Predictive control method and system for variable setting parameters of natural cooling system of data center

Abstract

The invention discloses a predictive control method and system for variable setting parameters of a natural cooling system of a data center, and the method comprises the steps: optimizing an air supply temperature set value Ts, a cold water supply temperature set value Tchw, s, and a cooling water temperature difference set value Tcw, s; predicting the operation mode of the cooling system by predicting the water temperature of a hot end outlet of the plate heat exchanger and a cold water supply temperature set value; according to the control method, the control precision of the system operation mode is improved, the time for utilizing the natural cold source is prolonged to the maximum extent on the basis of meeting the cold load of the data center, the requirement for on-demand cold supply of the data center is met, and the energy-saving rate can be improved compared with a traditional control mode.

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning engineering control, and particularly to a predictive control method for variable set parameters of a natural cooling system in a data center. Background Art

[0002] With the promotion of "new infrastructure", "big data", "artificial intelligence", etc., the data center industry has expanded rapidly; however, according to research reports, in 2021, the power consumption of data centers was 216.6 billion kWh, accounting for 2.6% of the total electricity consumption of the whole society. It is expected that the power consumption will reach 380 billion kWh in 2030, accounting for 4.1% of the total electricity consumption of the whole society. Among them, the natural cooling system accounts for up to 30% to 50% of the total energy consumption of the data center. Therefore, reducing the energy consumption of the natural cooling system in the data center has become the focus of attention in the entire field of data centers.

[0003] Compared with the traditional natural cooling system of data centers, the natural cooling system can reduce the running time of mechanical refrigeration or the refrigeration load of the chiller by using the free natural cold source outdoors, thereby reducing the energy consumption of the natural cooling system in the data center and achieving the goal of improving energy utilization efficiency.

[0004] The natural cooling system includes devices such as chillers, cooling water pumps, cooling towers, heat exchangers, chilled water pumps, natural water source side pumps (used when the natural cold source is lake water, river water, etc.), valves, controllers, etc. The system usually has three operating modes: mechanical refrigeration operating mode, partial natural cooling operating mode, and free natural cooling mode.

[0005] The operation mode control of the natural cooling system usually uses the measured value of the outdoor air temperature and a fixed temperature for discrimination to switch the operation mode, resulting in a reduction in the control accuracy of the operation mode and possibly an increase in the operation energy consumption of the natural cooling system. In order to achieve on-demand supply of cooling capacity, the predictive control method based on variable set parameters can maximize the utilization time of the natural cold source, thereby solving the overcooling problem of the data center and improving the energy efficiency of the cooling system.

[0006] At present, "emphasizing construction over operation and maintenance" is a common problem in data centers. The lack of effective control technology for the natural cooling system in data centers has led to the widespread phenomenon of overcooling and waste of cold sources in data centers. Therefore, in addition to measures such as optimizing the design of the natural cooling system and improving the energy efficiency of equipment, it is a feasible way to use the natural cold source and optimize the control strategy to reduce the energy consumption of the natural cooling system. Summary of the Invention

[0007] Objective of the Invention: To overcome the above deficiencies, the objective of the present invention is to provide a predictive control method for variable set parameters of a natural cooling system in a data center, so as to solve the problems in the prior art that due to using the measured value of the outdoor air temperature to discriminate with a fixed temperature to switch the operation mode, the control accuracy is relatively low, the natural cold source cannot be utilized to the maximum extent, and the data center is overcooled.

[0008] To solve the above technical problems, the present invention provides a predictive control method for variable set parameters of a natural cooling system in a data center, including:

[0009] S1: Set the constraint conditions for the boundary values of the supply air temperature set value, the chilled water supply temperature set value, and the cooling water temperature difference set value, and set the energy consumption objective function of the natural cooling system, and then optimize using a preset algorithm and output the optimization result;

[0010] S2: Predict the outlet temperature at the end of the plate heat exchanger according to the optimization result;

