Control method of cooling system, cooling system, device and storage medium

Abstract

The invention provides a control method of a cooling system, the cooling system, a device and a storage medium, particularly relates to the technical field of data center cooling systems, and is used for improving the operation efficiency of the data center cooling system. The control method of the cooling system comprises the following steps: acquiring real-time operation data corresponding to target equipment in the cooling system; utilizing a target cooling system model corresponding to the target equipment to determine performance parameters of the target equipment in the current operation state according to the operation data corresponding to the target equipment; determining target operation parameters corresponding to the target equipment according to the performance parameters; and controlling the operation of the target equipment according to the target operation parameters.

Description

Technical Field

[0001] The present application relates to the technical field of data center cooling systems, and in particular to a control method for a cooling system, a cooling system, a device, and a storage medium. Background Art

[0002] The data center cooling system refers to a specialized system used to reduce the temperature of the equipment inside the data center, which is usually composed of a series of cooling equipment and components, such as chillers, cooling towers, cooling water pumps, freezing water pumps, etc. The control parameters of this series of cooling equipment are closely related to the operating efficiency of the data center cooling system.

[0003] In the related art, a large amount of historical operation data of the data center cooling system is often collected and the cooling system model is trained based on the historical operation data. However, the historical operation data of the cooling system of the newly built data center is relatively small, resulting in inaccurate output results of the cooling system model, which affects the operating efficiency of the data center cooling system.

[0004] Therefore, how to improve the operating efficiency of the data center cooling system is an urgent problem to be solved. Summary of the invention

[0005] Embodiments of the present application provide a control method of a cooling system, a cooling system, a device, and a storage medium for improving the operating efficiency of a cooling system in a data center.

[0006] In order to achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, a method for controlling a cooling system is provided, the method comprising:

[0008] Obtain real-time operating data corresponding to the target equipment in the cooling system;

[0009] Using a target cooling system model corresponding to the target device, and according to operating data corresponding to the target device, determining a performance parameter of the target device in a current operating state;

[0010] Determine target operating parameters corresponding to the target device according to the performance parameters;

[0011] Control the operation of the target device according to the target operation parameters;

[0012] Among them, the target cooling system model corresponding to the target device is trained in the following way:

[0013] Acquire multiple source domain training samples and multiple target domain training samples corresponding to the target device, wherein the source domain training samples are determined based on historical operation data corresponding to other cooling systems; and the target domain training samples are determined based on historical operation data corresponding to the cooling system;

[0014] Training an initial cooling system model corresponding to the target device based on multiple source domain training samples to obtain a trained cooling system model corresponding to the target device;

[0015] The trained cooling system model corresponding to the target device is adjusted based on multiple target domain training samples to obtain a target cooling system model corresponding to the target device.

[0016] The technical solution provided by the embodiment of the present application brings at least the following beneficial effects: the embodiment of the present application trains the initial cooling system model corresponding to the target device through source domain training samples, and adjusts the trained cooling system model corresponding to the target device through target domain training samples, which can reduce the demand and dependence on the operating data of the target device and increase the generalization ability of the target cooling system model. That is, the target cooling system model corresponding to the target device is more in line with the operating conditions of the target device, thereby improving the accuracy of the target cooling system model. Furthermore, the target operating parameters determined by the target cooling system model corresponding to the target device are the optimal operating parameters of the target device. Controlling the operation of the target device with the target operating parameters can put the target device in the optimal operating state, thereby improving the operating efficiency of the cooling system of the data center.

[0017] In some embodiments, when the target device is a chiller module, the real-time operating data include: chilled water outlet temperature, cooling water inlet temperature; the above-mentioned target cooling system model corresponding to the target device is used to determine the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device, including: determining multiple reference cooling capacities within the cooling capacity range of each chiller in the chiller module; for each of the multiple reference cooling capacities, determining the cooling load rate corresponding to the reference cooling capacity, and inputting the chilled water outlet temperature set value, the cooling water inlet temperature and the cooling load rate into the target cooling system model corresponding to the target device to obtain the energy efficiency ratio corresponding to the reference cooling capacity; for each of the multiple reference cooling capacities, the power consumption corresponding to the reference cooling capacity is obtained based on the reference cooling capacity and the energy efficiency ratio corresponding to the reference cooling capacity; the performance parameters of the target device in the current operating state include the power consumption corresponding to each of the multiple reference cooling capacities.

[0018] In some embodiments, the above-mentioned determination of the target operating parameters corresponding to the target device based on the performance parameters includes: for each number of devices turned on among multiple numbers of devices turned on, based on multiple reference cooling capacities, the power consumption corresponding to each reference cooling capacity and the number of devices turned on, determining multiple total cooling capacities and a first total power consumption corresponding to the number of devices turned on; among all total cooling capacities and first total power consumption corresponding to the multiple numbers of devices turned on, determining a first target total power consumption corresponding to a total cooling capacity whose total cooling capacity is greater than a cooling load demand; and using the reference cooling capacity and the number of devices turned on corresponding to the smallest total power consumption among the first target total power consumption as the target operating parameters.

[0019] In some embodiments, when the target device is a cooling tower module, the real-time operating data includes: outdoor ambient wet-bulb temperature, cooling water target approximation, and cooling water temperature difference; using the target cooling system model corresponding to the target device, the performance parameters of the target device in the current operating state are determined according to the operating data corresponding to the target device, including: obtaining the cooling water target flow rate and multiple reference cooling tower fan frequencies within the cooling tower fan frequency range; for each reference cooling tower fan frequency among the multiple reference cooling tower fan frequencies, the reference cooling tower fan frequency, cooling water target flow rate, outdoor ambient wet-bulb temperature, and cooling water temperature difference are input into the target cooling system model corresponding to the target device to obtain the cooling tower approximation corresponding to the reference cooling tower fan frequency; the performance parameters of the target device in the current operating state include the cooling tower approximation corresponding to each reference cooling tower fan frequency among the multiple reference cooling tower fan frequencies.

[0020] In some embodiments, target operating parameters corresponding to a target device are determined based on performance parameters, including: for each number of devices turned on among a plurality of device turned on numbers, based on a plurality of reference cooling tower fan operating frequencies and the number of devices turned on, determining a plurality of cooling tower approximations corresponding to the number of devices turned on; among all cooling tower approximations corresponding to the plurality of device turned on numbers, determining a target cooling tower fan operating frequency corresponding to a cooling tower approximation whose cooling tower approximation is less than a preset approximation; and using the target cooling tower fan operating frequency and the number of devices turned on corresponding to the smallest second total power consumption among the second total power consumption corresponding to the target cooling tower fan operating frequency as target operating parameters.

[0021] In some embodiments, when the target device is a cooling water pump module, the real-time operating data includes the operating frequency of the cooling water pump and the number of valves opened of the cooling water pump; using the target cooling system model corresponding to the target device, the performance parameters of the target device in the current operating state are determined according to the operating data corresponding to the target device, including: obtaining the cooling water target flow rate and multiple reference water pump operating frequencies within the cooling water pump operating frequency range; for each reference cooling water pump operating frequency among the multiple reference cooling water pump operating frequencies, the reference cooling water pump operating frequency and the number of valves opened of the cooling water pump are input into the target cooling system model corresponding to the target device to obtain the head of the cooling water pump and the water flow rate of the cooling water pump corresponding to the reference cooling water pump operating frequency; the performance parameters of the target device in the current operating state include the head of the cooling water pump and the water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency among the multiple reference cooling water pump operating frequencies.

[0022] In some embodiments, target operating parameters corresponding to the target device are determined based on performance parameters, including: for each number of devices turned on among multiple numbers of devices turned on, based on multiple reference cooling water pump operating frequencies, the water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency, and the number of devices turned on, determining multiple first total water flow rates and multiple third total power consumptions corresponding to the number of devices turned on; among all first total water flow rates and third total power consumptions corresponding to the multiple numbers of devices turned on, determining a second target total power consumption corresponding to the cooling water pump operating frequency in which the first total water flow rate is greater than a first preset water flow rate and the head of the cooling water pump is greater than the first preset head; and taking the reference cooling water pump operating frequency and the number of devices turned on corresponding to the smallest third total power consumption among the second target total power consumption as the target operating parameters.

