Energy consumption control method, device and equipment of data center cooling system, storage medium and program product

Abstract

The invention relates to an energy consumption control method and device for a data center cooling system, equipment, a storage medium and a program product, and the method comprises the steps: obtaining the current operation state data of the data center cooling system, taking the minimization of the total energy consumption of the data center cooling system as a target, and predicting the energy consumption of the data center cooling system according to the operation state data and a target prediction model; a first flow parameter of a primary side water pump and a second flow parameter of a secondary side water pump in the data center cooling system are adjusted to obtain a first target flow of the primary side water pump and a second target flow of the secondary side water pump, and finally the current flow of the primary side water pump is adjusted to the first target flow. And the current flow of the secondary side water pump is adjusted to the second target flow. According to the method, the flow parameters of the primary-side water pump and the secondary-side water pump are adjusted in real time based on the target prediction model, so that the primary-side water pump and the secondary-side water pump operate in the optimal state and can flexibly cope with different operation environment changes, and then the accuracy of energy consumption control is improved.

Description

Technical Field

[0001] The present application relates to the field of data center cooling technology, and in particular to an energy consumption control method, device, equipment, storage medium and program product for a data center cooling system. Background Art

[0002] With the rapid development of information technology, the scale and number of data centers have shown explosive growth. However, with the rapid expansion of data centers, their energy consumption problem has become increasingly prominent, becoming a major challenge restricting their sustainable development.

[0003] The energy consumption of data centers mainly comes from information technology equipment, cooling systems and auxiliary equipment. Among them, the cooling system needs to maintain a suitable temperature for servers and other key equipment to ensure their normal operation, so the energy consumption of the cooling system accounts for a large proportion. Therefore, effectively controlling the energy consumption of the data center cooling system is the key to solving the energy consumption problem.

[0004] Currently, in the process of controlling the energy consumption of a data center cooling system, a PID control algorithm is usually used for control. However, the above energy consumption control method has the problem of inaccuracy. Summary of the invention

[0005] Based on this, it is necessary to provide an energy consumption control method, device, equipment, storage medium and program product for a data center cooling system that can improve control accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides an energy consumption control method for a data center cooling system, the method comprising:

[0007] Obtain the current operating status data of the data center cooling system;

[0008] With the goal of minimizing the total energy consumption of the data center cooling system, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted according to the operating status data and the target prediction model to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system;

[0009] The current flow rate of the primary-side water pump is adjusted to the first target flow rate, and the current flow rate of the secondary-side water pump is adjusted to the second target flow rate.

[0010] In one embodiment, with the goal of minimizing the total energy consumption of the data center cooling system, a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in the data center cooling system are adjusted according to the operating status data and the target prediction model to obtain a first target flow of the primary water pump and a second target flow of the secondary water pump, including:

[0011] Input the operating status data into the target prediction model for prediction, and obtain the server chip temperature and the total energy consumption of the data center cooling system;

[0012] The constraint conditions are established based on the server chip temperature, the flow regulation range of the primary water pump, and the flow regulation range of the secondary water pump;

[0013] With the goal of minimizing the total energy consumption of the data center cooling system, based on constraints, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump.

[0014] In one embodiment, the target prediction model includes a system state prediction model, a water pump energy consumption prediction model, a server state prediction model and a comprehensive loss prediction model. The operation state data is input into the target prediction model for prediction to obtain the server chip temperature and the total energy consumption of the data center cooling system, including:

[0015] Inputting the first operating state data in the operating state data into the system state prediction model for prediction, and obtaining the cooling tower energy consumption, the secondary side inlet water temperature and the secondary side outlet water temperature; the first operating state data includes the primary side flow rate, the secondary side flow rate, the outdoor temperature, the outdoor humidity and the server load;

[0016] Input the second operating state data in the operating state data into the water pump energy consumption prediction model for prediction, and obtain the primary side water pump energy consumption and the secondary side water pump energy consumption; the second operating state data includes the primary side flow rate, the secondary side flow rate, the primary side water pump energy consumption reference value, the secondary side water pump energy consumption reference value, the primary side water pump flow reference value under the primary side water pump energy consumption reference value, and the secondary side water pump flow reference value under the secondary side water pump energy consumption reference value;

[0017] Input the secondary side water inlet temperature, the secondary side water outlet temperature and the third operating state data in the operating state data into the server state prediction model for prediction to obtain the server chip temperature; the third operating state data includes the secondary side flow, the server load and the server chip heat dissipation area;

[0018] The cooling tower energy consumption, primary water pump energy consumption and secondary water pump energy consumption are input into the comprehensive loss prediction model and summed to obtain the total energy consumption of the data center cooling system.

[0019] In one embodiment, the server state prediction model includes a first prediction sub-model and a second prediction sub-model, and the secondary side water inlet temperature, the secondary side water outlet temperature and the third operating state data in the operating state data are input into the server state prediction model for prediction to obtain the server chip temperature, including:

[0020] The secondary side flow rate and the secondary side inlet water temperature are input into the first prediction sub-model for prediction to obtain the heat transfer thermal resistance of the server chip;

[0021] The secondary side water inlet temperature, the secondary side water outlet temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance are input into the second prediction sub-model for prediction to obtain the server chip temperature.

[0022] In one embodiment, with the goal of minimizing the total energy consumption of the data center cooling system, based on the constraint conditions, a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in the data center cooling system are adjusted to obtain a first target flow of the primary water pump and a second target flow of the secondary water pump, including:

[0023] Based on the constraint condition, a first flow parameter of a primary-side water pump and a second flow parameter of a secondary-side water pump in a cooling system of a data center are adjusted to obtain an adjusted first flow parameter and an adjusted second flow parameter;

[0024] Determine new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter, and return to execute the step of inputting the operating status data into the target prediction model for prediction, obtain the server chip temperature and the total energy consumption of the data center cooling system, and obtain the total energy consumption of the cooling systems of multiple data centers;

[0025] The value of the first flow parameter and the value of the second flow parameter corresponding to when the total energy consumption of the cooling system of the data center is the minimum total energy consumption are respectively determined as the first target flow rate and the second target flow rate.