[0011] S3: When it is predicted that the outlet temperature at the hot end of the plate heat exchanger is less than the chilled water supply temperature set value, set the natural cooling system to the free natural cooling mode, and then judge whether the measured value of the chilled water supply temperature is greater than the chilled water supply temperature set value and the duration exceeds the preset time. If so, switch the natural cooling system to the partial natural cooling operation mode. If not, set the natural cooling system to the free natural cooling operation mode;

[0012] S4: When it is predicted that the outlet temperature at the hot end of the plate heat exchanger is less than the measured value of the chilled water return temperature, set the natural cooling system to the partial natural cooling mode, and then judge whether the measured value of the outlet temperature at the hot end of the plate heat exchanger is greater than the measured value of the chilled water return temperature and the duration exceeds the preset time. If so, switch the natural cooling system to the mechanical refrigeration operation mode. If not, set the natural cooling system to the partial natural cooling operation mode;

[0013] S5: When it is predicted that the outlet temperature at the hot end of the plate heat exchanger exceeds the measured value of the chilled water return temperature, set the natural cooling system to the mechanical refrigeration cooling mode, and then judge whether the measured value of the chilled water supply temperature is less than the chilled water supply temperature set value and the duration exceeds the preset time. If so, switch the natural cooling system to the partial natural cooling operation mode. If not, set the natural cooling system to the mechanical refrigeration operation mode.

[0014] As a preferred mode of the present application, in S1, the method includes:

[0015] S11: Set the supply air temperature set value T s , the chilled water supply temperature set value T chw,s , and the constraint conditions for the boundary values of the cooling water temperature difference set value △T cw ;

[0016] S12: Set the energy consumption objective function of the natural cooling system:

[0017]

[0018] Where M is the free natural cooling mode, B is the partial natural cooling mode, and J is the mechanical refrigeration operation mode;

[0019] S13: Use the genetic algorithm for optimization and output the optimization result.

[0020] As a preferred embodiment of the present application, in S13, the calculation formula of the genetic algorithm is:

[0021] SGA = (C, E, P0, M, Φ, Γ, ψ, T)

[0022] Where C is the encoding method of individuals, E is the individual fitness evaluation function, P0 is the initial population, M is the population size, Φ is the selection operator, Γ is the crossover operator, Ψ is the mutation operator, and T is the termination condition of the genetic algorithm.

[0023] As a preferred embodiment of the present application, in S2, the hot end outlet temperature T of the plate heat exchanger hx,h,o is obtained by adding the outdoor wet bulb temperature T wb plus the cooling tower approach temperature T ct,app and the plate heat exchanger approach temperature T hx,app The calculation formula is: T hx,h,o = T wb + T ct,app + T hx,app .

[0024] As a preferred embodiment of the present application, in S4, the method includes:

[0025] S41: Judge whether the measured value of the hot end outlet temperature of the plate heat exchanger is less than the measured value of the cold water return temperature and lasts for more than the preset time;

[0026] S42: If so, switch the natural cooling system to the free natural cooling operation mode; if not, set the natural cooling system to the partial natural cooling operation mode.

[0027] As a preferred embodiment of the present application, the calculation method of the predicted value T of the hot end outlet temperature of the plate heat exchanger hx,h,o includes:

[0028] When the cooling tower is used as the natural cold source, the predicted value T of the hot end outlet temperature of the plate heat exchanger hx,h,o is the wet bulb temperature T of the environment wb plus the cooling tower approach temperature T ct plus the heat exchanger approach temperature Thx ;

[0029] When other natural water sources such as lake water and river water are used as natural cold sources, the predicted value T of the hot end outlet temperature of the plate heat exchanger hx,h,o is the natural water source temperature T w plus the approach temperature T of the heat exchanger hx .

[0030] As a preferred embodiment of the present application, the natural cooling system includes a cooling tower, a cooling water pump, a chiller, a plate heat exchanger, a chilled water pump, an electric control valve, a terminal device, a natural water source side pump, and a controller.

[0031] As a preferred embodiment of the present application, when the natural cooling system is in the free natural cooling operation mode, the cooling tower fan compares the measured value of the chilled water supply temperature with the set value of the chilled water supply temperature. If the measured value of the chilled water supply temperature is less than the set value of the chilled water supply temperature, the frequency of the cooling tower fan is reduced; otherwise, the frequency of the cooling tower fan is increased.

