Liquid cooling and air cooling combined control method, device, equipment, medium and product

Abstract

The invention provides a liquid cooling and air cooling combined control method and device, equipment, a medium and a product, and relates to the field of financial science and technology or other related fields. According to the method, a refrigeration result corresponding to each group of to-be-selected control parameters is obtained by combining a refrigeration result prediction model according to the obtained total power of a server and a plurality of groups of to-be-selected control parameters. And each refrigeration result is screened according to the liquid cooling refrigerating capacity and the air cooling refrigerating capacity in each refrigeration result and the air inlet temperature of each cabinet in the machine room, a target refrigeration result is obtained, and the liquid cooling system and the air cooling system are controlled to operate according to the to-be-selected control parameters corresponding to the target refrigeration result. According to the scheme, the refrigeration results are screened according to the liquid cooling refrigeration capacity, the air cooling refrigeration capacity and the air inlet temperature, the to-be-selected control parameters corresponding to the target refrigeration result obtained through screening are used for controlling the liquid cooling system and the air cooling system to operate, and the total refrigeration energy consumption is effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a combined control method, device, equipment, medium and product of liquid cooling and air cooling. Background Art

[0002] With the development of cloud computing technology, data centers have also developed as the physical platform of cloud computing. Data centers are composed of computer rooms, which have multiple cabinets and servers installed in them. How to ensure that the temperature of the server will not be too high during operation, thereby ensuring the computing efficiency of the server, is a problem that people are concerned about.

[0003] In the prior art, in order to cool the computer room, two refrigeration systems are installed in the computer room, namely a liquid cooling system and an air cooling system. The liquid cooling system and the air cooling system are independent, and the staff controls the two refrigeration systems respectively according to the situation of the computer room.

[0004] However, since the two refrigeration systems are controlled independently, the energy consumption of the two refrigeration systems is different, which will result in a higher total refrigeration energy consumption. Summary of the invention

[0005] The present application provides a combined control method, device, equipment, medium and product of liquid cooling and air cooling, which is used to solve the problem of high total refrigeration energy consumption caused by separate control of the liquid cooling system and the air cooling system in the prior art.

[0006] In a first aspect, the present application provides a combined control method of liquid cooling and air cooling, comprising:

[0007] Obtaining the total power of the server and multiple groups of candidate control parameters, each group of the candidate control parameters comprising the secondary side pressure difference and the secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system;

[0008] According to the total power of the server and each group of the control parameters to be selected, and a cooling result prediction model, a cooling result corresponding to each group of the control parameters to be selected is obtained, wherein the cooling result prediction model is a pre-trained neural network model that calculates the cooling result according to the total power of the server and the control parameters to be selected;

[0009] According to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain a target cooling result;

[0010] The operation of the liquid cooling system and the air cooling system are controlled according to the selected control parameters corresponding to the target cooling result.

[0011] In a second aspect, the present application provides a combined control device for liquid cooling and air cooling, comprising:

[0012] An acquisition module, used to acquire the total power of the server and multiple groups of candidate control parameters, each group of the candidate control parameters including the secondary side pressure difference and the secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system;

[0013] Processing modules for:

[0014] According to the total power of the server and each group of the control parameters to be selected, and a cooling result prediction model, a cooling result corresponding to each group of the control parameters to be selected is obtained, wherein the cooling result prediction model is a pre-trained neural network model that calculates the cooling result according to the total power of the server and the control parameters to be selected;

[0015] According to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain a target cooling result;

[0016] A control module is used to control the operation of the liquid cooling system and the air cooling system according to the selected control parameters corresponding to the target cooling result.

[0017] In a third aspect, the present application provides an electronic device, including:

[0018] Processor, memory, communication interface;

[0019] The memory is used to store executable instructions of the processor;

[0020] Wherein, the processor is configured to execute the combined control method of liquid cooling and air cooling as described in any one of the first aspects by executing the executable instructions.

[0021] In a fourth aspect, the present application provides a readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the combined control method of liquid cooling and air cooling as described in any one of the first aspects is implemented.

[0022] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the combined control method of liquid cooling and air cooling as described in any one of the first aspects.