[0026] In one embodiment, the method further comprises:

[0027] Determine whether the current number of cycles reaches the preset number;

[0028] If the current number of cycles does not reach the preset number of times, returning to the step of determining new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter;

[0029] If the current number of cycles reaches the preset number, the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system are respectively determined as the first target flow and the second target flow, including:

[0030] The value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system within a preset number of times are determined as the first target flow rate and the second target flow rate, respectively.

[0031] In a second aspect, the present application also provides an energy consumption control device for a data center cooling system, the device comprising:

[0032] An acquisition module is used to obtain the current operating status data of the data center cooling system;

[0033] A prediction module is used to adjust a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in the data center cooling system according to operation status data and a target prediction model with the goal of minimizing the total energy consumption of the data center cooling system, so as to obtain a first target flow rate of the primary water pump and a second target flow rate of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system;

[0034] The regulating module is used to regulate the current flow rate of the primary-side water pump to the first target flow rate, and to regulate the current flow rate of the secondary-side water pump to the second target flow rate.

[0035] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0036] Obtain the current operating status data of the data center cooling system;

[0037] With the goal of minimizing the total energy consumption of the data center cooling system, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted according to the operating status data and the target prediction model to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system;

[0038] The current flow rate of the primary-side water pump is adjusted to the first target flow rate, and the current flow rate of the secondary-side water pump is adjusted to the second target flow rate.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Obtain the current operating status data of the data center cooling system;

[0041] With the goal of minimizing the total energy consumption of the data center cooling system, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted according to the operating status data and the target prediction model to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system;

[0042] The current flow rate of the primary-side water pump is adjusted to the first target flow rate, and the current flow rate of the secondary-side water pump is adjusted to the second target flow rate.

[0043] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] Obtain the current operating status data of the data center cooling system;

[0045] With the goal of minimizing the total energy consumption of the data center cooling system, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted according to the operating status data and the target prediction model to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system;

[0046] The current flow rate of the primary-side water pump is adjusted to the first target flow rate, and the current flow rate of the secondary-side water pump is adjusted to the second target flow rate.

[0047] The energy consumption control method, device, equipment, storage medium and program product of the data center cooling system are described above. The method obtains the current operating status data of the data center cooling system, and then takes the total energy consumption of the data center cooling system as the goal, and adjusts the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system according to the operating status data and the target prediction model, so as to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump, and finally adjusts the current flow of the primary side water pump to the first target flow, and adjusts the current flow of the secondary side water pump to the second target flow. Among them, the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system. In the above method, since the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system, the flow parameters of the primary side and secondary side water pumps are adjusted in real time based on the target prediction model to make them operate in the best state, which can flexibly respond to different operating environment changes, improve the stability and reliability of the system, and thus improve the accuracy of energy consumption control, and at the same time, it can minimize unnecessary energy consumption, thereby reducing the operating cost of the data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is an application environment diagram of an energy consumption control method for a data center cooling system in one embodiment;

[0049] Figure 2 A schematic flow chart of an energy consumption control method for a data center cooling system in one embodiment;

[0050] Figure 3 A schematic flow chart of an energy consumption control method for a data center cooling system in another embodiment;

[0051] Figure 4 A schematic flow chart of an energy consumption control method for a data center cooling system in another embodiment;

[0052] Figure 5 A schematic flow chart of an energy consumption control method for a data center cooling system in another embodiment;

[0053] Figure 6 A schematic flow chart of an energy consumption control method for a data center cooling system in another embodiment;

[0054] Figure 7 A schematic flow chart of an energy consumption control method for a data center cooling system in another embodiment;

[0055] Figure 8 A schematic flow chart of an energy consumption control method for a data center cooling system in another embodiment;

[0056] Fig. 9 A structural block diagram of an energy consumption control device for a data center cooling system in one embodiment;

[0057] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] With the rapid development of information technology, the scale and number of data centers have exploded. However, with the rapid expansion of data centers, their energy consumption problem has become increasingly prominent, becoming a major challenge restricting their sustainable development. The energy consumption of data centers mainly comes from information technology equipment, cooling systems and auxiliary equipment. Among them, the cooling system needs to maintain the appropriate temperature of servers and other key equipment to ensure their normal operation, so the energy consumption of the cooling system accounts for a large proportion. Therefore, effectively controlling the energy consumption of the data center cooling system is the key to solving the energy consumption problem. At present, in the process of controlling the energy consumption of the data center cooling system, PID control algorithm is usually used for control. However, the above energy consumption control method has the problem of inaccuracy.

[0060] The present application provides an energy consumption control method for a data center cooling system, aiming to solve the above-mentioned technical problems. The following embodiments will specifically illustrate the energy consumption control method for a data center cooling system described in the present application.

[0061] The energy consumption control method of the data center cooling system provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the application environment includes a computer device 101 and a data center device 102. The computer device 101 is connected to a data center cooling system 102. The data center cooling system 102 includes a cooling tower 1021, a primary water pump 1022, a secondary water pump 1023, a plate heat exchanger 1024, and a server 1025. The computer device 101 is used to adjust a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in the data center cooling system to obtain a first target flow of the primary water pump and a second target flow of the secondary water pump, and control the energy consumption of the data center cooling system based on the first target flow and the second target flow. The data center cooling system 102 is divided into a primary cooling water cycle and a secondary cooling water cycle. The primary cooling water cycle includes a cooling tower and a primary water pump, and the secondary cooling water cycle includes a server cabinet and a secondary water pump. The primary cooling water from the cooling tower enters the plate heat exchanger to extract heat and is pumped to the cooling tower by the primary pump for cooling. The secondary cooling water cools the microchip in the server radiator, returns to the plate heat exchanger, and returns to the server through the secondary water pump.

[0062] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the data center cooling system to which the scheme of the present application is applied. The specific data center cooling system may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0063] In one embodiment, Figure 2 As shown, a method for controlling energy consumption of a data center cooling system is provided. Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0064] S201, obtaining current operating status data of a data center cooling system.

[0065] Among them, the operating status data includes primary side flow, secondary side flow, outdoor temperature, outdoor humidity, server load, primary side water pump energy consumption reference value, secondary side water pump energy consumption reference value, primary side water pump flow reference value under the primary side water pump energy consumption reference value and secondary side water pump flow reference value under the secondary side water pump energy consumption reference value, secondary side flow and at least one of the server chip heat dissipation area.