[0032] As a preferred embodiment of the present application, when the natural cooling system is in the partial natural cooling operation mode, the compressor frequency of the chiller compares the measured value of the chilled water supply temperature with the set value of the chilled water supply temperature. If the measured value of the chilled water supply temperature is less than the set value of the chilled water supply temperature, the compressor frequency of the chiller is reduced; otherwise, the compressor frequency of the chiller is increased.

[0033] As a preferred embodiment of the present application, when the natural cooling system is in the mechanical refrigeration operation mode, the cooling tower fan compares the measured value of the cooling water supply temperature with the set value of the cooling water supply temperature. If the measured value of the cooling water supply temperature is less than the set value of the cooling water supply temperature, the frequency of the cooling tower fan is reduced; otherwise, the frequency of the cooling tower fan is increased;

[0034] The compressor frequency of the chiller compares the measured value of the chilled water supply temperature with the set value of the chilled water supply temperature. If the measured value of the chilled water supply temperature is less than the set value of the chilled water supply temperature, the compressor frequency of the chiller is reduced; otherwise, the compressor frequency of the chiller is increased.

[0035] The present application also provides a predictive control system for variable set parameters of a data center natural cooling system using the above predictive control method, including:

[0036] An optimization module for setting the constraint conditions of the boundary values of the supply air temperature set value, the chilled water supply temperature set value, and the cooling water temperature difference set value and setting the natural cooling system energy consumption objective function, and then optimizing using a preset algorithm and outputting an optimization result;

[0037] A temperature prediction module for predicting the outlet temperature of the plate heat exchanger end according to the optimization result;

[0038] The first control module is used to set the natural cooling system to the free natural cooling mode when it is predicted that the temperature at the hot end outlet of the plate heat exchanger is less than the set value of the cold water supply temperature, and then determine whether the measured value of the cold water supply temperature is greater than the set value of the cold water supply temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the partial natural cooling operation mode. If not, the natural cooling system is still set to the free natural cooling operation mode;

[0039] The second control module is used to set the natural cooling system to the partial natural cooling mode when it is predicted that the temperature at the hot end outlet of the plate heat exchanger is less than the measured value of the cold water return temperature, and then determine whether the measured value of the temperature at the hot end outlet of the plate heat exchanger is greater than the measured value of the cold water return temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the mechanical refrigeration operation mode. If not, the natural cooling system is still set to the partial natural cooling operation mode;

[0040] The third control module is used to set the natural cooling system to the mechanical refrigeration cooling mode when it is predicted that the temperature at the hot end outlet of the plate heat exchanger exceeds the measured value of the cold water return temperature, and then determine whether the measured value of the cold water supply temperature is less than the set value of the cold water supply temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the partial natural cooling operation mode. If not, the natural cooling system is still set to the mechanical refrigeration operation mode.

[0041] As a preferred embodiment of the present application, the present application further provides a computer medium, on which a computer program is stored, and the computer program is executed by a processor to implement the predictive control method according to the variable setting parameters of the natural cooling system of the data center.

[0042] As a preferred embodiment of the present application, the present application further provides a computer, including the above-mentioned computer medium.

[0043] The above technical solution of the present application has the following advantages compared with the prior art:

[0044] 1. The operation mode control method for the variable setting parameters of the natural cooling system of the present application predicts the operation mode of the cooling system by optimizing the set value T of the supply air temperature s , the set value T of the cold water supply temperature chw,s , and the set value △T of the cooling water temperature difference cw , and determining the water temperature at the hot end outlet of the plate heat exchanger and the set value of the cold water supply temperature;

[0045] 2. Through the control method of the present application, the control accuracy of the system operation mode can be improved, and on the basis of meeting the cooling load of the data center, the time of using the natural cold source can be maximally extended and the demand for on-demand cooling of the data center can be met. Brief Description of the Drawings

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0047] Figure 1 It is a schematic diagram of the structure composition and principle of the natural cooling system provided by the embodiment of the present application.

[0048] Figure 2 It is a schematic diagram of the prediction process of the operation mode with variable set parameters of the natural cooling system provided by the embodiment of the present application.

[0049] Figure 3 It is a schematic diagram of the process of the genetic algorithm calculation adopted by the embodiment of the present application.

[0050] Figure 4 It is a schematic diagram of the process of the control method for the operation mode with variable set parameters of the natural cooling system provided by the embodiment of the present application.

[0051] Figure 5 It is a schematic diagram of the module connection of the prediction control system provided by the embodiment of the present application.

[0052] Description of the reference numerals in the drawings of the specification:

[0053] 1, cooling tower; 2, cooling water pump; 3, chiller; 4, plate heat exchanger; 5, chilled water pump; 6, electric control valve; 7, terminal equipment; 8, natural water source side pump; 100, optimization module; 101, temperature prediction module; 102, first control module; 103, second control module; 104, third control module. Detailed Embodiments

[0054] The following will describe in detail the embodiments of the present invention. The examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention, and should not be construed as a limitation to the present invention.

[0055] Referring to the figure, the natural cooling system in the present application includes a cooling tower, a cooling water pump, a chiller, a plate heat exchanger, a chilled water pump, an electric control valve, terminal equipment, a natural water source side pump, and a controller; among them, the quantity of the above-mentioned each device is set by the operator according to actual needs.

[0056] Exemplarily, for example, the electric control valves described in the present application may include valve V1, valve V2, valve V3, valve V4, valve V5, valve V6, valve V7, valve V8, and valve V9.

[0057] In some embodiments of the present application, the operating modes of the natural cooling system are at least divided into a mechanical refrigeration operating mode, a partial natural cooling operating mode, and a free natural cooling mode; wherein, in the mechanical refrigeration operating mode, valves V1, V8, V2, and V6 are in the open state, and other valves are in the closed state; the cooling tower, chiller, cooling water pump, and chilled water pump are turned on, and the plate heat exchanger and the natural water source side pump are turned off. In the partial natural cooling operating mode, valves V1, V8, V4, V5, V9, V2, and V7 are in the open state, and other valves are in the closed state; the cooling tower, chiller, cooling water pump, chilled water pump, natural water source side pump, and plate heat exchanger are turned on. In the free natural cooling operating mode, valves V4, V5, V9, V7, and V3 are in the open state, and other valves are in the closed state; the cooling tower, chiller, cooling water pump, chilled water pump, natural water source side pump, and plate heat exchanger are turned on.

[0058] Thus, referring to Figure 1 shown, Figure 1 shows a schematic structural diagram of a natural cooling system of the present invention, Figure 1 (a) is a schematic structural diagram when the cooling tower is used as a natural cold source; Figure 1 (b) is a schematic structural diagram when other natural water sources such as lake water and river water are used as natural cold sources.

[0059] In some embodiments, a predictive control method for variable set parameters of a natural cooling system in a data center is provided, and the method includes an operating mode prediction method and an operating mode control method.

[0060] Among them, referring to Figure 2 shown, the process of the operating mode prediction method for variable set parameters of the natural cooling system includes:

[0061] (1) Optimize the supply air temperature set value T s , the chilled water supply temperature set value T chw,s , and the cooling water temperature difference set value ΔT cw .

[0062] (2) Set the boundary value constraint conditions of the supply air temperature set value T s , the chilled water supply temperature set value T chw,s , and the cooling water temperature difference set value ΔT cw ; wherein, the constraint conditions are set by the operator according to actual needs. In the embodiments of the present application, it is preferably set as:

[0063] 18°C ≤ T s ≤ 27°C;

[0064] 11°C ≤ T chw,s ≤ 22°C;

[0065] T s ≥ T chw,s + 4;

[0066] 4°C ≤ ΔT cw ≤ 5°C.

[0067] Furthermore, set the energy consumption objective function of the natural cooling system, and its objective function is as follows:

[0068]

[0069] Wherein, M is the free natural cooling mode, B is the partial natural cooling mode, and J is the mechanical refrigeration operation mode.

