Cooling method, device and computer program product for a server

Abstract

The application discloses a kind of cooling processing method, device and computer program product of server.It involves the field of financial technology, which comprises: obtaining the load data of target server in historical period, inputting load data into load prediction model, and obtaining load prediction result in preset period by processing, wherein the load prediction result includes load change trend and predicted load data;Obtain the historical liquid cooling data of liquid cooling system deployed in the target server, and obtain the operation parameter adjustment strategy of the liquid cooling system according to the historical liquid cooling data and the load prediction result;Adjust the operation parameter of the liquid cooling system based on the operation parameter adjustment strategy, and cool the target server based on the adjusted liquid cooling system.Through the present application, the technical problem of low cooling efficiency in the related art when cooling the server is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a server cooling method, apparatus, and computer program product. Background Technology

[0002] With the rapid development of information technology, the computing power and storage capacity of server equipment are constantly increasing. Consequently, the heat generated by server equipment is also increasing, requiring a cooling system to dissipate the heat. Liquid cooling technology, due to its efficient heat transfer capabilities and good adaptability to high heat flux densities, can directly deliver the cooling medium (usually water or other liquids) to the critical heat-generating parts of the server for cooling. Compared with traditional air cooling, it can significantly improve cooling efficiency and the energy efficiency ratio of data centers.

[0003] However, existing liquid cooling systems face significant technical limitations in practical applications. Firstly, traditional liquid cooling systems are initially configured with coolant supply and temperature based on the anticipated maximum load. Once set, subsequent adjustments are limited to simple settings for coolant circulation rate and temperature. This approach fails to adapt flexibly to the dynamic changes in actual server load. During periods of low load or idle time, the coolant flow remains high, leading to excessive cooling that consumes unnecessary power and accelerates the aging of cooling equipment, resulting in low energy efficiency. When servers suddenly encounter high loads, such as large-scale data processing or high-performance computing tasks, the inability to quickly adjust coolant flow and temperature to appropriate levels can cause server overheating, impacting equipment stability and data processing capabilities.

[0004] Currently, to optimize the cooling strategy of liquid cooling systems, related technologies dynamically adjust the circulation rate and temperature of the coolant by monitoring the server's operating status in real time. While these solutions improve the response speed and energy efficiency of liquid cooling systems to some extent, they still fall short when faced with rapid changes in server load, such as sudden high-traffic access or computing tasks, making it difficult to achieve advance optimization and preventative control.

[0005] There is currently no effective solution to the technical problem of low cooling efficiency when cooling servers in related technologies. Summary of the Invention

[0006] The main objective of this application is to provide a server cooling method, apparatus, and computer program product to solve the technical problem of low cooling efficiency in the related art when cooling servers.

[0007] To achieve the above objectives, according to one aspect of this application, a server cooling method is provided. The method includes: acquiring load data of a target server over a historical time period; inputting the load data into a load prediction model; processing the data to obtain a load prediction result for a preset time period, wherein the load prediction result includes a load change trend and predicted load data; acquiring historical liquid cooling data of a liquid cooling system deployed on the target server; processing the historical liquid cooling data and the load prediction result to obtain an operating parameter adjustment strategy for the liquid cooling system; adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy; and cooling the target server based on the adjusted liquid cooling system.

[0008] Furthermore, the load prediction model includes a hidden layer and an output layer. Inputting load data into the load prediction model and processing it to obtain the load prediction result within a preset time period includes: converting the load data into a format to obtain a load sequence, where the load sequence includes load data at Y time points within a historical time period, where Y is a positive integer; for the load data at the i-th time point, obtaining the hidden state at the (i-1)-th time point, where the hidden layer calculates the hidden state at the i-th time point based on the load data at the i-th time point and the hidden state at the (i-1)-th time point, where the hidden state at the (i-1)-th time point refers to the hidden state of the load data at the (i-1)-th time point output by the hidden layer, where i is a positive integer; and obtaining historical load change characteristics within the historical time period, where the output layer processes the data based on the Y hidden states and the historical load change characteristics to obtain the load prediction result.

[0009] Furthermore, M sensors are deployed in the liquid cooling system to obtain historical liquid cooling data of the liquid cooling system deployed on the target server, including: obtaining historical liquid cooling data of the liquid cooling system collected by the M sensors to obtain M initial historical liquid cooling data, where M is a positive integer; and preprocessing the M initial historical liquid cooling data to obtain historical liquid cooling data.

[0010] Furthermore, the process of processing historical liquid cooling data and load prediction results to obtain the operating parameter adjustment strategy of the liquid cooling system includes: obtaining the operating constraints and objective function of the liquid cooling system, wherein the operating constraints are used to constrain the operating parameters of the liquid cooling system; constructing a strategy optimization algorithm based on the objective function and operating constraints; and processing the historical liquid cooling data and load prediction results based on the strategy optimization algorithm to obtain the operating parameter adjustment strategy.

[0011] Furthermore, based on the strategy optimization algorithm, historical liquid cooling data and load prediction results are processed to obtain the operating parameter adjustment strategy, which includes: randomly generating an initial population by the strategy optimization algorithm, wherein the initial population includes K individuals, each individual includes a set of adjustment parameters, each set of adjustment parameters includes initial opening adjustment parameters, initial flow adjustment parameters, and initial temperature adjustment parameters, where K is a positive integer; calculating the function value of the objective function based on the set of adjustment parameters of each individual in the initial population to obtain K initial function values; iteratively optimizing the K individuals based on the K initial function values ​​until one of the K optimized individuals has a function value that satisfies the operating constraints, and constructing the operating parameter adjustment strategy based on the adjustment parameters corresponding to the individual that satisfies the operating constraints.