[0023] The combined control method, device, equipment, medium and product of liquid cooling and air cooling provided in the present application obtain the cooling result corresponding to each group of the selected control parameters by combining the cooling result prediction model based on the acquired total server power and multiple groups of the selected control parameters. Then, according to the liquid cooling cooling capacity, air cooling cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain the target cooling result, and then the operation of the liquid cooling system and the air cooling system is controlled according to the selected control parameters corresponding to the target cooling result. This solution effectively reduces the total cooling energy consumption by screening the cooling results according to the liquid cooling cooling capacity, air cooling cooling capacity and air inlet temperature, and using the selected control parameters corresponding to the screened target cooling results to control the operation of the liquid cooling system and the air cooling system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0025] Figure 1 A schematic diagram of the architecture of the liquid cooling system provided for this application;

[0026] Figure 2 A schematic diagram of a flow chart of a first embodiment of a combined control method for liquid cooling and air cooling provided in the present application;

[0027] Figure 3 A schematic flow chart of a second embodiment of the combined control method for liquid cooling and air cooling provided in the present application;

[0028] Figure 4a A schematic diagram of a flow chart of a third embodiment of a combined control method for liquid cooling and air cooling provided in the present application;

[0029] Figure 4b A schematic diagram of the principle of the refrigeration result prediction model provided for this application;

[0030] Figure 5 A schematic diagram of the structure of an embodiment of a combined control device for liquid cooling and air cooling provided in the present application;

[0031] Figure 6 A schematic diagram of the structure of an electronic device provided in this application.

[0032] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0034] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] It should be noted that the combined control method, device, equipment, medium and product of liquid cooling and air cooling provided in the present application can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the combined control method, device, equipment, medium and product of liquid cooling and air cooling provided in the present application is not limited.

[0036] With the development of cloud computing technology, data centers have also developed as the physical platform of cloud computing. Data centers are composed of computer rooms, which have multiple cabinets and servers installed in them. As the computing load of servers continues to increase, the power of servers is also getting higher and higher, and the temperature of servers will rise. How to ensure that the temperature of servers will not be too high during operation, thereby ensuring the computing efficiency of servers, is a problem that people are concerned about.

[0037] In the prior art, in order to cool the computer room, two refrigeration systems are installed in the computer room, namely a liquid cooling system and an air cooling system. The liquid cooling system and the air cooling system are independent, and the staff controls the two refrigeration systems respectively according to the situation of the computer room.

[0038] For example, Figure 1 The schematic diagram of the liquid cooling system provided for this application is as follows: Figure 1As shown, the liquid cooling system includes a primary side and a secondary side. The primary side includes an external cold source, and the secondary side includes multiple cooling distribution units (CDUs) and multiple cabinets. Only two CDUs and two cabinets are shown in the figure, and each CDU exchanges heat with a cabinet through the secondary side heat exchange network. The external cold source exchanges heat with each CDU through the primary side heat exchange network. The dotted line in the heat exchange network in the figure represents the liquid supply part of the heat exchange network, and the solid line in the heat exchange network represents the return liquid part of the heat exchange network. There is coolant in the heat exchange network, and heat transfer is achieved by raising and lowering the temperature of the coolant. The primary side is also called the outdoor side, and the secondary side is also called the indoor side.

[0039] The liquid cooling system is an indirect liquid cooling system, and the coolant does not come into direct contact with the server components. The technical principle is that the high-heat generating components of the server transfer heat to the secondary heat exchange network through heat-conducting components, and then transfer the heat to the CDU by circulating the coolant inside the secondary heat exchange network. The CDU transfers heat to the primary heat exchange network through heat-conducting components, and then transfers the heat to the external cold source by circulating the coolant inside the primary heat exchange network.

[0040] The air cooling system in the computer room includes multiple air cooling units, each of which dissipates heat for the low-heat generating components of the server. The air cooling unit can be an air conditioner. The air cooling system is necessary for two reasons: first, the low-heat generating components of the liquid-cooled server, such as mechanical hard disks, cannot cover the heat conducting part and can only be dissipated through the air cooling system; second, the internal environment of the computer room also needs to be cooled.

[0041] The server dissipates heat during operation, and the heat dissipated is represented by the power of the server operation. The liquid cooling system and the air cooling system perform cooling to generate cooling capacity, and the cooling capacity is represented by the cooling power. When the sum of the cooling power of the liquid cooling system and the air cooling system is greater than or equal to the power of the server operation, it can be ensured that the heat dissipated by the server can be taken away by the liquid cooling system and the air cooling system.

[0042] When the staff controls the two refrigeration systems separately according to the situation of the computer room, they only consider that the sum of the refrigeration power of the liquid cooling system and the air cooling system is greater than or equal to the power of the server operation. However, when producing the same cooling capacity, the energy consumption of the liquid cooling system is lower than that of the air cooling system. Therefore, the existing technology does not consider the relationship between the liquid cooling system and the air cooling system, and controls the two refrigeration systems separately, which will lead to the problem of high total refrigeration energy consumption.