[0066] In the embodiment of the present application, temperature and humidity sensors can be pre-arranged outdoors in the data center, and flow sensors can be arranged at the outlets of the primary water pump and the secondary water pump of the cooling system, and connected to the computer device. The computer device can obtain parameters such as outdoor temperature and outdoor humidity through temperature and humidity sensors, monitor the server load in real time by starting a preset status query function, and obtain relevant attribute information of the primary water pump, relevant attribute information of the secondary water pump, and relevant attribute information of the server chip by crawling the network or querying the device parameter manual. Optionally, after obtaining the current operating status data of the cooling system of the data center, the computer device can perform pre-processing operations such as data cleaning, interpolation, and data enhancement on the operating status data to obtain pre-processed operating status data for subsequent use.

[0067] S202, with the goal of minimizing the total energy consumption of the data center cooling system, adjust the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system according to the operating status data and the target prediction model to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump.

[0068] The target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system. The target prediction model can be a neural network model, a machine algorithm model, or a mathematical model. The total energy consumption of the data center cooling system includes the energy consumption of the cooling tower, the energy consumption of the primary side water pump, and the energy consumption of the secondary side water pump.

[0069] In an embodiment of the present application, the computer device can construct a target prediction model in advance based on all equipment parameters and environmental parameters in the data center cooling system. Specifically, the initial prediction model can be trained according to all equipment parameter samples and environmental parameter samples to obtain the target prediction model. Optionally, the computer device can fine-tune the existing prediction model based on all equipment parameters and environmental parameters in the data center cooling system to obtain the target prediction model. Optionally, the computer device can construct a target prediction model based on all equipment parameters and environmental parameters in the data center cooling system in advance according to a preset mathematical algorithm. After the computer device obtains the operating status data and the target prediction model, the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system can be adjusted, and the first flow parameter and the second flow parameter after each adjustment can be input into the target prediction model for energy consumption prediction, and the total energy consumption of the data center cooling system after each adjustment can be obtained. Then, the minimum total energy consumption is determined among the multiple total energy consumptions, and the first flow parameter corresponding to the minimum total energy consumption is used as the first target flow, and the second flow parameter corresponding to the minimum total energy consumption is used as the second target flow.

[0070] S203, adjusting the current flow rate of the primary-side water pump to the first target flow rate, and adjusting the current flow rate of the secondary-side water pump to the second target flow rate.

[0071] In the embodiment of the present application, after the computer device obtains the first target flow rate of the primary water pump and the second target flow rate of the secondary water pump based on the above steps, it can control the primary water pump to adjust the current flow rate to the first target flow rate, and control the secondary water pump to adjust the current flow rate to the second target flow rate. Optionally, the first flow rate gear corresponding to the first target flow rate and the second flow rate gear corresponding to the second target flow rate can be determined, and then the current flow rate gear of the primary water pump is adjusted to the first flow rate gear, and the current flow rate gear of the secondary water pump is adjusted to the second flow rate gear.

[0072] The energy consumption control method of the data center cooling system provided in the embodiment of the present application obtains the current operating status data of the data center cooling system, and then takes the total energy consumption of the data center cooling system as the goal, and adjusts the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system according to the operating status data and the target prediction model, so as to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump, and finally adjusts the current flow of the primary side water pump to the first target flow, and adjusts the current flow of the secondary side water pump to the second target flow. Among them, the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system. In the above method, since the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system, the flow parameters of the primary side and secondary side water pumps are adjusted in real time based on the target prediction model to make them operate in the best state, which can flexibly respond to different operating environment changes, improve the stability and reliability of the system, and thus improve the accuracy of energy consumption control, and at the same time, it can minimize unnecessary energy consumption, thereby reducing the operating cost of the data center.

[0073] In one embodiment, a specific implementation method for adjusting a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in a data center cooling system is also provided, such as Figure 3 As shown, the above step S202 of "taking minimizing the total energy consumption of the data center cooling system as the goal, adjusting the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system according to the operating status data and the target prediction model to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump" includes:

[0074] S301, inputting the operation status data into the target prediction model for prediction, and obtaining the server chip temperature and the total energy consumption of the data center cooling system.

[0075] Among them, the target prediction model includes system status prediction model, water pump energy consumption prediction model, server status prediction model and comprehensive loss prediction model.

[0076] In an embodiment of the present application, after obtaining the operating status data and the target prediction model, the computer device can input the operating status data into the target prediction model, and predict the server chip temperature and the total energy consumption of the data center cooling system through the target prediction model to obtain the server chip temperature and the total energy consumption of the data center cooling system.

[0077] Optional, such as Figure 4 As shown, the above step S301 of "inputting the operating status data into the target prediction model for prediction to obtain the server chip temperature and the total energy consumption of the data center cooling system" includes:

[0078] S401, inputting the first operating state data in the operating state data into a system state prediction model for prediction, and obtaining cooling tower energy consumption, secondary side water inlet temperature, and secondary side water outlet temperature.

[0079] The first operation status data includes primary side flow, secondary side flow, outdoor temperature, outdoor humidity and server load. The system status prediction model includes cooling tower energy consumption prediction model, secondary side inlet water temperature prediction model and secondary side outlet water temperature prediction model.

[0080] In the embodiment of the present application, the computer device can pre-train the BP neural network based on the running status data sample to obtain the system status prediction model. The specific method is as follows:

[0081] 1. Obtain the operating condition data of the primary water pump and the secondary water pump under different environmental parameters and different server operating conditions of the data center cooling system as state data samples. Specifically, the operating state data samples include first sample data and second sample data. Among them, (1) the first sample data includes outdoor temperature, outdoor humidity, server load, primary water pump flow rate (which can be determined by the primary side flow), and secondary water pump flow rate (which can be determined by the secondary side flow). Since the operating data has a strong correlation with the subsequent model, the data can be obtained by field project collection. Specifically, temperature and humidity sensors are arranged outdoors in the data center, and flow sensors are arranged at the outlets of the primary water pump and the secondary water pump of the cooling system, and the workload of the data center servers is monitored at the same time. (2) The second sample data includes: server inlet water temperature, server outlet water temperature, secondary return water temperature, cooling tower outlet water temperature, primary side plate heat exchanger temperature, and cooling tower return water temperature. The data center cooling system operating condition data can be obtained through project field collection or simulation software in two forms: the first is field collection: obtaining the data center cooling system operating condition data through project field collection can more accurately show the relationship between the energy consumption of the data center cooling system components and the operating parameters, thereby making the dynamic control of the operation adjustment technology more effective. The second is the simulation software method: considering that the cooling system operating condition data is a process variable of the dynamic operation adjustment technology, after weighing the collection cost and the model prediction accuracy, after obtaining the first sample data, the water temperature of the data center cooling system and the energy consumption data of each component can be obtained through energy consumption software such as TRNSYS as the second sample data.