[0012] Furthermore, adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy includes: when the load prediction result indicates that the load change trend of the target server is increasing, extracting N first adjustment parameters from the operating parameter adjustment strategy, and adjusting the liquid cooling system according to the N first adjustment parameters, wherein the N first adjustment parameters include at least: a first opening adjustment parameter, a first flow adjustment parameter, and a first temperature adjustment parameter. The first opening adjustment parameter is used to increase the opening of the pipeline valves in the liquid cooling system, the first flow adjustment parameter is used to increase the flow rate of the coolant in the liquid cooling system, and the first temperature adjustment parameter is used to decrease the temperature of the coolant, where N is a positive integer; when the load prediction result indicates that the load change trend of the target server is decreasing, extracting N second adjustment parameters from the operating parameter adjustment strategy, and adjusting the liquid cooling system according to the N second adjustment parameters, wherein the N second adjustment parameters include at least: a second opening adjustment parameter, a second flow adjustment parameter, and a second temperature adjustment parameter. The second opening adjustment parameter is used to decrease the opening of the pipeline valves in the liquid cooling system, the second flow adjustment parameter is used to decrease the flow rate of the coolant in the liquid cooling system, and the second temperature adjustment parameter is used to increase the temperature of the coolant.

[0013] Furthermore, after adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, the method further includes: during the operation of the target server and the adjusted liquid cooling system, acquiring the load data of the target server within a preset time period to obtain the operating load data; extracting the predicted load data from the load prediction results, calculating the difference between the operating load data and the predicted load data to obtain the load data difference; and adjusting the operating parameter adjustment strategy when the load data difference is greater than or equal to a preset threshold, and performing cooling treatment on the target server based on the adjusted operating parameter adjustment strategy.

[0014] To achieve the above objectives, according to another aspect of this application, a server cooling device is provided. The device includes: a first acquisition unit, configured to acquire load data of a target server over a historical time period, input the load data into a load prediction model, and process it to obtain a load prediction result for a preset time period, wherein the load prediction result includes a load change trend and predicted load data; a second acquisition unit, configured to acquire historical liquid cooling data of a liquid cooling system deployed on the target server, and process the historical liquid cooling data and the load prediction result to obtain an operating parameter adjustment strategy for the liquid cooling system; and a first adjustment unit, configured to adjust the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and perform cooling treatment on the target server based on the adjusted liquid cooling system.

[0015] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the cooling process method of any of the above-described servers.

[0016] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory storing an executable program, and the processor for running the program, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-described server cooling methods.

[0017] According to another aspect of the present invention, a computer program product is also provided, the computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements any of the above-described server cooling methods.

[0018] In this embodiment, a server cooling method is adopted. Load data of the target server over a historical time period is obtained, and this load data is input into a load prediction model to obtain a load prediction result for a preset time period. The load prediction result includes load change trends and predicted load data. Historical liquid cooling data of the liquid cooling system deployed on the target server is obtained, and an operating parameter adjustment strategy for the liquid cooling system is obtained based on the historical liquid cooling data and the load prediction result. The operating parameters of the liquid cooling system are adjusted based on the operating parameter adjustment strategy, and the target server is cooled based on the adjusted liquid cooling system. This solves the technical problem of low cooling efficiency in related technologies. By inputting the target server's load data into a load prediction model and outputting load prediction results, processing the historical liquid cooling data and the load prediction result to obtain the operating parameter adjustment strategy for the liquid cooling system, and finally adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, the target server is cooled based on the adjusted liquid cooling system, thereby achieving the technical effect of improving the efficiency of server cooling. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a server cooling method;

[0021] Figure 2 This is a flowchart of a server cooling method provided according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of a server cooling device provided according to an embodiment of this application;

[0023] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, this system has interfaces with relevant users or organizations to provide users with corresponding operation data for them to choose to agree to or refuse automated decision-making results. Before obtaining relevant information, a request for obtaining the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained after receiving consent from the aforementioned user or organization; if the user chooses to refuse, the expert decision-making process is initiated. Users can view the purpose of data use in real time through authorization decoding and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.

[0027] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize use or refuse use.

[0028] Example 1

[0029] According to an embodiment of this application, a method embodiment for cooling a server is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1This is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a server cooling method, such as... Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1 The processor 102 (which may include, but is not limited to, a microprocessor MCU (Microcontroller Unit) or a programmable gate array (FPGA)) is shown as 102a, 102b, ..., 102n. It also includes a memory 104 for storing data and a transmission device 106 for communication functions. In addition, it may include: a display, an input / output interface, a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a keyboard, a cursor control device, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the server cooling method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned server cooling method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) and a network interface, which can be connected to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a radio frequency (RF) module, used for wireless communication with the Internet.

[0034] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0035] Under the aforementioned operating environment, this application provides the following: Figure 2 The cooling method for the server is shown. Figure 2 This is a flowchart of a server cooling method provided according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0036] Step S201: Obtain the load data of the target server in the historical time period, input the load data into the load prediction model, and process it to obtain the load prediction result in the preset time period. The load prediction result includes the load change trend and the predicted load data.

[0037] It's important to note that the target server refers to the server equipment requiring load prediction and liquid cooling strategy optimization. Load data refers to the target server's workload records over a past period, which may include metrics such as CPU (Central Processing Unit) utilization, memory usage, and network transmission rate. This data is typically collected through sensors and monitoring software installed inside the server. By analyzing this data, the periodic characteristics and seasonal variations of the server load can be identified, providing data support for building accurate predictive models. The load prediction model can be a mathematical model built based on models such as Long Short-Term Memory (LSTM) networks and Support Vector Machines, capable of predicting future load changes in the server. By inputting historical load data into the model, it can learn and understand historical patterns and relationships in server load changes, thereby outputting load prediction results. These results may include load change trends and predicted load data. The load change trend may be gradually increasing, gradually decreasing, or remaining stable. This prediction provides the liquid cooling system with forward-looking information, enabling the system to adjust its cooling strategy in advance to cope with upcoming load changes, thus achieving more efficient and timely cooling effects.

