Methods, apparatuses, devices, and storage media for temperature control

Abstract

According to embodiments of this disclosure, a method, apparatus, device, and storage medium for temperature control are provided. The method includes determining predicted load information of a target device based on historical operating information associated with the operation of that target device, the predicted load information including at least a predicted load of the target device at a first moment. The method further includes determining a predicted first temperature index of the coolant at the first moment based on the predicted load, historical temperature information of the coolant, and historical operating information of a coolant-driven device, wherein the coolant is used to cool the target device, and the coolant-driven device is used to drive the flow of the coolant. The method further includes determining a first operating parameter of the coolant-driven device at the first moment, at least based on the first temperature index. This improves the accuracy and stability of temperature control.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to methods, apparatuses, devices, and computer-readable storage media for temperature control. BACKGROUND

[0002] With the development of Internet big data technology, the amount of data to be stored and processed by servers in each data center is getting larger and larger, and switches and the like also need to perform a large amount of data transmission. This makes the power consumption and heat generation of devices such as servers and switches also larger and larger. In order to enable the data center to operate normally, the data center will often be equipped with an air cooling system or a liquid cooling system, so as to realize temperature control of devices such as servers and switches through air cooling or liquid cooling. Liquid cooling has more extensive applications due to its higher heat dissipation efficiency and lower energy consumption. SUMMARY

[0003] In a first aspect of the present disclosure, a method for temperature control is provided. The method comprises: determining predicted load information of a target device based on historical operation information associated with operation of the target device, the predicted load information comprising at least a predicted load of the target device at a first time; determining a predicted first temperature indicator of a cooling liquid at the first time based on the predicted load, historical temperature information of the cooling liquid, and historical operation information of a cooling liquid driving device, the cooling liquid being used to cool the target device, and the cooling liquid driving device being used to drive flow of the cooling liquid; and determining a first operation parameter of the cooling liquid driving device at the first time based on at least the first temperature indicator.

[0004] In a second aspect of the present disclosure, an apparatus for temperature control is provided. The apparatus comprises: a load information determination module configured to determine predicted load information of a target device based on historical operation information associated with operation of the target device, the predicted load information comprising at least a predicted load of the target device at a first time; a temperature indicator determination module configured to determine a predicted first temperature indicator of a cooling liquid at the first time based on the predicted load, historical temperature information of the cooling liquid, and historical operation information of a cooling liquid driving device, the cooling liquid being used to cool the target device, and the cooling liquid driving device being used to drive flow of the cooling liquid; and an operation parameter determination module configured to determine a first operation parameter of the cooling liquid driving device at the first time based on at least the first temperature indicator.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device comprises at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by the at least one processing unit, cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has stored thereon a computer program, which is executable by a processor to implement the method of the first aspect.

[0007] It should be understood that the matters described in the detailed content part of the present disclosure are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0008] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0009] Figure 1 A schematic diagram of an example liquid cooling system in which embodiments of the present disclosure can be implemented is shown;

[0010] Figure 2 A schematic diagram of an example architecture for temperature control in accordance with some embodiments of the present disclosure is shown;

[0011] Figure 3 A schematic diagram of one example of a nonlinear autoregressive neural network in accordance with some embodiments of the present disclosure is shown;

[0012] Figure 4 A schematic diagram of one example of a prediction control unit in accordance with some embodiments of the present disclosure is shown;

[0013] Figure 5 A flowchart of a process for temperature control in accordance with some embodiments of the present disclosure is shown;

[0014] Figure 6 A schematic block diagram of an apparatus for temperature control in accordance with certain embodiments of the present disclosure is shown; and

[0015] Figure 7 A block diagram of an electronic device in which one or more embodiments of the present disclosure can be implemented is shown. DETAILED DESCRIPTION

[0016] It can be understood that, before using the technical solutions disclosed by the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained in accordance with relevant laws and regulations.

[0017] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed by the user will require obtaining and using personal information of the user. Thus, the user can autonomously select whether to provide the personal information to the software or hardware, such as an electronic device, an application program, a server or a storage medium, performing the operation of the technical solution of the present disclosure according to the prompt information.

[0018] As an optional but non-limiting implementation, in response to receiving an active request of a user, the prompt information can be sent to the user in the form of a pop-up window, in which the prompt information can be presented in the form of text. In addition, the pop-up window can also carry selection controls for the user to select “agree” or “disagree” to provide personal information to the electronic device.

[0019] It can be understood that the above notification and obtaining user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other ways that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0020] It can be understood that the data involved in the technical solution (including but not limited to the data itself, the obtaining or use of the data) should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments described herein, rather, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the scope of protection of the present disclosure.

[0022] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment can be included under any section / subsection. Furthermore, embodiments described in any section / subsection can be combined with any other embodiment described in the same section / subsection and / or in a different section / subsection in any manner.

[0023] In the description of embodiments of the present disclosure, the term “comprising” and similar terms are to be understood as open-ended, i.e., “including but not limited to”. The term “based on” is to be understood as “based at least in part on”. The term “one embodiment” or “the embodiment” is to be understood as “at least one embodiment”. The term “some embodiments” is to be understood as “at least some embodiments”. Other explicit and implicit definitions can also be included below. The terms “first”, “second”, etc. can refer to different or the same objects. Other explicit and implicit definitions can also be included below.

[0024] As used herein, the term “model” can learn an association between a corresponding input and output from training data, so that after training is completed, a corresponding output can be generated for a given input. The generation of a model can be based on a machine learning technique. Deep learning is a machine learning algorithm that processes an input and provides a corresponding output by using multiple layers of processing units. In this document, a “model” can also be referred to as a “machine learning model”, a “machine learning network” or a “network”, which are used interchangeably herein. A model can in turn comprise different types of processing units or networks.

[0025] As used herein, the term “moment” can have any suitable length of time or unit. Such length of time or unit can be, for example, minutes, hours, half hours, days, etc.