[0023] In some embodiments, when the target device is a chilled water pump module, the real-time operating data includes the operating frequency of the chilled water pump and the number of valves opened of the chilled water pump; using the target cooling system model corresponding to the target device, the performance parameters of the target device in the current operating state are determined according to the operating data corresponding to the target device, including: obtaining the target flow rate of chilled water and multiple reference pump operating frequencies within the range of the chilled water pump operating frequency; for each reference chilled water pump operating frequency among the multiple reference chilled water pump operating frequencies, the reference chilled water pump operating frequency and the number of valves opened of the chilled water pump are input into the target cooling system model corresponding to the target device to obtain the head of the chilled water pump and the water flow rate of the chilled water pump corresponding to the reference chilled water pump operating frequency; the performance parameters of the target device in the current operating state include the head of the chilled water pump and the water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency among the multiple reference chilled water pump operating frequencies.

[0024] In some embodiments, target operating parameters corresponding to the target device are determined based on performance parameters, including: for each number of devices turned on among multiple numbers of devices turned on, based on multiple reference chilled water pump operating frequencies, the water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency, and the number of devices turned on, determining multiple second total water flow rates and fourth total power consumptions corresponding to the number of devices turned on; among all second total water flow rates and fourth total power consumptions corresponding to the multiple numbers of devices turned on, determining a third target total power consumption corresponding to a chilled water pump operating frequency in which the second total water flow rate is greater than a second preset water flow rate and the head of the chilled water pump is greater than the second preset head; and taking the reference chilled water pump operating frequency and the number of devices turned on corresponding to the smallest total power consumption among the third target total power consumption as the target operating parameters.

[0025] In a second aspect, an embodiment of the present application provides a cooling system, comprising:

[0026] An acquisition module, which is used to acquire real-time operating data corresponding to a target device in the cooling system;

[0027] A processing module, the processing module is used to determine the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device by using the target cooling system model corresponding to the target device;

[0028] The processing module is further used to determine the target operating parameters corresponding to the target device according to the performance parameters;

[0029] The processing module is also used to control the operation of the target device according to the target operation parameters;

[0030] Among them, the target cooling system model corresponding to the target device is trained in the following way:

[0031] The acquisition module acquires a plurality of source domain training samples and a plurality of target domain training samples corresponding to the target device, wherein the source domain training samples are determined based on the historical operation data corresponding to other cooling systems; and the target domain training samples are determined based on the historical operation data corresponding to the cooling system;

[0032] The processing module trains an initial cooling system model corresponding to the target device based on multiple source domain training samples to obtain a trained cooling system model corresponding to the target device;

[0033] The processing module adjusts the trained cooling system model corresponding to the target device based on multiple target domain training samples to obtain a target cooling system model corresponding to the target device.

[0034] In a third aspect, a communication device is provided, comprising: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute a control method for a cooling system as in the first aspect and any possible implementation thereof.

[0035] In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored. When the computer instructions are executed on a communication device, the communication device executes a control method for a cooling system as in the first aspect and any possible implementation thereof.

[0036] The specific description of the second to fourth aspects of the present invention and their various implementations can refer to the detailed description of the first aspect and its various implementations. The beneficial effects of the second to fourth aspects and their various implementations can refer to the beneficial effect analysis of the first aspect and its various implementations, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0038] Figure 1 A schematic diagram of the structure of a cooling system provided in an embodiment of the present application;

[0039] Figure 2 A schematic flow chart of a control method for a cooling system provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of a model training process provided in an embodiment of the present application;

[0041] Figure 4 A schematic flow chart of another method for controlling a cooling system according to an embodiment of the present application;

[0042] Figure 5 A schematic diagram of the structure of another cooling system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described below are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] In order to facilitate the description of the technical solution of the present application, in the present application, words such as "first" and "second" may be used to distinguish between technical features with the same or similar functions. The words such as "first" and "second" do not limit the quantity and execution order, and the words such as "first" and "second" do not necessarily limit them to be different. In the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations, and any embodiment or design described as "exemplary" or "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. The use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0045] The terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0046] It is understood that the "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments in the entire specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It is understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the present application.

[0047] It can be understood that in the present application, "when...", "in the case of...", "if" and "if" all mean that corresponding processing will be taken under certain objective circumstances, but do not limit the time, nor do they require any judgment action when implementing them, nor do they mean the existence of other limitations.

[0048] To facilitate understanding, the basic concepts of some terms or technologies involved in the embodiments of the present application are first briefly introduced and explained.

[0049] 1. Transfer Learning

[0050] Transfer learning is a learning process that uses the similarities between data, tasks, or models to apply the model learned in the old domain (source domain) to the new domain (target domain).

[0051] By introducing knowledge from other projects, transfer learning can build effective control models even when data is scarce, reducing the demand and dependence on data. Optimization control based on transfer learning methods can ensure that various equipment models of the cooling system are more generalized in new data centers, able to adapt to and handle diverse needs and changes in new projects, and promote the large-scale application of energy-saving optimization control methods.

[0052] 2. Source Domain Dataset and Target Domain Dataset

[0053] The source domain data set refers to the data set used when the model is trained, and the target domain data set is the new data set or new field to which the model will be applied. The source domain data contains a large amount of training data and trained models, while the target data contains less data. In this application, the source domain data can be operating data other than the cooling system of the newly built data center, and the target domain data can be the operating data of the cooling system of the newly built data center.

[0054] The above is an introduction to some concepts involved in the embodiments of the present application, which will not be repeated below.

[0055] As mentioned in the background technology, the data center cooling system refers to a special system used to reduce the temperature of the internal equipment of the data center, which is usually composed of a series of cooling equipment and components, such as chillers, cooling towers, cooling water pumps, freezing water pumps, etc. The control parameters of this series of cooling equipment are closely related to the operating efficiency of the data center cooling system.

[0056] In the related art, a large amount of historical operation data of the data center cooling system is often collected, and the cooling system model is trained based on the historical operation data. However, the historical operation data of the cooling system of the newly built data center is relatively small, and there is often a lack of sufficient historical operation data for model training, resulting in inaccurate output results of the cooling system model, which affects the operating efficiency of the data center cooling system. Therefore, how to improve the operating efficiency of the data center cooling system is an urgent problem to be solved.

[0057] In view of this, the embodiment of the present application trains the initial cooling system model corresponding to the target device through source domain training samples, and adjusts the trained cooling system model corresponding to the target device through target domain training samples, which can reduce the demand and dependence on the operating data of the target device and increase the generalization ability of the target cooling system model. That is, the target cooling system model corresponding to the target device is more in line with the operating conditions of the target device, thereby improving the accuracy of the target cooling system model. Furthermore, the target operating parameters determined by the target cooling system model corresponding to the target device are the optimal operating parameters of the target device. Controlling the operation of the target device with the target operating parameters can put the target device in the optimal operating state, thereby improving the operating efficiency of the data center cooling system.

[0058] The following is a detailed introduction to the embodiments of the present application in conjunction with the accompanying drawings.

[0059] The control method of the cooling system provided in the embodiment of the present application can be applicable to the cooling system. Figure 1 A schematic diagram of the structure of a cooling system provided in an embodiment of the present application.

[0060] like Figure 1 As shown, the cooling system 1 includes: a chiller module 10, a cooling tower module 20, a cooling water pump module 30 and a freezing water pump module 40.

[0061] The chiller module 10 is also called a freezer, a refrigeration unit, an ice water unit, a cooling device, etc., and is used to generate low-temperature cooling water through the circulation of a refrigerant. The chiller module 10 is connected to the cooling tower module 20 through a pipeline.