[0038] Step S202: Obtain historical liquid cooling data of the liquid cooling system deployed on the target server, and process the historical liquid cooling data and load prediction results to obtain the liquid cooling system's operating parameter adjustment strategy.

[0039] Specifically, after obtaining the load prediction results, it is also necessary to obtain the historical liquid cooling data of the liquid cooling system deployed on the target server, and then use the historical liquid cooling data to better understand the operation mode of the liquid cooling system. The historical liquid cooling data is used to indicate the operation status record of the liquid cooling system in the historical time period, which may include key indicators such as the temperature, flow rate, pressure of the coolant, and energy consumption of the liquid cooling system.

[0040] Furthermore, data analysis and optimization algorithms are used to process and calculate historical liquid cooling data and load prediction results to obtain the operating parameter adjustment strategy of the liquid cooling system. The operating parameter adjustment strategy refers to dynamically adjusting the coolant temperature, flow rate, and valve opening of the manifold branch pipes (the distribution network that distributes coolant to various components that need cooling (such as the CPU (Central Processing Unit) and GPU (Graphics Processing Unit) of a server, which may include one or more main manifolds and several branch pipes) in order to achieve a control strategy that meets the server's cooling needs while maximizing energy efficiency.

[0041] Step S203: Adjust the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and cool the target server based on the adjusted liquid cooling system.

[0042] Specifically, after obtaining the operating parameter adjustment strategy, the operating parameters of the liquid cooling system can be adjusted based on this strategy. For example, the coolant flow rate (the volume of coolant passing through the liquid cooling system per unit time), temperature (the current temperature of the coolant, affecting its heat absorption capacity), and valve opening can be adjusted (controlling the specific proportion of coolant distributed to each server, directly affecting the cooling effect). Finally, based on the adjusted operating parameters, the target server is effectively thermally managed, that is, the optimized coolant is distributed to each cooling node of the server, and the heat generated by the server is absorbed and carried away through the circulation of the liquid, keeping the internal components of the server within a safe operating temperature range.

[0043] The server cooling method provided in this application embodiment obtains the load data of the target server within a historical time period, inputs the load data into a load prediction model, and processes it to obtain the load prediction result within a preset time period. The load prediction result includes the load change trend and predicted load data. It also obtains historical liquid cooling data of the liquid cooling system deployed on the target server, processes the historical liquid cooling data and the load prediction result to obtain an operating parameter adjustment strategy for the liquid cooling system, adjusts the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and then cools the target server based on the adjusted liquid cooling system. This solves the technical problem of low cooling efficiency in related technologies. By inputting the load data of the target server into a load prediction model and outputting the load prediction result, processing the historical liquid cooling data and the load prediction result to obtain the operating parameter adjustment strategy for the liquid cooling system, and finally adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and then cooling the target server based on the adjusted liquid cooling system, the method achieves the technical effect of improving the efficiency of server cooling.

[0044] Optionally, in the server cooling method provided in this application embodiment, the load prediction model includes a hidden layer and an output layer. Inputting load data into the load prediction model and processing it to obtain a load prediction result within a preset time period includes: converting the load data into a format to obtain a load sequence, wherein the load sequence includes load data at Y time points within a historical time period, where Y is a positive integer; for the load data at the i-th time point, obtaining the hidden state at the (i-1)-th time point, and having the hidden layer calculate the hidden state at the i-th time point based on the load data at the i-th time point and the hidden state at the (i-1)-th time point, where the hidden state at the (i-1)-th time point refers to the hidden state of the load data at the (i-1)-th time point output by the hidden layer, where i is a positive integer; obtaining historical load change characteristics within a historical time period, and having the output layer process the data based on the Y hidden states and the historical load change characteristics to obtain a load prediction result.

[0045] Specifically, when using a load forecasting model for load forecasting, the first step is to convert the format of the collected historical load data to maintain data consistency and availability. Then, the converted data and the corresponding time points for each data point are combined into a load sequence. For example, if forecasting the load situation for the next day, load data from 24 time points can be selected, i.e., load data from one time point per hour.

[0046] Furthermore, after obtaining the load sequence, a hidden state can be generated based on this sequence. For the load data at time point i, the load prediction model processes the data using its unique hidden layer. At this point, the hidden layer calculates the hidden state at time point i based on the load data at time point i and the hidden state at time point i-1. The hidden state carries the dynamic information of the time series. Through the calculation of the hidden state, the model can capture the characteristics of load data changing over time and establish the correlation between various time points in the load sequence.

[0047] After processing the entire load sequence, the model can extract the variation features from the historical load data to obtain historical load variation characteristics. These characteristics can include periodic changes and trend changes in the load. Finally, the model's output layer uses the hidden states obtained from the hidden layer and the extracted historical load variation characteristics to perform comprehensive analysis and processing to obtain the load prediction results.

[0048] This embodiment extracts and analyzes historical load change characteristics, transforming the calculation results of the hidden layer into load prediction results. This provides key information for the dynamic adjustment of the liquid cooling system, helps to optimize the cooling strategy, reduce energy waste, improve cooling efficiency, and thus enhance the overall performance and energy efficiency ratio of the server.

[0049] Optionally, in the server cooling method provided in this application embodiment, deploying M sensors in the liquid cooling system and acquiring historical liquid cooling data of the liquid cooling system deployed on the target server includes: acquiring historical liquid cooling data of the liquid cooling system collected by the M sensors to obtain M initial historical liquid cooling data, where M is a positive integer; and preprocessing the M initial historical liquid cooling data to obtain historical liquid cooling data.

