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

Abstract

The invention relates to an energy consumption control method and device for a data center cooling system, equipment and a storage medium, and the method comprises the steps: obtaining the current operation state data and attribute data of the data center cooling system, inputting the operation state data and attribute data into a target energy consumption prediction model, and carrying out the prediction, obtaining a first target flow of a primary side water pump, a second target flow of a secondary side water pump and a third target flow of a cooling tower fan in the cooling tower, and finally, the current flow of the primary side water pump is adjusted to the first target flow, the current flow of the secondary side water pump is adjusted to the second target flow, and the current flow of the cooling tower fan is adjusted to the third target flow. According to the method, the flow parameter of the primary side water pump, the flow parameter of the secondary side water pump and the third flow parameter of the cooling tower fan are adjusted in real time based on the target energy consumption prediction model, different operation environment changes can be flexibly coped, the accuracy of energy consumption control is further improved, and energy consumption can also be reduced.

Description

Technical Field

[0001] This application relates to the field of data center cooling technology, and in particular to a method, apparatus, equipment and storage medium for energy consumption control of a data center cooling system. Background Technology

[0002] With the rapid advancement of information technology, global data center construction is experiencing an unprecedented expansion, gradually becoming a core infrastructure supporting the operation of modern society. To meet the increasing heat dissipation demands of data centers, liquid cooling systems have gradually become the mainstream type of liquid cooling system. The main energy-consuming components of liquid cooling systems are cooling tower fans and cooling water pumps. In the cooling water systems of large data centers and industrial production plants, multiple sets of cooling tower fans and cooling water pumps typically operate in parallel, and the energy consumption of liquid cooling systems accounts for a large proportion of the total energy consumption of data centers. Therefore, effectively controlling the energy consumption of data center cooling systems is key to reducing the overall energy consumption of data centers.

[0003] Currently, the energy consumption control methods described in related technologies cannot accurately control the energy consumption of liquid cooling systems, resulting in high energy consumption of liquid cooling systems. Summary of the Invention

[0004] Therefore, it is necessary to provide an energy consumption control method, apparatus, equipment, and storage medium for a data center cooling system that can accurately control and reduce the energy consumption of the liquid cooling system, in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides an energy consumption control method for a data center cooling system, the data center cooling system including a cooling tower, a primary side water pump, a secondary side water pump, servers, and other related equipment, the method comprising:

[0006] Obtain the current operating status data and attribute data of the data center cooling system; the operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0007] The operating status data and attribute data are input into the target energy consumption prediction model for prediction, to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system;

[0008] Adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0009] In some embodiments, operating status data and attribute data are input into a target energy consumption prediction model for prediction, resulting in a first target flow rate of the primary side water pump, a second target flow rate of the secondary side water pump, and a third target flow rate of the cooling tower fan in the cooling tower, including:

[0010] The operating status data and attribute data are input into the target energy consumption prediction model for prediction to obtain the prediction data. The prediction data includes the primary side cooling water temperature, the primary side cooling water return temperature, the secondary side chilled water temperature, the secondary side chilled water return temperature, the server operating temperature, the heat dissipation of the cooling tower to the outside, the energy consumption of the primary side water pump, the energy consumption of the secondary side water pump, and the energy consumption of the cooling tower fan, which is the total energy consumption of the data center cooling system.

[0011] The target constraints are determined based on the predicted data and attribute data, and are constructed based on the predicted data; the target constraints include at least one of power consumption constraints, temperature constraints, and flow constraints.

[0012] With the goal of minimizing the total energy consumption of the data center cooling system, and based on the target constraints, the flow parameters of the primary side water pump, the secondary side water pump, and the cooling tower fan in the target energy consumption prediction model are adjusted to obtain the first target flow rate, the second target flow rate, and the third target flow rate.

[0013] In some embodiments, the target energy consumption prediction model includes a thermodynamic prediction sub-model and an energy consumption prediction sub-model. Operating state data and attribute data are input into the target energy consumption prediction model for prediction, resulting in predicted data, including:

[0014] The operating status data and attribute data are input into the thermodynamic prediction sub-model for prediction, and the primary side cooling water temperature, primary side cooling water return temperature, secondary side chilled water temperature, secondary side chilled water return temperature, server operating temperature and cooling tower heat dissipation are obtained.

[0015] The attribute data is input into the energy consumption prediction sub-model for prediction, and the energy consumption of the primary side water pump, the secondary side water pump, and the cooling tower fan are obtained.

[0016] In some embodiments, the thermodynamic prediction sub-model includes a first prediction sub-model, a second prediction sub-model, a third prediction sub-model, and a fourth prediction sub-model. Operating status data and attribute data are input into the thermodynamic prediction sub-model for prediction, resulting in the primary side cooling water temperature, the primary side cooling water return temperature, the secondary side chilled water temperature, the secondary side chilled water return temperature, the server operating temperature, and the heat dissipation of the cooling tower.

[0017] The operating status data is input into the first prediction sub-model to predict the fluid temperature on the primary side, and the primary side cooling water temperature and the primary side cooling water return temperature are obtained.

[0018] The operating status data is input into the second prediction sub-model to predict the secondary side fluid temperature, and the secondary side chilled water temperature and the secondary side chilled water return temperature are obtained.

[0019] The secondary chilled water temperature, the server load power in the operating status data, and the specific heat capacity of the secondary fluid in the attribute data are input into the third prediction sub-model for prediction to obtain the server operating temperature.

[0020] The primary cooling water temperature, primary cooling water return temperature, and specific heat capacity of the primary fluid in the attribute data are input into the fourth prediction sub-model to predict the cooling tower's cooling capacity and obtain the cooling tower's heat dissipation to the outside.

[0021] In some embodiments, the energy consumption prediction sub-model includes a fifth prediction sub-model and a sixth prediction sub-model. Attribute data is input into the energy consumption prediction sub-model for prediction to obtain the primary side water pump energy consumption, secondary side water pump energy consumption, and cooling tower fan energy consumption, including:

[0022] The reference values ​​of the pump's energy consumption power and the pump flow rate under the reference power in the attribute data are input into the fifth prediction sub-model for prediction to obtain the primary pump energy consumption and the secondary pump energy consumption.

[0023] The reference values ​​of fan energy consumption power and fan flow rate under the reference power in the attribute data are input into the sixth prediction sub-model for prediction to obtain the cooling tower fan energy consumption.

[0024] In some embodiments, determining the total energy consumption of the data center cooling system based on predicted data and attribute data includes:

[0025] The first difference is determined based on the server operating temperature and the server safe temperature, and the second difference is determined based on the minimum outlet water temperature of the cooling tower and the primary side cooling water temperature.

[0026] Select the largest value from the first difference, the second difference, and the preset value as the temperature item;

[0027] The energy consumption items are obtained by summing the energy consumption of the primary water pump, the secondary water pump, and the cooling tower fan.

[0028] The total energy consumption of the data center cooling system is determined based on the temperature and energy consumption parameters.