[0043] In view of the problems existing in the prior art, the inventors found in the process of studying the combined control method of liquid cooling and air cooling that multiple groups of candidate control parameters can be determined first, and each group of candidate control parameters includes the secondary side pressure difference and secondary side liquid supply temperature of each CDU in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system. The secondary side pressure difference refers to the pressure difference of the refrigerant liquid in the liquid supply part and the return liquid part of the secondary side pipe network, and the secondary side liquid supply temperature refers to the temperature of the refrigerant liquid in the liquid supply part of the secondary side pipe network. The liquid cooling system and the air cooling system can remove the heat emitted by the server when operating according to each group of candidate control parameters.

[0044] Then, the cooling result corresponding to each group of candidate control parameters combined with the total power of the server is determined, and the candidate control parameters corresponding to the cooling result whose air inlet temperature of the cabinet meets the requirements and whose total cooling energy consumption is low are selected from all cooling results, and then the liquid cooling system and the air cooling system are controlled to operate according to the candidate control parameters, which can reduce the total cooling power consumption. Based on the above inventive concept, a joint control scheme of liquid cooling and air cooling in this application is designed.

[0045] The executor of the combined control method of liquid cooling and air cooling in the present application may be a computer, a server, a terminal device, etc. The present application does not limit it and the following description will be made using a computer as an example.

[0046] The following is an example of an application scenario of the combined control method of liquid cooling and air cooling provided in the present application.

[0047] For example, in this application scenario, a liquid cooling system and an air cooling system are deployed in the computer room to dissipate heat for the server. When the cooling capacity needs to be adjusted, the computer first obtains the total power of the server and multiple groups of candidate control parameters, and then obtains the cooling result corresponding to each group of candidate control parameters based on the total power of the server and each group of candidate control parameters, as well as the cooling result prediction model.

[0048] The computer then screens each cooling result according to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result to obtain a target cooling result, so that the air inlet temperature of each cabinet in the target cooling result meets the requirements, and the ratio of the air cooling capacity to the liquid cooling capacity in the target cooling result is low. The operation of the liquid cooling system and the air cooling system is controlled according to the selected control parameters corresponding to the target cooling result, which can reduce the total cooling energy consumption.

[0049] It should be noted that the above scenario is only an example of an application scenario provided by an embodiment of the present application. The embodiment of the present application does not limit the actual form of the various devices included therein, nor does it limit the interaction method between the devices. In the specific application of the solution, it can be set according to actual needs.

[0050] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0051] Figure 2 This is a flow chart of the first embodiment of the combined control method of liquid cooling and air cooling provided by the present application. The present embodiment of the present application describes how the computer determines the cooling result corresponding to each group of candidate control parameters according to the total power of the server, and then controls the operation of the liquid cooling system and the air cooling system according to the candidate control parameters corresponding to the target cooling result obtained from the screening. The method in this embodiment can be implemented by software, hardware, or a combination of software and hardware. Figure 2 As shown, the combined control method of liquid cooling and air cooling specifically includes the following steps:

[0052] S201: Obtain the total power of the server and multiple groups of control parameters to be selected.

[0053] In this step, when the cooling capacity needs to be adjusted, the computer first obtains the total power of the server and multiple groups of control parameters to be selected.

[0054] Each group of candidate control parameters includes the secondary side pressure difference and secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system.

[0055] It should be noted that the total server power is the sum of the power of all servers running in the computer room.

[0056] It should be noted that the computer may obtain the total server power and multiple groups of control parameters to be selected in the following manner: when the computer detects that the total server power change rate does not fall within the preset power change range, the computer obtains the total server power and multiple groups of control parameters to be selected. It may also be: the total server power and multiple groups of control parameters to be selected are obtained at every preset time interval. It may also be: when a control instruction is received, the total server power and multiple groups of control parameters to be selected are obtained. The embodiment of the present application does not limit the manner in which the computer obtains the total server power and multiple groups of control parameters to be selected, and it may be determined according to actual conditions.

[0057] By obtaining the total server power and multiple groups of selectable control parameters in multiple ways, the flexibility of controlling the air cooling system and the liquid cooling system can be improved.

[0058] It should be noted that the server obtains the total power of the server once every preset monitoring time interval. When the total power of the server is obtained for the first time, the change rate of the total power of the server is determined to be 0. After each subsequent acquisition of the total power of the server, the total power of the server is subtracted from the total power of the server obtained last time and then divided by the total power of the server this time to obtain the change rate of the total power of the server this time. The preset monitoring time can be 1 second, 1 minute, 10 minutes, 30 minutes, etc., the preset power change range can be [-20%, 20%], [-10%, 10%], [-5%, 5%], etc., the preset time can be 1 second, 1 minute, 10 minutes, 30 minutes, etc. The embodiment of the present application does not limit the preset monitoring time, the preset power change range, and the preset time, and can be determined according to actual conditions.