[0082] 2. Establish a system state prediction model based on BP neural network based on the operation state data samples. The computer equipment can first normalize the operation state data samples, and divide the processed data into training set and test set in proportion. Since there is a nonlinear relationship between the outdoor parameters, server load, fluid operation conditions, and energy consumption data of each component during the operation of the cooling system, in order to accurately express the global energy consumption of the data center cooling system, a BP neural network is used to establish a system state prediction model. The specific process is as follows:

[0083] (1) The running status data samples are normalized by a normalization formula, and the same data is normalized to [0, 1]. The normalization formula is:

[0084]

[0085] Where y represents the normalized data, x represents the original data of the running status data sample, and min(x) and max(x) represent the minimum and maximum values ​​of the original data.

[0086] (2) The normalized data is randomly divided into a training data set and a test data set according to the specified ratio. In the specific example, 75% of the total samples are used as the model training data set, and 25% of the total samples are used as the model test data set.

[0087] (3) Based on the BP neural network, a system state prediction model is built, in which the input variables involved are all parameter variables of the operating state data samples. When constructing the BP neural network, it is necessary to determine the input layer, output layer and hidden layer structure of the corresponding model neural network. The input layer and output layer are generally determined by the model requirements and data, while the hidden layer structure usually refers to the formula to determine the number of hidden layer neuron nodes, and the optimal number of nodes is obtained by trial and error. The reference formula for the hidden layer nodes is:

[0088]

[0089] Among them, l represents the number of hidden layer nodes, m represents the number of output layer nodes, n represents the number of input layer nodes, and a represents a constant between 0 and 10.

[0090] Specifically, the system state prediction model includes a cooling tower energy consumption prediction model, a secondary side inlet water temperature prediction model, and a secondary side outlet water temperature prediction model. The specific construction process is as follows:

[0091] ①Construct cooling tower energy consumption prediction model

[0092] The input variables of the cooling tower energy consumption prediction model are primary side flow, secondary side flow, outdoor temperature, outdoor humidity, server chip load power (determined by server load), and the output variable is cooling tower energy consumption. The obtained cooling tower energy consumption prediction model is:

[0093]

[0094] in, represents the energy consumption of cooling tower, is the primary side flow, is the secondary side flow, is the outdoor temperature, is the outdoor humidity, is the server chip load power.

[0095] ②Construct a secondary side inlet water temperature prediction model

[0096] In order to calculate the server chip temperature, the secondary side fluid temperature before entering the server is predicted, and a secondary side water inlet temperature prediction model is established using a BP neural network. The input variables in the model are primary side flow, secondary side flow, outdoor temperature, outdoor humidity, and server load rate, and the output variable is the secondary side water inlet temperature. The secondary side fluid water inlet temperature prediction model is:

[0097]

[0098] in, Indicates the secondary side fluid inlet water temperature and server inlet water temperature, secondary side return water temperature, is the primary side flow, is the secondary side flow, is the outdoor temperature, is the outdoor humidity, is the server chip load power.

[0099] ③Construct a secondary side outlet water temperature prediction model

[0100] In order to calculate the server chip temperature, the secondary side fluid temperature flowing out of the server is predicted, and a secondary side outlet water temperature prediction model is established using a BP neural network. The input variables in the model are primary side flow, secondary side flow, outdoor temperature, outdoor humidity, and server load rate, and the output variable is the secondary side inlet water temperature. The secondary side fluid outlet water temperature prediction model is obtained:

[0101]

[0102] in, Indicates the secondary side fluid outlet water temperature, is the primary side flow, is the secondary side flow, is the outdoor temperature, is the outdoor humidity, is the server chip load power.

[0103] After obtaining the operation status data, the computer device can input the first operation status data in the operation status data into the system status prediction model for prediction, and obtain the cooling tower energy consumption, the secondary side inlet water temperature and the secondary side outlet water temperature. Specifically, the first operation status data can be input into the cooling tower energy consumption prediction model for prediction, and the cooling tower energy consumption can be obtained; the first operation status data can be input into the secondary side inlet water temperature prediction model for prediction, and the secondary side inlet water temperature can be obtained; the first operation status data can be input into the secondary side outlet water temperature prediction model for prediction, and the secondary side outlet water temperature can be obtained.

[0104] S402: Input the second operating state data in the operating state data into a water pump energy consumption prediction model for prediction to obtain the primary side water pump energy consumption and the secondary side water pump energy consumption.

[0105] The second operation state data includes a primary side flow rate, a secondary side flow rate, a primary side water pump energy consumption reference value, a secondary side water pump energy consumption reference value, a primary side water pump flow reference value under the primary side water pump energy consumption reference value, and a secondary side water pump flow reference value under the secondary side water pump energy consumption reference value. The water pump energy consumption prediction model includes a primary side water pump energy consumption prediction model and a secondary side water pump energy consumption prediction model.

[0106] In the embodiment of the present application, the computer device can pre-build a water pump energy consumption prediction model. It can be expressed by the following relationship:

[0107]

[0108] in, is the energy consumption of the pump, is the reference value of water pump energy consumption power, is the pump flow rate, is the reference value of the water pump flow rate under the reference power. Similarly, the water pump energy consumption prediction model can be constructed using the above water pump energy consumption prediction model to construct the primary side water pump energy consumption prediction model and secondary side water pump energy consumption prediction model .

[0109] After obtaining the operating status data, the computer device can input the second operating status data in the operating status data into the water pump energy consumption prediction model for prediction, and obtain the primary side water pump energy consumption and the secondary side water pump energy consumption. Specifically, the second operating status data can be input into the water pump energy consumption prediction model on the primary side for prediction, and the primary side water pump energy consumption can be obtained, and the second operating status data can be input into the water pump energy consumption prediction model on the secondary side for prediction, and the secondary side water pump energy consumption can be obtained.

[0110] S403, inputting the secondary side water inlet temperature, the secondary side water outlet temperature and the third operating state data in the operating state data into a server state prediction model for prediction to obtain the server chip temperature.