[0062] Optionally, the chiller module 10 may include a refrigerant circulation loop consisting of a compressor, a condenser, an expansion valve, and an evaporator. The compressor inhales low-temperature, low-pressure refrigerant gas, and then increases its temperature and pressure through compression to turn it into a high-temperature, high-pressure gas. In this process, the refrigerant gas is compressed and converted into a high-temperature, high-pressure gas, while releasing a large amount of heat. After the high-temperature, high-pressure refrigerant gas enters the condenser, it transfers heat to the environment through heat exchange with the external environment, thereby reducing its own temperature and turning it into a high-pressure liquid. Before the high-pressure liquid enters the evaporator through the expansion valve, it will pass through the throttling effect of the expansion valve, causing its pressure and temperature to drop significantly and become a low-temperature, low-pressure liquid. After the low-temperature, low-pressure refrigerant liquid enters the evaporator, it will absorb the heat of the cooled object, thereby increasing its own temperature and turning it into a low-temperature, low-pressure gas. The refrigerant gas in the evaporator is sucked in by the compressor again to start a new round of circulation.

[0063] The cooling tower module 20 is used to cool the cooling water that has absorbed heat and flows out of the chiller module 10. The cooling tower transfers heat to the atmosphere by exchanging heat between the cooling water and the air, thereby reducing the temperature of the cooling water.

[0064] Optionally, the cooling tower module 20 includes a cooling water circulation loop consisting of a fan and a water collection tank. The output end of the cooling tower module 20 is connected to the input end of the condenser, and the input end of the cooling tower module 20 is connected to the output end of the condenser. The cooling water in the cooling water circulation loop and the refrigerant in the refrigerant circulation loop exchange heat at the condenser of the chiller module 10.

[0065] The fan is used as a power component of the cooling tower module 20 to blow air into the cooling tower module 20 to promote evaporation and heat dissipation of cooling water. The water collection tank is used to receive and store cooled cooling water.

[0066] The cooling water pump module 30 is used to transport cooling water from the cooling tower module 20 to the chiller module 10, and to transport the cooled cooling water to the equipment or system that needs to be cooled. Optionally, the output end of the cooling water pump in the cooling water pump module 30 is connected to the evaporator input end of the chiller in the chiller module 10 to provide cooled water for the chiller, and the input end of the cooling water pump is connected to the output end of the cooling equipment.

[0067] The chilled water pump module 40 is used to transport the low-temperature chilled water generated by the chiller to the equipment or system that needs the chilled water for cooling. Optionally, the output end of the chilled water pump in the chilled water pump module 40 is connected to the input end of the cooling tower module 20, and the input end of the chilled water pump is connected to the output end of the condenser in the chiller.

[0068] It can be understood that the number of devices in the above-mentioned chiller module 10, cooling tower module 20, cooling water pump module 30 and freezing water pump module 40 can be one or more, and the embodiment of the present application does not limit the number of devices in the chiller module 10, cooling tower module 20, cooling water pump module 30 and freezing water pump module 40 in the cooling system 1.

[0069] A control method for a cooling system provided in an embodiment of the present application is described below in conjunction with the accompanying drawings.

[0070] Figure 2 The present invention provides a flow chart of a control method for a cooling system, which can be applied to a cooling system. Figure 2 As shown, the control method of the cooling system provided in the present application includes the following steps S1-S4.

[0071] S1. Obtain real-time operating data corresponding to the target equipment in the cooling system.

[0072] The target device may be one or more of a chiller module, a cooling tower, a cooling water pump and a refrigeration water pump.

[0073] Optionally, when the target device is a chiller module, the real-time operating data may include: chilled water outlet temperature, cooling water inlet temperature; when the target device is a cooling tower module, the real-time operating data may include: outdoor ambient wet-bulb temperature, cooling water target approach, cooling water temperature difference; when the target device is a cooling water pump module, the real-time operating data may include the cooling water pump operating frequency and the number of cooling water pump valves opened; when the target device is a chilled water pump module, the real-time operating data may include the chilled water pump operating frequency and the number of chilled water pump valves opened.

[0074] As a possible implementation, the cooling system includes a plurality of temperature sensors and a data acquisition system connected to a programmable logic controller (PLC). The plurality of temperature sensors are used to detect the chilled water outlet temperature, the cooling water inlet temperature, and the outdoor environment wet bulb temperature; the data acquisition system is used to detect the number of cooling water pumps and the chilled water pumps that are turned on and the operating frequency. The temperature data from the plurality of temperature sensors and the number of cooling water pumps and the chilled water pumps that are turned on and the operating frequency from the data acquisition system can be received by the PLC.

[0075] S2. Using the target cooling system model corresponding to the target device, and according to the operating data corresponding to the target device, determine the performance parameters of the target device in the current operating state.

[0076] Optionally, when the target device is a chiller module, the performance parameters of the target device in the current operating state include the power consumption corresponding to each reference cooling capacity among multiple reference cooling capacities; when the target device is a cooling tower module, the performance parameters of the target device in the current operating state include the cooling tower approximation corresponding to each reference cooling tower fan frequency among multiple reference cooling tower fan frequencies; when the target device is a cooling water pump module, the performance parameters of the target device in the current operating state include the cooling water pump head and the water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency among multiple reference cooling water pump operating frequencies; when the target device is a chilled water pump module, the performance parameters of the target device in the current operating state include the chilled water pump head and the water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency among multiple reference chilled water pump operating frequencies.

[0077] S3. Determine target operating parameters corresponding to the target device according to the performance parameters.

[0078] Optionally, when the target device is a chiller module, the target operating parameters may include the number of chillers in the chiller that are turned on and the cooling capacity of the chiller; when the target device is a cooling tower module, the target operating parameters may include the operating frequency of the cooling tower fan and the number of cooling towers in the cooling tower module that are turned on; when the target device is a cooling water pump module, the target operating parameters may include the number of valves of the cooling water pump that are turned on and the operating frequency of the cooling water pump; when the target device is a freezing water pump module, the target operating parameters may include the number of valves of the freezing water pump that are turned on and the operating frequency of the freezing water pump.

[0079] S4. Control the operation of the target device according to the target operation parameters.

[0080] As a possible implementation, the target cooling system model corresponding to the target device is obtained through the following steps S401-S403:

[0081] S401: Acquire multiple source domain training samples and multiple target domain training samples corresponding to a target device.

[0082] The source domain training samples are determined based on the historical operation data corresponding to other cooling systems, and the target domain training samples are determined based on the historical operation data corresponding to the cooling system. The other cooling system may be a cooling system different from but similar to the cooling system in the embodiment of the present application.

[0083] As a possible implementation method, historical operation data related to the cooling system is obtained through an internal data warehouse to generate source domain training samples.

[0084] As another possible implementation manner, source domain training samples are generated by generating source domain data through a data generator or a simulator.

[0085] Optionally, before generating source domain training samples and target domain training samples, the following data preprocessing steps are also included:

[0086] Step 1: Use the interquartile range method to select outliers in the source domain data and the target domain data, and delete the outliers. The interquartile range method is a statistic that describes the degree of data dispersion and is mainly used to identify and process outliers in the data. The interquartile range method can be expressed as the following formula:

[0087] UL=Q3+1.5×IQR

[0088] LL=Q1-1.5×IQR

[0089] IQR=Q3-Q1

[0090] Among them, UL is the upper limit of normal value, LL is the lower limit of normal value, IQR is the difference between the third range and the first range, Q1 is the first quartile, and Q3 is the third quartile.

[0091] Step 2: Use the linear interpolation method to fill in the outliers and missing values ​​in the source domain data and the target domain data.

[0092] Step 3: Use standardization tools to scale the source domain dataset and the target domain dataset to a specific range (such as [0,1]). Formula:

[0093]

[0094] Among them, x i is the i-th data in the data set X, x iN is the standardized x_i value. max is the maximum value in the data set X, X min is the minimum value in the data set X.

[0095] It is understandable that the accuracy of the data can be improved by removing or correcting errors and outliers in the data through the interquartile range method. The integrity of the data can be ensured by using the linear difference method to fill in outliers and missing values ​​in the source domain data and the target domain data. Using standardization tools to scale the source domain dataset and the target domain dataset to the same order of magnitude can make different features comparable, and scaling the data to a specific range can make the model training converge faster.