[0050] Specifically, to obtain liquid cooling data from the liquid cooling system, historical liquid cooling data can first be collected by multiple sensors deployed at key nodes of the liquid cooling system. These sensors can monitor the temperature, flow rate, and pressure of the coolant, as well as the server load in real time, providing a solid foundation for subsequent data analysis and prediction. Since the collected data initially exists in the form of raw data—liquid cooling parameters collected independently by each sensor—this data may include a large number of real-time measurements and may contain noise, outliers, or incomplete information. Therefore, the initial historical liquid cooling data needs to be preprocessed, such as removing noise, correcting outliers, filling in missing data, and standardizing the data format, to transform the initial historical liquid cooling data into more accurate, consistent, and easier-to-analyze historical liquid cooling data.

[0051] This embodiment utilizes sensors to collect liquid cooling data, providing high-quality data input for the next step of load prediction model processing. This helps improve the scientific validity and effectiveness of liquid cooling system operating parameter adjustment strategies, ultimately achieving intelligent optimization of the liquid cooling system and improving server cooling performance and energy efficiency.

[0052] Optionally, in the server cooling method provided in this application embodiment, the process of obtaining the liquid cooling system's operating parameter adjustment strategy based on historical liquid cooling data and load prediction results includes: obtaining the liquid cooling system's operating constraints and objective function, wherein the operating constraints are used to constrain the liquid cooling system's operating parameters; constructing a strategy optimization algorithm based on the objective function and operating constraints; and processing the historical liquid cooling data and load prediction results based on the strategy optimization algorithm to obtain the operating parameter adjustment strategy.

[0053] Specifically, after obtaining historical liquid cooling data and load prediction results from the model output, the operating constraints and objective function of the liquid cooling system can be obtained first. For example, the temperature of the coolant cannot be lower than a certain set value to prevent freezing, nor can it be too high to avoid overheating of the equipment; the flow rate of the coolant needs to be within the rated flow rate range of the pump to avoid overloading or inefficiency of the pump; the opening degree of the manifold branch valve also needs to be within a certain range to ensure uniform distribution of the coolant; the objective function can ensure the cooling effect of the server (such as maintaining the server temperature within a certain safe range) while minimizing energy consumption (such as electricity costs).

[0054] Furthermore, a strategy optimization algorithm is constructed using the aforementioned objective function and operational constraints. This involves employing intelligent optimization algorithms such as genetic algorithms, particle swarm optimization, or genetic programming. These algorithms can search for the optimal combination of operating parameters for the liquid cooling system, considering both the objective function and operational constraints to find a solution that satisfies cooling requirements while achieving an optimal balance in energy consumption. Finally, the constructed strategy optimization algorithm, through iteration and intelligent search, finds a set of optimal operating parameters in the liquid cooling system, such as coolant temperature, flow rate, and the opening degree of the manifold branch valves, thus obtaining the optimal operating parameter adjustment strategy.

[0055] This embodiment utilizes a strategy optimization algorithm to output an operational parameter adjustment strategy. This not only ensures that the adjustment of the liquid cooling system's operational parameters remains within physical and safety boundaries, but also allows for the pre-calculation of the optimal operational parameter adjustment strategy based on server load predictions. This improves the intelligence and responsiveness of the liquid cooling system, significantly promoting energy conservation, emission reduction, and operational efficiency improvement in data centers.

[0056] Optionally, in the server cooling method provided in this application embodiment, the process of processing historical liquid cooling data and load prediction results based on the strategy optimization algorithm to obtain the operating parameter adjustment strategy includes: randomly generating an initial population by the strategy optimization algorithm, wherein the initial population includes K individuals, each individual includes a set of adjustment parameters, each set of adjustment parameters includes initial opening adjustment parameters, initial flow adjustment parameters, and initial temperature adjustment parameters, where K is a positive integer; calculating the function value of the objective function based on the set of adjustment parameters of each individual in the initial population to obtain K initial function values; iteratively optimizing the K individuals based on the K initial function values ​​until one of the K optimized individuals has a function value that satisfies the operating constraints, and constructing the operating parameter adjustment strategy based on the adjustment parameters corresponding to the individual that satisfies the operating constraints.

[0057] Specifically, when using a strategy optimization algorithm, an initial population of K individuals can be generated randomly. Each individual represents a specific set of operating parameters, including initial opening adjustment parameters (controlling the opening of the manifold branch valve), initial flow adjustment parameters (determining the coolant flow rate), and initial temperature adjustment parameters (setting the coolant temperature). This randomly generated initial population provides the algorithm with a diverse starting point, facilitating the search for a broader set of solutions and increasing the likelihood of finding the optimal solution.

[0058] For each individual in the initial population, i.e., for each specific set of operating parameters, a predefined objective function is used to calculate its function value. Since the objective function can aim to minimize energy consumption, maximize cooling effect, or both, the calculated function value can take into account historical liquid cooling data and load prediction results to evaluate the performance of the liquid cooling system under the current parameter settings. Furthermore, based on the calculated initial function value, the individuals in the population are iteratively optimized. In each iteration, the algorithm can generate a new generation of the population through operations such as selection, crossover, and mutation, and recalculate the objective function value. This process continues until an individual's function value satisfies the operating constraints, indicating that the corresponding operating parameter adjustment strategy for that individual can effectively cope with changes in server load while ensuring the stable and safe operation of the liquid cooling system.

[0059] Once the iterative optimization reaches the stop bar, the algorithm can output the adjustment parameters corresponding to this individual as the running parameter adjustment strategy. This strategy includes optimization suggestions for adjusting the opening degree of the manifold branch valve, coolant flow rate, and temperature.

[0060] This embodiment combines machine learning algorithms with intelligent optimization of liquid cooling system operating parameters through steps such as randomly generating an initial population, calculating the objective function value, iterative optimization, and generating operating parameter adjustment strategies. It can not only find the optimal cooling strategy that meets the operating constraints, but also conduct a comprehensive search in multiple parameter combinations. This allows the liquid cooling system to maintain efficient cooling and achieve energy savings when dealing with changes in server load, thus enhancing the flexibility and adaptability of intelligent control of the liquid cooling system.