[0111] The third operation status data includes secondary side flow, server load, and server chip heat dissipation area. The server status prediction model can be a neural network model, a machine algorithm model, or a mathematical model.

[0112] In an embodiment of the present application, the computer device may pre-train an initial server state prediction model based on an operation state data sample to obtain a server state prediction model. Optionally, the computer device may obtain an existing prediction model and use it as the server state prediction model in this embodiment. Optionally, the computer device may pre-build a server state prediction model based on a preset mathematical algorithm. After obtaining the secondary side water inlet temperature, the secondary side water outlet temperature and the operation state data, the computer device may input the secondary side water inlet temperature, the secondary side water outlet temperature and the third operation state data in the operation state data into the server state prediction model for prediction to obtain the server chip temperature.

[0113] Optional, such as Figure 5 As shown, the server status prediction model includes a first prediction sub-model and a second prediction sub-model. On this basis, the "inputting the secondary side water inlet temperature, the secondary side water outlet temperature and the third operating status data in the operating status data into the server status prediction model for prediction to obtain the server chip temperature" in the above step S403 includes:

[0114] S4031, input the secondary side flow rate and the secondary side water inlet temperature into the first prediction sub-model for prediction to obtain the heat transfer thermal resistance of the server chip.

[0115] Among them, the first prediction sub-model is a server chip heat transfer thermal resistance prediction model.

[0116] In the embodiment of the present application, the computer device may pre-build the first prediction sub-model, and the specific construction method is as follows:

[0117] The server chip heat transfer thermal resistance prediction model is fitted by the least squares method. In order to calculate the server chip temperature, it is necessary to accurately express the nonlinear relationship between the server chip heat transfer thermal resistance and the secondary side fluid. The server chip heat transfer thermal resistance is strongly correlated with the temperature and flow rate of the secondary side fluid flowing through the server chip. Therefore, the server chip heat transfer thermal resistance prediction model can be expressed as follows by fitting the least squares method:

[0118]

[0119] in, is the heat transfer resistance of the server chip, is the secondary side flow, Indicates the secondary side inlet water temperature.

[0120] After the computer device obtains the secondary side flow rate and the secondary side water inlet temperature, the secondary side flow rate and the secondary side water inlet temperature can be input into the first prediction sub-model for prediction to obtain the heat transfer thermal resistance of the server chip.

[0121] S4032, input the secondary side water inlet temperature, the secondary side water outlet temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance into the second prediction sub-model for prediction to obtain the server chip temperature.

[0122] Among them, the second prediction sub-model is a server chip temperature prediction model.

[0123] In the embodiment of the present application, the computer device may pre-build the second prediction sub-model, and the specific construction method is as follows:

[0124] Assuming that the server chip surface is adiabatic to the surrounding environment and the fluid flow is stable, according to Fourier's law, the server chip temperature It can be expressed as:

[0125]

[0126] in, is the server chip temperature, is the average temperature of the secondary side fluid flowing through the server, is the server chip load power, is the heat dissipation area of ​​the server chip, Thermal resistance of server chip.

[0127] Furthermore, the average temperature of the secondary fluid flowing through the server It can be expressed as:

[0128]

[0129] in, is the secondary side inlet water temperature, is the secondary side outlet water temperature.

[0130] After the computer equipment obtains the secondary side water inlet temperature, the secondary side water outlet temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance, the secondary side water inlet temperature, the secondary side water outlet temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance can be input into the second prediction sub-model for prediction to obtain the server chip temperature.

[0131] S404: Input the cooling tower energy consumption, the primary water pump energy consumption and the secondary water pump energy consumption into the comprehensive loss prediction model for summing, thereby obtaining the total energy consumption of the data center cooling system.

[0132] Among them, the comprehensive loss prediction model is used to sum the cooling tower energy consumption, the primary side water pump energy consumption and the secondary side water pump energy consumption.

[0133] In an embodiment of the present application, after the computer equipment obtains the cooling tower energy consumption, the primary water pump energy consumption and the secondary water pump energy consumption based on the above steps, the cooling tower energy consumption, the primary water pump energy consumption and the secondary water pump energy consumption can be input into a comprehensive loss prediction model. The cooling tower energy consumption, the primary water pump energy consumption and the secondary water pump energy consumption are summed up by the comprehensive loss prediction model to obtain the total energy consumption of the data center cooling system.

[0134] S302: Construct constraint conditions according to the server chip temperature, the flow rate regulation range of the primary side water pump, and the flow rate regulation range of the secondary side water pump.

[0135] In the embodiment of the present application, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted by using the sand cat group algorithm. After the computer device obtains the server chip temperature based on the above steps, it can construct constraint conditions according to the server chip temperature, the flow adjustment range of the primary water pump and the flow adjustment range of the secondary water pump. The specific construction process is:

[0136] (1) Initialize the initial population of sand cats and determine the relevant parameters. Specifically, determine the maximum number of iterations of the sand cat swarm algorithm. , Search Dimension and population size In the target prediction model, the items to be optimized are the flow rate of the primary water pump (i.e., the primary flow rate) and the flow rate of the secondary water pump (i.e., the secondary flow rate), so the search dimension .

[0137] The flow rate regulation range of the primary side water pump and the flow rate regulation range of the secondary side water pump cannot exceed the selection range, so the search space of the primary side flow rate and the secondary side flow rate are respectively and .

[0138] When the population is initialized, the position of each sand cat individual is a combination of the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump. , and the initial population of sand cats is randomly generated. The formula for generating random population initialization by the sand cat swarm algorithm is:

[0139]

[0140] in, It is The location of an individual, yes A random number between is the upper bound of the search space, is the lower bound of the search space.

[0141] Step S302, update the search space of sand cat population individuals. The primary goal of the data center cooling system is to ensure the safe operation of the data center, that is, to ensure that the server chip temperature is below the safe temperature. In order to ensure that the server chip temperature is not higher than the safe temperature, it is necessary to constrain the optimization algorithm through the constraint condition. The constraint condition is: the operating temperature of the server cannot exceed the safe temperature

[0142]

[0143] in, is the server chip temperature, Safe temperature for server chips.

[0144] S303, with the goal of minimizing the total energy consumption of the data center cooling system, based on constraints, adjust the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump.