[0059] It should be noted that for each set of selectable control parameters, each cooling capacity distribution unit in the liquid cooling system operates according to the secondary side pressure difference and secondary side liquid supply temperature of the cooling capacity distribution unit in the selectable control parameters, and each air cooling unit in the air cooling system operates according to the temperature setting value of the air cooling unit in the selectable control parameters. No matter how large the current total power of the server is, the total cooling capacity of the air cooling system and the liquid cooling system is greater than the heat dissipated by the server.

[0060] S202: Obtaining a cooling result corresponding to each group of candidate control parameters according to the total power of the server and each group of candidate control parameters, and a cooling result prediction model.

[0061] In this step, after the computer obtains the total power of the server and each group of candidate control parameters, it obtains the cooling result corresponding to each group of candidate control parameters according to the total power of the server and each group of candidate control parameters, as well as the cooling result prediction model.

[0062] Each cooling result includes liquid cooling capacity, air cooling capacity and air inlet temperature of each cabinet in the computer room. The cooling result prediction model is a pre-trained neural network model that calculates the cooling result based on the total power of the server and the selected control parameters.

[0063] Specifically, for each group of candidate control parameters, the candidate control parameters and the total power of the server are input into the cooling result prediction model to obtain the cooling result corresponding to the candidate control parameters.

[0064] The accuracy of the refrigeration result can be improved by determining the instruction result through the refrigeration result prediction model.

[0065] S203: Filter each cooling result according to the liquid cooling capacity, the air cooling capacity, and the air inlet temperature of each cabinet in the computer room in each cooling result to obtain a target cooling result.

[0066] In this step, after the computer obtains the cooling results corresponding to each set of candidate control parameters, in order to screen out the cooling results with smaller total cooling power consumption, it is necessary to screen each cooling result according to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result to obtain the target cooling result.

[0067] Specifically, for each cooling result, if the air inlet temperature of each cabinet in the cooling result belongs to the preset temperature range, the cooling result is used as the first cooling result. Since the air inlet temperature of the cabinet belongs to the preset temperature range, the heat dissipation of the low-heat generating components in the server can be ensured in time, so the preset temperature range is used for screening.

[0068] It should be noted that the preset temperature range can be 15 degrees Celsius-30 degrees Celsius, 18 degrees Celsius-27 degrees Celsius, and 20 degrees Celsius-25 degrees Celsius. The embodiment of the present application does not limit the preset temperature range and can be determined according to actual conditions.

[0069] Furthermore, for each first refrigeration result, the ratio of the air-cooling refrigeration capacity to the liquid-cooling refrigeration capacity in the first refrigeration result is used as the refrigeration ratio of the first refrigeration result; and then, according to the refrigeration ratio of each first refrigeration result, each first refrigeration result is screened to obtain a target refrigeration result.

[0070] Since the liquid cooling system has lower energy consumption, the cooling result with lower cooling ratio is selected as the target cooling result.

[0071] In one implementation, the refrigeration result with the smallest refrigeration ratio among all the first refrigeration results is used as the target refrigeration result.

[0072] In another implementation, all the first refrigeration results whose refrigeration ratio is less than a preset ratio are used as the second refrigeration results; and then one refrigeration result is selected from all the second refrigeration results as the target refrigeration result.

[0073] It should be noted that the preset ratio may be 0.1, 0.25, 0.45, etc. The embodiment of the present application does not limit the preset ratio, which may be determined according to actual conditions.

[0074] The cooling results are screened by liquid cooling capacity, air cooling capacity and air inlet temperature to obtain the target cooling results, so that the liquid cooling system and the air cooling system operate according to the target cooling results. Not only does the air inlet temperature meet the requirements, but the total cooling energy consumption is also low.

[0075] It should be noted that in order to further ensure that the total cooling capacity of the liquid cooling system and the air cooling system is greater than or equal to the heat dissipated by the server, after obtaining the first cooling result, all cooling results in which the sum of the liquid cooling capacity and the air cooling capacity is less than the total power of the server are eliminated to obtain the third cooling result, and then each third cooling result is screened according to the cooling ratio of each third cooling result to obtain the target cooling result.

[0076] S204: Controlling the operation of the liquid cooling system and the air cooling system according to the selected control parameters corresponding to the target cooling result.