[0029] In some embodiments, power consumption constraints include the following:

[0030] The sum of the primary side water pump energy consumption, secondary side water pump energy consumption, cooling tower fan energy consumption, and server load power in the attribute data equals the heat dissipation of the cooling tower to the outside.

[0031] The temperature constraints include the following:

[0032] The server operating temperature in the predicted data is lower than the server safe temperature in the attribute data.

[0033] And / or, the primary cooling water temperature is greater than the minimum outlet water temperature of the cooling tower;

[0034] The flow constraints include the following:

[0035] The flow rate of the primary pump is within the first preset flow rate threshold range;

[0036] The flow rate of the secondary water pump is within the second preset flow rate threshold range;

[0037] The flow rate of the cooling tower fan is within the third preset flow rate threshold range.

[0038] Secondly, this application also provides an energy consumption control device for a data center cooling system, the device comprising:

[0039] The acquisition module is used to acquire the current operating status data and attribute data of the data center cooling system. The operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power. The attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0040] The prediction module is used to input operating status data and attribute data into the target energy consumption prediction model for prediction, and obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system;

[0041] The adjustment module is used to adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0042] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0043] Obtain the current operating status data and attribute data of the data center cooling system; the operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0044] The operating status data and attribute data are input into the target energy consumption prediction model for prediction, to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system;

[0045] Adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0046] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0047] Obtain the current operating status data and attribute data of the data center cooling system; the operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0048] The operating status data and attribute data are input into the target energy consumption prediction model for prediction, to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system;

[0049] Adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0050] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, performs the following steps:

[0051] Obtain the current operating status data and attribute data of the data center cooling system; the operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0052] The operating status data and attribute data are input into the target energy consumption prediction model for prediction, to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system;

[0053] Adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0054] The aforementioned energy consumption control method, apparatus, equipment, and storage medium for data center cooling systems involve acquiring current operating status and attribute data of the data center cooling system. This data is then input into a target energy consumption prediction model for prediction, yielding a first target flow rate for the primary-side water pump, a second target flow rate for the secondary-side water pump, and a third target flow rate for the cooling tower fan. Finally, the current flow rates of the primary-side water pump, the secondary-side water pump, and the cooling tower fan are adjusted to the first, second, and third target flow rates, respectively. Because the target energy consumption prediction model is constructed from all equipment and environmental parameters within the data center cooling system, it allows for real-time adjustment of the flow parameters of the primary, secondary, and cooling tower pumps, ensuring optimal operation. This enables flexible responses to changes in the operating environment, improves system stability and reliability, enhances the accuracy of energy consumption control, and minimizes unnecessary energy consumption, thereby reducing data center operating costs. Attached Figure Description

[0055] Figure 1 This is an application environment diagram of the energy consumption control method for data center cooling systems in some embodiments;

[0056] Figure 2 This is one of the flowcharts illustrating the energy consumption control method for a data center cooling system in some embodiments;

[0057] Figure 3 This is a second flowchart illustrating the energy consumption control method for a data center cooling system in some embodiments;

[0058] Figure 4 This is the third flowchart illustrating the energy consumption control method for a data center cooling system in some embodiments;

[0059] Figure 5 This is the fourth flowchart illustrating the energy consumption control method for a data center cooling system in some embodiments;

[0060] Figure 6 This is the fifth flowchart illustrating the energy consumption control method for a data center cooling system in some embodiments;

[0061] Figure 7 This is a flowchart illustrating the energy consumption control method for a data center cooling system in some embodiments (sixth example).

[0062] Figure 8 This is the seventh flowchart illustrating the energy consumption control method for a data center cooling system in some embodiments;

[0063] Figure 9 This is a structural block diagram of the energy consumption control device for the data center cooling system in some embodiments;

[0064] Figure 10 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0065] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0066] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0067] In the embodiments of this application, the term "at least one" means one or more. For example, at least one of A, B and C can represent six situations: A exists alone, B exists alone, C exists alone, A and B exist simultaneously, A and C exist simultaneously, B and C exist simultaneously, and A, B and C exist simultaneously.

[0068] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0069] With the rapid advancement of information technology, global data center construction is experiencing an unprecedented expansion, gradually becoming a core infrastructure supporting the operation of modern society. To meet the increasing heat dissipation demands of data centers, liquid cooling systems have gradually become the mainstream type of liquid cooling system. The main energy-consuming components of liquid cooling systems are cooling tower fans and cooling water pumps. In the cooling water systems of large data centers and industrial production plants, multiple sets of cooling tower fans and cooling water pumps typically operate in parallel, and the energy consumption of liquid cooling systems accounts for a large proportion of the total energy consumption of data centers. Therefore, effectively controlling the energy consumption of data center cooling systems is key to reducing the overall energy consumption of data centers. Currently, the energy consumption control methods described in related technologies cannot accurately control the energy consumption of liquid cooling systems, resulting in high energy consumption.

[0070] In view of this, embodiments of this application propose an energy consumption control method, apparatus, equipment, and storage medium for a data center cooling system. By adjusting the flow parameters of the primary side water pump, the secondary side water pump, and the cooling tower fan in real time, the system can be kept in optimal condition, flexibly responding to different changes in the operating environment, improving the stability and reliability of the system, thereby improving the accuracy of energy consumption control, and minimizing unnecessary energy consumption, thereby reducing the operating cost of the data center.

[0071] It should be noted that the beneficial effects or technical problems solved by the embodiments of this application are not limited to this one, but may also be other implicit or related problems. For details, please refer to the description of the embodiments below.

[0072] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0073] In some embodiments, the energy consumption control method for a data center cooling system provided in this application can be applied to, for example... Figure 1In the illustrated application environment, the application environment includes computer equipment 101 and a data center cooling system 102, which are connected. The data center cooling system 102 includes a cooling tower 1021, a primary-side water pump 1022, a secondary-side water pump 1023, a plate heat exchanger 1024, and a server 1025. The computer equipment 101 is used to adjust the first flow parameters of the primary-side water pump, the second flow parameters of the secondary-side water pump, and the flow parameters of the cooling tower fan in the data center cooling system to minimize the total energy consumption of the data center cooling system. The data center cooling system 102 is divided into a primary cooling water circulation and a secondary cooling water circulation. The primary cooling water circulation includes the cooling tower and the primary-side water pump, while the secondary cooling water circulation includes the server rack and the secondary-side water pump. The primary cooling water from the cooling tower enters the plate heat exchanger, extracts heat, and is then pumped back to the cooling tower for cooling. The secondary cooling water cools the microchips in the server radiator, returns to the plate heat exchanger, and is then pumped back to the server via the secondary-side water pump.

[0074] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the application environment in which the solution of this application is applied. The specific application environment may include more or fewer components than shown in the figure, or a combination of certain components, or different component arrangements.

[0075] In some embodiments, such as Figure 2 As shown, an energy consumption control method for a data center cooling system is provided, which is applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0076] S201, obtain the current operating status data and attribute data of the data center cooling system.