[0096] S402: Train an initial cooling system model corresponding to the target device based on multiple source domain training samples to obtain a trained cooling system model corresponding to the target device.

[0097] As a possible implementation method, the source domain training samples are input into the initial cooling system model corresponding to the target device, and the prediction results corresponding to the source domain training samples in the source domain sample set are obtained. According to the prediction results and the actual results of the source domain training samples, the loss value of the source domain sample set is determined. According to the loss value of the sample set, it is judged whether the initial cooling system model corresponding to the target device converges. If not, according to the loss value of the source domain sample set, the weight parameters in the initial cooling system model corresponding to the target device are updated, and the source domain training samples are input into the initial cooling system model corresponding to the target device to obtain the prediction results corresponding to the source domain training samples in the source domain sample set; if so, the initial cooling system model corresponding to the current target device is determined as the trained cooling system model.

[0098] S403: Adjust the trained cooling system model corresponding to the target device based on multiple target domain training samples to obtain a target cooling system model corresponding to the target device.

[0099] As a possible implementation method, the target domain training samples are input into the trained cooling system model to obtain the prediction results corresponding to the target domain training samples in the target domain sample set, and the loss value of the target domain sample set is determined based on the prediction results and true results of the target domain training samples. Whether the initial cooling system model corresponding to the target device has converged is determined based on the loss value of the sample set. If not, the weight parameters in the initial cooling system model corresponding to the target device are updated based on the loss value of the target domain sample set, and the target domain training samples are continuously input into the initial cooling system model corresponding to the target device to obtain the prediction results corresponding to the target domain training samples in the target domain sample set; if so, the current cooling system model is determined as the target cooling system model.

[0100] Figure 2 The illustrated embodiment brings at least the following beneficial effects: The embodiment of the present application trains the initial cooling system model corresponding to the target device through source domain training samples, and adjusts the trained cooling system model corresponding to the target device through target domain training samples, which can reduce the demand and dependence on the operating data of the target device and increase the generalization ability of the target cooling system model. That is, the target cooling system model corresponding to the target device is more in line with the operating conditions of the target device, thereby improving the accuracy of the target cooling system model. Furthermore, the target operating parameters determined by the target cooling system model corresponding to the target device are the optimal operating parameters of the target device. Controlling the operation of the target device with the target operating parameters can put the target device in the optimal operating state, thereby improving the operating efficiency of the cooling system of the data center.

[0101] Figure 3 A flow chart of a model training process provided in an embodiment of the present application. Figure 3 As shown, the initial cooling system model corresponding to the chiller is the initial chiller model; the initial cooling system model corresponding to the cooling tower is the initial cooling tower model; the cooling system model corresponding to the cooling water pump is the initial cooling water pump model; and the cooling system model corresponding to the freezing water pump is the initial freezing water pump model.

[0102] The source domain data and the target domain data are cleaned, completed and standardized to obtain the preprocessed source domain data and the preprocessed target domain data.

[0103] The preprocessed source domain data is input into the initial chiller model, initial cooling tower model, initial cooling water pump model and initial refrigerating water pump model, and the initial chiller model, initial cooling tower model, initial cooling water pump model and initial refrigerating water pump model are trained respectively to obtain the trained chiller model, trained cooling tower model, trained cooling water pump model and trained refrigerating water pump model. The preprocessed target domain data is then input into the trained chiller model, trained cooling tower model, trained cooling water pump model and trained refrigerating water pump model for adjustment to obtain the target chiller model, target cooling tower model, target cooling water pump model and target refrigerating water pump model respectively.

[0104] In some embodiments, the above step S2 can be implemented as the following steps S201-S203:

[0105] S201. Determine a plurality of reference cooling capacities within a cooling capacity range of each chiller in a chiller module.

[0106] The chiller module may include one or more chillers. The cooling capacity range of the chiller is related to the brand and model of the chiller, and the cooling capacity can be determined by the product of the cooling power and the energy efficiency ratio. Usually, the cooling capacity range of the chiller is between 30kw-70kw, where kw is the power unit kilowatt.

[0107] S202. For each reference cooling capacity among multiple reference cooling capacities, determine the cooling load rate corresponding to the reference cooling capacity, and input the chilled water outlet temperature setting value, the cooling water inlet temperature and the cooling load rate into the target cooling system model corresponding to the target device to obtain the energy efficiency ratio corresponding to the reference cooling capacity.

[0108] The chilled water outlet temperature setting value is set by the designer of the cooling system at the factory, and can also be set by the user.

[0109] Optionally, the refrigeration load rate corresponding to the reference refrigeration capacity may be determined by a ratio between the refrigeration power corresponding to the reference refrigeration capacity and the rated refrigeration capacity.

[0110] Optionally, the inlet temperature of the cooling water may be determined by the outdoor ambient wet bulb temperature, the set value of the cooling tower approach and the set value of the cooling water temperature difference. The set value of the cooling tower approach and the set value of the cooling water temperature difference may be set by the designer of the cooling system at the factory or by the user.

[0111] S203. For each reference cooling capacity among the multiple reference cooling capacities, obtain the power consumption corresponding to the reference cooling capacity based on the reference cooling capacity and the energy efficiency ratio corresponding to the reference cooling capacity.

[0112] As a possible implementation manner, the power consumption corresponding to the reference cooling capacity may be determined by a ratio between the reference cooling capacity and an energy efficiency ratio corresponding to the reference cooling capacity.

[0113] Optionally, the performance parameter of the target device in the current operating state includes power consumption corresponding to each reference cooling capacity of multiple reference cooling capacities.

[0114] It can be seen from the above embodiments that by inputting the chilled water outlet temperature setting value, the cooling water inlet temperature and the cooling load rate corresponding to each of the multiple reference cooling capacities into the target cooling system model corresponding to the chiller module, the energy efficiency ratio corresponding to each of the multiple reference cooling capacities can be obtained. Then, the power consumption corresponding to each reference cooling capacity is determined according to the energy efficiency ratio corresponding to each reference cooling capacity.

[0115] In some embodiments, the above step S3 can be implemented as the following steps S301-S303:

[0116] S301. For each of a plurality of device-on numbers, based on a plurality of reference cooling capacities, the power consumption corresponding to each reference cooling capacity, and the number of devices turned on, determine a plurality of total cooling capacities and a first total power consumption corresponding to the number of devices turned on.

[0117] It is understandable that the number of devices turned on should be less than or equal to the total number of chillers in the chiller module.

[0118] As a possible implementation manner, the total cooling capacity corresponding to the number of switched-on devices may be determined by multiplying the number of switched-on devices by a reference cooling capacity.

[0119] For example, when the number of devices turned on is 3 and the reference cooling capacity is akw, the total cooling capacity corresponding to akw is 3akw. When the number of devices turned on is 4 and the reference cooling capacity is bkw, the total cooling capacity corresponding to bkw is 4bkw.

[0120] As a possible implementation manner, the first total power consumption is determined by the product of the number of devices turned on and the power consumption corresponding to the reference cooling capacity, that is, the first total power consumption corresponding to the reference cooling capacity = the number of devices turned on * the power consumption corresponding to the reference cooling capacity.

[0121] S302. Determine, among all total cooling capacities and first total power consumptions corresponding to the number of devices turned on, a first target total power consumption corresponding to a total cooling capacity whose total cooling capacity is greater than a cooling load demand.

[0122] It can be understood that when the total cooling capacity is greater than the cooling load demand, it means that the cooling demand of the chiller module under the current operating state can meet the cooling demand of the user. Therefore, the first total power consumption is the total power consumption of the chiller module when the cooling demand of the chiller module can meet the cooling demand of the user.

[0123] S303: Taking the reference cooling capacity and the number of devices turned on corresponding to the minimum total power consumption in the first target total power consumption as target operating parameters.

[0124] It can be seen from the above embodiments that by determining the total cooling capacity and the first total power consumption of each scheme under different chiller opening numbers and different reference cooling capacity schemes, the first total power consumption corresponding to the scheme in which the total cooling capacity meets the cooling load demand can be used as the first target total power consumption. The reference cooling capacity and the number of equipment openings corresponding to the minimum total power consumption are selected from the first target total power consumption as the target operating parameters, so that the opening number and cooling capacity of the chiller module are controlled by the target operating parameters, so that the power consumption of the chiller module can be minimized.