[0026] As briefly mentioned above, in order to enable a data center to function properly, liquid cooling systems are equipped in the data center to cool down the data center. Current liquid cooling systems mainly include three types of immersion, cold plate and spray, among which the immersion liquid cooling system is the most widely used. The immersion liquid cooling system immerses the heat generating equipment in the cooling liquid, so that the heat generating equipment is in direct contact with the cooling liquid, and then heat exchange is performed. For example, the immersion liquid cooling system with an internal integrated heat exchanger can efficiently realize the cooling demand of self-circulation heat dissipation of servers, switches and other equipment.

[0027] In a conventional temperature control scheme for an immersion liquid cooling system, the temperature difference between the inlet and outlet liquid in the internal circulation is taken as a controlled parameter to control the working frequency of the circulating pump. This enables the liquid to flow at a certain speed and take away the heat of the heat generating equipment to ensure the normal operation of the electronic equipment such as servers. However, due to the high power consumption of servers and switches and the frequent change of power consumption with business, this conventional temperature control scheme has a certain hysteresis and cannot effectively control the temperature in time. For example, in the scenario of frequent business load, the temperature of the server may be too high. For another example, in the scenario of infrequent business load, the temperature of the server may be too low. Insufficient cooling will affect the operation of various equipment in the data center, while excessive cooling will cause waste of energy. Therefore, this traditional scheme cannot effectively control the temperature in time on the one hand, and on the other hand, it will also increase energy consumption, which is not conducive to energy saving and emission reduction.

[0028] In the foregoing, the problem of the traditional temperature control scheme is described by taking a data center as an example. It should be understood that similar problems can also exist in other scenarios that require temperature control. In view of this, it is desirable to provide a temperature control method to solve one or more of the above technical problems and other potential problems.

[0029] Embodiments of the present disclosure propose a scheme for temperature control. According to various embodiments of the present disclosure, based on historical operation information associated with operation of a target device (which serves as a heat generating device), predicted load information of the target device is determined, the predicted load information at least comprising a predicted load of the target device at a time instant of interest. Based on the predicted load, historical temperature information of a cooling liquid and historical operation information of a cooling liquid driving device, a temperature indicator of the cooling liquid at the time instant is predicted, the cooling liquid being used to cool the target device and the cooling liquid driving device being used to drive flow of the cooling liquid. At least based on the predicted temperature indicator, an operation parameter of the cooling liquid driving device at the time instant is determined. The operation parameter is used to control power, rotational speed, operation frequency, etc. of the cooling liquid driving device.

[0030] In embodiments of the present disclosure, the predicted load information of the heat generating device, the historical temperature information of the cooling liquid and the historical operation information of the cooling liquid driving device are utilized to predict how the cooling liquid driving device should operate at a certain time instant. That is, operation of the cooling liquid driving device can be controlled in combination with prediction of load condition of the heat generating device. In this way, timely and effective temperature control can be advantageously achieved, thereby enhancing stability and safety of operation of the heat generating device. Moreover, the cooling liquid driving device can be facilitated to operate with appropriate power consumption.

[0031] Example liquid cooling system

[0032] Figure 1 A schematic diagram of an example liquid cooling system 100 in which embodiments of the present disclosure can be implemented is shown. In the example liquid cooling system 100, a target device 120 can be any type of heat generating device that needs to be cooled. In some embodiments, the target device 120 can be an electronic device in a data center. For example, the target device 120 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers. The target device 120 can also be other purpose devices in a data center, such as switches, etc.

[0033] A container 140 includes a water inlet 141 and a water outlet 142. The target device 120 is placed inside the container 140. The cooling liquid driving device 130 drives the cooling liquid to flow from the water inlet 141 into the container 140, flow through the target device 120 and flow out of the container 140 from the water outlet 142. In this way, the cooling liquid can take away heat of the target device 120, thereby achieving temperature control of the target device 120. The cooling liquid driving device 130 is used to operate based on an operation parameter to drive flow of the cooling liquid, thereby achieving temperature control of the target device 120. The cooling liquid driving device 130 can be any suitable type of device capable of controlling flow of liquid, such as a circulation pump. Although one cooling liquid driving device is shown in Figure 1 In the example liquid cooling system 100, the cooling liquid driving device 130 is used to drive flow of the cooling liquid in the container 140. The cooling liquid driving device 130 is used to drive flow of the cooling liquid in the container 140. The cooling liquid driving device 130 can be any suitable type of device capable of controlling flow of liquid, such as a circulation pump. Although one cooling liquid driving device is shown in

[0034] The electronic device 110 predicts a predicted load of the target device 120 at a certain time based on historical running information associated with the target device 120, and further determines a temperature index at the certain time based on the predicted load, historical temperature information of the cooling liquid, and historical operation information of the cooling liquid driving device 130. Then, the electronic device 110 determines an operation parameter of the cooling liquid driving device 130 at the certain time based on the temperature index.

[0035] To this end, the electronic device 110 and the cooling liquid driving device 130 can have a function of data communication with each other, i.e., a communication connection can be established between the electronic device 110 and the cooling liquid driving device 130 in a wireless communication or wired communication manner. The electronic device 110 can acquire the historical operation information of the cooling liquid driving device 130 through the communication connection. Alternatively, the historical operation information of the cooling liquid driving device 130 can be directly stored in the electronic device 110. On the other hand, the electronic device 110 can send the determined operation parameter to the cooling liquid driving device 130 to control the operation of the cooling liquid driving device 130.

[0036] The electronic device 110 and the target device 120 can have a function of data communication with each other, i.e., a communication connection can be established between the electronic device 110 and the target device 120 in a wireless communication or wired communication manner. The electronic device 110 can acquire the historical running information associated with the target device 120 through the communication connection. In some examples, the target device 120 is further provided with a temperature acquisition device, and the target device 120 acquires the temperature information of the cooling liquid in real time and sends it to the electronic device 110. In other examples, the temperature acquisition device is provided in the electronic device 110, and the electronic device 110 acquires the temperature information of the cooling liquid through the temperature acquisition device and stores it in the memory for subsequent prediction of the temperature index at a certain time using the historical temperature information.