[0077] The operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of primary fluid, specific heat capacity of secondary fluid, server safe temperature, minimum outlet water temperature of cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0078] In this embodiment, temperature and humidity sensors can be pre-installed outdoors in the data center, and flow sensors can be installed at the outlets of the primary and secondary water pumps of the liquid cooling system, connected to computer equipment. The computer equipment can obtain parameters such as the current outdoor temperature and humidity through the temperature and humidity sensors, monitor server load in real time by activating a preset status query function, and obtain attribute data of the data center cooling system through web crawling or querying equipment parameter manuals. Optionally, after obtaining the current operating status data of the data center cooling system, the computer equipment can perform preprocessing operations such as data cleaning, interpolation, and data augmentation to obtain preprocessed operating status data for subsequent use.

[0079] S202, input the operating status data and attribute data into the target energy consumption prediction model for prediction, and obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower.

[0080] The target energy consumption prediction model is constructed from 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.

[0081] In this embodiment, after the computer device obtains the operating status data and attribute data based on the above steps, it can input the operating status data and attribute data into the target energy consumption prediction model. The target energy consumption prediction model then predicts the current energy consumption of the data center cooling system, predicting the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan corresponding to the minimum total energy consumption. It should be noted that the computer device can pre-build the target energy consumption prediction model based on all equipment parameters and environmental parameters in the data center cooling system. Specifically, the initial prediction model can be trained based on all equipment parameter samples and environmental parameter samples to obtain the target energy consumption 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 energy consumption prediction model. Optionally, the computer device can pre-build the target energy consumption prediction model based on all equipment parameters and environmental parameters in the data center cooling system according to a preset mathematical algorithm.

[0082] S203, adjust the current flow rate of the primary side water pump to the first target flow rate, adjust the current flow rate of the secondary side water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0083] In this embodiment, after the computer device obtains the first target flow rate of the primary water pump, the second target flow rate of the secondary water pump, and the third target flow rate of the cooling tower fan in the cooling tower based on the above steps, it can control the primary water pump to adjust its current flow rate to the first target flow rate, control the secondary water pump to adjust its current flow rate to the second target flow rate, and control the cooling tower fan to adjust its current flow rate to the third target flow rate. Optionally, a first flow rate level corresponding to the first target flow rate, a second flow rate level corresponding to the second target flow rate, and a third flow rate level corresponding to the third target flow rate can be determined, and then the current flow rate level of the primary water pump can be adjusted to the first flow rate level, the current flow rate level of the secondary water pump can be adjusted to the second flow rate level, and the current flow rate level of the cooling tower fan can be adjusted to the third flow rate level.

[0084] The energy consumption control method for a data center cooling system provided in this application acquires the current operating status data and attribute data of the data center cooling system. This data is then input into a target energy consumption prediction model for prediction, resulting in a first target flow rate for the primary-side water pump, a second target flow rate for the secondary-side water pump, and a third target flow rate for the cooling tower fan. Finally, the current flow rates of the primary-side water pump, the secondary-side water pump, and the cooling tower fan are adjusted to the first, second, and third target flow rates, respectively. In this method, since the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters within the data center cooling system, the flow parameters of the primary-side water pump, the secondary-side water pump, and the third flow parameter of the cooling tower fan are adjusted in real time based on the target energy consumption prediction model to ensure optimal operation. This allows for flexible responses to changes in the operating environment, improving system stability and reliability, thereby enhancing the accuracy of energy consumption control. Simultaneously, it minimizes unnecessary energy consumption, thereby reducing the operating costs of the data center.

[0085] In some embodiments, a specific implementation method for traffic flow prediction using a target energy consumption prediction model is also provided, such as... Figure 3 As shown, the phrase "inputting the operating status data and attribute data into the target energy consumption prediction model for prediction to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower" in S202 above includes:

[0086] S301, input the operating status data and attribute data into the target energy consumption prediction model for prediction, and obtain the prediction data.

[0087] The predicted data includes primary-side cooling water temperature, primary-side cooling water return temperature, secondary-side chilled water temperature, secondary-side chilled water return temperature, server operating temperature, cooling tower heat dissipation, primary-side water pump energy consumption, secondary-side water pump energy consumption, and cooling tower fan energy consumption. Primary-side cooling water temperature represents the temperature of the fluid flowing out of the cooling tower, primary-side cooling water return temperature represents the temperature of the fluid flowing into the cooling tower, secondary-side chilled water temperature represents the temperature of the fluid flowing into the server, and secondary-side chilled water return temperature represents the temperature of the fluid flowing out of the server.

[0088] In this embodiment of the application, after the computer device obtains the operating status data and attribute data, it can input the operating status data and attribute data into the target energy consumption prediction model. The target energy consumption prediction model can predict the fluid temperature of the primary side water pump to obtain the primary side cooling water temperature and the primary side cooling water return temperature, predict the fluid temperature of the secondary side water pump to obtain the secondary side chilled water temperature and the secondary side chilled water return temperature, predict the chip temperature of the server to obtain the server operating temperature, predict the cooling capacity of the cooling tower to obtain the heat dissipation of the cooling tower to the outside, predict the pump energy consumption of the cooling system to obtain the primary side water pump energy consumption and the secondary side water pump energy consumption, and predict the cooling tower fan energy consumption of the cooling system to obtain the cooling tower fan energy consumption.

[0089] Optionally, the above-mentioned target energy consumption prediction model includes a thermodynamic prediction sub-model and an energy consumption prediction sub-model. Based on this, such as Figure 4 As shown, S301 specifically includes:

[0090] S3011 inputs the operating status data and attribute data into the thermodynamic prediction sub-model for prediction, and obtains the primary side cooling water temperature, the primary side cooling water return temperature, the secondary side chilled water temperature, the secondary side chilled water return temperature, the server operating temperature, and the heat dissipation of the cooling tower to the outside.

[0091] The target energy consumption prediction model includes a thermodynamic prediction sub-model and an energy consumption prediction sub-model. The thermodynamic prediction sub-model is used to predict the primary side cooling water temperature, the primary side cooling water return temperature, the secondary side chilled water temperature, the secondary side chilled water return temperature, the server operating temperature, and the heat dissipation of the cooling tower.

[0092] In this embodiment of the application, after obtaining the operating status data and attribute data, the computer device can input the operating status data and attribute data into the thermodynamic prediction sub-model. The thermodynamic prediction sub-model can predict the fluid temperature of the primary side water pump to obtain the primary side cooling water temperature and the primary side cooling water return temperature, predict the fluid temperature of the secondary side water pump to obtain the secondary side chilled water temperature and the secondary side chilled water return temperature, predict the chip temperature of the server to obtain the server operating temperature, and predict the cooling capacity of the cooling tower to obtain the heat dissipation of the cooling tower to the outside.