[0145] In the embodiment of the present application, after the computer device constructs the constraint conditions based on the above steps, the total energy consumption of the data center cooling system can be minimized, and based on the constraint conditions, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system can be adjusted to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump. The specific process is as follows:

[0146] (1) Constructing individual evaluation indicators for sand cat populations

[0147] The parameters that affect the data target prediction model include outdoor temperature and humidity, server load, and cooling system operating conditions. Therefore, under the premise of ensuring the safe operation of the server, the liquid cooling system in the data center needs to optimize the primary side flow and secondary side flow regulation to find the optimal fluid operating conditions on the server side and the cooling source side, and ultimately minimize the total energy consumption of the data center cooling system. That is, the optimization objective function of the model is:

[0148]

[0149] in, It is the optimal operating condition for primary and secondary side fluids; is the cooling tower energy consumption, is the energy consumption of the primary water pump, is the energy consumption of the secondary side water pump.

[0150] The optimization goal of the model is to find the optimal operating conditions of the data center cooling system. It is necessary to determine the optimal individual of the sand cat population so that the individuals in the predatory state can move to the optimal individual during the iteration process. Therefore, the indicator for evaluating the optimal individual of the sand cat population in each iteration is:

[0151]

[0152] in, is the optimal individual, It can be calculated by the following formula:

[0153]

[0154] in, is the total energy consumption of the data center cooling system.

[0155] In one embodiment, a specific implementation method for adjusting a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in a data center cooling system is also provided, such as Figure 6 As shown, the above step S303 of "taking the total energy consumption of the data center cooling system as the goal, based on the constraint conditions, adjusting the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump" includes:

[0156] S501, based on the constraint condition, adjusting a first flow parameter of a primary side water pump and a second flow parameter of a secondary side water pump in a cooling system of a data center to obtain an adjusted first flow parameter and an adjusted second flow parameter.

[0157] In an embodiment of the present application, after obtaining the constraint conditions, the computer equipment can adjust the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system within the constraint conditions to obtain the adjusted first flow parameter and the adjusted second flow parameter.

[0158] S502, determine new operating status data based on the adjusted first flow parameter and the adjusted second flow parameter, and return to execute the step of inputting the operating status data into the target prediction model for prediction, obtain the server chip temperature and the total energy consumption of the data center cooling system, and obtain the total energy consumption of multiple data center cooling systems.

[0159] In an embodiment of the present application, after the computer device obtains the adjusted first flow parameter and the adjusted second flow parameter based on the above steps, it can update the first flow parameter and the second flow parameter in the operating status data to obtain new operating status data, and return to execute the step of inputting the operating status data into the target prediction model for prediction to obtain the server chip temperature and the total energy consumption of the data center cooling system, that is, return to execute the step of S301 to obtain the total energy consumption of multiple data center cooling systems.

[0160] S503: Determine the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the cooling system of the data center as the first target flow rate and the second target flow rate, respectively.

[0161] In an embodiment of the present application, after the computer obtains the total energy consumption of multiple data center cooling systems based on the above steps, the value of the first flow parameter corresponding to the total energy consumption of the data center cooling system is the minimum total energy consumption can be determined as the first target flow, and the value of the second flow parameter corresponding to the total energy consumption of the data center cooling system is the minimum total energy consumption can be determined as the second target flow.

[0162] The method described in the embodiment of the present application ensures the temperature of the data center server chip by establishing an optimization model for the optimal scheduling of the data center natural cooling system based on the sand cat group optimization algorithm, thereby ensuring the safe operation of the data center to the greatest extent. A mathematical model of the cooling system components is established through BP neural network and transmitted to the cooling system operation optimization layer. On this basis, based on the sand cat group optimization algorithm, with the goal of minimizing the total energy consumption of the data center cooling system, the total energy consumption of the data center cooling system is finally optimized under the conditions of outdoor parameters, server load, and system component operating conditions.

[0163] In one embodiment, Figure 7 As shown, the energy consumption control method of the data center cooling system further includes:

[0164] S601, determining whether the current number of cycles reaches a preset number.

[0165] In the embodiment of the present application, the computer device can pre-set a preset number of times as the maximum number of iterations according to the algorithm optimization accuracy. During the system optimization process, the computer device can record the number of optimizations each time as the number of cycles, and determine whether the current number of cycles reaches the preset number. Specifically, it is determined whether the algorithm has reached the maximum number of iterations. If the maximum number of iterations is reached, the optimal parameters are obtained, and the optimal solution is output as the optimal operating condition of the cooling system.

[0166] S602: If the current number of cycles does not reach the preset number, return to the step of determining new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter.

[0167] In the embodiment of the present application, if the current number of cycles does not reach the preset number, the process returns to the step of determining new operating status data based on the adjusted first flow parameter and the adjusted second flow parameter, that is, returns to the step of executing S502.

[0168] If the current number of cycles reaches the preset number of times, the computer device executes S503 "determine the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system as the first target flow and the second target flow, respectively", and specifically executes:

[0169] S603: Determine the first flow parameter value and the second flow parameter value corresponding to the minimum total energy consumption of the data center cooling system within a preset number of times as the first target flow rate and the second target flow rate, respectively.

[0170] In an embodiment of the present application, if the current number of cycles reaches a preset number, the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system within the preset number are determined as the first target flow and the second target flow, respectively.

[0171] The method described in the embodiment of the present application gradually optimizes the energy consumption of the data center cooling system by cyclically adjusting the flow parameters, and finally determines the target flow parameters that minimize the total energy consumption. This method can significantly reduce energy consumption, improve system efficiency, and enhance system stability, thereby achieving the goals of intelligent management and energy conservation and emission reduction.

[0172] Based on all the above embodiments, a method for controlling energy consumption of a data center cooling system is also provided. Figure 8 As shown, the method includes:

[0173] S701, obtaining current operating status data of a data center cooling system.

[0174] S702: Input the first operating state data in the operating state data into the system state prediction model for prediction to obtain cooling tower energy consumption, secondary side water inlet temperature and secondary side water outlet temperature. The first operating state data includes primary side flow, secondary side flow, outdoor temperature, outdoor humidity and server load.