[0125] In some embodiments, the above step S2 can be implemented as the following steps S204-S205:

[0126] S204, obtaining a target cooling water flow rate and a plurality of reference cooling tower fan frequencies within a cooling tower fan frequency range.

[0127] The target flow rate of cooling water can be determined according to the number of cooling units opened, the cooling capacity of the cooling units and the target temperature difference of cooling water. The frequency range of cooling tower fans is generally between 30Hz and 60Hz, where Hz is the frequency unit Hertz.

[0128] S205. For each reference cooling tower fan frequency among multiple reference cooling tower fan frequencies, the reference cooling tower fan frequency, the cooling water target flow rate, the outdoor ambient wet-bulb temperature, and the cooling water temperature difference are input into the target cooling system model corresponding to the target device to obtain the cooling tower approximation corresponding to the reference cooling tower fan frequency.

[0129] Among them, the approximation of the cooling tower is an important parameter for evaluating the performance of the cooling tower. It reflects the ability of the cooling tower to cool water to a temperature close to the wet bulb temperature of the air. The smaller the approximation of the cooling tower, the better the cooling effect of the cooling tower.

[0130] Exemplarily, when the reference cooling tower fan frequency is cHz, cHz, cooling water target flow, outdoor ambient wet bulb temperature, and cooling water temperature difference are input into the target cooling system model corresponding to the cooling tower module to obtain the cooling tower approximation corresponding to cHz.

[0131] Optionally, the performance parameter of the target device in the current operating state includes a cooling tower approximation corresponding to each reference cooling tower fan frequency of a plurality of reference cooling tower fan frequencies.

[0132] It can be seen from the above embodiments that by inputting a reference cooling tower fan frequency, a cooling water target flow rate, an outdoor environment wet bulb temperature, and a cooling water temperature difference into the target cooling system corresponding to the cooling tower module, a cooling tower approximation corresponding to multiple reference cooling tower fan frequencies can be obtained. The cooling tower approximation corresponding to multiple reference cooling tower fan frequencies can reflect the different cooling effects of the cooling tower under different reference cooling tower fan frequencies.

[0133] In some embodiments, the above step S3 can be implemented as the following steps S304-S305:

[0134] S304. For each device-on number among the multiple device-on numbers, based on multiple reference cooling tower fan operating frequencies and device-on numbers, determine multiple cooling tower approximations corresponding to the device-on numbers.

[0135] It should be noted that the number of cooling towers opened in the cooling tower module is different, and the approximation of cooling towers corresponding to different opening numbers is also different. The number of equipment openings is less than or equal to the number of cooling towers in the cooling tower module.

[0136] As a possible implementation, the approximation of the cooling tower corresponding to the number of equipment openings can be determined by the approximation of the cooling tower, the number of cooling towers openings, the water flow through one cooling tower and the total water flow through all cooling towers.

[0137] Exemplarily, the approximation of the cooling tower corresponding to the number of devices turned on = ∑ (cooling tower approximation * water flow of one cooling tower) / total water flow of the cooling tower.

[0138] S305. Determine, among all cooling tower approximations corresponding to the number of devices turned on, a target cooling tower fan operating frequency corresponding to a cooling tower approximation whose cooling tower approximation is less than a preset approximation; and use the target cooling tower fan operating frequency and the number of devices turned on that correspond to the smallest second total power consumption among the second total power consumption corresponding to the target cooling tower fan operating frequency as target operating parameters.

[0139] The preset approximation degree may be set by a designer at the factory or by a user.

[0140] It is understandable that if the cooling tower approximation is less than the cooling tower approximation of the preset approximation, it means that the cooling effect of the cooling tower can meet the use requirements. Determine the target cooling tower fan operating frequency corresponding to each cooling tower approximation among the multiple cooling tower approximations that can meet the cooling requirements, and then determine the second total power consumption under each combination based on different target cooling tower fan operating frequencies and different cooling tower opening numbers. The target cooling tower fan operating frequency and the number of cooling tower openings corresponding to the smallest second total power consumption among the multiple second total power consumptions are used as target operating parameters. In this way, the opening number of cooling towers and the cooling tower fan operating frequency in the cooling tower module are controlled by the target operating parameters, so that the power consumption of the cooling tower module can be minimized.

[0141] In some embodiments, the above step S2 can be implemented as the following steps S206-S207:

[0142] S206: Obtain a target cooling water flow rate and a plurality of reference water pump operating frequencies within a cooling water pump operating frequency range.

[0143] The target flow rate of cooling water can be determined according to the number of cooling units turned on, the cooling capacity of the cooling units and the target temperature difference of cooling water. The operating frequency range of the cooling water pump is usually between 30Hz and 50Hz.

[0144] S207. For each reference cooling water pump operating frequency among multiple reference cooling water pump operating frequencies, the reference cooling water pump operating frequency and the number of valve openings of the cooling water pump are input into the target cooling system model corresponding to the target device to obtain the cooling water pump head and the water flow rate of the cooling water pump corresponding to the reference cooling water pump operating frequency.

[0145] Among them, the head of the cooling water pump refers to the height to which the cooling water pump can lift or transport water. The size of the head affects the performance of the water pump and the overall efficiency of the cooling system.

[0146] Optionally, the number of cooling water pump valves opened may be the same as the number of cooling tower valves opened in the cooling tower module.

[0147] Optionally, the performance parameters of the target device in the current operating state include a head of the cooling water pump and a water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency among a plurality of reference cooling water pump operating frequencies.

[0148] It can be seen from the above embodiments that by inputting the reference cooling water pump operating frequency and the number of valve openings of the cooling water pump into the target cooling system model corresponding to the cooling water pump, the heads of the cooling water pumps and the water flow rates of the cooling water pumps corresponding to the multiple reference cooling water pump operating frequencies can be obtained. Different heads of cooling water pumps can reflect different pumping capacities of the cooling water pumps.

[0149] In some embodiments, the above step S3 can be implemented as the following steps S306-S308:

[0150] S306. For each of the multiple numbers of devices turned on, based on multiple reference cooling water pump operating frequencies, the water flow of the cooling water pump corresponding to each reference cooling water pump operating frequency, and the number of devices turned on, determine multiple first total water flow rates and multiple third total power consumptions corresponding to the number of devices turned on.

[0151] Among them, the number of devices turned on is less than or equal to the number of cooling water pumps in the cooling system.

[0152] As a possible implementation, the first total water flow rate can be determined by the product of the water flow rate of the cooling water pump and the number of devices turned on. The third total power consumption can be determined by the operating frequency of the cooling water pump and the number of cooling water pumps turned on.

[0153] S307. Among all first total water flows and third total power consumptions corresponding to the number of devices turned on, determine the second target total power consumption corresponding to the cooling water pump operating frequency when the first total water flow is greater than the first preset water flow and the head of the cooling water pump is greater than the first preset head.

[0154] The first preset water flow rate and the first preset head can be set by the designer at the factory or by the user.

[0155] It can be understood that when the first total water flow is greater than the first preset water flow and the head of the cooling water pump is greater than the first preset head, it means that the cooling water flow provided by the cooling water pump module can meet the cooling water flow demand of the cooling system. By determining the second target power consumption corresponding to the operating frequency of the cooling water pump in multiple solutions that meet the cooling water flow demand of the cooling system, the total power consumption of each solution in the multiple solutions that meet the cooling water flow demand of the cooling system can be obtained.

[0156] S308: Use the reference cooling water pump operating frequency and the number of devices turned on that correspond to the smallest third total power consumption in the second target total power consumption as target operating parameters.

[0157] The water pump operating frequency and the number of equipment turned on corresponding to the solution with the lowest power consumption among the solutions that meet the cooling water flow requirements of the cooling system are used as target operating parameters. In this way, the power consumption of the cooling water pump module can be minimized by controlling the number of cooling water pumps turned on and the water pump operating frequency of the cooling water pump module with the target operating parameters.