[0077] In this step, after the computer obtains the target cooling result, it controls the operation of the liquid cooling system and the air cooling system according to the selected control parameters corresponding to the target cooling result, that is, each cooling capacity distribution unit in the liquid cooling system is controlled to operate according to the secondary side pressure difference and the secondary side liquid supply temperature of the cooling capacity distribution unit in the selected control parameters, and each air cooling unit in the air cooling system is controlled to operate according to the temperature setting value of the air cooling unit in the selected control parameters. The cooling capacity of the liquid cooling system can reach the liquid cooling capacity in the target cooling result, the cooling capacity of the air cooling system can reach the air cooling capacity in the target cooling result, and the air inlet temperature of each cabinet is within the preset temperature range.

[0078] The combined control method of liquid cooling and air cooling provided in this embodiment obtains the cooling result corresponding to each group of candidate control parameters by combining the cooling result prediction model based on the acquired total server power and multiple groups of candidate control parameters. Then, according to the liquid cooling cooling capacity, air cooling cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain the target cooling result, and then the operation of the liquid cooling system and the air cooling system is controlled according to the candidate control parameters corresponding to the target cooling result. Compared with the prior art that controls the liquid cooling system and the air cooling system separately, this solution screens the cooling results according to the liquid cooling cooling capacity, air cooling cooling capacity and air inlet temperature, and uses the candidate control parameters corresponding to the target cooling results obtained by screening to control the operation of the liquid cooling system and the air cooling system, thereby effectively reducing the total cooling energy consumption.

[0079] Figure 3 This is a flow chart of the second embodiment of the combined control method of liquid cooling and air cooling provided by the present application. Based on the above embodiment, the present embodiment of the present application describes the situation where the computer generates multiple sets of candidate control parameters before obtaining the total power of the server and multiple sets of candidate control parameters. Figure 3 As shown, the combined control method of liquid cooling and air cooling specifically includes the following steps:

[0080] S301: Obtaining a preset secondary side pressure difference range of each cooling capacity distribution unit, a preset secondary side liquid supply temperature range of each cooling capacity distribution unit, and a preset temperature range of each air cooling unit.

[0081] In order to improve the efficiency of controlling the air cooling system and the liquid cooling system, multiple groups of candidate control parameters can be generated before control.

[0082] In this step, the preset secondary side pressure difference range of each cooling capacity distribution unit, the preset secondary side liquid supply temperature range of each cooling capacity distribution unit, and the preset temperature range of each air cooling unit are first obtained.

[0083] It should be noted that the preset secondary side pressure difference range can be 1 kPa-10 kPa, 5 kPa-15 kPa, 7 kPa-30 kPa, etc., the preset secondary side liquid supply temperature range can be 20 degrees Celsius-50 degrees Celsius, 30 degrees Celsius-45 degrees Celsius, 35 degrees Celsius-40 degrees Celsius, etc., the preset temperature range can be 10 degrees Celsius-40 degrees Celsius, 15 degrees Celsius-30 degrees Celsius, 20 degrees Celsius-35 degrees Celsius, etc. The embodiment of the present application does not limit the preset secondary side pressure difference range, the preset secondary side liquid supply temperature range, and the preset temperature range, and can be determined according to actual conditions.

[0084] S302: Generate multiple groups of control parameters to be selected according to each preset secondary side pressure difference range, each preset secondary side liquid supply temperature range and each preset temperature range.

[0085] In this step, after the computer obtains the preset secondary side pressure difference range, the preset secondary side liquid supply temperature range, and the preset temperature range, it generates multiple groups of candidate control parameters according to each preset secondary side pressure difference range, each preset secondary side liquid supply temperature range, and each preset temperature range.

[0086] Specifically, for the preset secondary side pressure difference range of each cooling distribution unit, each interval preset pressure difference is taken from the preset secondary side pressure difference range to obtain the pressure difference set corresponding to the cooling distribution unit. For the preset secondary side liquid supply temperature range of each cooling distribution unit, each interval first preset temperature is taken from the preset secondary side liquid supply temperature range to obtain the first temperature set corresponding to the cooling distribution unit. For the preset temperature range of each air cooling unit, each interval second preset temperature is taken from the preset temperature range to obtain the second temperature set corresponding to the air cooling unit.

[0087] Then, elements are selected from each pressure difference set, each first temperature set, and each second temperature set respectively, and then combined to obtain multiple groups of candidate control parameters, each group of candidate control parameters includes the secondary side pressure difference and secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system. The number of groups of candidate control parameters is equal to the product of the number of elements in each pressure difference set, the number of elements in each first temperature set, and the number of elements in each second temperature set. At least one of the secondary side pressure difference, secondary side liquid supply temperature, and temperature setting value of different groups of candidate control parameters is different.