[0070] Furthermore, use a preset algorithm for optimization and output the optimization result; wherein, the preset algorithm includes but is not limited to optimization algorithms such as genetic algorithm, ant colony algorithm, particle swarm algorithm, bee colony algorithm, differential evolution algorithm, etc., and is specifically set by the operator according to actual needs.

[0071] Exemplarily, this application takes the genetic algorithm as an example: The basic idea of the basic genetic algorithm is to simulate the phenomena of reproduction, crossover, and gene mutation that occur in the process of natural selection and natural inheritance, and leave a group of candidate solutions in each iteration. Then, select the relatively excellent individuals in the solution group according to a certain index, and then use genetic operators such as selection, crossover, and mutation to combine these relatively excellent individuals to generate a new generation of candidate solution groups. By repeating the above process until the stopping criterion is met, an optimal solution is obtained. Its basic genetic algorithm can be expressed as:

[0072] SGA = (C, E, P0, M, Φ, Γ, ψ, T)

[0073] Wherein, C is the encoding method of individuals, E is the individual fitness evaluation function, P0 is the initial population, M is the population size, Φ is the selection operator, Γ is the crossover operator, Ψ is the mutation operator, and T is the termination condition of the genetic algorithm.

[0074] The basic calculation process of its genetic algorithm refers to Figure 3 as shown, and mainly includes the following processes:

[0075] 1) Determine the parameter set of the actual problem, and thus encode it;

[0076] 2) Generate a population composed of several individuals to initialize the population;

[0077] 3) Establish a fitness function associated with the objective function and calculate the individual fitness values;

[0078] 4) Select individuals with high fitness from the population for inheritance;

[0079] 5) Recombine between individuals to generate new individuals;

[0080] 6) Mutate the genes of the individuals to generate new individuals;

[0081] 7) Judge the termination condition.

[0082] Among them, the population size, constraint precision, precision of the objective function, and crossover probability are set, and their values are 400, 10 -4 , 10 -10 and 0.8.

[0083] (3) Output the optimized supply air temperature setting value T s , chilled water supply temperature setting value T chw,s , cooling water temperature difference setting value △T cw .

[0084] (4) Predict the hot end outlet temperature T of the plate heat exchanger hx,h,o .

[0085] Among them, the hot end outlet temperature T of the plate heat exchanger hx,h,o is obtained by adding the outdoor wet bulb temperature T wb plus the cooling tower approach temperature T ct,app and the plate heat exchanger approach temperature T hx,app , so it is T hx,h,o = T wb + T ct,app + T hx,app .

[0086] (5) When the predicted hot end outlet temperature T of the plate heat exchanger hx,h,o < chilled water supply temperature setting value T chw,s , then the predicted operating mode of the cooling system is the free natural cooling mode; when the predicted hot end outlet temperature T of the plate heat exchanger hx,h,o ≥ chilled water supply temperature setting value T chw,s , enter the next step.

[0087] (6) When the predicted hot end outlet temperature T of the plate heat exchanger hx,h,o < chilled water return temperature measurement value T chw,r , then the predicted operating mode of the cooling system is the partial natural cooling mode; when the predicted hot end outlet temperature T of the plate heat exchanger hx,h,o≥Measured value T of the chilled water return temperature chw,r When this is the case, it is predicted that the operating mode of the cooling system is the mechanical refrigeration cooling mode.

[0088] Among them, referring to Figure 4 As shown, the control method flow of the variable set parameter operating mode of the natural cooling system includes:

[0089] (1) When the predicted operating mode is the free natural cooling operating mode, determine whether the measured value T of the chilled water supply temperature chw,s,m > Set value T of the chilled water supply temperature chw,s , and the duration > t. If the determination condition is met, it is determined that the cooling system switches to the partial natural cooling operating mode. If the determination condition is not met, it is determined that the cooling system remains in the free natural cooling operating mode.

[0090] (2) When the predicted operating mode is the partial natural cooling operating mode, determine whether the measured value T of the hot end outlet temperature of the plate heat exchanger hx,h,o,m > Measured value T of the chilled water return temperature chw,r,m , and the duration > t. If the determination condition is met, it is determined that the cooling system switches to the mechanical refrigeration operating mode. If the determination condition is not met, it is determined that the cooling system remains in the partial natural cooling operating mode; or determine whether the measured value T of the hot end outlet temperature of the plate heat exchanger hx,h,o,m < Set value T of the chilled water supply temperature chw,s , and the duration > t. If the determination condition is met, it is determined that the cooling system switches to the free natural cooling operating mode. If the determination condition is not met, it is determined that the cooling system remains in the partial natural cooling operating mode.

[0091] (3) When the predicted operating mode is the mechanical refrigeration operating mode, the measured value T of the chilled water supply temperature chw,s,m < Set value T of the chilled water supply temperature chw,s , and the duration > t. If the determination condition is met, it is determined that the cooling system switches to the partial natural cooling operating mode. If the determination condition is not met, it is determined that the cooling system remains in the mechanical refrigeration operating mode.

[0092] The calculation method of the predicted value T of the hot end outlet temperature of the plate heat exchanger in this example hx,h,o is as follows: When the cooling tower is used as the natural cold source, the predicted value T of the hot end outlet temperature of the plate heat exchanger hx,h,o = Wet bulb temperature T of the environment wb + Cooling tower approach temperature T ct + Heat exchanger approach temperature T hx ; When other natural water sources such as lake water and river water are used as the natural cold source, the predicted value T of the hot end outlet temperature of the plate heat exchanger hx,h,o = Temperature T of the natural water source w + Heat exchanger approach temperature T hx .

[0093] In some embodiments of the present application, when the operating mode is the free natural cooling operating mode, the cooling tower fan compares the measured value of the chilled water supply temperature with the set value of the chilled water supply temperature. If the measured value of the chilled water supply temperature < the set value of the chilled water supply temperature, the frequency of the cooling tower fan is reduced; otherwise, the frequency of the cooling tower fan is increased.

[0094] In some embodiments of the present application, when the operating mode is the partial natural cooling operating mode, the compressor frequency of the chiller compares the measured value of the chilled water supply temperature with the set value of the chilled water supply temperature. If the measured value of the chilled water supply temperature < the set value of the chilled water supply temperature, the compressor frequency of the chiller is reduced; otherwise, the compressor frequency of the chiller is increased.

[0095] In some embodiments of the present application, when the operating mode is the mechanical refrigeration operating mode, the cooling tower fan compares the measured value of the cooling water supply temperature with the set value of the cooling water supply temperature. If the measured value of the cooling water supply temperature < the set value of the cooling water supply temperature, the frequency of the cooling tower fan is reduced; otherwise, the frequency of the cooling tower fan is increased. The compressor frequency of the chiller compares the measured value of the chilled water supply temperature with the set value of the chilled water supply temperature. If the measured value of the chilled water supply temperature < the set value of the chilled water supply temperature, the compressor frequency of the chiller is reduced; otherwise, the compressor frequency of the chiller is increased.

[0096] Therefore, the above embodiments are only a part of the present application. As long as the described natural cooling system includes two of the above three operating modes, it is applicable to the predictive control method for variable set parameters of the natural cooling system provided by the present invention.

[0097] In some embodiments of the present application, referring to Figure 5 as shown, the present application also relates to a predictive control system for variable set parameters of a data center natural cooling system, including:

[0098] An optimization setting module for setting the constraint conditions of the boundary values of the supply air temperature set value, the chilled water supply temperature set value, and the cooling water temperature difference set value and setting the energy consumption objective function of the natural cooling system, and then optimizing and outputting the optimization result by using a preset algorithm;

[0099] A temperature prediction module for predicting the temperature at the outlet of the plate heat exchanger according to the optimization result;

[0100] The first control module is used to set the natural cooling system to the free natural cooling mode when it is predicted that the hot-end outlet temperature of the plate heat exchanger is lower than the set value of the cold water supply temperature, and then determine whether the measured value of the cold water supply temperature is greater than the set value of the cold water supply temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the partial natural cooling operation mode. If not, the natural cooling system is still set to the free natural cooling operation mode;