[0093] Specifically, the aforementioned thermodynamic prediction sub-models include a first prediction sub-model, a second prediction sub-model, a third prediction sub-model, and a fourth prediction sub-model. Based on this, such as... Figure 5 As shown, S3011 specifically includes:

[0094] S30111, input the operating status data into the first prediction sub-model to predict the fluid temperature on the primary side, and obtain the primary side cooling water temperature and the primary side cooling water return temperature.

[0095] The first prediction sub-model includes a primary cooling water temperature prediction sub-model and a primary cooling water return temperature prediction sub-model.

[0096] S30112, input the operating status data into the second prediction sub-model to predict the secondary side fluid temperature, and obtain the secondary side chilled water temperature and the secondary side chilled water return temperature.

[0097] The second prediction sub-model includes a secondary chilled water temperature prediction sub-model and a secondary chilled water return temperature prediction sub-model.

[0098] In this embodiment, after obtaining the operating status data, the computer device can input the operating status data into a first prediction sub-model to predict the primary-side fluid temperature, obtaining the primary-side cooling water temperature and the primary-side cooling water return temperature. It can also input the operating status data into a second prediction sub-model to predict the secondary-side fluid temperature, obtaining the secondary-side chilled water temperature and the secondary-side chilled water return temperature. It should be noted that the computer device can pre-train a BP neural network based on operating status data samples to obtain the first and second prediction sub-models. The specific method is as follows:

[0099] 1. Acquire operating data of the primary water pump, secondary water pump, and cooling tower under different environmental parameters and server operating conditions of the data center cooling system, as status data samples. These operational status data samples include outdoor temperature, outdoor humidity, server load (determined by load power), primary water pump flow rate (determined by primary flow rate), secondary water pump flow rate (determined by secondary flow rate), cooling tower fan flow rate, fluid temperature of the primary and secondary water pumps, energy consumption of the primary and secondary water pumps, and energy consumption of the cooling tower fans. In the optimization and control of the data center liquid cooling system, historical operating data is the fundamental support for building accurate predictive models and achieving intelligent control. Historical data serves as a bridge connecting the system's physical characteristics and intelligent algorithms; its comprehensiveness, accuracy, and timeliness directly determine the optimization effect.

[0100] Specifically, data on the operating conditions of data center cooling systems can be obtained through two methods: on-site data collection or simulation software. First, on-site collection: This method provides a more accurate representation of the relationship between the energy consumption and operating parameters of the data center cooling system components, leading to more effective dynamic control of the operation adjustment technology. Second, simulation software: Given that the operating conditions of the cooling system are process variables in dynamic operation adjustment technology, after weighing the cost of data collection against the accuracy of model prediction, after obtaining the first sample data (outdoor temperature, outdoor humidity, server load, primary pump flow rate, secondary pump flow rate, cooling tower fan flow rate, fluid temperature of the primary pump, and fluid temperature of the secondary pump), energy consumption software such as TRNSYS can be used to obtain the water temperature and energy consumption data of each component of the data center cooling system as the second sample data (energy consumption of the primary pump, energy consumption of the secondary pump, and energy consumption of the cooling tower fan).

[0101] 2. When constructing a BP neural network model for the operation and control of a data center liquid cooling system, proper data preprocessing is crucial to model performance. The computer equipment can first normalize the operating status data samples, and then divide the processed data into training and test sets proportionally. Specifically, this includes:

[0102] (1) In order to simplify the input layer parameters of the BP neural network prediction, the outdoor temperature and outdoor humidity can be converted into outdoor wet-bulb temperature by using preset methods.

[0103] (2) For missing values ​​in the collected data, linear interpolation or feature mean averaging is used to fill in the missing values. For outliers in the collected data, engineering thresholding combined with system physical constraints is used to remove outlier values.

[0104] (3) Normalize the running status data samples using a normalization formula, normalizing the same type of data to [0, 1]. The normalization formula is:

[0105]

[0106] 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.

[0107] (4) The normalized data is randomly divided into training and testing datasets according to the specified ratio. In a specific example, 75% of the total samples are used as the model training dataset and 25% of the total samples are used as the model testing dataset.

[0108] 3. Establish a system state prediction model based on BP neural network (including the first and second prediction sub-models) based on operational status data samples. In liquid-cooled data center cooling systems, the fluid temperatures on the primary and secondary sides directly affect the system's energy efficiency and stability. Since the outdoor parameters, server load, fluid operating conditions, and energy consumption data of each component during the cooling system's operation are non-linear, and the model has the ability to learn from historical data and optimize itself, it can adapt to dynamic changes in the system. Accurately predicting fluid temperature not only helps optimize system operation but also provides a scientific basis for the joint control of variable frequency pumps and cooling tower fans. Therefore, using BP neural network to establish a system state prediction model is relatively accurate.

[0109] (1) Construct the first prediction sub-model (including the primary side cooling water temperature prediction sub-model and the primary side cooling water return temperature prediction sub-model).

[0110] ① Primary-side fluid temperature is one of the factors affecting the energy consumption of cooling tower fans. The primary-side cooling water temperature is influenced by outdoor parameters and the operating conditions of the refrigeration system. Specifically, the input variables for the primary-side cooling water temperature prediction sub-model are server load power, primary-side water pump flow rate, secondary-side water pump flow rate, outdoor wet-bulb temperature, and cooling tower fan flow rate. The output variable is the primary-side cooling water temperature. The specific relationship is as follows:

[0111]

[0112] in, Indicates the primary cooling water temperature. This refers to the server load power (specifically, the load power of the server chip). The flow rate of the primary water pump. This refers to the flow rate of the secondary water pump. Outdoor wet-bulb temperature, This refers to the flow rate of the cooling tower fan.

[0113] ② The primary cooling water return temperature is affected by the server load power and the operating conditions of the cooling tower and the refrigeration system. Specifically, the input variables for the primary cooling water return temperature prediction sub-model are the server load power, the primary pump flow rate, the secondary pump flow rate, and the primary cooling water temperature. The output variable is the primary cooling water return temperature. The specific relationship is as follows:

[0114]

[0115] in, Indicates the primary cooling water return temperature. For server load power, The flow rate of the primary water pump. This refers to the flow rate of the secondary water pump. This indicates the primary cooling water temperature.

[0116] (2) Construct the second prediction sub-model (including the secondary chilled water temperature prediction sub-model and the secondary chilled water return temperature prediction sub-model).

[0117] ① Secondary fluid temperature is one of the factors affecting the safe operation of server chips without overheating. The secondary chilled water temperature is influenced by parameters such as server load power and cooling system operating conditions. The secondary chilled water temperature prediction sub-model uses server load power, primary pump flow rate, secondary pump flow rate, outdoor wet-bulb temperature, and cooling tower fan flow rate as input variables, and outputs the secondary chilled water temperature. The specific relationship is as follows:

[0118]

[0119] in, Indicates the temperature of the secondary chilled water. For server load power, The flow rate of the primary water pump. This refers to the flow rate of the secondary water pump. Outdoor wet-bulb temperature, This refers to the flow rate of the cooling tower fan.