[0088] Exemplarily, there is a pressure difference set, a first temperature set and a second temperature set, the pressure difference set is {a, b}, the first temperature set is {c, d, e}, and the second temperature set is {f, g}. A total of 12 groups of control parameters to be selected are: {a, c, f}, {a, c, g}, {a, d, f}, {a, d, g}, {a, e, f}, {a, e, g}, {b, c, f}, {b, c, g}, {b, d, f}, {b, d, g}, {b, e, f}, {b, e, g}.

[0089] It should be noted that the preset pressure difference can be 1 kPa, 2 kPa, 5 kPa, etc., the first preset temperature can be 1 degree Celsius, 2 degrees Celsius, 5 degrees Celsius, etc., and the second preset temperature can be 1 degree Celsius, 2 degrees Celsius, 5 degrees Celsius, etc. The embodiment of the present application does not limit the preset pressure difference, the first preset temperature, and the second preset temperature, and they can be determined according to actual conditions.

[0090] The combined control method of liquid cooling and air cooling provided in this embodiment can improve the control efficiency when subsequently controlling the liquid cooling system and the air cooling system by first determining the candidate control parameters. In addition, the liquid cooling system and the air cooling system can meet the heat dissipation requirements of the computer room when they are operated according to each set of candidate control parameters.

[0091] Figure 4a This is a flow chart of the third embodiment of the combined control method of liquid cooling and air cooling provided by the present application. Based on the above embodiment, the present embodiment trains the initial neural network model by a computer to obtain the result of the refrigeration result prediction model. Figure 4a As shown, the combined control method of liquid cooling and air cooling specifically includes the following steps:

[0092] S401: Select a set of training control parameters from a training data set.

[0093] In this step, in order to train the cooling result prediction model, it is necessary to first select a set of training control parameters from the training data set. Each set of training control parameters includes the total server power, the secondary side pressure difference and secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system. Each set of training control parameters has a corresponding real cooling result, which includes the liquid cooling capacity, air cooling capacity, and the air inlet temperature of each cabinet in the computer room.

[0094] S402: Input the training control parameters into the initial neural network model to obtain the refrigeration training results.

[0095] In this step, after the computer obtains the training control parameters, the training control parameters are input into the initial neural network model to obtain the refrigeration training results. The refrigeration training results include the liquid cooling capacity, the air cooling capacity and the air inlet temperature of each cabinet in the computer room.

[0096] S403: Calculate the loss value according to the refrigeration training result and the actual refrigeration result corresponding to the training control parameter.

[0097] In this step, after the computer obtains the refrigeration training result, it calculates the loss value according to the refrigeration training result and the actual refrigeration result corresponding to the training control parameter.

[0098] It should be noted that the loss value can be calculated using a loss function, which may be an L1 norm loss function, a mean square error loss function, a cross entropy loss function, etc. The embodiment of the present application does not limit the loss function and can be determined according to actual conditions.

[0099] S404: Update the initial neural network model according to the loss value to obtain a trained neural network model.

[0100] S405: Verify the trained neural network model according to the verification data set to obtain verification indicators.

[0101] In the above steps, after the computer obtains the loss value, it updates the initial neural network model according to the loss value to obtain the trained neural network model, and then verifies the trained neural network model according to the verification data set to obtain the verification index.

[0102] It should be noted that the verification indicator may be accuracy, precision, recall rate, etc. The embodiment of the present application does not limit the verification indicator and it can be determined according to actual conditions.

[0103] S406: Determine whether the verification index is greater than a preset threshold; if the verification index is greater than the preset threshold, execute step S407; if the verification index is less than or equal to the preset threshold, execute step S408.

[0104] In this step, after the computer obtains the verification index, in order to determine whether to continue training, it is necessary to determine whether the verification index is greater than a preset threshold.

[0105] It should be noted that the preset threshold may be 50%, 70%, 90%, etc. The embodiment of the present application does not limit the preset threshold, and it may be determined according to actual conditions.

[0106] S407: Using the trained neural network model as a refrigeration result prediction model.

[0107] In this step, if the computer determines that the verification index is greater than the preset threshold, it means that the accuracy of the current model is high, and the training can be stopped, and the trained neural network model can be used as the refrigeration result prediction model.

[0108] S408: Use the trained neural network model as a new initial neural network model and execute step S401.

[0109] In this step, if the computer determines that the verification index is less than or equal to the preset threshold, it means that the accuracy of the current model is low and further training is needed. The trained neural network model is used as the new initial neural network model and the process returns to step S401.

[0110] That is, a new set of training control parameters is selected and input into a new initial neural network model to obtain a new refrigeration training result. After obtaining a new loss value based on the new refrigeration training result, the new initial neural network model is updated to obtain a new trained neural network model. After obtaining a new verification index based on the verification data set, if the new verification index is less than or equal to the preset threshold, this process is repeated until the new verification index is greater than the preset threshold, and the new trained neural network model is used as the refrigeration result prediction model.

