cooling control method, which is not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device provided by the present application. As shown in fig. 6, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further comprises a communication component 503. The processor 501, the memory 502, and the communication unit 503 are connected via a bus.
In a specific implementation, at least one processor 501 executes computer-executable instructions stored in memory 502, such that at least one processor 501 performs the server cooling control method embodiment described above.
The specific implementation process of the processor 501 may refer to the above-mentioned method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.
In the above embodiment, it should be understood that the Processor may be a central processing unit (Central Processing Unit, abbreviated as CPU), other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, abbreviated as DSP), application SPECIFIC INTEGRATED Circuit (ASIC), and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
The Memory may include high-speed Memory (Random Access Memory, RAM) or may further include Non-volatile Memory (NVM), such as at least one disk Memory.
The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (PERIPHERAL COMPONENT, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or to one type of bus.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is configured to perform the steps of any of the server cooling control method embodiments described above when run.
In an exemplary embodiment, the computer readable storage medium may include, but is not limited to, a U disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, etc. various media in which a computer program may be stored.
Embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor, implements the steps of any of the embodiments of the server cooling control method described above.
Embodiments of the present application also provide another computer program product comprising a non-volatile computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of any of the server cooling control method embodiments described above.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The server cooling control method and the related equipment provided by the application are described in detail. The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present application and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the application can be made without departing from the principles of the application and these modifications and adaptations are intended to be within the scope of the application as defined in the following claims.
Claims (15)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510978235.6A CN120491791B (en) | 2025-07-16 | 2025-07-16 | Server cooling control method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510978235.6A CN120491791B (en) | 2025-07-16 | 2025-07-16 | Server cooling control method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120491791A true CN120491791A (en) | 2025-08-15 |
| CN120491791B CN120491791B (en) | 2025-09-19 |
Family
ID=96681538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510978235.6A Active CN120491791B (en) | 2025-07-16 | 2025-07-16 | Server cooling control method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120491791B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100030395A1 (en) * | 2008-08-02 | 2010-02-04 | Susumu Shimotono | Heat Dissipation System for Computers |
| US20110320055A1 (en) * | 2009-03-19 | 2011-12-29 | Fujitsu Limited | Electronic apparatus |
| CN116954334A (en) * | 2023-07-31 | 2023-10-27 | 苏州浪潮智能科技有限公司 | Heat dissipation control method, device, server, computer equipment and storage medium |
| CN119002655A (en) * | 2024-07-31 | 2024-11-22 | 苏州元脑智能科技有限公司 | Control method and device of server temperature control equipment, storage medium and electronic equipment |
| CN120255670A (en) * | 2025-03-24 | 2025-07-04 | 苏州元脑智能科技有限公司 | Temperature control method, device, electronic device and storage medium |
-
2025
- 2025-07-16 CN CN202510978235.6A patent/CN120491791B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100030395A1 (en) * | 2008-08-02 | 2010-02-04 | Susumu Shimotono | Heat Dissipation System for Computers |
| US20110320055A1 (en) * | 2009-03-19 | 2011-12-29 | Fujitsu Limited | Electronic apparatus |
| CN116954334A (en) * | 2023-07-31 | 2023-10-27 | 苏州浪潮智能科技有限公司 | Heat dissipation control method, device, server, computer equipment and storage medium |
| CN119002655A (en) * | 2024-07-31 | 2024-11-22 | 苏州元脑智能科技有限公司 | Control method and device of server temperature control equipment, storage medium and electronic equipment |
| CN120255670A (en) * | 2025-03-24 | 2025-07-04 | 苏州元脑智能科技有限公司 | Temperature control method, device, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120491791B (en) | 2025-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7298494B2 (en) | Learning device, learning method, learning program, determination device, determination method, and determination program | |
| CN107480028B (en) | Method and device for acquiring usable residual time of disk | |
| CN107301570B (en) | Traffic prediction method, abnormal traffic detection device and electronic equipment | |
| KR20250047971A (en) | Device and method for predicting state of battery | |
| CN111855019B (en) | Temperature measuring method and device, wrist-worn equipment and storage medium | |
| CN106092371B (en) | Method and device for predicting temperature | |
| JP7374868B2 (en) | Information processing device, information processing method and program | |
| JP2009167751A (en) | Inflow forecasting system, inflow forecasting method and program | |
| CN120353134B (en) | Heat dissipation device control method, device, equipment and storage medium | |
| JP6792272B1 (en) | Power generation control system and power generation control method | |
| CN114294824A (en) | Water use habit analysis method and device, terminal equipment and storage medium | |
| CN118011246A (en) | Residual electric quantity detection method, device and medium | |
| CN119879357B (en) | Energy-saving control method and system for heat pump | |
| CN106662463B (en) | Detection method and device of sensor background noise | |
| CN120491791B (en) | Server cooling control method and related equipment | |
| WO2019207622A1 (en) | Power demand prediction device, power demand prediction method, and program therefor | |
| CN118443165A (en) | Image unsteady state correction method, device, equipment and medium | |
| CN114739557B (en) | Tension sensor data processing method, device and terminal equipment | |
| JP7058025B1 (en) | Equipment operation support equipment and programs | |
| CN106537442A (en) | Collection amount regulation assist apparatus, collection amount regulation assist method, and computer-readable recording medium | |
| CN114722343A (en) | Clutch position signal filtering method and device, storage medium and terminal | |
| JP5281983B2 (en) | Creep error compensation device and creep error compensation method | |
| CN112990595A (en) | Travel time prediction method, travel time prediction device, storage medium and electronic equipment | |
| JP4965280B2 (en) | Analog output device | |
| JP7646534B2 (en) | Method, system and program for visualizing internal states of a plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |