Cooling system control method, terminal and readable storage medium

Abstract

The invention relates to the technical field of temperature control, and discloses a cooling system control method, a terminal and a readable storage medium, and the method comprises the steps: obtaining the operation data of a cooling system, and building a thermodynamic power model of the cooling system according to the operation data and the mechanism of the cooling system; optimizing control parameters of the cooling system according to the thermodynamic power model to obtain optimized control parameters; and controlling the cooling system to work according to the optimized control parameters. According to the invention, through a data + mechanism dual-drive mode, a control strategy follows a thermal principle, is separated from pure data dependence, avoids inverse logic, has higher reliability and better energy-saving effect, and greatly improves the prediction accuracy of the dual-drive model and significantly reduces the calculation complexity and cost by making the two prediction models complement each other.

Description

Technical Field

[0001] The present invention relates to the field of temperature control technology, and in particular to a cooling system control method, a terminal and a readable storage medium. Background Art

[0002] Data centers are used to provide computing power support for technologies such as cloud computing, 5G communications, artificial intelligence, the Internet of Things, and large models. With the development of these technologies, the energy consumption of data centers has continued to grow. Not only due to the need for energy conservation and emission reduction, but also due to the limitation of electricity supply, it is urgent to reduce the energy consumption of data centers. The energy consumption of data centers mainly includes IT equipment, refrigeration systems, power supply and distribution systems, lighting systems and other facilities (including security equipment, fire extinguishing, waterproofing, sensors, and management systems of related data center buildings, etc.). Among them, the key to reducing the energy consumption of data centers is to improve the refrigeration efficiency. The energy consumption of the refrigeration system is one of the key factors in whether the PUE (Power Usage Effectiveness) of the data center can be reduced to a reasonable level.

[0003] The existing BA (Building Automation) system is based on the HVAC mechanism for specific programming control. It monitors the status of all equipment in real time, and based on the configuration and control parameters, links specific equipment according to rules and strategies, and realizes system control through closed-loop automatic control. The core is to ensure the reliable operation of the HVAC system. Generally, strict constraints are set on the control parameters, and it is ensured that the system has sufficient safety margin. The system operation mode is relatively fixed, but with the change of seasonal climate and the adjustment of IT load, the parameters need to be adjusted to adapt to the changes. Traditionally, this adjustment is manually made by operation and maintenance experts, which not only relies on manual experience, but also consumes operation and maintenance manpower.

[0004] To this end, the existing technology adopts a tuning solution based on the development of AI algorithms and driven by AI algorithms, mainly for refrigeration systems. Compared with BA system automatic control or manual tuning by operation experts, AI has the advantages of strong adaptability, faster tuning cycle, focus on global optimization and data decision-making, and generally can achieve good tuning results. However, the use of data fitting algorithms such as deep learning and reinforcement learning only uses pure data samples in limited scenarios, with high data costs, strong dependence on historical data, long training cycles, lack of interpretability, easy to reverse logic control, and low reliability under extreme working conditions. Summary of the invention

[0005] The purpose of the present invention is to provide a cooling system control method, a terminal and a readable storage medium, which are intended to solve the problems that the existing cooling system using neural networks is not interpretable, is prone to reverse logic control, and has low reliability under extreme working conditions.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0007] The present invention provides a cooling system control method, the cooling system control method comprising:

[0008] Acquiring operating data of the cooling system, and establishing a thermodynamic power model of the cooling system according to the operating data and the mechanism of the cooling system;

[0009] Optimizing the control parameters of the cooling system according to the thermodynamic power model to obtain optimized control parameters;

[0010] The cooling system is controlled to operate according to the optimized control parameters.

[0011] Furthermore, the step of establishing a thermodynamic power model of the cooling system according to the operating data and the mechanism of the cooling system specifically includes:

[0012] Establishing a thermodynamic partial model of the cooling system according to the operating data and the mechanism of the cooling system;

[0013] Connecting the thermodynamic partial models to obtain a thermodynamic mathematical power model;

[0014] A neural network is trained according to the thermodynamic mathematical power model to obtain a neural network with a control parameter as input and a total power of the cooling system as output as the thermodynamic power model.

[0015] Furthermore, the thermodynamic partial model of the cooling system is established according to the operating data and the mechanism of the cooling system, specifically including:

[0016] According to the mechanism of the cooling system, a white box model of each part of the cooling system is established;

[0017] Mathematically abstract each white box model to obtain a gray box model of each part of the cooling system as the thermodynamic partial model.

[0018] Furthermore, the thermodynamic partial model includes a chiller power model, a chiller load rate model, a cooling water flow model, a cooling tower outlet water temperature, a cooling tower power model, a cooling return water temperature model, a cooling water flow model, a chilled return water temperature model and a cooling water pump power model.

[0019] Furthermore, the control parameters of the cooling system are optimized according to the thermodynamic power model to obtain optimized control parameters, which specifically includes:

[0020] Generate a plurality of optimized individuals according to the control parameters, and form a population from the plurality of optimized individuals;

[0021] According to the upper and lower limits of the population, sampling and generating search points for optimized individuals;

[0022] According to the optimized individuals and populations, an evolutionary algorithm is used to iteratively obtain the optimal solution of the thermodynamic power model to obtain the optimized control parameters.

[0023] Furthermore, the evolutionary algorithm is used to iteratively obtain the optimal solution of the thermodynamic power model, and each iteration includes:

[0024] Substitute the control parameters corresponding to each optimized individual into the thermodynamic power model to obtain the fitness corresponding to each optimized individual;

[0025] Screening is performed according to the fitness corresponding to each optimized individual to obtain the parent individuals that pass the screening to form the parent population;

[0026] Generate new optimized individuals based on the parent individuals and form a population.

[0027] Furthermore, the step of generating new optimized individuals according to the parent individuals and forming a population specifically includes:

[0028] A plurality of parent pairs are selected from the parent population, each parent pair including two parent individuals;

[0029] Each parent pair generates two offspring individuals based on the two parent individuals;

[0030] The generated offspring individuals are subjected to random mutation to obtain a plurality of the optimized individuals.

[0031] Furthermore, the control parameters include the number of chillers, chiller outlet water temperature, the number of refrigeration water pumps, the refrigeration water pump frequency, the number of cooling water pumps, the cooling water pump frequency, the number of cooling towers and the cooling tower outlet water temperature.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, which includes: a memory, a processor, and a cooling system control program stored in the memory and executable on the processor, and when the cooling system control program is executed by the processor, the terminal is controlled to implement the steps of the cooling system control method as described above.

[0033] In addition, to achieve the above-mentioned purpose, the present invention further provides a readable storage medium, wherein the readable storage medium stores a cooling system control program, and when the cooling system control program is executed by a processor, the steps of the cooling system control method as described above are implemented.

[0034] The present invention adopts the above technical solution to achieve the following effects:

[0035] The present invention uses the dual-drive mode of data + mechanism to allow the control strategy to follow thermal principles, break away from pure data dependence, and avoid anti-logic. It has higher reliability and better energy-saving effects. By taking advantage of the strengths of the two prediction models and complementing each other, the prediction accuracy of the dual-drive model is greatly improved, and the calculation complexity and cost are significantly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of the steps of the cooling system control method in a preferred embodiment of the present invention;

[0037] Figure 2 is a schematic diagram of a thermodynamic mathematical power model in a preferred embodiment of the present invention;

[0038] Figure 3 is a search schematic diagram of an evolutionary algorithm in a preferred embodiment of the present invention;

[0039] Figure 4 It is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention. All other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0041] Embodiment 1

[0042] Embodiment 1 of the present application is a cooling system control method, which comprises the following steps:

[0043] S1. Acquire operating data of a cooling system, and establish a thermodynamic power model of the cooling system according to the operating data and the mechanism of the cooling system.

[0044] Specifically, in this embodiment, the cooling system includes key equipment of the HVAC system, including a refrigeration host, a chilled water pump, a cooling water pump, a cooling tower, a plate heat exchanger, and pipelines.

[0045] After that, firstly, a clear white-box model of each thermodynamic part is established according to the cooling system, and then mathematical abstraction is performed based on the established white-box model to establish a gray-box model.

[0046] Specifically, firstly, a white box model is constructed for each thermodynamic part of the cooling system. Taking the cooling water pump power model as an example, by analyzing the physical characteristics of the cooling water pump, the power of the cooling water pump is in a cubic relationship with the cooling water flow rate. With the cooling water flow rate as flow and the cooling water pump power as Power1, the relationship between the cooling water pump power and the cooling water flow rate is as follows:

[0047] Power1=a[3]*flow 3 +a[4]*flow 2 +a[5]*flow+a[6];

[0048] Among them, a[3], a[4], a[5] and a[6] are the coefficients of the cooling water pump and the project air-conditioning system, which are related to the actual pipeline construction of the project and the factory model of the cooling water pump and are set according to specific circumstances.

[0049] It can be seen that to predict the power, we must first determine the cooling water flow rate, which is related to the equipment heat generation, building heat gain, chiller power and chilled water pump power. Specifically, it is:

[0050]

[0051] Among them, P IT Indicates the heat generated by the device, a[0]P IT represents the heat gain of the building, a[0] is the conversion factor between the heat gain of the building and the heat gain of the equipment, Power chiller Indicates the power value of the chiller, a[1]Power chiller represents the amount of heat that the chiller needs to remove with cooling water, a[1] is the chiller power conversion factor, Power chwp Indicates the power value of the chilled water pump, a[2]Power chwp represents the amount of heat that the chilled water pump needs to remove with cooling water, a[2] represents the chilled water pump power conversion factor, and Δt represents the supply and return water temperature difference of the cooling water system, which is the control variable of the cooling water pump.

[0052] Among them, Power chiller 、Power chwp , P IT and Δt are both acquired by sensors.

[0053] After completing the modeling of the white box model, mathematical abstraction is performed on each white box model to clarify the equipment objectives, input features, selected models and loss functions, and obtain the gray box model corresponding to the equipment. In this embodiment, the cooling water pump power model is still taken as an example for explanation. In this embodiment, the cooling water pump power is taken as the target and the cooling water pump frequency is taken as the input. It can be seen from the previous white box model that the cooling water pump power is a cubic function. Therefore, in this embodiment, the gray box model of the cooling water pump is also a cubic function, and the loss function is defined as the square difference between the true value and the predicted value.

[0054] At this point, the gray box model of the cooling water pump power is finally simplified to:

[0055] Power1=a1x 1 +a2x 2 +a3x 3 +ε;

[0056] Among them, a1, a2 and a3 are coefficients to be determined, x is the cooling water pump frequency, ε is a random number, and ε conforms to the normal distribution N(0,1).

[0057] Finally, based on the operating data, the gradient descent algorithm is used to solve the gray box model of the cooling water pump. Specifically, the loss function is defined as follows:

[0058] cost = (Preal - Ppred) 2 ;

[0059] Among them, cost represents the loss value, Preal represents the predicted value of the cooling water pump power, and Ppred represents the actual value of the cooling water pump power, which is obtained through collection.

[0060] For example, in the gray box model of the cooling water pump, the predicted value of the cooling water pump power is expanded as follows:

[0061] Ppred=a1x 1 +a2x 2 +a3x 3 +ε;

[0062] Then, the loss function can be written as:

[0063] cost=(Preal-(a1x 1 +a2x 2 +a3x 3 +ε)) 2 ;

[0064] Afterwards, the gradient descent algorithm is used to find a1, a2, and a3 when the loss value cost is the smallest, thereby determining the gray box model of the cooling water pump.

[0065] By repeating the above steps, all devices are abstracted into corresponding gray box models in turn. In this embodiment, it specifically includes a chiller power model, a chiller load rate model, a cooling water flow model, a cooling tower outlet water temperature, a cooling tower power model, a cooling return water temperature model, a cooling water flow model, a chilled return water temperature model and a cooling water pump power model.

[0066] Finally, if Figure 2 As shown, the various thermodynamic models are integrated to establish a thermodynamic mathematical power model of the cooling system.

[0067] Specifically, in each thermodynamic model, the power model serves the calculation of total energy consumption, the flow model serves the calculation of intermediate variables, the temperature difference model serves the calculation of the refrigeration system control value, and the return water temperature model and load rate model serve the calculation of the safety margin.

[0068] Through the above thermodynamic mathematical power model, the model is built and trained by the neural network algorithm. Finally, a system model is obtained as the thermodynamic power model, and the mapping f from (environmental variables, IT (computing unit) load, control combination) to (total power, safety boundary) is established:

[0069] Power,Boundary=f(x),x∈(environment,IT,controls);

[0070] Among them, Power represents the total system power, Boundary represents the constraints of the safety boundary, including the chilled water return temperature constraint, the chiller load rate constraint, and the cooling tower load rate constraint, environment represents environmental variables, including the current temperature, IT represents the IT load, and controls represents the control variables.

[0071] S2. Optimizing control parameters of the cooling system according to the thermodynamic power model to obtain optimized control parameters.

[0072] In this embodiment, the control parameters of the cooling system are optimized by a search algorithm. Based on the system model constructed above, all possible combinations of controllable parameters are calculated by an optimization algorithm at a certain operating point to find the optimal solution that meets the constraints. The controllable parameter value corresponding to the optimal solution is the optimization strategy at this operating point.

[0073] In this embodiment, in order to simplify the search process, an evolutionary algorithm is used to search and optimize the global control parameters. The evolutionary algorithm has the characteristics of better effect on global optimization problems, faster convergence speed, and not easy to fall into local minima. It can quickly search for the parameter values ​​corresponding to the optimal target value based on the existing data fitting relationship between multiple parameters, and is more suitable for the application scenario of this embodiment.

[0074] That is, an evolutionary algorithm is used. Based on the system model constructed above, at a certain operating point, an optimization algorithm is calculated for all possible combinations of controllable parameters to find the optimal solution that meets the constraints. The controllable parameter value corresponding to the optimal solution is the tuning strategy under this operating point.

[0075] There are two types of entities in the evolutionary algorithm, population and optimized individuals. The population contains n optimized individuals and is the main body of an evolution. Each optimized individual contains 8 control variables of the cooling system, namely the number of chillers, chiller outlet water temperature, number of chilled water pumps, chilled water pump frequency, number of cooling water pumps, cooling water pump frequency, number of cooling towers and cooling tower outlet water temperature.

[0076] In this embodiment, the optimization goal is to reduce power consumption as much as possible, so the task of the evolutionary algorithm can be expressed as finding the individual with the lowest global power.

[0077] The optimization steps of the evolutionary algorithm include:

[0078] S21. Encode multiple optimized individuals to form a population.

[0079] In this embodiment, the evolutionary algorithm uses foat32 encoding.

[0080] S22. Set the adoption points for population changes.

[0081] The purpose of this step is to initialize the population. In this step, the upper and lower limits of the control variables are set, and sampling is performed using a normal distribution based on the upper and lower limits of the control variables.

[0082] S23. An evolutionary algorithm is used to iteratively obtain the optimal solution of the thermodynamic power model to obtain the optimized control parameters.

[0083] Specifically, each iteration includes the following steps:

[0084] S231. Bring each optimized individual into the thermodynamic power model to obtain the fitness corresponding to each optimized individual.

[0085] S232. Screening is performed according to the fitness corresponding to each optimized individual to obtain parent individuals that pass the screening to form a parent population.

[0086] Specifically, in this embodiment, according to the fitness of the optimized individuals, the optimized individuals with the top 20% fitness are selected to enter the mating pool as parent individuals to form the parent population.

[0087] S233. Generate new optimized individuals based on the parent individuals and form a population.

[0088] Specifically, in this embodiment, firstly, parent pairs are allocated and selected from the parent population, each parent pair includes two parent individuals, and the two parent individuals of the parent pair generate two offspring individuals.

[0089] The specific method of generating two offspring individuals is related to the encoding method. In this embodiment, an arithmetic crossover method is used to generate two offspring individuals.

[0090] After the offspring individuals are generated, in this embodiment, the offspring individuals are randomly mutated to obtain new optimized individuals to form a population. The role of random mutation is to enhance the randomness of the offspring sample space and avoid falling into a local optimal solution.

[0091] Please refer to Figure 3 , Figure 3 Demonstrates the iterative process of controlling parameters, which evolve to the optimal value through multiple iterations. Figure 3 1-6 in the figure represent the six stages of evolution from early to late.

[0092] S3. Controlling the operation of the cooling system according to the optimized control parameters.

[0093] The cooling system control method of the present invention realizes equipment modeling and system modeling by modeling the cooling system through a combination of big data machine learning and equipment mechanism, which has wider applicability and better energy-saving effect. Through the dual-drive mode of data + mechanism, the control strategy follows the thermal principle, breaks away from pure data dependence, avoids anti-logic, has higher reliability and better energy-saving effect, and by taking advantage of the two prediction models, the prediction accuracy of the dual-drive model is greatly improved, and the computational complexity and cost are significantly reduced.

[0094] Embodiment 2

[0095] See also Figure 4 Based on the above method, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 4 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0096] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal, etc. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a cooling system control program 40 is stored on the memory 20, and the cooling system control program 40 can be executed by the processor 10.

[0097] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing relevant programs of the cooling system control method.

[0098] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0099] In one embodiment, when the processor 10 executes the cooling system control program 40 in the memory 20 , the steps of the cooling system control method described above are implemented.

[0100] The memory 20 may be an internal storage unit of the terminal in some embodiments, such as a hard disk or memory of the terminal. The memory 20 may also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal, etc. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a cooling system control program is stored on the memory 20, and the cooling system control program can be executed by the processor 10, thereby realizing the cooling system control method in the present application.

[0101] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the cooling system control method.

[0102] Embodiment 3

[0103] This embodiment provides a storage medium, wherein the readable storage medium stores a cooling system control program, and when the cooling system control program is executed by a processor, the steps of the cooling system control method described above are implemented.

[0104] In summary, the present invention uses the dual-drive mode of data + mechanism to allow the control strategy to follow thermal principles, break away from pure data dependence, avoid anti-logic, and have higher reliability and better energy-saving effects. By taking advantage of the strengths of the two prediction models and complementing each other, the prediction accuracy of the dual-drive model is greatly improved, and the computational complexity and cost are significantly reduced.

[0105] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0106] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, an optical disk, etc.

[0107] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A cooling system control method, characterized in that: The cooling system control method comprises: Acquiring operating data of the cooling system, and establishing a thermodynamic power model of the cooling system according to the operating data and the mechanism of the cooling system; Optimizing the control parameters of the cooling system according to the thermodynamic power model to obtain optimized control parameters; The cooling system is controlled to operate according to the optimized control parameters.

2. A cooling system control method according to claim 1, characterized in that: The step of establishing a thermodynamic power model of the cooling system according to the operating data and the mechanism of the cooling system specifically includes: Establishing a thermodynamic partial model of the cooling system according to the operating data and the mechanism of the cooling system; Connecting the thermodynamic partial models to obtain a thermodynamic mathematical power model; A neural network is trained according to the thermodynamic mathematical power model to obtain a neural network with a control parameter as input and a total power of the cooling system as output as the thermodynamic power model.

3. A cooling system control method according to claim 2, characterized in that: The step of establishing a thermodynamic partial model of the cooling system according to the operating data and the mechanism of the cooling system specifically includes: According to the mechanism of the cooling system, a white box model of each part of the cooling system is established; Mathematically abstract each white box model to obtain a gray box model of each part of the cooling system as the thermodynamic partial model.

4. A cooling system control method according to claim 2, characterized in that: The thermodynamic partial model includes a chiller power model, a chiller load rate model, a cooling water flow model, a cooling tower outlet water temperature, a cooling tower power model, a cooling return water temperature model, a cooling water flow model, a refrigeration return water temperature model and a cooling water pump power model.

5. A cooling system control method according to claim 1, characterized in that: The optimizing the control parameters of the cooling system according to the thermodynamic power model to obtain the optimized control parameters specifically includes: Generate a plurality of optimized individuals according to the control parameters, and form a population from the plurality of optimized individuals; According to the upper and lower limits of the population, sampling and generating search points for optimized individuals; According to the optimized individuals and populations, an evolutionary algorithm is used to iteratively obtain the optimal solution of the thermodynamic power model to obtain the optimized control parameters.

6. A cooling system control method according to claim 5, characterized in that: The evolutionary algorithm is used to iteratively obtain the optimal solution of the thermodynamic power model, and each iteration includes: Substitute the control parameters corresponding to each optimized individual into the thermodynamic power model to obtain the fitness corresponding to each optimized individual; Screening is performed according to the fitness corresponding to each optimized individual to obtain the parent individuals that pass the screening to form the parent population; Generate new optimized individuals based on the parent individuals and form a population.

7. A cooling system control method according to claim 6, characterized in that: The generating of new optimized individuals according to the parent individuals and forming a population specifically includes: A plurality of parent pairs are selected from the parent population, each parent pair including two parent individuals; Each parent pair generates two offspring individuals based on the two parent individuals; The generated offspring individuals are subjected to random mutation to obtain a plurality of the optimized individuals.

8. A cooling system control method according to claim 1, characterized in that: The control parameters include the number of chillers, chiller outlet water temperature, the number of refrigeration water pumps, the refrigeration water pump frequency, the number of cooling water pumps, the cooling water pump frequency, the number of cooling towers and the cooling tower outlet water temperature.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a cooling system control program stored in the memory and executable on the processor. When the cooling system control program is executed by the processor, the terminal is controlled to implement the steps of the cooling system control method according to any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium stores a cooling system control program, and when the cooling system control program is executed by a processor, the steps of the cooling system control method according to any one of claims 1 to 8 are implemented.

Images