[0111] For example, Figure 4b The schematic diagram of the cooling result prediction model provided for this application is as follows: Figure 4b As shown in Figure 1, the input of the cooling result prediction model is: total server power, secondary side pressure difference and secondary side liquid supply temperature of each cooling capacity distribution unit, and the temperature setting value of each air cooling unit in the air cooling system. The output of the cooling result prediction model is: liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room.

[0112] The combined control method of liquid cooling and air cooling provided in this embodiment obtains a refrigeration result prediction model by training an initial neural network model using training control parameters, thereby improving the accuracy of the refrigeration result prediction model.

[0113] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0114] Figure 5 This is a schematic diagram of the structure of an embodiment of a combined control device for liquid cooling and air cooling provided in this application. Figure 5 As shown, the combined control device 50 for liquid cooling and air cooling includes:

[0115] An acquisition module 51 is used to acquire the total power of the server and multiple groups of candidate control parameters, each group of the candidate control parameters includes the secondary side pressure difference and the secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system;

[0116] The processing module 52 is used to:

[0117] According to the total power of the server and each group of the control parameters to be selected, and a cooling result prediction model, a cooling result corresponding to each group of the control parameters to be selected is obtained, wherein the cooling result prediction model is a pre-trained neural network model that calculates the cooling result according to the total power of the server and the control parameters to be selected;

[0118] According to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain a target cooling result;

[0119] The control module 53 is used to control the operation of the liquid cooling system and the air cooling system according to the selected control parameters corresponding to the target cooling result.

[0120] Furthermore, the processing module 52 is specifically configured to:

[0121] For each of the cooling results, if the air inlet temperature of each cabinet in the cooling result belongs to the preset temperature range, the cooling result is taken as the first cooling result;

[0122] For each of the first cooling results, taking the ratio of the air cooling capacity to the liquid cooling capacity in the first cooling result as the cooling ratio of the first cooling result;

[0123] Each of the first cooling results is screened according to the cooling ratio of each of the first cooling results to obtain the target cooling result.

[0124] Furthermore, the processing module 52 is further configured to:

[0125] taking the cooling result with the smallest cooling ratio among all the first cooling results as the target cooling result;

[0126] or,

[0127] The cooling results whose cooling ratio is less than the preset ratio among all the first cooling results are used as the second cooling results; and a cooling result is selected from all the second cooling results as the target cooling result.

[0128] Furthermore, the processing module 52 is further configured to:

[0129] For each group of the control parameters to be selected, the control parameters to be selected and the total power of the server are input into the cooling result prediction model to obtain the cooling results corresponding to the control parameters to be selected.

[0130] Furthermore, the acquisition module 51 is specifically used for:

[0131] When it is detected that the total power change rate of the server does not fall within the preset power change range, the total power of the server and multiple groups of control parameters to be selected are obtained;

[0132] or,

[0133] At each preset interval, the total server power and multiple groups of control parameters to be selected are obtained;

[0134] or,

[0135] When a control instruction is received, the total power of the server and multiple groups of control parameters to be selected are obtained.

[0136] Furthermore, the acquisition module 51 is also used to acquire a preset secondary side pressure difference range of each of the cooling distribution units, a preset secondary side liquid supply temperature range of each of the cooling distribution units, and a preset temperature range of each of the air cooling units;

[0137] Furthermore, the processing module 52 is further configured to generate the plurality of groups of control parameters to be selected according to each of the preset secondary side pressure difference ranges, each of the preset secondary side liquid supply temperature ranges and each of the preset temperature ranges.

[0138] The combined control device for liquid cooling and air cooling provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0139] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 6 As shown, the electronic device 60 includes:

[0140] Processor 61, memory 62, and communication interface 63;

[0141] The memory 62 is used to store executable instructions of the processor 61;

[0142] The processor 61 is configured to execute the technical solution in any of the aforementioned method embodiments by executing the executable instructions.

[0143] Optionally, the memory 62 may be independent or integrated with the processor 61 .

[0144] Optionally, when the memory 62 is a device independent of the processor 61, the electronic device 60 may further include:

[0145] The bus 64 , the memory 62 and the communication interface 63 are connected to the processor 61 via the bus 64 and communicate with each other. The communication interface 63 is used to communicate with other devices.

[0146] Optionally, the communication interface 63 may be implemented by a transceiver. The communication interface is used to implement communication between the database access device and other devices (such as a client, a read-write library, and a read-only library). The memory may include a random access memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0147] The bus 64 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0148] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0149] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principle and technical effect are similar and will not be repeated here.