[0061] Optionally, in the server cooling method provided in this application embodiment, adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy includes: when the load prediction result indicates that the load change trend of the target server is increasing, extracting N first adjustment parameters from the operating parameter adjustment strategy, and adjusting the liquid cooling system according to the N first adjustment parameters, wherein the N first adjustment parameters include at least: a first opening adjustment parameter, a first flow adjustment parameter, and a first temperature adjustment parameter, the first opening adjustment parameter being used to increase the opening of the pipe valves in the liquid cooling system, and the first flow adjustment parameter being used to increase the cooling capacity of the liquid cooling system. The flow rate of the liquid is adjusted. The first temperature adjustment parameter is used to reduce the temperature of the coolant, and N is a positive integer. When the load prediction result indicates that the load change trend of the target server is decreasing, N second adjustment parameters are extracted from the operating parameter adjustment strategy, and the liquid cooling system is adjusted according to the N second adjustment parameters. The N second adjustment parameters include at least: a second opening adjustment parameter, a second flow rate adjustment parameter, and a second temperature adjustment parameter. The second opening adjustment parameter is used to reduce the opening of the pipe valves in the liquid cooling system, the second flow rate adjustment parameter is used to reduce the flow rate of the coolant in the liquid cooling system, and the second temperature adjustment parameter is used to increase the temperature of the coolant.

[0062] Specifically, when adjusting the operating parameters of the liquid cooling system, if the load prediction results indicate that the load trend of the target server will increase, multiple first adjustment parameters can be extracted from the operating parameter adjustment strategy generated by the strategy optimization algorithm. These parameters are then used to adjust the liquid cooling system, preventing performance degradation or damage to the server due to overheating, while simultaneously achieving efficient energy utilization. It should be noted that the first opening adjustment parameter in the first adjustment parameters indicates increasing the opening of the manifold branch pipe valves to improve coolant distribution efficiency, allowing more coolant to flow to the server with increased load and meet its cooling needs; the first flow rate adjustment parameter indicates increasing the coolant flow rate to prevent server overheating; and the first temperature adjustment parameter indicates lowering the coolant temperature. Lowering the coolant temperature enhances its heat absorption capacity, especially when the server load increases leading to increased heat generation. Low-temperature coolant can more effectively exchange heat, improving the cooling effect.

[0063] Conversely, when the load forecast indicates a decrease in load, a second adjustment parameter is extracted from the operating parameter adjustment strategy. This second parameter is then used to adjust the liquid cooling system to meet the cooling requirements of the low load. The second adjustment parameter may include a second opening adjustment parameter, which reduces the opening of the manifold branch pipe valves, reducing coolant distribution and avoiding unnecessary energy waste under low load conditions; a second flow adjustment parameter, which indicates a reduction in coolant flow rate, thereby reducing coolant circulation energy consumption and preventing overcooling, maintaining a balanced energy usage; and a second temperature adjustment parameter, which indicates an increase in coolant temperature, thereby reducing cooling system energy consumption and maintaining the server within a safe operating temperature range.

[0064] This embodiment enhances cooling capacity in advance by increasing valve opening, increasing coolant flow, and lowering temperature, effectively addressing the high heat generation of the server. When the load decreases, the cooling strategy is adjusted by decreasing valve opening, reducing coolant flow, and appropriately increasing temperature, avoiding unnecessary energy waste. This not only improves the cooling efficiency of the liquid cooling system but also optimizes energy management.

[0065] Optionally, in the server cooling method provided in this application embodiment, after adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, the method further includes: during the operation of the target server and the adjusted liquid cooling system, acquiring the load data of the target server within a preset time period to obtain operating load data; extracting the predicted load data from the load prediction results, calculating the difference between the operating load data and the predicted load data to obtain a load data difference; and when the load data difference is greater than or equal to a preset threshold, adjusting the operating parameter adjustment strategy, and performing cooling treatment on the target server based on the adjusted operating parameter adjustment strategy.

[0066] Specifically, during the operation of the target server and the adjusted liquid cooling system, load data of the target server can be collected in real time within a preset time period using load sensors inside the server. This data reflects the server's current actual load status. Then, predicted load data for the time period corresponding to the real-time collected operating load data is extracted from the previously obtained load prediction results. Finally, the real-time acquired operating load data is compared with the pre-predicted load data, and the difference between the two is calculated. This difference reflects the deviation between the predicted and actual load.

[0067] Furthermore, it's determined whether the difference between the actual operating load data and the predicted load data exceeds an acceptable range. If the load data difference is greater than or equal to a preset threshold, it indicates that the current operating parameter adjustment strategy cannot meet the server's actual cooling needs, or there is a risk of energy waste. In this case, the current operating parameter adjustment strategy needs to be adjusted, such as updating valve openings, recalculating coolant flow and temperature settings, to more closely match the server's actual load changes. After adjusting the strategy, the liquid cooling system can perform cooling based on the latest and more accurate operating parameter adjustment strategy, updating coolant flow, temperature, and valve openings to adapt to the server's real-time load requirements.

[0068] This embodiment, through threshold judgment and strategy adjustment, enables the liquid cooling system to respond instantly to actual changes in server load, avoiding insufficient or excessive cooling, maintaining stable server operation and the economy of the liquid cooling system, thereby improving the cooling efficiency and energy utilization efficiency of the liquid cooling system, reducing the negative impact on server performance, and providing strong support for the stable operation and energy conservation and emission reduction of the data center.

[0069] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0070] Example 2

[0071] This application also provides a server cooling device. It should be noted that the server cooling device of this application can be used to execute the server cooling method provided in this application. The server cooling device provided in this application will be described below.

[0072] According to an embodiment of this application, an apparatus for implementing the above-described server cooling method is also provided. Figure 3 This is a schematic diagram of a server cooling device provided according to an embodiment of this application, as shown below. Figure 3 As shown, the device includes: a first acquisition unit 30, a second acquisition unit 31, and a first adjustment unit 32.