[0175] S703, inputting the second operating state data in the operating state data into the water pump energy consumption prediction model for prediction, and obtaining the primary side water pump energy consumption and the secondary side water pump energy consumption. The second operating state data includes the primary side flow rate, the secondary side flow rate, the primary side water pump energy consumption reference value, the secondary side water pump energy consumption reference value, the primary side water pump flow reference value under the primary side water pump energy consumption reference value, and the secondary side water pump flow reference value under the secondary side water pump energy consumption reference value.

[0176] S704: Input the secondary side flow rate and the secondary side water inlet temperature into the first prediction sub-model for prediction to obtain the heat transfer thermal resistance of the server chip.

[0177] S705, input the secondary side water inlet temperature, the secondary side water outlet temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance into the second prediction sub-model for prediction to obtain the server chip temperature. The third operating state data includes the secondary side flow, the server load and the server chip heat dissipation area.

[0178] S706: Input the cooling tower energy consumption, the primary side water pump energy consumption and the secondary side water pump energy consumption into the comprehensive loss prediction model for summing, thereby obtaining the total energy consumption of the data center cooling system.

[0179] S707: Construct constraint conditions according to the server chip temperature, the flow rate regulation range of the primary side water pump, and the flow rate regulation range of the secondary side water pump.

[0180] S708, based on the constraint condition, adjusting the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system to obtain an adjusted first flow parameter and an adjusted second flow parameter.

[0181] S709, determine new operating status data based on the adjusted first flow parameter and the adjusted second flow parameter, and return to execute the step of inputting the operating status data into the target prediction model for prediction, obtain the server chip temperature and the total energy consumption of the data center cooling system, and obtain the total energy consumption of multiple data center cooling systems.

[0182] S710, determining whether the current number of cycles reaches a preset number.

[0183] S711, if the current number of cycles does not reach the preset number, return to the step of determining new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter.

[0184] S712, if the current number of cycles reaches the preset number, the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system within the preset number are determined as the first target flow and the second target flow, respectively.

[0185] S713, adjusting the current flow rate of the primary-side water pump to the first target flow rate, and adjusting the current flow rate of the secondary-side water pump to the second target flow rate.

[0186] The methods described in the above steps are all described in the above embodiments. Please refer to the above description for details and will not be repeated here.

[0187] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0188] Based on the same inventive concept, the embodiment of the present application also provides an energy consumption control device for a data center cooling system for implementing the energy consumption control method for a data center cooling system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the energy consumption control device for a data center cooling system provided below can refer to the limitations of the energy consumption control method for a data center cooling system above, and will not be repeated here.

[0189] In one embodiment, Fig. 9 As shown, an energy consumption control device for a data center cooling system is provided, comprising:

[0190] The acquisition module 11 is used to acquire the current operating status data of the data center cooling system.

[0191] The prediction module 12 is used to adjust the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system according to the operating status data and the target prediction model, with the goal of minimizing the total energy consumption of the data center cooling system, to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system.

[0192] The regulating module 13 is used to regulate the current flow rate of the primary-side water pump to the first target flow rate, and to regulate the current flow rate of the secondary-side water pump to the second target flow rate.

[0193] In one embodiment, the prediction module includes:

[0194] The prediction unit is used to input the operating status data into the target prediction model for prediction, and obtain the server chip temperature and the total energy consumption of the data center cooling system.

[0195] The construction unit is used to construct constraint conditions according to the server chip temperature, the flow regulation range of the primary side water pump and the flow regulation range of the secondary side water pump.

[0196] The regulating unit is used to adjust the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system based on the constraint conditions with the goal of minimizing the total energy consumption of the data center cooling system, so as to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump.

[0197] In one embodiment, the prediction unit includes:

[0198] The first prediction subunit is used to input the first operating status data in the operating status data into the system status prediction model for prediction, so as to obtain the cooling tower energy consumption, the secondary side inlet water temperature and the secondary side outlet water temperature; the first operating status data includes the primary side flow rate, the secondary side flow rate, the outdoor temperature, the outdoor humidity and the server load.

[0199] The second prediction subunit is used to input the second operating status data in the operating status data into the water pump energy consumption prediction model for prediction, so as to obtain the primary side water pump energy consumption and the secondary side water pump energy consumption; the second operating status data includes the primary side flow, the secondary side flow, the primary side water pump energy consumption reference value, the secondary side water pump energy consumption reference value, the primary side water pump flow reference value under the primary side water pump energy consumption reference value, and the secondary side water pump flow reference value under the secondary side water pump energy consumption reference value.

[0200] The third prediction subunit is used to input the secondary side water inlet temperature, the secondary side water outlet temperature and the third operating status data in the operating status data into the server status prediction model for prediction to obtain the server chip temperature; the third operating status data includes secondary side flow, server load, and server chip heat dissipation area.

[0201] The summing subunit is used to input the cooling tower energy consumption, the primary side water pump energy consumption and the secondary side water pump energy consumption into the comprehensive loss prediction model for summing to obtain the total energy consumption of the data center cooling system.

[0202] In one embodiment, the above-mentioned third prediction sub-unit is specifically used to input the secondary side flow rate and the secondary side inlet water temperature into the first prediction sub-model for prediction to obtain the server chip heat transfer thermal resistance; the secondary side inlet water temperature, the secondary side outlet water temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance are input into the second prediction sub-model for prediction to obtain the server chip temperature.

[0203] In one embodiment, the adjustment unit comprises:

[0204] The regulating subunit is used to regulate the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system based on the constraint conditions to obtain the regulated first flow parameter and the regulated second flow parameter.

[0205] The first loop sub-unit is used to determine new operating status data based on the adjusted first flow parameter and the adjusted second flow parameter, and return to execute the step of inputting the operating status data into the target prediction model for prediction, obtaining the server chip temperature and the total energy consumption of the data center cooling system, and obtaining the total energy consumption of multiple data center cooling systems.

[0206] The first determination subunit is used to determine the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system as the first target flow and the second target flow, respectively.

[0207] In one embodiment, the adjustment unit further includes:

[0208] The second determining subunit is used to determine whether the current cycle number reaches a preset number.

[0209] The second cycle subunit is used to return to the step of determining new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter if the current cycle number does not reach the preset number.

[0210] The third determination subunit is used to determine the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system within the preset number of times as the first target flow and the second target flow, respectively, if the current number of cycles reaches the preset number of times.