[0120] ② The secondary chilled water return temperature is affected by parameters such as server load power and refrigeration system operating conditions. The neural network model is constructed with the server load power, primary pump flow rate, secondary pump flow rate, and secondary chilled water temperature as input variables, and the secondary chilled water return temperature as the output variable. The specific relationship is as follows:

[0121]

[0122] in, Indicates the secondary chilled water return temperature. For server load power, The flow rate of the primary water pump. This refers to the flow rate of the secondary water pump. This indicates the temperature of the secondary chilled water.

[0123] S30113 inputs the secondary chilled water temperature, the server load power in the operating status data, and the specific heat capacity of the secondary fluid in the attribute data into the third prediction sub-model for prediction to obtain the server operating temperature.

[0124] The server operating temperature refers to the temperature of the server chip.

[0125] In this embodiment, after obtaining the secondary chilled water temperature based on the above steps, the computer device can input the secondary chilled water temperature, the server load power in the operating status data, and the specific heat capacity of the secondary fluid in the attribute data into the third prediction sub-model for prediction to obtain the server operating temperature. It should be noted that in liquid-cooled data centers, the temperature control of server chips directly affects the system's reliability, energy efficiency, and equipment lifespan. Ensuring that the chip temperature remains below a safe threshold is a core requirement for the stable operation and control of the data center cooling system. The computer device can pre-build the third prediction sub-model... This can be expressed by the following relation:

[0126]

[0127] in, For server operating temperature, Indicates the temperature of the secondary chilled water. For server load power, Let be the specific heat capacity of the secondary fluid (which is a constant). This refers to the flow rate of the secondary water pump.

[0128] S30114 inputs the primary side cooling water temperature, the primary side cooling water return temperature, and the specific heat capacity of the primary side fluid in the attribute data into the fourth prediction sub-model to predict the cooling tower cooling capacity and obtain the heat dissipation of the cooling tower to the outside.

[0129] In this embodiment, after obtaining the primary-side cooling water temperature and the primary-side cooling water return temperature based on the above steps, the computer device can input the primary-side cooling water temperature, the primary-side cooling water return temperature, and the specific heat capacity of the primary-side fluid from the attribute data into the fourth prediction sub-model to predict the cooling tower's cooling capacity and obtain the cooling tower's external heat dissipation. It should be noted that for data center liquid-cooled natural cooling systems, the cooling tower's cooling capacity directly affects the overall system's cooling efficiency and energy consumption. The computer device can pre-build the fourth prediction sub-model. This can be expressed by the following relation:

[0130]

[0131] in, The amount of heat dissipated by the cooling tower to the outside. The flow rate of the primary water pump. The specific heat capacity of the primary fluid. Indicates the primary cooling water return temperature. This indicates the primary cooling water temperature.

[0132] S3012, input the attribute data into the energy consumption prediction sub-model for prediction, and obtain the primary side water pump energy consumption, secondary side water pump energy consumption and cooling tower fan energy consumption.

[0133] Among them, the energy consumption prediction sub-model is used to predict the energy consumption of the primary side water pump, the secondary side water pump, and the cooling tower fan.

[0134] In this embodiment, after obtaining the attribute data, the computer device can input the attribute data into the energy consumption prediction sub-model for prediction, obtaining the primary side water pump energy consumption, secondary side water pump energy consumption, and cooling tower fan energy consumption. Variable frequency water pumps and cooling tower fans are core power equipment in the liquid cooling system, typically accounting for a large proportion of energy consumption, and the system's cooling capacity is mainly adjusted through the frequency conversion of the water pumps and fans. Therefore, the operating efficiency of the water pumps and fans directly determines the optimization effect of the entire cooling system.

[0135] Specifically, the aforementioned energy consumption prediction sub-model includes a fifth prediction sub-model and a sixth prediction sub-model. Based on this, such as Figure 6 As shown, S3012 specifically includes:

[0136] S30121, input the reference value of the energy consumption power of the water pump and the reference value of the water pump flow rate under the reference power in the attribute data into the fifth prediction sub-model for prediction, and obtain the primary side water pump energy consumption and the secondary side water pump energy consumption.

[0137] The fifth prediction sub-model is the cooling system pump set energy consumption model, used to predict the energy consumption of the primary and secondary water pumps, specifically the energy consumption of the primary and secondary variable frequency water pumps. The pump energy consumption power reference values ​​include those for both the primary and secondary pumps. The pump flow rate reference values ​​also include those for both the primary and secondary pumps.

[0138] In this embodiment, after obtaining the attribute data, the computer device can input the reference value of the pump's energy consumption power and the reference value of the pump flow rate under the reference power into the fifth prediction sub-model for prediction, thereby obtaining the primary-side pump energy consumption and the secondary-side pump energy consumption. It should be noted that, in order to achieve efficient optimization of the cooling water system, establishing a computationally simple and highly accurate variable frequency pump mathematical model can provide important support for energy-saving control in actual operation. The computer device can pre-build the fifth prediction sub-model. This can be expressed by the following relation:

[0139]

[0140] in, This refers to the energy consumption of the water pump (including the energy consumption of the primary water pump and the energy consumption of the secondary water pump). This is a reference value for the energy consumption power of the water pump. The flow rate of the water pump (including the flow rate of the primary pump and the flow rate of the secondary pump). This is a reference value for the water pump flow rate at the reference power.

[0141] S30122, input the reference value of fan energy consumption power and the reference value of fan flow under the reference power in the attribute data into the sixth prediction sub-model for prediction to obtain the cooling tower fan energy consumption.

[0142] The sixth prediction sub-model is the cooling tower fan energy consumption model of the cooling system, which is used to predict the cooling tower fan energy consumption.

[0143] In this embodiment of the application, after obtaining the attribute data, the computer device can input the fan energy consumption power reference value and the fan flow reference value under the reference power into the sixth prediction sub-model for prediction to obtain the cooling tower fan energy consumption.

[0144] It should be noted that, in order to achieve efficient optimization of the cooling water system, establishing a computationally simple and highly accurate cooling tower fan energy consumption model can provide important support for energy-saving control in actual operation. Computer equipment can pre-build a sixth predictive sub-model. This can be expressed by the following relation:

[0145]

[0146] in, For cooling tower fan energy consumption, This is a reference value for the energy consumption of the wind turbine. The flow rate of the cooling tower fan. This is a reference value for the fan flow rate at the reference power.

[0147] S302, determine the total energy consumption of the data center cooling system based on the predicted data and attribute data, and construct target constraints based on the predicted data.

[0148] The target constraints include at least one of power consumption constraints, temperature constraints, and flow constraints.

[0149] In this embodiment of the application, after obtaining the prediction data and attribute data, the computer device can determine the total energy consumption of the data center cooling system based on the prediction data and attribute data, and construct target constraints based on the prediction data.