[0073] The first acquisition unit 30 is used to acquire the load data of the target server in a historical time period, input the load data into the load prediction model, and process it to obtain the load prediction result in a preset time period. The load prediction result includes the load change trend and the predicted load data.

[0074] The second acquisition unit 31 is used to acquire historical liquid cooling data of the liquid cooling system deployed on the target server, and process the historical liquid cooling data and load prediction results to obtain the liquid cooling system's operating parameter adjustment strategy.

[0075] The first adjustment unit 32 is used to adjust the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and to cool the target server based on the adjusted liquid cooling system.

[0076] The server cooling device provided in this application embodiment acquires load data of the target server within a historical time period through a first acquisition unit 30, inputs the load data into a load prediction model, and processes it to obtain a load prediction result within a preset time period. The load prediction result includes load change trends and predicted load data. A second acquisition unit 31 acquires historical liquid cooling data of the liquid cooling system deployed on the target server, and processes the historical liquid cooling data and load prediction results to obtain an operating parameter adjustment strategy for the liquid cooling system. A first adjustment unit 32 adjusts the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and cools the target server based on the adjusted liquid cooling system. This solves the technical problem of low cooling efficiency when cooling servers in related technologies. By inputting the load data of the target server into the load prediction model and outputting the load prediction result, processing the historical liquid cooling data and load prediction results to obtain the operating parameter adjustment strategy for the liquid cooling system, and finally adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and cooling the target server based on the adjusted liquid cooling system, the device achieves the technical effect of improving the efficiency of server cooling.

[0077] Optionally, in the server cooling processing apparatus provided in this application embodiment, the first acquisition unit 30 includes: a conversion module, used to convert the load data into a format to obtain a load sequence, wherein the load sequence includes load data at Y time points within a historical time period, where Y is a positive integer; a first acquisition module, used to acquire the hidden state at the (i-1)th time point for the load data at the i-th time point, and the hidden layer calculates the hidden state at the i-th time point by the load data at the i-th time point and the hidden state at the (i-1)th time point, wherein the hidden state at the (i-1)th time point refers to the hidden state of the load data at the (i-1)th time point output by the hidden layer, where i is a positive integer; and a second acquisition module, used to acquire historical load change characteristics within a historical time period, and the output layer processes the data based on the Y hidden states and historical load change characteristics to obtain a load prediction result.

[0078] Optionally, in the server cooling device provided in this application embodiment, the second acquisition unit 31 includes: a third acquisition module, used to acquire historical liquid cooling data of the liquid cooling system collected by M sensors to obtain M initial historical liquid cooling data, where M is a positive integer; and a processing module, used to preprocess the M initial historical liquid cooling data to obtain historical liquid cooling data.

[0079] Optionally, in the server cooling device provided in this application embodiment, the second acquisition unit 31 includes: a fourth acquisition module, used to acquire the operating constraints and objective function of the liquid cooling system, wherein the operating constraints are used to constrain the operating parameters of the liquid cooling system; and a construction module, used to construct a strategy optimization algorithm based on the objective function and operating constraints, and to process historical liquid cooling data and load prediction results based on the strategy optimization algorithm to obtain an operating parameter adjustment strategy.

[0080] Optionally, in the server cooling device provided in this application embodiment, the second acquisition unit 31 includes: a generation module, used to randomly generate an initial population by a strategy optimization algorithm, wherein the initial population includes K individuals, each individual includes a set of adjustment parameters, each set of adjustment parameters includes an initial opening adjustment parameter, an initial flow adjustment parameter, and an initial temperature adjustment parameter, and K is a positive integer; a calculation module, used to calculate the function value of the objective function based on the set of adjustment parameters of each individual in the initial population, to obtain K initial function values; and an iteration module, wherein the tower iteratively optimizes the K individuals based on the K initial function values ​​until there is one individual among the K optimized individuals whose function value satisfies the operating constraints, and the adjustment parameters corresponding to the individual that satisfies the operating constraints constitute the operating parameter adjustment strategy.

[0081] Optionally, in the server cooling device provided in this application embodiment, the first adjustment unit 32 includes: a first extraction module, used to extract N first adjustment parameters from the operating parameter adjustment strategy when the load prediction result indicates that the load change trend of the target server is an increase in load, and to adjust the liquid cooling system according to the N first adjustment parameters, wherein the N first adjustment parameters include at least: a first opening adjustment parameter, a first flow rate adjustment parameter, and a first temperature adjustment parameter, the first opening adjustment parameter being used to increase the opening of the pipe valves in the liquid cooling system, the first flow rate adjustment parameter being used to increase the flow rate of the coolant in the liquid cooling system, and the first temperature adjustment parameter being used to increase the opening of the pipe valves in the liquid cooling system. The temperature adjustment parameter is used to reduce the temperature of the coolant, where N is a positive integer. The second extraction module is used to extract N second adjustment parameters from the operating parameter adjustment strategy when the load prediction result indicates that the load change trend of the target server is decreasing, and to adjust the liquid cooling system according to the N second adjustment parameters. The N second adjustment parameters include at least: a second opening adjustment parameter, a second flow adjustment parameter, and a second temperature adjustment parameter. The second opening adjustment parameter is used to reduce the opening of the pipe valves in the liquid cooling system, the second flow adjustment parameter is used to reduce the flow rate of the coolant in the liquid cooling system, and the second temperature adjustment parameter is used to increase the temperature of the coolant.

[0082] Optionally, in the server cooling device provided in this application embodiment, the device further includes: a third acquisition unit, used to acquire load data of the target server within a preset time period during the operation of the target server and the adjusted liquid cooling system after adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, to obtain operating load data; an extraction unit, used to extract predicted load data from the load prediction result, calculate the difference between the operating load data and the predicted load data, to obtain a load data difference; and a second adjustment unit, used to adjust the operating parameter adjustment strategy when the load data difference is greater than or equal to a preset threshold, and to perform cooling treatment on the target server based on the adjusted operating parameter adjustment strategy.

