Operating parameter optimization method and device of air conditioning system

Abstract

The invention provides an air conditioning system operation parameter optimization method and device, and the method comprises the steps: obtaining the cold load historical data of a to-be-optimized air conditioning system in each unit time in a first preset time period, and inputting the cold load historical data into a cold load prediction model, outputting the predicted cold load data of each unit time in the second preset time period in the future; based on the respective rated refrigerating capacity of each host of the to-be-optimized air conditioning system, performing equal-proportion distribution on the cooling load data to predict the respective refrigerating capacity of each host in each unit time of a second preset time period in the future; and based on a preset energy-saving optimization model and the respective refrigerating capacity of each host in each unit time of a second preset time period in the future, solving the energy-saving optimization model to obtain the output of the energy-saving optimization model. Therefore, the optimal control of the heating ventilation air conditioning system can be realized through dynamic adjustment, the energy efficiency is remarkably improved, the energy consumption cost is reduced, and the economic benefit of a user is maximized.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of air conditioning systems, and in particular, to a method and device for optimizing the operating parameters of an air conditioning system. Background Art

[0002] As a key refrigeration device in modern buildings, industries, data centers and other places, the operating efficiency of a heating, ventilation and air conditioning (HVAC) system directly affects energy consumption and operating costs. The energy-saving optimization of the HVAC system aims to minimize the system power while ensuring that the refrigeration demand is met by precisely regulating four key parameters: chilled water supply temperature, chilled water supply and return temperature difference, cooling water return temperature, and cooling water supply and return temperature difference, thereby significantly reducing energy consumption and improving energy utilization efficiency.

[0003] Currently, there are mainly two technical solutions for the energy-saving optimization of HVAC systems. One is the rule-based control method based on expert experience. This method relies on the professional knowledge and long-term experience accumulation of operators, and manually or according to preset rules adjusts the temperature and temperature difference of chilled water and cooling water according to external factors such as outdoor temperature, seasonal changes, and weather conditions to achieve energy-saving purposes. Another solution is to independently optimize some parameters such as chilled water supply temperature and temperature difference, cooling water return temperature and temperature difference by establishing detailed mechanism models and characteristic curves of the core components of the HVAC system (such as the main unit, refrigeration system, cooling system, cooling tower, etc.).

[0004] However, the above solutions have the following disadvantages: The method of adjusting based on preset rules lacks flexibility and accuracy, and it is difficult to cope with complex and changeable operating environments; Establishing a mechanism model of the HVAC system requires strong business background support, and there are deviations between the mechanism model and the actual on-site operation conditions, resulting in inaccurate model results. Moreover, there is strong coupling between various systems of the HVAC system. The existing technologies only optimize some parameters and equipment, and the energy-saving rate is low. The existing technologies only optimize according to the current cooling load, and there is a lag in optimization control when the cooling load changes.

[0005] In summary, the existing energy-saving optimization solutions for HVAC systems have the problems of lacking flexibility and accuracy, being difficult to adapt to complex environments, large deviations between mechanism models and actual situations, strong system coupling, limited energy-saving effects, and lagging responses to changes in cooling loads. Summary of the Invention

[0006] The embodiments of the present application provide a method and device for optimizing the operating parameters of an air conditioning system to solve the problems of the existing energy-saving optimization solutions for HVAC systems, such as lacking flexibility and accuracy, being difficult to adapt to complex environments, large deviations between mechanism models and actual situations, strong system coupling, limited energy-saving effects, and lagging responses to changes in cooling loads.

[0007] To solve the above technical problems, the present application is implemented as follows:

[0008] In a first aspect, an embodiment of the present application provides a method for optimizing operating parameters of an air conditioning system. The method includes:

[0009] Obtain the historical cooling load data for each unit time within a first preset time period of the air conditioning system to be optimized, input the historical cooling load data into a cooling load prediction model, and output the predicted cooling load data for each unit time within a future second preset time period;

[0010] Based on the rated cooling capacity of each main unit of the air conditioning system to be optimized, proportionally allocate the cooling load data to predict the cooling capacity of each main unit within each unit time of the future second preset time period;

[0011] Based on a preset energy-saving optimization model and the cooling capacity of each main unit within each unit time of the future second preset time period, solve the energy-saving optimization model to obtain the output of the energy-saving optimization model. The solution of the energy-saving optimization model is: on the premise of satisfying the constraint conditions of the energy-saving optimization model, find the operating state of the equipment in the air conditioning system to be optimized within each unit time of the future second preset time period and the parameter setting values of the air conditioning system within each unit time of the future second preset time period that minimize the objective function of the energy-saving optimization model, and use them as the output of the energy-saving optimization model. The objective function is used to represent the total energy consumption of the air conditioning system to be optimized.