[0150] Specifically, such as Figure 7 As shown, the "determining the total energy consumption of the data center cooling system based on predicted data and attribute data" in S302 above specifically includes:

[0151] S3021, determine the first difference based on the server operating temperature and the server safe temperature, and determine the second difference based on the minimum outlet water temperature of the cooling tower and the primary side cooling water temperature.

[0152] S3022, select the largest value from the first difference, the second difference, and the preset value as the temperature item.

[0153] S3023 sums the energy consumption of the primary water pump, the secondary water pump, and the cooling tower fan to obtain the energy consumption item.

[0154] S3024, determine the total energy consumption of the data center cooling system based on the temperature and energy consumption items.

[0155] In this embodiment, a necessary condition for the operation and control of the cooling system is to ensure that the temperature of the data center server chip does not exceed the limit; that is, the server chip must operate within a safe temperature under different load power conditions. Furthermore, the cooling tower outlet water temperature is limited by the maximum water-to-air ratio achievable by the current equipment. To ensure that the server chip temperature does not exceed the safe temperature and considering the cooling water outlet temperature limit, a penalty function needs to be introduced in conjunction with the constraints to improve the design of the fitness function. A penalty factor is introduced. For infeasible solutions that handle chip temperature and cooling tower outlet water temperature exceeding limits, the penalty factor should be set to a large value. The improved fitness function (i.e., the total energy consumption function of the data center cooling system) can then be expressed by the following relationship:

[0156]

[0157] in, This refers to the energy consumption of the primary water pump. For the energy consumption of the secondary water pump, For cooling tower fan energy consumption, As a penalty factor, For server operating temperature, For server safety temperature, Indicates the primary cooling water temperature. This indicates the lowest outlet water temperature of the cooling tower. The first difference is... The second difference is The temperature term is Energy consumption item is .

[0158] Specifically, the "constructing target constraints based on predicted data" in S302 above includes:

[0159] (1) The power consumption constraints include the following: the sum of the primary side water pump energy consumption, secondary side water pump energy consumption, cooling tower fan energy consumption, and server load power in the prediction data is equal to the heat dissipation of the cooling tower, that is, the heat cooled by the cooling tower is equal to the sum of the cooling capacity required by the user-side server chip and the power consumption of the power equipment. Specifically, this can be expressed by the following relationship:

[0160]

[0161] in, This refers to the heat dissipation of the cooling tower to the outside. This refers to the energy consumption of the primary water pump. For the energy consumption of the secondary water pump, For cooling tower fan energy consumption, This refers to the server load power.

[0162] (2) Temperature constraints include the following: the server operating temperature in the predicted data is lower than the server safe temperature in the attribute data, and / or, the primary cooling water temperature is higher than the minimum outlet water temperature of the cooling tower. Specifically, this includes:

[0163] ① The primary goal of a data center cooling system is to ensure that server chip temperatures remain below safe operating temperatures. To guarantee that server chip temperatures do not exceed safe operating temperatures, i.e., that the server operating temperature is lower than the server's safe operating temperature, this can be expressed by the following formula:

[0164]

[0165] in, For server operating temperature, This is the safe temperature for the server.

[0166] ② The outlet water temperature of the cooling tower is limited by the maximum water-to-air ratio achievable by the current equipment. Therefore, existing cooling tower specifications have a minimum achievable outlet water temperature, meaning the primary side cooling water temperature is greater than the minimum outlet water temperature of the cooling tower. This can be expressed by the following formula:

[0167]

[0168] in, Indicates the primary cooling water temperature. This indicates the lowest outlet water temperature of the cooling tower.

[0169] (2) The flow constraints include the following: the flow rate of the primary pump is within the first preset flow rate threshold range; the flow rate of the secondary pump is within the second preset flow rate threshold range; and the flow rate of the cooling tower fan is within the third preset flow rate threshold range. This can be expressed by the following formula:

[0170]

[0171]

[0172] in, This indicates the lower limit of the frequency converter flow rate of the water pump (including the lower limit of the flow rate of the primary pump and the lower limit of the flow rate of the secondary pump). This indicates the upper limit of the pump flow rate (including the upper limit of the primary pump flow rate and the upper limit of the secondary pump flow rate). This indicates the lower limit of the flow rate of the cooling tower fan. This indicates the upper limit of the flow rate of the cooling tower fan.

[0173] S303 aims to minimize the total energy consumption of the data center cooling system. Based on the target constraints, it adjusts the flow parameters of the primary side water pump, the secondary side water pump, and the cooling tower fan in the target energy consumption prediction model to obtain the first target flow rate, the second target flow rate, and the third target flow rate.

[0174] In this embodiment, based on the analysis of the above steps, the overall energy consumption of the data center is mainly affected by three key parameters: outdoor environmental parameters, server load rate, and cooling system operating conditions. Under the premise of ensuring the safe and stable operation of the servers, the optimization focus of the data center liquid cooling system is to seek the optimal system operating conditions between the server rack end and the cooling source end through joint regulation of the primary and secondary fluid flow rates and the cooling tower fan flow rate, thereby achieving the goal of minimizing the overall energy consumption of the entire cooling system. The computer equipment constructs the total energy consumption and target constraints of the data center cooling system based on the above steps. Then, with the goal of minimizing the total energy consumption of the data center cooling system, and based on the target constraints, the whale algorithm is used to optimize the joint regulation strategy of the data center liquid cooling system. The flow parameters of the primary side water pump, the secondary side water pump, and the cooling tower fan in the target energy consumption prediction model are adjusted to obtain the first target flow rate, the second target flow rate, and the third target flow rate.

[0175] Specifically, the computer equipment can adjust the first flow parameter of the primary-side water pump, the second flow parameter of the secondary-side water pump, and the third flow parameter of the cooling tower fan in the data center cooling system based on constraints, obtaining adjusted first, second, and third flow parameters. Then, based on these adjusted parameters, new operating status data is determined, and the process returns to step S301 to obtain the total energy consumption of multiple data center cooling systems. Finally, the values ​​of the first, second, and third flow parameters corresponding to the minimum total energy consumption of the data center cooling system are defined as the first target flow rate, the second target flow rate, and the third target flow rate, respectively.

[0176] The specific process of optimizing the joint control strategy of the data center liquid cooling system based on the whale algorithm is as follows:

[0177] (1) Initialize the initial whale population: Determine the maximum number of iterations for the whale optimization algorithm. Screw constant and population size In the global energy consumption model of the data center cooling system, the optimization terms are the flow rates of the primary-side water pumps, the secondary-side water pumps, and the cooling tower fans. Furthermore, the flow rate adjustment ranges of the water pumps and cooling tower fans cannot exceed the selection range. Therefore, the search spaces for the flow rates of the primary-side water pumps and the secondary-side water pumps are respectively... and The search space for the flow rate of the cooling tower fan is When initializing the whale population, the initial whale population is randomly generated within permissible limits, and each individual whale is represented as a combination of flow parameters. .