[0037] The electronic device 110 can be any type of device with computing capability, including a terminal device or a server device. The terminal device can be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device may, for example, include a computing system, a server, and the like.

[0038] It should be appreciated that the structure and function of the liquid cooling system 100 are described for illustrative purposes only and are not intended to imply any limitation on the scope of the present disclosure. For example, although the electronic device 110 is shown separately from the cooling liquid driving device 130, in some embodiments, the electronic device 110 can be implemented in the cooling liquid driving device 130, e.g., as a controller therein. Moreover, the manner in which the electronic device 110 obtains historical operation information and historical running information described above is also illustrative and is not intended to limit the scope of the present disclosure. In embodiments of the present disclosure, the electronic device 110 can obtain data required for temperature control in any suitable manner.

[0039] Some example embodiments of the present disclosure will be described below with continued reference to the drawings.

[0040] Overall architecture of temperature control

[0041] Figure 2 A schematic diagram of an example architecture 200 of temperature control according to some embodiments of the present disclosure is shown. Generally, the architecture 200 generally includes a load prediction unit 210 and a predictive control unit 220. In some embodiments, the architecture 200 can also include a conversion unit 230. These units in the architecture 200 and other units not shown can be implemented in the electronic device 110.

[0042] The load prediction unit 210 is configured to predict load information of the target device 120 based on historical running information 201 associated with running of the target device 120. In other words, the load prediction unit 210 determines predicted load information 202 of the target device 120 based on the historical running information 201. The predicted load information 202 includes at least a predicted load of the target device 120 at a time t (also referred to as a first time). The time t can be a current time or any future time.

[0043] In some embodiments, the predicted load information 202 determined by the load prediction unit 210 can include respective predicted loads of the target device 120 at multiple times. These times can include the time t and one or more times after the time t.

[0044] In some embodiments, the historical operation information 201 can include historical loads of the target device 120 in a period of time before the time t. The load prediction unit 210 can predict the predicted load information 202 of the target device 120 at the time t based on the historical loads. In other embodiments, to make the predicted load information 202 more accurate, the historical operation information 201 can include, in addition to the historical loads of the target device 120 in a period of time before the time t, environmental factors experienced by the target device 120 in a period of time before the time t. The environmental factors are auxiliary factors for predicting the load, and can include, for example, environmental temperature, season, humidity, etc. Each item of information in the historical operation information 201, such as each historical load, each environmental factor, can have a time stamp to identify the corresponding historical time.

[0045] The same historical time period or different historical time periods can be considered for the historical loads and the environmental factors. For example, the historical loads can include loads of the target device 120 in a first historical time period before the time t, and the environmental factors can include environmental factors experienced by the target device 120 in a second historical time period before the time t. The first historical time period can be the same as or different from the second historical time period.

[0046] The load of the target device 120 can be predicted based on the historical operation information 201 based on any suitable algorithm. Since the historical operation information 201 is time series data, in some embodiments, the load prediction unit 210 can use a model or a neural network involving time series to determine the predicted load information 202. Examples of the model or the neural network involving time series can include, but are not limited to, a recurrent neural network (RNN), a time-delay neural network (TDNN), and a nonlinear autoregressive (NARX) neural network, etc. An example of determining the predicted load information 202 based on the historical operation information 201 is described below taking the NARX neural network as an example. Figure 3 A schematic diagram of a NARX neural network 300 is shown in accordance with some embodiments of the present disclosure. The NARX 300 can be implemented in the load prediction unit 210.

[0047] As Figure 3As shown, the trained NARX neural network 300 determines the predicted load information 202 based on the historical operation information 201. In this example, the NARX neural network 300 includes an input layer, a first layer, a second layer, and an output layer. It should be understood, however, that this is merely exemplary and not intended to limit the scope of the present disclosure. In this example, the historical operation information 201 includes historical loads and historical environmental factors. Specifically, to predict the load at time t, the historical environmental factors 301-1 and 301-2 experienced by the target device 120 over a historical time period before time t and the historical loads 302-1, 302-2, and 302-3 of the target device 120 over a historical time period before time t are input to the NARX neural network 300. After processing by the first layer, the second layer, and the output layer of the NARX neural network 300, the predicted load of the target device 120 at time t is obtained as at least part of the predicted load information 202.

[0048] As an example, the prediction of the load by the NARX neural network 300 can be represented as follows:

[0049] y(t) = f(x(t-1),..., x(t-d x ), y(t-1), y(t-2),..., y(t-d y )) (1)

[0050] where x represents the environmental factor, y represents the load, t represents time t, t-1, t-2, t-d x , t-d y represent time before time t, x(t-1),..., x(t-d x ) represent the environmental factors corresponding to times t-1,..., t-d x , y(t-1), y(t-2),..., y(t-d y ) represent the historical loads corresponding to times t-1, t-2,..., t-d y , d x (also referred to as input delay) is related to the length of the historical time period considered for the environmental factor, and d y (also referred to as output delay) is related to the length of the historical time period considered for the load.

[0051] The above describes an example of predicting the load at time t with reference to Figure 3 and equation (1). Predicting the load at other times (e.g., time t+1, time t+2) is similar. In addition, reference is made to Figure 3Equation (1) is merely exemplary and is not intended to limit the scope of the present disclosure. In embodiments of the present disclosure, the load prediction unit 210 can determine the predicted load information 202 of the target device 120 using any known or future developed model or neural network.