[0150] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the technical solution provided by any of the aforementioned method embodiments when executed by a processor.

[0151] An embodiment of the present application also provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the technical solution provided by any of the aforementioned method embodiments is implemented.

[0152] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0153] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0154] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0157] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0158] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A combined control method of liquid cooling and air cooling, characterized in that: include: Obtaining the total power of the server and multiple groups of candidate control parameters, each group of the candidate control parameters comprising the secondary side pressure difference and the secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system; According to the total power of the server and each group of the control parameters to be selected, and a cooling result prediction model, a cooling result corresponding to each group of the control parameters to be selected is obtained, wherein the cooling result prediction model is a pre-trained neural network model that calculates the cooling result according to the total power of the server and the control parameters to be selected; According to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain a target cooling result; The operation of the liquid cooling system and the air cooling system are controlled according to the selected control parameters corresponding to the target cooling result.

2. The method according to claim 1, characterized in that The step of screening each cooling result according to the liquid cooling capacity, the air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result to obtain a target cooling result includes: For each of the cooling results, if the air inlet temperature of each cabinet in the cooling result belongs to the preset temperature range, the cooling result is taken as the first cooling result; For each of the first cooling results, taking the ratio of the air cooling capacity to the liquid cooling capacity in the first cooling result as the cooling ratio of the first cooling result; Each of the first cooling results is screened according to the cooling ratio of each of the first cooling results to obtain the target cooling result.

3. The method according to claim 2, characterized in that The step of screening each of the first refrigeration results according to the refrigeration ratio of each of the first refrigeration results to obtain the target refrigeration result includes: taking the cooling result with the smallest cooling ratio among all the first cooling results as the target cooling result; or, The cooling results whose cooling ratio is less than the preset ratio among all the first cooling results are used as the second cooling results; and a cooling result is selected from all the second cooling results as the target cooling result.

4. The method according to claim 1, characterized in that: The step of obtaining the cooling result corresponding to each group of the control parameters to be selected according to the total power of the server and each group of the control parameters to be selected, and the cooling result prediction model, comprises: For each group of the control parameters to be selected, the control parameters to be selected and the total power of the server are input into the cooling result prediction model to obtain the cooling results corresponding to the control parameters to be selected.

5. The method according to claim 1, characterized in that The obtaining of the total server power and multiple groups of control parameters to be selected includes: When it is detected that the total power change rate of the server does not fall within the preset power change range, the total power of the server and multiple groups of control parameters to be selected are obtained; or, At each preset interval, the total server power and multiple groups of control parameters to be selected are obtained; or, When a control instruction is received, the total power of the server and multiple groups of control parameters to be selected are obtained.

6. The method according to any one of claims 1 to 5, characterized in that: Before obtaining the total power of the server and multiple groups of control parameters to be selected, the method further includes: Obtaining a preset secondary side pressure difference range of each of the cooling distribution units, a preset secondary side liquid supply temperature range of each of the cooling distribution units, and a preset temperature range of each of the air cooling units; The plurality of groups of control parameters to be selected are generated according to each of the preset secondary side pressure difference ranges, each of the preset secondary side liquid supply temperature ranges and each of the preset temperature ranges.

7. A combined control device for liquid cooling and air cooling, characterized in that: include: An acquisition module, used to acquire the total power of the server and multiple groups of candidate control parameters, each group of the candidate control parameters including the secondary side pressure difference and the secondary side liquid supply temperature of each cooling capacity distribution unit in the liquid cooling system, and the temperature setting value of each air cooling unit in the air cooling system; Processing modules for: According to the total power of the server and each group of the control parameters to be selected, and a cooling result prediction model, a cooling result corresponding to each group of the control parameters to be selected is obtained, wherein the cooling result prediction model is a pre-trained neural network model that calculates the cooling result according to the total power of the server and the control parameters to be selected; According to the liquid cooling capacity, air cooling capacity and the air inlet temperature of each cabinet in the computer room in each cooling result, each cooling result is screened to obtain a target cooling result; A control module is used to control the operation of the liquid cooling system and the air cooling system according to the selected control parameters corresponding to the target cooling result.

8. An electronic device, characterized in that: include: Processor, memory, communication interface; The memory is used to store executable instructions of the processor; Wherein, the processor is configured to execute the combined control method of liquid cooling and air cooling according to any one of claims 1 to 6 by executing the executable instructions.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the combined control method of liquid cooling and air cooling according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, is used to implement the combined control method of liquid cooling and air cooling as described in any one of claims 1 to 6.

Images