[0158] In some embodiments, the above step S2 can be implemented as the following steps S208-S209:

[0159] S208. Obtain a target chilled water flow rate and a plurality of reference water pump operating frequencies within a chilled water pump operating frequency range.

[0160] The target flow rate of chilled water can be determined according to the number of refrigeration units turned on, the cooling capacity of the refrigeration units and the target temperature difference of chilled water. The operating frequency range of the chilled water pump is usually between 25Hz and 50Hz.

[0161] S209. For each reference chilled water pump operating frequency among multiple reference chilled water pump operating frequencies, the reference chilled water pump operating frequency and the number of valve openings of the chilled water pump are input into the target cooling system model corresponding to the target device to obtain the chilled water pump head and the water flow rate of the chilled water pump corresponding to the reference chilled water pump operating frequency.

[0162] Among them, the head of the chilled water pump refers to the height to which the chilled water pump can lift or transport water. The size of the head affects the performance of the water pump and the overall efficiency of the cooling system.

[0163] Optionally, the number of valves opened on the chilled water pump may be the same as the number of valves opened on the chiller module.

[0164] Optionally, the performance parameters of the target device in the current operating state include a head of the chilled water pump and a water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency among a plurality of reference chilled water pump operating frequencies.

[0165] As can be seen from the above embodiments, by inputting a reference chilled water pump operating frequency and the number of valve openings of the chilled water pump into the target cooling system model corresponding to the chilled water pump, the heads of the chilled water pumps and the water flow rates of the chilled water pumps corresponding to multiple reference chilled water pump operating frequencies can be obtained. Different heads of the chilled water pumps can reflect different pumping capacities of the chilled water pumps.

[0166] In some embodiments, the above step S3 can be implemented as the following steps S309-S311:

[0167] S309. For each of the multiple device-on numbers, based on multiple reference chilled water pump operating frequencies, the water flow of the chilled water pump corresponding to each reference chilled water pump operating frequency, and the number of devices turned on, determine multiple second total water flow rates and fourth total power consumption corresponding to the number of devices turned on.

[0168] As a possible implementation, the second total water flow rate can be determined by the product of the water flow rate of the chilled water pump and the number of devices turned on. The fourth total power consumption can be determined by the operating frequency of the chilled water pump and the number of chilled water pumps turned on.

[0169] S310. Among all the second total water flows and fourth total power consumptions corresponding to the number of devices turned on, determine the third target total power consumption corresponding to the operating frequency of the chilled water pump when the second total water flow is greater than the second preset water flow and the head of the chilled water pump is greater than the second preset head.

[0170] The second preset water flow rate and the second preset head can be set by the designer at the factory or by the user.

[0171] It can be understood that when the second total water flow is greater than the second preset water flow and the head of the chilled water pump is greater than the second preset head, it means that the chilled water flow provided by the chilled water pump module can meet the chilled water demand of the cooling system. By determining the third target total power consumption corresponding to the operating frequency of the chilled water pump in multiple solutions that meet the chilled water flow demand of the cooling system, the total power consumption of each solution in the solutions that meet the chilled water flow demand of the cooling system can be obtained.

[0172] S311. Taking the reference chilled water pump operating frequency and the number of devices turned on corresponding to the smallest total power consumption in the third target total power consumption as target operating parameters.

[0173] The water pump operating frequency and the number of equipment turned on corresponding to the solution with the lowest power consumption among the solutions that meet the chilled water flow demand of the cooling system are used as the target operating parameters. In this way, the power consumption of the chilled water pump module can be minimized by controlling the number of chilled water pumps turned on and the water pump operating frequency of the chilled water module with the target operating parameters.

[0174] Figure 4 FIG. 1 is a flow chart of another method for controlling a cooling system according to an embodiment of the present application. Figure 4 As shown,

[0175] The obtained cooling water inlet temperature, chilled water outlet temperature setting value and multiple refrigeration load rates are input into the target chiller model to obtain the energy consumption ratio corresponding to the refrigeration load. The optimal opening number and optimal refrigeration load of the chiller are obtained by combining the energy consumption ratio corresponding to the refrigeration load and the chiller module optimization strategy. Among them, the chiller optimization strategy is to calculate the power consumption of the chiller module under different chiller opening numbers and different refrigeration loads, determine the opening number of the chiller under the condition of minimum power consumption as the optimal opening number of the chiller, and determine the refrigeration load under the condition of minimum power consumption as the optimal refrigeration load of the chiller.

[0176] The optimal opening number of the chiller is used as the opening number of the chilled water pump valve, and the opening number of the chilled water pump valve and the operating frequencies of multiple chilled water pumps are input into the target chilled water pump model to obtain the head of the chilled water pump and the water flow of the chilled water pump corresponding to the operating frequencies of the chilled water pump. The optimal opening number of the chilled water pump and the optimal operating frequency of the chilled water pump are obtained by combining the head of the chilled water pump, the water flow of the chilled water pump and the optimization strategy of the chilled water pump module corresponding to the operating frequency of the chilled water pump. Among them, the optimization strategy of the chilled water pump module is to calculate the power consumption of the chilled water pump module under different opening numbers of chilled water pumps and different operating frequencies of chilled water pumps, determine the opening number of the chilled water pump when the power consumption is the minimum as the optimal opening number of the chilled water pump, and determine the operating frequency of the chilled water pump when the power consumption is the minimum as the optimal operating frequency of the chilled water pump.

[0177] The obtained cooling water temperature difference, cooling water target flow, cooling water target approximation, outdoor wet bulb temperature and multiple cooling tower fan operating frequencies are input into the target cooling tower model to obtain the approximation of the cooling tower corresponding to the cooling tower fan operating frequency. The optimal starting number of cooling towers and the optimal operating frequency of cooling tower fans are obtained by combining the approximation of the cooling tower corresponding to the cooling tower fan operating frequency and the cooling tower module optimization strategy. Among them, the cooling tower module optimization strategy is to calculate the power consumption of the cooling tower module under each number of cooling towers opened and cooling tower fan operating frequency in different cooling tower opening numbers and different cooling tower fan operating frequencies. Determine the number of cooling towers opened when the power consumption is minimized as the optimal number of cooling tower modules opened, and determine the cooling tower fan operating frequency when the power consumption is minimized as the optimal operating frequency of the cooling tower fan.

[0178] The optimal opening number of the cooling tower is used as the opening number of the cooling water pump valve, and the opening number of the cooling water pump valve and the operating frequencies of multiple cooling water pumps are input into the target cooling water pump model to obtain the head of the cooling water pump and the water flow of the cooling water pump corresponding to the operating frequencies of the cooling water pump. The optimal opening number of the cooling water pump and the optimal operating frequency of the cooling water pump are obtained by combining the head of the cooling water pump, the water flow of the cooling water pump and the cooling water pump module optimization strategy corresponding to the operating frequency of the cooling water pump. Among them, the cooling water pump module optimization strategy is to calculate the power consumption of the cooling water pump module under different opening numbers of cooling water pumps and different operating frequencies of cooling water pumps, determine the opening number of the cooling water pump when the power consumption is the minimum as the optimal opening number of the cooling water pump, and determine the operating frequency of the cooling water pump when the power consumption is the minimum as the optimal operating frequency of the cooling water pump.

[0179] Output cooling system optimization strategy, the optimization strategy may include the optimal opening number of the chiller, the optimal cooling load of the chiller, the optimal opening number of the cooling tower, the fan operating frequency of the cooling tower, the optimal opening number of the cooling water pump, the cooling water pump operating frequency, the optimal opening number of the chilled water pump and the chilled water pump operating frequency.