[0083] It should be noted that the first acquisition unit 30, the second acquisition unit 31, and the first adjustment unit 32 mentioned above correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.

[0084] Example 3

[0085] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced with a mobile terminal or an electronic device, etc.

[0086] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0087] In this embodiment, the computer terminal described above can execute the program code for the following steps in the server cooling method: obtaining load data of the target server within a historical time period, inputting the load data into a load prediction model, and processing it to obtain a load prediction result within a preset time period, wherein the load prediction result includes load change trends and predicted load data; obtaining historical liquid cooling data of the liquid cooling system deployed on the target server, and processing the historical liquid cooling data and load prediction results to obtain an operating parameter adjustment strategy for the liquid cooling system; adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and performing cooling treatment on the target server based on the adjusted liquid cooling system.

[0088] Optionally, the aforementioned computer terminal can execute the program code for the following steps in the server cooling method: converting the load data into a format to obtain a load sequence, wherein the load sequence includes load data at Y time points within a historical time period, where Y is a positive integer; for the load data at the i-th time point, obtaining the hidden state at the (i-1)-th time point, and having the hidden layer calculate the load data at the i-th time point and the hidden state at the (i-1)-th time point to obtain the hidden state at the i-th time point, wherein the hidden state at the (i-1)-th time point refers to the hidden state of the load data at the (i-1)-th time point output by the hidden layer, where i is a positive integer; obtaining historical load change characteristics within a historical time period, and having the output layer process the data based on the Y hidden states and historical load change characteristics to obtain a load prediction result.

[0089] Optionally, the computer terminal described above can execute the program code for the following steps in the server cooling process: acquiring historical liquid cooling data of the liquid cooling system collected by M sensors to obtain M initial historical liquid cooling data, where M is a positive integer; preprocessing the M initial historical liquid cooling data to obtain historical liquid cooling data.

[0090] Optionally, the aforementioned computer terminal can execute program code for the following steps in the server cooling process: processing historical liquid cooling data and load prediction results to obtain an operating parameter adjustment strategy for the liquid cooling system, including: obtaining the operating constraints and objective function of the liquid cooling system, wherein the operating constraints are used to constrain the operating parameters of the liquid cooling system; constructing a strategy optimization algorithm based on the objective function and operating constraints, and processing the historical liquid cooling data and load prediction results based on the strategy optimization algorithm to obtain the operating parameter adjustment strategy.

[0091] Optionally, the aforementioned computer terminal can execute the program code for the following steps in the server cooling method: An initial population is randomly generated by a strategy optimization algorithm, wherein the initial population includes K individuals, each individual includes a set of adjustment parameters, each set of adjustment parameters includes initial opening adjustment parameters, initial flow adjustment parameters, and initial temperature adjustment parameters, where K is a positive integer; the function value of the objective function is calculated based on the set of adjustment parameters for each individual in the initial population, resulting in K initial function values; the K individuals are iteratively optimized based on the K initial function values ​​until one of the K optimized individuals has a function value that satisfies the operating constraints; and the operating parameter adjustment strategy is constructed based on the adjustment parameters corresponding to the individual that satisfies the operating constraints.

[0092] Optionally, the aforementioned computer terminal can execute program code for the following steps in the server cooling method: When the load prediction result indicates that the target server's load trend is increasing, extract N first adjustment parameters from the operating parameter adjustment strategy, and adjust the liquid cooling system according to the N first adjustment parameters. The N first adjustment parameters include at least: a first opening adjustment parameter, a first flow rate adjustment parameter, and a first temperature adjustment parameter. The first opening adjustment parameter is used to increase the opening of the pipe valves in the liquid cooling system, the first flow rate adjustment parameter is used to increase the flow rate of the coolant in the liquid cooling system, and the first temperature adjustment parameter is used to decrease the temperature of the coolant. N is a positive integer. When the load prediction result indicates that the target server's load trend is decreasing, extract N second adjustment parameters from the operating parameter adjustment strategy, and adjust the liquid cooling system according to the N second adjustment parameters. The N second adjustment parameters include at least: a second opening adjustment parameter, a second flow rate adjustment parameter, and a second temperature adjustment parameter. The second opening adjustment parameter is used to decrease the opening of the pipe valves in the liquid cooling system, the second flow rate adjustment parameter is used to decrease the flow rate of the coolant in the liquid cooling system, and the second temperature adjustment parameter is used to increase the temperature of the coolant.

[0093] Optionally, the aforementioned computer terminal may execute program code for the following steps in the server cooling method: during the operation of the target server and the adjusted liquid cooling system, acquire the load data of the target server within a preset time period to obtain the operating load data; extract the predicted load data from the load prediction results, calculate the difference between the operating load data and the predicted load data to obtain the load data difference; if the load data difference is greater than or equal to a preset threshold, adjust the operating parameter adjustment strategy, and perform cooling treatment on the target server based on the adjusted operating parameter adjustment strategy.

[0094] Optionally, Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0095] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the server cooling method and apparatus in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the aforementioned server cooling method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0096] The processor can access the information and application programs stored in the memory via the transmission device to execute the steps described above in the server cooling method.

[0097] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, the electronic device may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0098] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0099] Example 4

[0100] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the server cooling method provided in Embodiment 1.

[0101] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0102] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: obtaining load data of the target server within a historical time period, inputting the load data into a load prediction model, and processing it to obtain a load prediction result within a preset time period, wherein the load prediction result includes load change trends and predicted load data; obtaining historical liquid cooling data of the liquid cooling system deployed on the target server, and processing the historical liquid cooling data and load prediction results to obtain an operating parameter adjustment strategy for the liquid cooling system; adjusting the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and cooling the target server based on the adjusted liquid cooling system.