[0101] The second control module is used to set the natural cooling system to the partial natural cooling mode when it is predicted that the hot-end outlet temperature of the plate heat exchanger is lower than the measured value of the cold water return temperature, and then determine whether the measured value of the hot-end outlet temperature of the plate heat exchanger is greater than the measured value of the cold water return temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the mechanical refrigeration operation mode. If not, the natural cooling system is still set to the partial natural cooling operation mode;

[0102] The third control module is used to set the natural cooling system to the mechanical refrigeration cooling mode when it is predicted that the hot-end outlet temperature of the plate heat exchanger exceeds the measured value of the cold water return temperature, and then determine whether the measured value of the cold water supply temperature is lower than the set value of the cold water supply temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the partial natural cooling operation mode. If not, the natural cooling system is still set to the mechanical refrigeration operation mode.

[0103] In some embodiments of the present application, the present application also relates to a computer medium, on which a computer program is stored, and the computer program is executed by a processor to implement the predictive control method according to the variable set parameters of the natural cooling system of the data center.

[0104] In some embodiments of the present application, the present application also relates to a computer, including the above-mentioned computer medium.

[0105] The operation mode control method and system for the variable set parameters of the natural cooling system provided by the embodiments of the present application optimize the set value T of the supply air temperature s and the set value T of the cold water supply temperature chw,s , and the set value △T of the cooling water temperature difference cw , and predict the operation mode of the cooling system by determining the hot-end outlet water temperature of the plate heat exchanger and the set value of the cold water supply temperature; this control method improves the control accuracy of the system operation mode, maximally extends the time of using natural cold sources on the basis of meeting the cooling load of the data center, meets the demand for on-demand cooling of the data center, and the energy saving rate is as high as 4.48% - 20.51% compared with the traditional control method. The specific example parameters are shown in the following table:

[0106] Table: Energy saving rate of the present application compared with the traditional fixed parameter control method

[0107]

[0108] In the description of this specification, the descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples.

[0109] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A predictive control method for variable setting parameters of a data center natural cooling system, characterized in that: The following steps are involved: S1: Set the boundary value constraints of the air supply temperature setting value, the cold water supply temperature setting value, and the cooling water temperature difference setting value, and set the energy consumption objective function of the natural cooling system, and then use the preset algorithm to optimize and output the optimization results; S2: predicting the outlet temperature of the plate heat exchanger according to the optimization result; S3: When it is predicted that the outlet temperature of the hot end of the plate heat exchanger is lower than the set value of the cold water supply temperature, the free cooling system is set to the free free cooling mode, and then it is determined whether the measured value of the cold water supply temperature is higher than the set value of the cold water supply temperature and the duration exceeds the preset time. If so, the free cooling system is switched to the partial free cooling operation mode; if not, the free cooling system is still set to the free free cooling operation mode; S4: when it is predicted that the outlet temperature of the hot end of the plate heat exchanger is lower than the measured value of the cold water return temperature, the natural cooling system is set to the partial natural cooling mode, and then it is determined whether the measured value of the outlet temperature of the hot end of the plate heat exchanger is higher than the measured value of the cold water return temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the mechanical refrigeration operation mode; if not, the natural cooling system is still set to the partial natural cooling operation mode; S5: When it is predicted that the hot end outlet temperature of the plate heat exchanger exceeds the measured value of the cold water return temperature, the natural cooling system is set to the mechanical refrigeration cooling mode, and then it is determined whether the measured value of the cold water supply temperature is less than the set value of the cold water supply temperature and the duration exceeds the preset time. If so, the natural cooling system is switched to the partial natural cooling operation mode. If not, the natural cooling system is still set to the mechanical refrigeration operation mode.

2. A predictive control method for variable setting parameters of a data center natural cooling system according to claim 1, characterized in that: In S1, the method comprises: S11: Set the air supply temperature setting value T s , cold water supply temperature setting value T chw,s , Cooling water temperature difference setting value △T cw The boundary value constraints of ; S12: Set the energy consumption objective function of the free cooling system: Among them, M is the free natural cooling mode, B is the partial natural cooling mode, and J is the mechanical refrigeration operation mode; S13: Utilize genetic algorithm to optimize and output optimization results.