[0052] With continued reference to Figure 2 The predicted load information 202 is provided to a prediction control unit 220. The prediction control unit 220 also acquires historical temperature information 204 of the cooling fluid. The historical temperature information 204 of the cooling fluid can include temperature indicators of the cooling fluid at one or more time instants before the time instant t. In embodiments of the present disclosure, the temperature indicators can include any data capable of indicating the temperature of the cooling fluid. In some embodiments, the temperature indicators can include the temperature of the cooling fluid at a certain location on its flow path (e.g., the water inlet 141 or the water outlet 142). Alternatively or additionally, in some embodiments, the temperature indicators can include the average temperature of the cooling fluid at multiple locations. Alternatively or additionally, in some embodiments, the temperature indicators can include the difference between the temperature of the cooling fluid at a first location and the temperature at a second location of the flow path, also referred to simply as the temperature difference. For example, the temperature indicators can include the temperature difference of the cooling fluid between the water inlet 141 and the water outlet 142. By using such temperature difference, the heat dissipated by cooling the target device 120 can be more truly reflected, thus facilitating more accurate temperature control.

[0053] The prediction control unit 220 also acquires historical operation information 203 of the cooling fluid driving device 130. The historical operation information 203 can include operation parameters of the cooling fluid driving device 130 at one or more time instants before the time instant t. In embodiments of the present disclosure, the operation parameters can include any data related to the driving of the cooling fluid. For example, the operation parameters can include the running power, the operating frequency and the rotation speed of the cooling fluid driving device 130 (e.g., the circulating pump), etc.

[0054] The historical operation information 203 and the historical temperature information 204 can also have timestamps to identify the corresponding historical time instants. Based on the predicted load information 202, the historical operation information 203 and the historical temperature information 204, the prediction control unit 220 can predict the operation parameters of the cooling fluid driving device 130 at the time instant t. That is, the prediction control unit 220 determines the predicted operation parameters 205. It can be appreciated that, to make the prediction result of the prediction control unit 220 more accurate, the historical operation parameters included in the historical operation information 203 and the historical temperature indicators of the historical temperature information 204 are corresponding values at the same one or more time instants before the time instant t.

[0055] In particular, the prediction control unit 220 first determines a predicted temperature indicator of the coolant at time t, which is also referred to as a first temperature indicator. To predict the temperature indicator at time t, the prediction control unit 220 can be based on a predicted load at time t, historical temperature information of the coolant, and historical operation information of the coolant driving device 130. In some embodiments, a neural network can be utilized to predict the temperature indicator at time t based on the predicted load, the historical temperature information, and the historical operation information. In some embodiments, to predict the temperature indicator at time t, a correlation for the coolant temperature, also referred to as a temperature correlation, can also be additionally considered. The temperature correlation indicates the dependency of the temperature indicator of the coolant on the operation parameters of the coolant driving device 130 and the load of the target device 120. For example, the temperature correlation can indicate the relationship of the temperature difference at time t with the operation parameters and the load at a time before time t. The temperature correlation will be described in detail below with reference to Figure 4

[0056] Then, the prediction control unit 220 determines the operation parameter of the coolant driving device 130 at time t, i.e., the predicted operation parameter 205, based on the predicted temperature indicator at time t. The prediction control unit 220 can utilize any suitable algorithm to predict the operation parameter. In some embodiments, a trained machine learning model can be utilized to predict the operation parameter. Alternatively, in some embodiments, a relationship between the temperature indicator and the operation parameter can be constructed based on the historical temperature information and the historical operation information, e.g., a relationship between the temperature difference and the rotational speed can be constructed. Then, the value of the operation parameter at time t can be predicted based on the relationship. In some embodiments, the temperature correlation mentioned above can also be additionally considered to predict the operation parameter. Such embodiments will be described below with reference to Figure 4

[0057] Continuing to refer to Figure 2 In some embodiments, the prediction control unit 220 can directly provide the predicted operation parameter 205 to the coolant driving device 130. Alternatively, in some embodiments, the dimension of the predicted operation parameter 205 determined by the prediction control unit 220 can be different from the operation parameter actually used by the coolant driving device 130. For this purpose, as shown in FIG. 2, the architecture 200 can further include a conversion unit 230. The converted operation parameter 206 output by the conversion unit 230 can be directly received by the coolant driving device 130 and the coolant driving device 130 operates according to the converted operation parameter 206 to drive the coolant flow. Figure 2

[0058] The above describes an example architecture 200 for temperature control. It should be understood that the division of the units in the architecture 200 and their functions are only exemplary and are not intended to limit the scope of the present disclosure.

[0059] ​​​Prediction of temperature and operating parameters

[0060] As briefly mentioned above with reference to Figure 2 In some embodiments, to predict the temperature indicator at time t and / or the operation parameter at time t, the prediction control unit 220 can take into account the temperature correlation. The following describes an example embodiment. Figure 4 Figure 4 A schematic diagram showing one example of the prediction control unit 220 according to some embodiments of the present disclosure is shown.

[0061] As mentioned above with reference to Figure 2 The temperature correlation 402 indicates the dependency of the temperature indicator of the cooling liquid on the operation parameter of the cooling liquid driving device 130 and the load of the target device 120. The temperature correlation 402 can be determined by analyzing the relationship between the historical temperature information of the cooling liquid, the historical operation information of the cooling liquid driving device 130 and the historical load of the target device 120.

[0062] In some embodiments, the temperature correlation 402 can be determined offline based on the historical information described above. In such embodiments, the electronic device 101 can read the locally stored temperature correlation 402, or receive the already determined temperature correlation 402 from other suitable devices.

[0063] In some embodiments, the temperature correlation 402 can be determined online by the electronic device 110. The electronic device 110 can dynamically update the temperature correlation 402 based on the temperature information, the operation information and the load of the previous period of time every certain period of time (e.g., periodically). In such embodiments, the dynamically updated temperature correlation 402 can better depict the relationship between the components of the liquid cooling system (e.g., the target device 120, the cooling liquid driving device 130).