[0180] It can be seen that the above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. To achieve the above functions, the embodiment of the present application provides a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily appreciate that, in combination with the modules and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0181] The embodiment of the present application can divide the controller into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0182] In the case of dividing each functional module into corresponding functional modules, Figure 5 A schematic diagram of the structure of another cooling system provided in an embodiment of the present application. Figure 5 As shown, the cooling system 5 includes: an acquisition module 501 and a processing module 502. Among them,

[0183] The acquisition module 501 is used to acquire the real-time operation data corresponding to the target device in the cooling system;

[0184] The processing module 502 is used to determine the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device using the target cooling system model corresponding to the target device;

[0185] The processing module 502 is further used to control the operation of the target device according to the target operation parameters;

[0186] Among them, the target cooling system model corresponding to the target device is trained in the following way:

[0187] The acquisition module 501 acquires a plurality of source domain training samples and a plurality of target domain training samples corresponding to the target device, wherein the source domain training samples are determined based on the historical operation data corresponding to other cooling systems; and the target domain training samples are determined based on the historical operation data corresponding to the cooling system;

[0188] The processing module 502 trains an initial cooling system model corresponding to the target device based on a plurality of source domain training samples to obtain a trained cooling system model corresponding to the target device;

[0189] The processing module 502 adjusts the trained cooling system model corresponding to the target device based on a plurality of target domain training samples to obtain a target cooling system model corresponding to the target device.

[0190] In some embodiments, the processing module 502 is further configured to determine a plurality of reference cooling capacities within a cooling capacity range of each chiller in the chiller module;

[0191] The processing module 502 is further used to determine the refrigeration load rate corresponding to each reference refrigeration capacity of the multiple reference refrigeration capacities, and input the chilled water outlet temperature setting value, the cooling water inlet temperature and the refrigeration load rate into the target cooling system model corresponding to the target device to obtain the energy efficiency ratio corresponding to the reference refrigeration capacity;

[0192] The processing module 502 is further configured to obtain, for each reference cooling capacity among the multiple reference cooling capacities, a power consumption corresponding to the reference cooling capacity based on the reference cooling capacity and the energy efficiency ratio corresponding to the reference cooling capacity;

[0193] The performance parameter of the target device in the current operating state includes power consumption corresponding to each reference cooling capacity of a plurality of reference cooling capacities.

[0194] In some embodiments, the processing module 502 is further configured to determine, for each device-on number in the plurality of device-on numbers, a plurality of total cooling capacities and a first total power consumption corresponding to the device-on number based on a plurality of reference cooling capacities, the power consumption corresponding to each reference cooling capacity, and the device-on number;

[0195] The processing module 502 is further configured to determine, among all total cooling capacities and first total power consumptions corresponding to the number of devices turned on, a first target total power consumption corresponding to a total cooling capacity whose total cooling capacity is greater than a cooling load demand;

[0196] The processing module 502 is further configured to use the reference cooling capacity and the number of devices turned on corresponding to the minimum total power consumption in the first target total power consumption as target operating parameters.

[0197] In some embodiments, the acquisition module 501 is used to acquire a target cooling water flow rate and a plurality of reference cooling tower fan frequencies within a cooling tower fan frequency range;

[0198] The processing module 502 is further used to input the reference cooling tower fan frequency, the cooling water target flow rate, the outdoor environment wet bulb temperature, and the cooling water temperature difference into the target cooling system model corresponding to the target device for each reference cooling tower fan frequency among the multiple reference cooling tower fan frequencies, and obtain the cooling tower approximation corresponding to the reference cooling tower fan frequency;

[0199] The performance parameter of the target device in the current operating state includes a cooling tower approximation corresponding to each reference cooling tower fan frequency of a plurality of reference cooling tower fan frequencies.

[0200] In some embodiments, the processing module 502 is further configured to determine, for each device-on number in the plurality of device-on numbers, a plurality of cooling tower approximations corresponding to the device-on number based on a plurality of reference cooling tower fan operating frequencies and the device-on number;

[0201] The processing module 502 is also used to determine the target cooling tower fan operating frequency corresponding to the cooling tower approach degree that is less than the preset approach degree among all cooling tower approach degrees corresponding to the number of devices turned on; and use the target cooling tower fan operating frequency and the number of devices turned on that correspond to the smallest second total power consumption among the second total power consumption corresponding to the target cooling tower fan operating frequency as target operating parameters.

[0202] In some embodiments, the acquisition module 501 is further used to acquire a target cooling water flow rate and a plurality of reference water pump operating frequencies within a cooling water pump operating frequency range;

[0203] The processing module 502 is further used to input the reference cooling water pump operating frequency and the number of valve openings of the cooling water pump into the target cooling system model corresponding to the target device for each reference cooling water pump operating frequency among the multiple reference cooling water pump operating frequencies, so as to obtain the head of the cooling water pump and the water flow rate of the cooling water pump corresponding to the reference cooling water pump operating frequency;

[0204] The performance parameters of the target device in the current operating state include the head of the cooling water pump and the water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency among a plurality of reference cooling water pump operating frequencies.

[0205] In some embodiments, the processing module 502 is further configured to determine, for each device-on number in the plurality of device-on numbers, a plurality of first total water flows and a plurality of third total power consumptions corresponding to the number of device-on numbers based on a plurality of reference cooling water pump operating frequencies, a water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency, and the number of device-on numbers;

[0206] The processing module 502 is further configured to determine, among all first total water flows and third total power consumptions corresponding to the number of devices turned on, a second target total power consumption corresponding to the operating frequency of the cooling water pump at which the first total water flow is greater than the first preset water flow and the head of the cooling water pump is greater than the first preset head;

[0207] The processing module 502 is further configured to use the reference cooling water pump operating frequency and the number of devices turned on, corresponding to the smallest third total power consumption in the second target total power consumption, as target operating parameters.

[0208] In some embodiments, the acquisition module 501 is further used to acquire a target flow rate of chilled water and a plurality of reference water pump operating frequencies within a range of operating frequencies of the chilled water pump;

[0209] The processing module 502 is further used to input the reference chilled water pump operating frequency and the number of valve openings of the chilled water pump into the target cooling system model corresponding to the target device for each reference chilled water pump operating frequency among the multiple reference chilled water pump operating frequencies, and obtain the head of the chilled water pump and the water flow rate of the chilled water pump corresponding to the reference chilled water pump operating frequency;

[0210] The performance parameters of the target device in the current operating state include the head of the chilled water pump and the water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency among a plurality of reference chilled water pump operating frequencies.

[0211] In some embodiments, the processing module 502 is further configured to determine, for each device-on number in the plurality of device-on numbers, a plurality of second total water flows and a fourth total power consumption corresponding to the device-on number based on a plurality of reference chilled water pump operating frequencies, a water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency, and the device-on number;

[0212] The processing module 502 is further configured to determine, among all the second total water flow rates and the fourth total power consumption corresponding to the number of devices turned on, a third target total power consumption corresponding to the operating frequency of the chilled water pump at which the second total water flow rate is greater than the second preset water flow rate and the head of the chilled water pump is greater than the second preset head;

[0213] The processing module 502 is further configured to use the reference chilled water pump operating frequency and the number of devices turned on corresponding to the minimum total power consumption in the third target total power consumption as target operating parameters.

[0214] An embodiment of the present application also provides a computer-readable storage medium, including computer-executable instructions, which, when executed on a computer, enable the computer to execute any one of the cooling system control methods provided in the above embodiments.

[0215] An embodiment of the present application also provides a computer program product including computer executable instructions, which, when executed on a computer, enables the computer to execute any one of the cooling system control methods provided in the above embodiments.

[0216] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more servers that can be integrated with the medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0217] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0218] Although the present application is described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0219] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for controlling a cooling system, characterized in that: The method comprises: Acquire real-time operating data corresponding to the target device in the cooling system; Determining the performance parameters of the target device in a current operating state according to the operating data corresponding to the target device using the target cooling system model corresponding to the target device; Determining a target operating parameter corresponding to the target device according to the performance parameter; Controlling the operation of the target device according to the target operation parameters; The target cooling system model corresponding to the target device is trained in the following way: Acquire multiple source domain training samples and multiple target domain training samples corresponding to the target device, wherein the source domain training samples are determined based on historical operation data corresponding to other cooling systems; and the target domain training samples are determined based on historical operation data corresponding to the cooling system; Training an initial cooling system model corresponding to the target device based on a plurality of source domain training samples to obtain a trained cooling system model corresponding to the target device; The trained cooling system model corresponding to the target device is adjusted based on a plurality of the target domain training samples to obtain a target cooling system model corresponding to the target device.