[0178] (2) Iterative optimization process: The Whale Optimization Algorithm (WOA) simulates the "bubble net hunting" behavior of humpback whales, and is divided into three stages: surrounding the prey, spiral update, and random search. Through the global search capability of the Whale Optimization Algorithm, the cooling energy consumption of the data center can be effectively reduced, while ensuring the safe operation of the server.

[0179] ① Surrounding the Prey Phase: The model optimization objective is to find the optimal operating condition of the data center cooling system. During the iteration process, individuals in a predatory state move towards the optimal individual, and each whale (candidate solution) moves closer to the current optimal individual.

[0180]

[0181]

[0182] in, and The system vector is , , Decreasing linearly from 2 to 0, and It is a random vector within [0,1]; It is the optimal individual. , .

[0183] ② Spiral Renewal Phase: Simulating a whale spiraling upwards to approach its prey:

[0184]

[0185] in, It is the distance between the current individual and the optimal solution. ; This is the helical shape constant; It is a random number in the range [-1, 1].

[0186] ③ Random search phase: through Controlling the global search of an individual, when At that time, randomly select individuals for a global search:

[0187]

[0188] in, The location of a randomly selected individual whale.

[0189] (3) Energy consumption optimization method for data center liquid cooling system based on joint control of cooling system components. Determine the optimal operating condition for global energy consumption of data center liquid cooling system: Determine whether the algorithm meets the preset termination condition. If the preset termination condition is met, the optimal operating parameters are obtained, and the output pump and fan operating power is used as the joint control parameter for minimizing global energy consumption of data center liquid cooling system. Among them, the preset termination condition includes the current cycle number reaching the preset number, and / or the difference in total energy consumption of data center cooling system between two adjacent cycles is less than the preset threshold; the preset number and preset threshold can be determined according to actual needs.

[0190] In summary, based on all the above embodiments, an energy consumption control method for a data center cooling system is also provided, such as... Figure 8 As shown, the method includes:

[0191] S401, obtain the current operating status data and attribute data of the data center cooling system.

[0192] The operational status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power. The attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0193] S402, input the operating status data into the first prediction sub-model to predict the fluid temperature on the primary side, and obtain the primary side cooling water temperature and the primary side cooling water return temperature.

[0194] S403, input the operating status data into the second prediction sub-model to predict the secondary side fluid temperature, and obtain the secondary side chilled water temperature and the secondary side chilled water return temperature.

[0195] S404 inputs the secondary chilled water temperature, the server load power in the operating status data, and the specific heat capacity of the secondary fluid in the attribute data into the third prediction sub-model for prediction to obtain the server operating temperature.

[0196] S405 inputs the primary side cooling water temperature, the primary side cooling water return temperature, and the specific heat capacity of the primary side fluid in the attribute data into the fourth prediction sub-model to predict the cooling tower's cooling capacity and obtain the cooling tower's heat dissipation to the outside.

[0197] S406, input the reference value of the pump's energy consumption power and the reference value of the pump flow rate under the reference power in the attribute data into the fifth prediction sub-model for prediction, and obtain the primary side pump energy consumption and the secondary side pump energy consumption.

[0198] S407: Input the reference value of fan energy consumption power and the reference value of fan flow under the reference power in the attribute data into the sixth prediction sub-model for prediction to obtain the cooling tower fan energy consumption.

[0199] The predicted data includes primary cooling water temperature, primary cooling water return temperature, secondary chilled water temperature, secondary chilled water return temperature, server operating temperature, cooling tower heat dissipation, primary water pump energy consumption, secondary water pump energy consumption, and cooling tower fan energy consumption.

[0200] S408 determines the first difference based on the server operating temperature and the server safe temperature, and determines the second difference based on the minimum outlet water temperature of the cooling tower and the primary side cooling water temperature.

[0201] S409, select the largest value from the first difference, the second difference, and the preset value as the temperature item.

[0202] S410 sums the energy consumption of the primary water pump, the secondary water pump, and the cooling tower fan to obtain the energy consumption item.

[0203] S411, determine the total energy consumption of the data center cooling system based on the temperature and energy consumption terms.

[0204] S412, construct target constraints based on the predicted data.

[0205] The target constraints include at least one of power consumption constraints, temperature constraints, and flow rate constraints. Power consumption constraints include: the sum of the primary-side water pump energy consumption, secondary-side water pump energy consumption, cooling tower fan energy consumption, and server load power in the predicted data equals the heat dissipation of the cooling tower. Temperature constraints include: the server operating temperature in the predicted data is lower than the server safe temperature in the attribute data, and / or, the primary-side cooling water temperature is higher than the minimum outlet temperature of the cooling tower. Flow rate constraints include: the primary-side water pump flow rate is within a first preset flow rate threshold range; the secondary-side water pump flow rate is within a second preset flow rate threshold range; and the cooling tower fan flow rate is within a third preset flow rate threshold range.

[0206] S413 aims to minimize the total energy consumption of the data center cooling system. Based on the target constraints, the flow parameters of the primary side water pump, the secondary side water pump, and the cooling tower fan in the target energy consumption prediction model are adjusted to obtain the first target flow rate, the second target flow rate, and the third target flow rate.

[0207] S414, adjust the current flow rate of the primary side water pump to the first target flow rate, adjust the current flow rate of the secondary side water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0208] The method described in this application, for the operation control of a data center liquid cooling system, comprehensively considers the operation and regulation of the cooling tower fans and primary and secondary side pumps, the dynamic changes in server load and outdoor parameters, simplifies model parameters and optimizes model calculation efficiency, and builds a comprehensive data center liquid cooling system energy consumption model to meet the high-efficiency calculation requirements of real-time optimization. Combining the data center liquid cooling system energy consumption model with the whale optimization algorithm, considering the nonlinear coupling characteristics between control parameters and operating parameters, a suitability function is constructed to handle the nonlinear constraints of the optimization solution, optimizing the whale algorithm into a directly applicable online optimization algorithm, realizing an online control and optimization method for joint system components under dynamic changes.

[0209] The methods described in each of the above steps have been described in the foregoing embodiments. For details, please refer to the foregoing descriptions. They will not be repeated here.

[0210] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0211] Based on the same inventive concept, this application also provides an energy consumption control device for a data center cooling system to implement the energy consumption control method for the data center cooling system described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the energy consumption control device for a data center cooling system provided below can be found in the limitations of the energy consumption control method for the data center cooling system described above, and will not be repeated here.

[0212] In some embodiments, such as Figure 9 As shown, an energy consumption control device for a data center cooling system is provided, comprising:

[0213] The acquisition module 11 is used to acquire the current operating status data and attribute data of the data center cooling system; the operating status data includes at least one of the current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power.

[0214] The prediction module 12 is used to input the operating status data and attribute data into the target energy consumption prediction model for prediction, and obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower. The target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system.

[0215] The adjustment module 13 is used to adjust the current flow rate of the primary side water pump to the first target flow rate, adjust the current flow rate of the secondary side water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

[0216] The various modules in the energy consumption control device of the aforementioned data center cooling system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0217] In some embodiments, a computer device is provided, which may be a terminal or a server, and its internal structure diagram may be as follows. Figure 10As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an energy consumption control method for a data center cooling system. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0218] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0219] In some embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the energy consumption control method for the data center cooling system described in any of the above embodiments.