[0064] Specifically, the prediction control unit 220 can determine the respective historical temperature indicators of the cooling liquid at a plurality of historical time instants before time t based on the historical temperature information 204. The prediction control unit 220 can determine the respective historical operation parameters of the cooling liquid driving device 130 at the plurality of historical time instants based on the historical operation information 203. Further, based on the respective historical temperature indicators, the respective historical operation parameters and the respective historical loads of the target device 120 at the plurality of historical time instants, the prediction control unit 220 can determine the respective parameters in the correlation, thereby deriving the temperature correlation 402. For example, the prediction control unit 220 can employ any suitable algorithm such as the least mean square (LMS) algorithm, the recursive least square (RLS) algorithm and the gradient descent method to determine the respective parameters in the correlation.

[0065] ​As an example of temperature indicator being temperature difference and operation parameter being power, the temperature correlation 402 can be represented by the following equation:

[0066]

[0067] wherein is the temperature difference of the cooling liquid at the inlet 141 and at the outlet 142 of the container 140 at the time t0, is the temperature difference at the time t0-1, Δt is related to the time span between the time t and the time t-1, i.e. the actual time difference between the time t-1 and the time t, and P represents the power of the cooling liquid driving device 130, represents the load of the target device 120 at the time t0, and a, C, U are equation parameters.

[0068] The parameters a, C, U can be determined based on historical load, historical power and historical temperature difference using a suitable algorithm such as the RLS algorithm. Specifically, when determining the temperature correlation 402, a plurality of historical times can be used as t0, respectively, so that a plurality of equations including the parameters a, C, U can be obtained based on equation (2). Then, the values of the parameters a, C, U can be determined using the RLS algorithm. In this way, the above-mentioned temperature correlation 402 is determined. In the above, temperature difference and power are used as examples to describe the temperature correlation, but this is only exemplary. For other types of temperature indicators and operation parameters, the temperature correlation can be determined in a similar way.

[0069] After obtaining the temperature correlation 402, the prediction control unit 220 can determine the predicted temperature indicator 401 of the cooling liquid at the time t based on the load prediction information 202, the historical operation information 203 and the historical temperature information 204 according to the temperature correlation 402. Specifically, the historical temperature information 204 can include the temperature indicator of the cooling liquid at the time t-1, the historical operation information 203 can include the operation parameter of the cooling liquid driving device 130 at the time t-1, and the predicted load information 202 includes the predicted load at the time t. According to the temperature correlation, the predicted temperature indicator 401 can be obtained based on the temperature indicator at the time t-1, the operation parameter at the time t-1 and the predicted load at the time t.

[0070] In some embodiments, the predicted temperature indicator 401 of the coolant at the time t determined by the prediction control unit 220 comprises a difference between the temperature of the coolant at the first location of the flow path and the temperature of the coolant at the second location. For example, the difference between the temperature of the coolant at the water inlet 141 of the container 140 and the temperature of the coolant at the water outlet 142 of the container 140 can be included. In the example described above, the time t can be taken as t0 in equation (2). The temperature difference at the time t-1, the power at the time t-1, and the predicted load at the time t can be applied to equation (2) to predict the temperature difference at the time t.

[0071] The above describes an example process of obtaining the predicted temperature indicator 401. The following describes an example process of predicting the operation parameter. Figure 4 The example process of predicting the operation parameter is continued to be described. In some embodiments, the prediction of the operation parameter can be implemented by using a model predictive control (MPC) algorithm. By using the MPC algorithm, a temperature control plan can be generated according to the predicted load and the like in a predetermined time range, and the first operation parameter that satisfies the temperature control target can be applied to the coolant driving device 130.

[0072] To this end, the prediction control unit 220 can further comprise a target construction unit 410 and an optimization unit 420. Specifically, the target construction unit 410 is configured to construct the temperature control target 403 for the target device 120. In the liquid cooling system, a basic target of the temperature control is to make the temperature indicator as close as possible to a preset reference temperature indicator. For example, the expected temperature difference is desired to be as close as possible to the reference temperature difference. The reference temperature indicator can be an optimal temperature indicator that guarantees the normal operation of the target device 120, or a target temperature indicator corresponding to a smaller power consumption of the coolant driving device 130. To this end, the temperature control target 403 at least comprises a temperature term for reducing the difference between the corresponding predicted temperature indicator at a plurality of times and the reference temperature indicator. The times include the time t and one or more times after the time t.

[0073] Further, an optional target of the temperature control is to achieve the expected temperature control effect with as low power consumption as possible. Accordingly, in some embodiments, the temperature control target 403 can additionally comprise a power consumption term for reducing the power consumption of the coolant driving device 130 at the above-mentioned plurality of times. In this way, it can be avoided that more is supplied than demanded, so as to reduce the power consumption of the liquid cooling system. The combination of the two targets is beneficial to the balance of supply and demand, and can enhance the stability and safety of the liquid cooling system in the case of failure.

[0074] Taking the temperature difference as the temperature indicator, the temperature control target 403 can be represented by the following equation:

[0075]

[0076] wherein J(t) represents a temperature control target for the time t, which can also be regarded as a loss function; is a temperature term; is a power consumption term; Q, R, N, T d respectively represent a state weighting coefficient, an input weighting coefficient, a time window, and a reference temperature indicator (in this example, a reference temperature difference), and N is an integer greater than 1. ΔP can represent a difference between a predicted power and a reference power of the cooling liquid driving device 130 at the time considered, or represent a difference between predicted powers of adjacent times.

[0077] The optimization unit 420 extracts the respective predicted loads of the target device 120 at the above-mentioned multiple times from the predicted load information 202. Then, the optimization unit 420 determines the parameter values of the predicted operation parameters 205 according to the temperature control target 403 based on the respective predicted loads, the predicted temperature indicator 401, and the temperature correlation 402. The optimization unit 420 can determine the parameter values of the operation parameters at the time t by minimizing the temperature control target 403. For example, by minimizing J(t), the powers P at the above-mentioned multiple times can be obtained, wherein the value of P corresponding to the time t can be used as the determined operation parameter to control the cooling liquid driving device 130.