[0103] This application also provides a computer program product, which, when executed on a data processing device, is adapted to perform the steps of a server cooling process method.

[0104] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0105] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0109] If the integrated unit is implemented as 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 this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0110] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A cooling method for a server, characterized in that, include: The load data of the target server in a historical time period is obtained, the load data is input into the load prediction model, and the load prediction result in a preset time period is obtained. The load prediction result includes the load change trend and the predicted load data. Obtain historical liquid cooling data of the liquid cooling system deployed on the target server, and process the historical liquid cooling data and the load prediction results to obtain the liquid cooling system's operating parameter adjustment strategy; The operating parameters of the liquid cooling system are adjusted based on the aforementioned operating parameter adjustment strategy, and the target server is cooled based on the adjusted liquid cooling system.

2. The method according to claim 1, characterized in that, The load prediction model includes a hidden layer and an output layer. The load data is input into the load prediction model, and the resulting load prediction results for a preset time period are obtained as follows: The load data is format-converted to obtain a load sequence, wherein the load sequence includes load data at Y time points within the historical time period, where Y is a positive integer; For the load data at time point i, the hidden state at time point i-1 is obtained. The hidden layer calculates the load data at time point i and the hidden state at time point i-1 to obtain the hidden state at time point i. The hidden state at time point i-1 refers to the hidden state of the load data at time point i-1 output by the hidden layer, where i is a positive integer. The historical load change characteristics within the historical time period are obtained, and the output layer processes the data based on Y hidden states and the historical load change characteristics to obtain the load prediction result.

3. The method according to claim 1, characterized in that, The liquid cooling system deploys M sensors to acquire historical liquid cooling data of the liquid cooling system deployed on the target server, including: Obtain historical liquid cooling data of the liquid cooling system collected by the M sensors to obtain M initial historical liquid cooling data, where M is a positive integer; The M initial historical liquid cooling data are preprocessed to obtain the historical liquid cooling data.

4. The method according to claim 1, characterized in that, The operational parameter adjustment strategy for the liquid cooling system, obtained by processing the historical liquid cooling data and the load prediction results, includes: Obtain the operating constraints and objective function of the liquid cooling system, wherein the operating constraints are used to constrain the operating parameters of the liquid cooling system; A strategy optimization algorithm is constructed based on the objective function and the operating constraints. The historical liquid cooling data and the load prediction results are then processed based on the strategy optimization algorithm to obtain the operating parameter adjustment strategy.

5. The method according to claim 4, characterized in that, Based on the strategy optimization algorithm, the historical liquid cooling data and the load prediction results are processed to obtain the operating parameter adjustment strategy, which includes: An initial population is randomly generated by the strategy optimization algorithm, wherein the initial population includes K individuals, each individual includes a set of adjustment parameters, each set of adjustment parameters includes initial opening adjustment parameters, initial flow adjustment parameters and initial temperature adjustment parameters, and K is a positive integer; The function value of the objective function is calculated based on a set of adjustment parameters for each individual in the initial population, resulting in K initial function values; The K individuals are iteratively optimized based on the K initial function values ​​until one of the K optimized individuals has a function value that satisfies the running constraints. The running parameter adjustment strategy is then constructed based on the adjustment parameters corresponding to the individual that satisfies the running constraints.

6. The method according to claim 1, characterized in that, Adjusting the operating parameters of the liquid cooling system based on the aforementioned operating parameter adjustment strategy includes: When the load prediction result indicates that the load change trend of the target server is an increasing load, N first adjustment parameters are extracted from the operating parameter adjustment strategy, and the liquid cooling system is adjusted according to the N first adjustment parameters. The N first adjustment parameters include at least: a first opening adjustment parameter, a first flow adjustment parameter, and a first temperature adjustment parameter. The first opening adjustment parameter is used to increase the opening of the pipeline valves in the liquid cooling system, the first flow adjustment parameter is used to increase the flow rate of the coolant in the liquid cooling system, and the first temperature adjustment parameter is used to decrease the temperature of the coolant. N is a positive integer. When the load prediction result indicates that the load change trend of the target server is decreasing, N second adjustment parameters are extracted from the operating parameter adjustment strategy, and the liquid cooling system is adjusted according to the N second adjustment parameters. The N second adjustment parameters include at least: a second opening adjustment parameter, a second flow adjustment parameter, and a second temperature adjustment parameter. The second opening adjustment parameter is used to reduce the opening of the pipeline valves in the liquid cooling system, the second flow adjustment parameter is used to reduce the flow rate of the coolant in the liquid cooling system, and the second temperature adjustment parameter is used to increase the temperature of the coolant.

7. The method according to claim 1, characterized in that, After adjusting the operating parameters of the liquid cooling system based on the aforementioned operating parameter adjustment strategy, the method further includes: During the operation of the target server and the adjusted liquid cooling system, the load data of the target server within the preset time period is obtained to obtain the operating load data; Extract the predicted load data from the load prediction results, calculate the difference between the running load data and the predicted load data, and obtain the load data difference. If the difference in load data is greater than or equal to a preset threshold, the operating parameter adjustment strategy is adjusted, and the target server is cooled based on the adjusted operating parameter adjustment strategy.

8. A server cooling device, characterized in that, include: The first acquisition unit is used to acquire the load data of the target server in a historical time period, input the load data into the load prediction model, and process it to obtain the load prediction result in a preset time period. The load prediction result includes the load change trend and the predicted load data. The second acquisition unit is used to acquire historical liquid cooling data of the liquid cooling system deployed on the target server, and process the historical liquid cooling data and the load prediction results to obtain the operating parameter adjustment strategy of the liquid cooling system. The first adjustment unit is used to adjust the operating parameters of the liquid cooling system based on the operating parameter adjustment strategy, and to cool the target server based on the adjusted liquid cooling system.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the cooling method for the server according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the cooling process method for the server according to any one of claims 1 to 7.

Images