2. The method according to claim 1, characterized in that In the case where the target device is a chiller module, the real-time operation data includes: chilled water outlet temperature and cooling water inlet temperature; The using the target cooling system model corresponding to the target device and determining the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device includes: Determining a plurality of reference cooling capacities within a cooling capacity range of each chiller in the chiller module; For each reference cooling capacity of the multiple reference cooling capacities, determining a cooling load rate corresponding to the reference cooling capacity, and inputting the chilled water outlet temperature setting value, the cooling water inlet temperature and the cooling load rate into a target cooling system model corresponding to the target device, to obtain an energy efficiency ratio corresponding to the reference cooling capacity; For each reference cooling capacity among the multiple reference cooling capacities, obtaining the power consumption corresponding to the reference cooling capacity based on the reference cooling capacity and the energy efficiency ratio corresponding to the reference cooling capacity; The performance parameter of the target device in the current operating state includes the power consumption corresponding to each reference cooling capacity of the multiple reference cooling capacities.

3. The method according to claim 2, characterized in that The determining, according to the performance parameter, a target operating parameter corresponding to the target device includes: For each device-on number in the plurality of device-on numbers, based on the plurality of reference cooling capacities, the power consumption corresponding to each of the reference cooling capacities, and the device-on number, determining a plurality of total cooling capacities and a first total power consumption corresponding to the device-on number; Determine, among all total cooling capacities and first total power consumptions corresponding to the number of devices turned on, a first target total power consumption corresponding to a total cooling capacity whose total cooling capacity is greater than a cooling load demand; The reference cooling capacity and the number of devices turned on corresponding to the minimum total power consumption in the first target total power consumption are used as the target operating parameters.

4. The method according to claim 1, characterized in that: In the case where the target device is a cooling tower module, the real-time operation data includes: outdoor environment wet-bulb temperature, cooling water target approach, cooling water temperature difference; The using the target cooling system model corresponding to the target device and determining the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device includes: obtaining a cooling water target flow rate and a plurality of reference cooling tower fan frequencies within a cooling tower fan frequency range; For each reference cooling tower fan frequency among the multiple reference cooling tower fan frequencies, input the reference cooling tower fan frequency, the cooling water target flow rate, the outdoor environment wet bulb temperature, and the cooling water temperature difference into a target cooling system model corresponding to the target device to obtain a cooling tower approximation corresponding to the reference cooling tower fan frequency; The performance parameter of the target device in the current operating state includes a cooling tower approximation corresponding to each reference cooling tower fan frequency of the multiple reference cooling tower fan frequencies.

5. The method according to claim 4, characterized in that The determining, according to the performance parameter, a target operating parameter corresponding to the target device includes: For each device-on number among the plurality of device-on numbers, based on the plurality of reference cooling tower fan operating frequencies and the device-on numbers, determining a plurality of cooling tower approximations corresponding to the device-on number; Among all cooling tower approximations corresponding to the number of devices turned on, determine the target cooling tower fan operating frequency corresponding to the cooling tower approximation whose cooling tower approximation is less than the preset approximation; and use the target cooling tower fan operating frequency and the number of devices turned on corresponding to the smallest second total power consumption among the second total power consumption corresponding to the target cooling tower fan operating frequency as the target operating parameters.

6. The method according to claim 1, characterized in that In the case where the target device is a cooling water pump module, the real-time operation data includes the operating frequency of the cooling water pump and the number of valves opened by the cooling water pump; The using the target cooling system model corresponding to the target device and determining the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device includes: Acquire a cooling water target flow rate and a plurality of reference water pump operating frequencies within the cooling water pump operating frequency range; For each reference cooling water pump operating frequency among a plurality of reference cooling water pump operating frequencies, the reference cooling water pump operating frequency and the number of valve openings of the cooling water pump are input into a target cooling system model corresponding to the target device, and the head of the cooling water pump and the water flow rate of the cooling water pump corresponding to the reference cooling water pump operating frequency are obtained; The performance parameters of the target device in the current operating state include the head of the cooling water pump and the water flow rate of the cooling water pump corresponding to each reference cooling water pump operating frequency among the multiple reference cooling water pump operating frequencies.

7. The method according to claim 6, characterized in that The determining, according to the performance parameter, a target operating parameter corresponding to the target device includes: For each of the plurality of device-on numbers, based on the plurality of reference cooling water pump operating frequencies, the water flow of the cooling water pump corresponding to each of the reference cooling water pump operating frequencies, and the number of devices on, determine a plurality of first total water flow rates and a plurality of third total power consumptions corresponding to the number of devices on; Among all the first total water flow rates and third total power consumptions corresponding to the number of devices turned on, determine the second target total power consumption corresponding to the operating frequency of the cooling water pump at which the first total water flow rate is greater than the first preset water flow rate and the head of the cooling water pump is greater than the first preset head; The reference cooling water pump operating frequency and the number of equipment turned on corresponding to the smallest third total power consumption in the second target total power consumption are used as the target operating parameters.

8. The method according to claim 1, characterized in that: In the case where the target device is a chilled water pump module, the real-time operation data includes the chilled water pump operation frequency and the number of valve openings of the chilled water pump; The using the target cooling system model corresponding to the target device and determining the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device includes: Acquire a target chilled water flow rate and a plurality of reference water pump operating frequencies within the chilled water pump operating frequency range; For each reference chilled water pump operating frequency among a plurality of reference chilled water pump operating frequencies, the reference chilled water pump operating frequency and the number of valve openings of the chilled water pump are input into a target cooling system model corresponding to the target device, and the head of the chilled water pump and the water flow rate of the chilled water pump corresponding to the reference chilled water pump operating frequency are obtained; The performance parameters of the target device in the current operating state include the head of the chilled water pump and the water flow rate of the chilled water pump corresponding to each reference chilled water pump operating frequency among the multiple reference chilled water pump operating frequencies.

9. The method according to claim 8, characterized in that The determining, according to the performance parameter, a target operating parameter corresponding to the target device includes: For each of the plurality of device-on numbers, based on the plurality of reference chilled water pump operating frequencies, the water flow of the chilled water pump corresponding to each of the reference chilled water pump operating frequencies, and the device-on numbers, determine a plurality of second total water flow rates and fourth total power consumption corresponding to the device-on numbers; Among all the second total water flow rates and fourth total power consumptions corresponding to the number of devices turned on, determine the third target total power consumption corresponding to the operating frequency of the chilled water pump at which the second total water flow rate is greater than the second preset water flow rate and the head of the chilled water pump is greater than the second preset head; The reference chilled water pump operating frequency and the number of devices turned on corresponding to the smallest total power consumption in the third target total power consumption are used as the target operating parameters.

10. A cooling system, characterized in that: include: An acquisition module, the acquisition module is used to acquire real-time operation data corresponding to the target device in the cooling system; A processing module, the processing module is used to determine the performance parameters of the target device in the current operating state according to the operating data corresponding to the target device by using the target cooling system model corresponding to the target device; The processing module is further used to determine the target operating parameters corresponding to the target device according to the performance parameters; The processing module is further used to control the operation of the target device according to the target operation parameter; The target cooling system model corresponding to the target device is trained in the following way: The acquisition module acquires a plurality of source domain training samples and a plurality of target domain training samples corresponding to the target device, wherein the source domain training samples are determined based on historical operation data corresponding to other cooling systems; and the target domain training samples are determined based on historical operation data corresponding to the cooling system; The processing module trains the initial cooling system model corresponding to the target device based on the plurality of source domain training samples to obtain a trained cooling system model corresponding to the target device; The processing module adjusts the trained cooling system model corresponding to the target device based on a plurality of the target domain training samples to obtain a target cooling system model corresponding to the target device.

11. A communication device, characterized in that: It comprises a memory and a processor; the memory and the processor are coupled, the memory is used to store a computer program, and the processor implements the control method of the cooling system according to any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on the communication device, the communication device executes the control method of the cooling system according to any one of claims 1 to 9.

Images