[0078] In some embodiments, the optimization unit 420 can additionally consider constraint conditions in minimizing the temperature control target 403. That is, the optimization unit 430 can minimize the temperature control target 493 under one or more constraint conditions. As an example, the constraint conditions can include a value range of the predicted temperature indicator. That is, the temperature indicator at each time should not exceed the expected value range. For example, the constraint conditions can include upper and lower limits for the temperature difference. By considering the value range of the temperature indicator, it can be avoided that the temperature of the target device 120 is too high to cause abnormal operation.

[0079] Alternatively or additionally, the constraint conditions can include a value range of the respective operation parameters of the cooling liquid driving device 130 at the above-mentioned multiple times. For example, the constraint conditions can include upper and lower limits for the power of the cooling liquid driving device 130. By considering the value range of the operation parameters, it can be avoided that the power consumption of the cooling liquid driving device 130 is too large.

[0080] Still taking the example of using the temperature difference as the temperature indicator and taking the example of using the power as the operation parameter, the constraint condition regarding the value range of the predicted temperature indicator can be represented as formula (6), and the constraint condition regarding the value range of the operation parameter can be represented as formula (7):

[0081]

[0082]

[0083]

[0084] P min ≤ P(t+k-1) ≤ P max (7)

[0085] wherein denotes the minimum value of the temperature difference, denotes the maximum value of the temperature difference, P min denotes the minimum value of the power, P max denotes the maximum value of the power.

[0086] In this example, the temperature control target of formula (3) is minimized under the constraint conditions represented by formulas (6) and (7), so as to determine the predicted value of the operation parameter at time t.

[0087] The above reference Figures 2 to 4 describes the prediction of the operation parameter at time t. At time t, the predicted value of the operation parameter is applied to the cooling liquid driving device 130. That is, at time t, the cooling liquid driving device 130 will operate according to the determined operation parameter. Then, the temperature control enters the next stage, and the data such as the load of the target device 120 at time t, the temperature index of the cooling liquid at time t, etc. will be used as historical information for the determination of the operation parameter at time t+1. In this way, the temperature control of the liquid cooling system realizes a cycle process of feedback, adjustment and control. It is a self-learning MPC model based on business and temperature to control the temperature and ensure heat dissipation in the case of frequent changes in business.

[0088] In the traditional temperature control system based on model algorithm, the environmental information is implanted in the temperature control in the form of mathematical modeling, but the instability and model error are always difficult to solve. As one of the efficient algorithms in model algorithm, the efficiency of MPC is directly related to the modeling accuracy. However, in the case of complex environment and multiple influence factors, the modeling accuracy is reduced, and the efficiency of MPC is also greatly discounted. At the same time, the generalization of model algorithm is poor, and each model needs to be specially customized according to the environment.

[0089] In contrast, in the above-described embodiments of the present disclosure, the predicted load is introduced into the MPC model, which is obtained based on the analysis of multiple data. In this way, compared with the traditional scheme, the stability and robustness are increased, and the energy saving performance is also improved.

[0090] Further, machine learning models have good performance in building multi-region models with nonlinearity, non-stationarity, and time-varying, and are widely recognized for their performance in processing large amounts of data and regional data. Machine learning algorithms can learn from historical data to improve the model and optimize the control logic, and machine learning can also predict the heat dissipation needs of IT equipment through complex data analysis. As described above, in some embodiments, machine learning models can be combined with MPC to achieve more accurate and efficient temperature control. For example, a neural network is used to analyze and predict the load of the target device, and then the MPC algorithm is adjusted based on the predicted load, etc. In the combination of machine learning models and MPC, on the one hand, the MPC model can assist the machine learning model to mine and learn information in the data, and on the other hand, the analysis of multiple data and the prediction of the load can be completed by the machine learning model, and then the MPC model is controlled.

[0091] Example process

[0092] Figure 5 A flowchart of a process 500 for temperature control is shown in accordance with some embodiments of the present disclosure. The process 500 can be implemented at the electronic device 110. The process 500 is described below with reference to Figure 1 and Figure 2 The process 500.

[0093] At block 510, the electronic device 110 determines predicted load information 202 of the target device 120 based on historical operation information 201 associated with operation of the target device 120. The predicted load information 202 includes at least a predicted load of the target device 120 at a first time.

[0094] In some embodiments, the historical operation information includes a load of the target device 120 over a first historical time period that precedes the first time, and environmental factors experienced by the target device 120 over a second historical time period that precedes the first time.

[0095] At block 520, the electronic device 110 determines a predicted first temperature indicator of the coolant at the first time based on the predicted load, historical temperature information 204 of the coolant, and historical operation information 203 of the coolant driving device 130. The coolant is used to cool the target device 120, and the coolant driving device 130 is used to drive the flow of the coolant.

[0096] In some embodiments, the historical temperature information 204 comprises a second temperature indicator of the cooling liquid at a second time instance, and the historical operation information 203 comprises a second operation parameter of the cooling liquid driving device 130 at the second time instance, the second time instance being before the first time instance. The electronic device 110 determines the first temperature indicator comprises obtaining a correlation for cooling liquid temperature, the correlation indicating a dependency of a temperature indicator of the cooling liquid on an operation parameter of the cooling liquid driving device 130 and a load of the target device 120. The electronic device 110 predicts the first temperature indicator based on the predicted load, the second temperature indicator and the second operation parameter according to the correlation.

[0097] In some embodiments, to obtain the correlation, the electronic device 110 determines, based on the historical temperature information 204, respective historical temperature indicators of the cooling liquid at a plurality of historical time instances before the first time instance. The electronic device 110 determines, based on the historical operation information, respective historical operation parameters of the cooling liquid driving device 130 at the plurality of historical time instances. The electronic device 110 derives the correlation based on the respective historical temperature indicators, the respective historical operation parameters 203 and respective historical loads of the target device 120 at the plurality of historical time instances.