[0211] Each module in the energy consumption control device of the data center cooling system can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0212] In one embodiment, a computer device is provided. The computer device may be a terminal or a server. The internal structure diagram thereof may be as follows: Fig.10As shown, the computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an energy consumption control method for a data center cooling system is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0213] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0214] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the energy consumption control method for a data center cooling system described in any of the above embodiments are implemented.

[0215] The computer device provided in the above embodiment has an implementation principle and technical effects similar to those of the above method embodiment, which will not be described in detail here.

[0216] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the energy consumption control method for a data center cooling system described in any of the above embodiments are implemented.

[0217] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0218] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the method for controlling energy consumption of a data center cooling system described in any of the above embodiments.

[0219] The above embodiment provides a computer program product, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0220] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0221] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0222] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for controlling energy consumption of a data center cooling system, characterized in that: The method comprises: Obtain the current operating status data of the data center cooling system; With the goal of minimizing the total energy consumption of the data center cooling system, a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in the data center cooling system are adjusted according to the operating status data and the target prediction model to obtain a first target flow of the primary water pump and a second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the data center cooling system; The current flow rate of the primary-side water pump is adjusted to the first target flow rate, and the current flow rate of the secondary-side water pump is adjusted to the second target flow rate.

2. The method according to claim 1, characterized in that The method takes minimizing the total energy consumption of the data center cooling system as the goal, and adjusts the first flow parameter of the primary side water pump and the second flow parameter of the secondary side water pump in the data center cooling system according to the operating status data and the target prediction model to obtain the first target flow of the primary side water pump and the second target flow of the secondary side water pump, including: Inputting the operating status data into a target prediction model for prediction to obtain the server chip temperature and the total energy consumption of the data center cooling system; Establishing constraint conditions according to the server chip temperature, the flow rate regulation range of the primary water pump, and the flow rate regulation range of the secondary water pump; With the goal of minimizing the total energy consumption of the data center cooling system, based on the constraints, the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system are adjusted to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump.

3. The method according to claim 2, characterized in that The target prediction model includes a system state prediction model, a water pump energy consumption prediction model, a server state prediction model and a comprehensive loss prediction model. The operation state data is input into the target prediction model for prediction to obtain the server chip temperature and the total energy consumption of the data center cooling system, including: Inputting the first operating state data in the operating state data into the system state prediction model for prediction to obtain cooling tower energy consumption, secondary side water inlet temperature and secondary side water outlet temperature; the first operating state data includes primary side flow, secondary side flow, outdoor temperature, outdoor humidity and server load; Input the second operating state data in the operating state data into the water pump energy consumption prediction model for prediction, and obtain the primary side water pump energy consumption and the secondary side water pump energy consumption; the second operating state data includes the primary side flow rate, the secondary side flow rate, the primary side water pump energy consumption reference value, the secondary side water pump energy consumption reference value, the primary side water pump flow reference value under the primary side water pump energy consumption reference value, and the secondary side water pump flow reference value under the secondary side water pump energy consumption reference value; The secondary side water inlet temperature, the secondary side water outlet temperature and the third operating state data in the operating state data are input into the server state prediction model for prediction to obtain the server chip temperature; the third operating state data includes the secondary side flow, the server load, and the server chip heat dissipation area; The cooling tower energy consumption, the primary side water pump energy consumption and the secondary side water pump energy consumption are input into the comprehensive loss prediction model for summing, thereby obtaining the total energy consumption of the data center cooling system.

4. The method according to claim 3, characterized in that The server state prediction model includes a first prediction sub-model and a second prediction sub-model, and the secondary side water inlet temperature, the secondary side water outlet temperature and the third operating state data in the operating state data are input into the server state prediction model for prediction to obtain the server chip temperature, including: Input the secondary side flow rate and the secondary side water inlet temperature into the first prediction sub-model for prediction to obtain the heat transfer thermal resistance of the server chip; The secondary side water inlet temperature, the secondary side water outlet temperature, the server load, the server chip heat dissipation area and the server chip heat transfer thermal resistance are input into the second prediction sub-model for prediction to obtain the server chip temperature.

5. The method according to any one of claims 2 to 4, characterized in that: The method takes minimizing the total energy consumption of the data center cooling system as the goal and, based on the constraint conditions, adjusts the first flow parameter of the primary water pump and the second flow parameter of the secondary water pump in the data center cooling system to obtain the first target flow of the primary water pump and the second target flow of the secondary water pump, including: Based on the constraint condition, adjusting a first flow parameter of a primary-side water pump and a second flow parameter of a secondary-side water pump in the data center cooling system to obtain an adjusted first flow parameter and an adjusted second flow parameter; Determine new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter, and return to execute the step of inputting the operating status data into the target prediction model for prediction, obtain the server chip temperature and the total energy consumption of the data center cooling system, and obtain the total energy consumption of multiple data center cooling systems; The value of the first flow parameter and the value of the second flow parameter corresponding to when the total energy consumption of the data center cooling system is the minimum total energy consumption are respectively determined as the first target flow and the second target flow.

6. The method according to claim 5, characterized in that The method further comprises: Determine whether the current number of cycles reaches the preset number; If the current number of cycles does not reach the preset number of cycles, returning to the step of determining new operating status data according to the adjusted first flow parameter and the adjusted second flow parameter; If the current number of cycles reaches the preset number of times, the value of the first flow parameter and the value of the second flow parameter corresponding to the minimum total energy consumption of the data center cooling system are determined as the first target flow and the second target flow, respectively, including: The value of the first flow parameter and the value of the second flow parameter corresponding to when the total energy consumption of the cooling system of the data center within the preset number of times is the minimum total energy consumption are respectively determined as the first target flow and the second target flow.

7. An energy consumption control device for a data center cooling system, characterized in that: The device comprises: An acquisition module is used to obtain the current operating status data of the data center cooling system; A prediction module, for adjusting a first flow parameter of a primary water pump and a second flow parameter of a secondary water pump in the cooling system of the data center according to the operating status data and a target prediction model, with the goal of minimizing the total energy consumption of the cooling system of the data center, to obtain a first target flow of the primary water pump and a second target flow of the secondary water pump; the target prediction model is constructed by all equipment parameters and environmental parameters in the cooling system of the data center; The regulating module is used to regulate the current flow rate of the primary-side water pump to the first target flow rate, and to regulate the current flow rate of the secondary-side water pump to the second target flow rate.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images