3. A predictive control method for variable setting parameters of a data center natural cooling system according to claim 2, characterized in that: In S13, the genetic algorithm calculation formula is: SGA=(C,E,P0,M,Φ,Γ,ψ,T) Among them, C is the individual encoding method, E is the individual fitness evaluation function, P0 is the initial population, M is the population size, Φ is the selection operator, Γ is the crossover operator, Ψ is the mutation operator, and T is the termination condition of the genetic algorithm.

4. The predictive control method for variable setting parameters of a data center natural cooling system according to claim 1, characterized in that: In S2, the hot end outlet temperature of the plate heat exchanger is T hx,h,o The outdoor wet bulb temperature T wb Add the cooling tower approach T ct,app And plate heat exchanger approximation T hx,app The calculation formula is: T hx,h,o =T wb +T ct,app +T hx,app .

5. The predictive control method for variable setting parameters of a data center natural cooling system according to claim 1, characterized in that: In S4, the method comprises: S41: Determine whether the measured value of the hot end outlet temperature of the plate heat exchanger is less than the measured value of the cold water return temperature and the duration exceeds a preset time; S42: If yes, the free cooling system is switched to the free free cooling operation mode; if no, the free cooling system is still set to the partial free cooling operation mode.

6. A predictive control method for variable setting parameters of a data center natural cooling system according to claim 1 or 5, characterized in that: The predicted value of the hot end outlet temperature of the plate heat exchanger T hx,h,o The calculation methods include: When the cooling tower is used as a natural cooling source, the predicted value of the hot end outlet temperature of the plate heat exchanger is T hx,h,o is the ambient wet bulb temperature T wb Add the cooling tower approach T ct Add the heat exchanger approximation T hx ; When lake water, river water or other natural water sources are used as natural cooling sources, the predicted value of the hot end outlet temperature of the plate heat exchanger is T hx,h,o is the natural water source temperature T w Add the heat exchanger approximation T hx .

7. The predictive control method for variable setting parameters of a data center natural cooling system according to claim 1, characterized in that: The natural cooling system comprises a cooling tower, a cooling water pump, a chiller, a plate heat exchanger, a chilled water pump, an electric control valve, a terminal device, a natural water source side water pump and a controller.

8. The predictive control method for variable setting parameters of a data center natural cooling system according to claim 7, characterized in that: When the natural cooling system is in free natural cooling operation mode, the cooling tower fan compares the cold water supply temperature measurement value with the cold water supply temperature setting value. If the cold water supply temperature measurement value is less than the cold water supply temperature setting value, the frequency of the cooling tower fan is reduced; otherwise, the frequency of the cooling tower fan is increased.

9. The predictive control method for variable setting parameters of a data center natural cooling system according to claim 7, characterized in that: When the natural cooling system is in partial natural cooling operation mode, the compressor frequency of the chiller is compared with the cold water supply temperature measurement value and the cold water supply temperature setting value. If the cold water supply temperature measurement value is less than the cold water supply temperature setting value, the compressor frequency of the chiller is reduced; otherwise, the compressor frequency of the chiller is increased.

10. The predictive control method for variable setting parameters of a data center natural cooling system according to claim 1, characterized in that: When the natural cooling system is in mechanical refrigeration operation mode, the cooling tower fan compares the cooling water supply temperature measurement value with the cooling water supply temperature setting value. If the cooling water supply temperature measurement value is less than the cooling water supply temperature setting value, the cooling tower fan frequency is reduced; otherwise, the cooling tower fan frequency is increased; The compressor frequency of the chiller is compared with the measured value of the cold water supply temperature and the set value of the cold water supply temperature. If the measured value of the cold water supply temperature is less than the set value of the cold water supply temperature, the compressor frequency of the chiller is reduced; otherwise, the compressor frequency of the chiller is increased.

Images