[0098] In some embodiments, the first temperature indicator comprises a difference between a temperature of the cooling liquid at a first location of the flow path and a temperature of the cooling liquid at a second location.

[0099] At block 530, the prediction control unit 220 in the electronic device 110 determines the first operation parameter of the cooling liquid driving device 130 at the first time instance based on at least the first temperature indicator.

[0100] In some embodiments, the predicted load information comprises respective predicted loads of the target device at a plurality of time instances, the plurality of time instances comprising at least the first time instance and a third time instance after the first time instance. To determine the first operation parameter, the prediction control unit 220 constructs a temperature control objective, the temperature control objective being at least for reducing a difference between respective predicted temperature indicators at the plurality of time instances and a reference temperature indicator. The prediction control unit 220 determines a parameter value of the first operation parameter based on the respective predicted loads, the first temperature indicator and a correlation for cooling liquid temperature according to the temperature control objective, the correlation indicating a dependency of a temperature indicator of the cooling liquid on an operation parameter of the cooling liquid driving device 130 and a load of the target device.

[0101] In some embodiments, the temperature control objective is further for reducing a power consumption of the cooling liquid driving device 130 at the plurality of time instances.

[0102] In some embodiments, the determination of the parameter value of the first operation parameter is further according to at least one of a range of values for the respective predicted temperature indicators and a range of values of respective operation parameters of the cooling liquid driving device 130 at the plurality of time instances.

[0103] Example apparatus and device

[0104] Figure 6 A schematic structural block diagram of an apparatus 600 for temperature control is shown according to some embodiments of the present disclosure. The apparatus 600 can be implemented as or included in the electronic device 110. Various modules / components in the apparatus 600 can be implemented by hardware, software, firmware, or any combination thereof.

[0105] As shown, the apparatus 600 includes a load information determination module 610 configured to determine predicted load information of a target device based on historical operation information associated with operation of the target device, the predicted load information comprising at least a predicted load of the target device at a first time instant. The apparatus 600 further includes a temperature indicator determination module 620 configured to determine a predicted first temperature indicator of a cooling liquid at the first time instant based on the predicted load, historical temperature information of the cooling liquid, and historical operation information of a cooling liquid driving device, the cooling liquid being used to cool the target device, and the cooling liquid driving device being used to drive flow of the cooling liquid. The apparatus 600 further includes an operation parameter determination module 630 configured to determine a first operation parameter of the cooling liquid driving device at the first time instant based on at least the first temperature indicator.

[0106] In some embodiments, the historical temperature information comprises a second temperature indicator of the cooling liquid at a second time instant, and the historical operation information comprises a second operation parameter of the cooling liquid driving device at the second time instant, the second time instant being prior to the first time instant. The temperature indicator determination module 620 comprises: an association relationship obtaining module configured to obtain an association relationship for the cooling liquid temperature, the association relationship indicating dependency of the temperature indicator of the cooling liquid on the operation parameter of the cooling liquid driving device and the load of the target device; and a temperature indicator prediction module configured to predict the first temperature indicator according to the association relationship based on the predicted load, the second temperature indicator, and the second operation parameter.

[0107] In some embodiments, the association relationship obtaining module comprises: a historical temperature indicator determination module configured to determine respective historical temperature indicators of the cooling liquid at a plurality of historical time instants prior to the first time instant based on the historical temperature information; a historical operation parameter determination module configured to determine respective historical operation parameters of the cooling liquid driving device at the plurality of historical time instants based on the historical operation information; and an association relationship determination module configured to derive the association relationship based on the respective historical temperature indicators, the respective historical operation parameters, and respective historical loads of the target device at the plurality of historical time instants.

[0108] In some embodiments, the first temperature indicator comprises a difference between a temperature of the cooling liquid at a first location of the flow path and a temperature of the cooling liquid at a second location of the flow path.

[0109] In some embodiments, the predicted load information comprises respective predicted loads of the target device at a plurality of time instants, the plurality of time instants comprising at least the first time instant and a third time instant after the first time instant. The operation parameter determination module 630 comprises a temperature control target construction module configured to construct a temperature control target for reducing a difference between respective predicted temperature indicators at the plurality of time instants and a reference temperature indicator, and a parameter value determination module configured to determine, based on the respective predicted loads, the first temperature indicator, and a correlation for a temperature of the coolant, a parameter value of the first operation parameter according to the temperature control target, the correlation indicating a dependency of a temperature indicator of the coolant on the operation parameter of the coolant driving device and the load of the target device.

[0110] In some embodiments, the temperature control target is further for reducing power consumption of the coolant driving device at the plurality of time instants.

[0111] In some embodiments, the determining the parameter value of the first operation parameter is further according to at least one of a range of values for the respective predicted temperature indicators, and a range of values of the respective operation parameters of the coolant driving device at the plurality of time instants.

[0112] In some embodiments, the historical operation information comprises a load of the target device in a first historical time period before the first time instant, and an environmental factor experienced by the target device in a second historical time period before the first time instant.

[0113] Figure 7 A block diagram of an electronic device 700 in which one or more embodiments of the disclosure can be implemented is shown. It should be understood that Figure 7 The electronic device 700 shown is merely exemplary and should not be construed as limiting the scope of the embodiments described herein. Figure 7 The electronic device 700 shown can be used to implement Figure 1 the electronic device 110.

[0114] As Figure 7 shown, the electronic device 700 is in the form of a general electronic device. Components of the electronic device 700 can include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 can be a real or virtual processor and is capable of executing various processing in accordance with programs stored in the memory 720. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 700.

[0115] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any available media that is accessible by the electronic device 700 and includes both volatile and nonvolatile media, removable and non-removable media. The memory 720 can be volatile (such as register, cache, RAM), non-volatile (such as ROM, EEPROM, flash memory), or some combination of the two. The storage device 730 can be a removable or non-removable media, and can include machine-readable media, such as flash drives, magnetic disks, or any other medium that can be used to store information and / or data (e.g., training data for training) and that can be accessed by the electronic device 700.