[0220] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the energy consumption control method for the data center cooling system described in any of the above embodiments.

[0221] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the energy consumption control method for the data center cooling system described in any of the above embodiments.

[0222] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0223] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0224] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for controlling energy consumption in a data center cooling system, characterized in that, The data center cooling system includes a cooling tower, a primary water pump, a secondary water pump, servers, and other related equipment. The method includes: The system acquires the current operating status data and attribute data of the data center cooling system. The operating status data includes at least one of the following: current outdoor temperature, current outdoor humidity, and server load power. The attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power. The operating status data and the attribute data are input into the target energy consumption prediction model for prediction to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system; Adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

2. The method according to claim 1, characterized in that, The step of inputting the operating status data and the attribute data into the target energy consumption prediction model for prediction, to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower, includes: The operating status data and the attribute data are input into the target energy consumption prediction model for prediction to obtain prediction data; the prediction data includes primary side cooling water temperature, primary side cooling water return temperature, secondary side chilled water temperature, secondary side chilled water return temperature, server operating temperature, heat dissipation of the cooling tower to the outside, primary side water pump energy consumption, secondary side water pump energy consumption and cooling tower fan energy consumption. The total energy consumption of the data center cooling system is determined based on the predicted data and the attribute data, and target constraints are constructed based on the predicted data; the target constraints include at least one of power consumption constraints, temperature constraints, and flow constraints. With the goal of minimizing the total energy consumption of the data center cooling system, and based on the target constraints, the flow parameters of the primary side water pump, the secondary side water pump, and the cooling tower fan in the target energy consumption prediction model are adjusted to obtain the first target flow rate, the second target flow rate, and the third target flow rate.

3. The method according to claim 2, characterized in that, The target energy consumption prediction model includes a thermodynamic prediction sub-model and an energy consumption prediction sub-model. The operating status data and the attribute data are input into the target energy consumption prediction model for prediction to obtain prediction data, including: The operating status data and the attribute data are input into the thermodynamic prediction sub-model for prediction to obtain the primary side cooling water temperature, the primary side cooling water return temperature, the secondary side chilled water temperature, the secondary side chilled water return temperature, the server operating temperature, and the heat dissipation of the cooling tower to the outside. The attribute data is input into the energy consumption prediction sub-model for prediction to obtain the primary side water pump energy consumption, secondary side water pump energy consumption and cooling tower fan energy consumption.

4. The method according to claim 3, characterized in that, The thermodynamic prediction sub-model includes a first prediction sub-model, a second prediction sub-model, a third prediction sub-model, and a fourth prediction sub-model. The process of inputting the operating status data and the attribute data into the thermodynamic prediction sub-model for prediction yields the primary side cooling water temperature, the primary side cooling water return temperature, the secondary side chilled water temperature, the secondary side chilled water return temperature, the server operating temperature, and the heat dissipation of the cooling tower to the outside, including: The operating status data is input into the first prediction sub-model to predict the primary side fluid temperature, thereby obtaining the primary side cooling water temperature and the primary side cooling water return temperature. The operating status data is input into the second prediction sub-model to predict the secondary side fluid temperature, thereby obtaining the secondary side chilled water temperature and the secondary side chilled water return temperature. The secondary chilled water temperature, the server load power in the operating status data, and the specific heat capacity of the secondary fluid in the attribute data are input into the third prediction sub-model for prediction to obtain the server operating temperature. The primary cooling water temperature, the primary cooling water return temperature, and the specific heat capacity of the primary fluid in the attribute data are input into the fourth prediction sub-model to predict the cooling tower's cooling capacity, thereby obtaining the heat dissipation of the cooling tower to the outside.

5. The method according to claim 3, characterized in that, The energy consumption prediction sub-model includes a fifth prediction sub-model and a sixth prediction sub-model. The step of inputting the attribute data into the energy consumption prediction sub-model for prediction, to obtain the primary side water pump energy consumption, secondary side water pump energy consumption, and cooling tower fan energy consumption, includes: The energy consumption power reference value and the water pump flow rate reference value under the reference power in the attribute data are input into the fifth prediction sub-model for prediction to obtain the primary side water pump energy consumption and the secondary side water pump energy consumption. The reference values ​​of fan energy consumption power and fan flow rate under the reference power in the attribute data are input into the sixth prediction sub-model for prediction to obtain the cooling tower fan energy consumption.

6. The method according to any one of claims 2-5, characterized in that, Determining the total energy consumption of the data center cooling system based on the predicted data and the attribute data includes: A first difference is determined based on the server operating temperature and the server safe temperature, and a second difference is determined based on the minimum outlet water temperature of the cooling tower and the primary cooling water temperature. Select the largest value from the first difference, the second difference, and the preset value as the temperature item; The energy consumption of the primary water pump, the secondary water pump, and the cooling tower fan are summed to obtain the energy consumption item. The total energy consumption of the data center cooling system is determined based on the temperature item and the energy consumption item.

7. The method according to any one of claims 2-5, characterized in that, The power consumption constraints include the following: The sum of the primary side water pump energy consumption, secondary side water pump energy consumption, cooling tower fan energy consumption in the predicted data, and server load power in the attribute data equals the heat dissipation of the cooling tower to the outside. The temperature constraint conditions include the following: The server operating temperature in the predicted data is lower than the server safe temperature in the attribute data. And / or, the primary cooling water temperature is greater than the minimum outlet water temperature of the cooling tower; The flow constraints include the following: The flow rate of the primary water pump is within the first preset flow rate threshold range; The flow rate of the secondary water pump is within the second preset flow rate threshold range; The flow rate of the cooling tower fan is within the third preset flow rate threshold range.

8. An energy consumption control device for a data center cooling system, characterized in that, The device includes: The acquisition module is used to acquire the current operating status data and attribute data of the data center cooling system; the operating status data includes at least one of the current outdoor temperature, current outdoor humidity, and server load power; the attribute data includes at least one of the following: specific heat capacity of the primary fluid, specific heat capacity of the secondary fluid, server safe temperature, minimum outlet water temperature of the cooling tower, reference value of water pump energy consumption power, reference value of water pump flow rate at reference power, reference value of fan energy consumption power, and reference value of fan flow rate at reference power. The prediction module is used to input the operating status data and the attribute data into the target energy consumption prediction model for prediction, so as to obtain the first target flow rate of the primary side water pump, the second target flow rate of the secondary side water pump, and the third target flow rate of the cooling tower fan in the cooling tower; the target energy consumption prediction model is constructed from all equipment parameters and environmental parameters in the data center cooling system; The adjustment module is used to adjust the current flow rate of the primary water pump to the first target flow rate, adjust the current flow rate of the secondary water pump to the second target flow rate, and adjust the current flow rate of the cooling tower fan to the third target flow rate.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images