[0116] The electronic device 700 can further include additional removable / non-removable, volatile / nonvolatile storage media. Although not shown in the electronic device 700, common Figure 7 buses (not shown) via one or more data media interfaces. The memory 720 can include a computer program product 725 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0117] The communication unit 740 enables communications with other electronic devices over a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented in a single computing cluster or a plurality of computer machines capable of communicating with one another over a communication connection. As such, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes.

[0118] The input device 750 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 760 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through the communication unit 740, with one or more devices that enable a user to interact with the electronic device 700, or with any devices (e.g., a network card, a modem, etc.) that enables the electronic device 700 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0119] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0120] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0121] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0122] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0123] The computer program product of the present disclosure can have a signal including said computer program. This signal can be electronic, electromagnetic, optical, or any other suitable type of signal. Such a signal can be provided through a communication connection, such as electrical wiring, optical fiber, wireless interface, etc. Examples of computer program products include computer program implemented on a personal computer, server, or other networked device. A non-transitory computer readable medium, such as a floppy disk, CD-ROM, DVD-ROM, Blu-ray Disc, hard disk, or memory stick, can also be used to implement the present disclosure. The computer program product of the present disclosure can also be provided as a service to download and use the computer program over a network, such as the Internet.

[0124] Having described several implementations of the present disclosure, it will be clear to those skilled in the art that many modifications, additions, and substitutions are possible without departing from the scope and spirit of the described implementations. Many modifications and variations of the present disclosure are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims, the present disclosure can be practiced otherwise than as specifically described. While the present disclosure has been described with reference to the implementation figures, it will be understood by those skilled in the art that various changes can be made and equivalents can be substituted for elements thereof without departing from the scope of the present disclosure. In addition, many modifications can be made to adapt to a particular situation and the teachings of the present disclosure to a specific implementation, without departing from the central novel teachings of the application. The implementation(s) illustrated and described herein are meant only to serve as examples. Departures in form and detail are within the scope of the disclosure. Therefore, one skilled in the art can restructure the implementation(s) as needed, while still adhering to the principles of the present disclosure.

Claims

1. A temperature control method, comprising: determining predicted load information of a target device based on historical operation information associated with operation of the target device, the predicted load information comprising at least a predicted load of the target device at a first time instant; determining a predicted first temperature indicator of a cooling fluid at the first time instant according to a correlation for cooling fluid temperature based on the predicted load, historical temperature information of the cooling fluid, and historical operation information of a cooling fluid driving device, the cooling fluid being used to cool the target device and the cooling fluid driving device being used to drive flow of the cooling fluid, the correlation indicating dependency of temperature indicators of the cooling fluid on operation parameters of the cooling fluid driving device and load of the target device, and the correlation being periodically updated, the first temperature indicator comprising a difference between temperature of the cooling fluid at a first location and temperature of the cooling fluid at a second location of a flow path; and determining a first operation parameter of the cooling fluid driving device at the first time instant based at least on the first temperature indicator. 2.The method of claim 1, wherein the historical temperature information comprises a second temperature indicator of the cooling fluid at a second time instant, the historical operation information comprises a second operation parameter of the cooling fluid driving device at the second time instant, the second time instant being before the first time instant, and determining the first temperature indicator comprises: predicting the first temperature indicator according to the correlation based on the predicted load, the second temperature indicator, and the second operation parameter. 3.The method of claim 2, wherein the correlation is obtained by: determining respective historical temperature indicators of the cooling fluid at a plurality of historical time instants before the first time instant based on the historical temperature information; determining respective historical operation parameters of the cooling fluid driving device at the plurality of historical time instants based on the historical operation information; and deriving the correlation based on the respective historical temperature indicators, the respective historical operation parameters, and respective historical loads of the target device at the plurality of historical time instants. 4.The method of claim 1, wherein the predicted load information comprises respective predicted loads of the target device at a plurality of time instants, the plurality of time instants comprising at least the first time instant and a third time instant after the first time instant, and determining the first operation parameter comprises: constructing a temperature control objective, the temperature control objective being used at least to reduce difference between respective predicted temperature indicators at the plurality of time instants and a reference temperature indicator; and determining a parameter value of the first operation parameter according to the temperature control objective based on the respective predicted loads, the first temperature indicator, and the correlation for cooling fluid temperature. 5.The method of claim 4, wherein the temperature control objective is further used to reduce power consumption of the cooling fluid driving device at the plurality of time instants. 6.The method of claim 4, wherein determining the parameter value of the first operation parameter is further according to at least one of: a range of values for the respective predicted temperature indicators, ​ a range of values of a corresponding operation parameter of the coolant driving device at the plurality of time instants.

7. The method of claim 1, wherein the historical operation information comprises: a load of the target device in a first historical time period before the first time instant, an environmental factor experienced by the target device in a second historical time period before the first time instant.

8. An apparatus for temperature control, comprising: a load information determination module configured to determine predicted load information of a target device based on historical operation information associated with operation of the target device, the predicted load information comprising at least a predicted load of the target device at a first time instant; a temperature indicator determination module configured to determine, based on the predicted load, historical temperature information of a coolant and historical operation information of a coolant driving device, a predicted first temperature indicator of the coolant at the first time instant according to a correlation for coolant temperature, the coolant being used to cool the target device and the coolant driving device being used to drive flow of the coolant, the correlation indicating dependency of temperature indicators of the coolant on operation parameters of the coolant driving device and loads of the target device, and the correlation being periodically updated, the first temperature indicator comprising a difference between a temperature of the coolant at a first location and a temperature of the coolant at a second location of a flow path; and an operation parameter determination module configured to determine, based on at least the first temperature indicator, a first operation parameter of the coolant driving device at the first time instant.

9. An electronic device, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit cause the electronic device to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, the computer program being executable by a processor to implement the method according to any one of claims 1-7.

Images