[0012] Optionally, the operating state of the equipment in the air conditioning system to be optimized within each unit time of the future second preset time period includes:

[0013] The on / off state xi of the i-th main unit i , the on / off state yi of the i-th chilled water pump i , the on / off state zi of the i-th cooling water pump i and the on / off state ki of the i-th cooling tower fan i ;

[0014] The parameter setting values of the air conditioning system within each unit time of the future second preset time period include:

[0015] The chilled water supply-return temperature difference △t w,e , the cooling water return temperature t w,c,L , the cooling water supply-return temperature difference △t w,c , the chilled water supply temperature ti of the i-th main unit i w,e,L , where i is a positive integer.

[0016] Optionally, before solving the energy-saving optimization model based on the preset energy-saving optimization model and the cooling capacity of each host in each unit time within the next second preset time period to obtain the output of the energy-saving optimization model, the method further includes:

[0017] Establish the energy-saving optimization model, including:

[0018] Establish a host model, a cooling water pump energy consumption model, a chilled water pump energy consumption model, and a cooling tower fan performance model;

[0019] Based on the host model, the cooling water pump energy consumption model, the chilled water pump energy consumption model, and the cooling tower fan performance model, establish the energy-saving optimization model.

[0020] Optionally, the objective function of the energy-saving optimization model is:

[0021]

[0022] wherein, the N is the number of hosts, N e is the number of chilled water pumps, N c is the number of cooling water pumps, N t is the number of cooling tower fans, R i is the total operation duration of the i-th host, the Var function represents the measure of the imbalance of the operation duration, λ is the balance coefficient, the P i,j chiller is the host model, the P i,j e is the chilled water pump energy consumption model, the P i,j c is the cooling water pump energy consumption model, the P i,j t is the cooling tower fan performance model, the x ij is the startup state of the i-th host in the j-th unit time, the y ij is the startup state of the i-th chilled water pump in the j-th unit time, the z ij is the startup state of the i-th cooling water pump in the j-th unit time, and the k ij is the startup state of the i-th cooling tower fan in the j-th unit time;

[0023] The total energy consumption is the sum of the total energy consumption of each host, the total energy consumption of each cooling water pump, the total energy consumption of each chilled water pump, and the total energy consumption of each cooling tower fan of the air conditioning system to be optimized;

[0024] The constraint conditions of the energy-saving optimization model include at least one of the following: refrigeration load constraint, temperature constraint, start-stop interval constraint of the host, and start-stop state constraints of the host, the chilled water pump, the cooling water pump, and the cooling tower fan.

[0025] Optionally, the chilled water pump energy consumption model is established by the following formula:

[0026] Formula 1: P e = H e G w,e / (367×(a 1 G w,e 3 + b 1 G w,e 2 + c 1 G w,e + d 1 ))×(0.94187×(1 - e -9.04fe ))×(0.5087 + 1.287f e - 1.42f e 2 + 0.5834f e 3 ));

[0027] Formula 2: H e = a 2 G w,e 2 + b 2 f e G w,e + c 2 f e 2 ;

[0028] Formula 3: y e (G w,e ) = f e ;

[0029] Wherein, the P e is the obtained historical input power of the chilled water pump, the H e is the obtained historical head of the chilled water pump, the G w,e is the obtained historical chilled water flow rate, and the f e is the obtained historical frequency percentage of the chilled water pump;

[0030] Substitute the P e , the H e , the G w,e and the f e into the Formulas 1, 2, and 3 to fit the coefficients a 1 , b 1, c 1 , d 1 , a 2 , b 2 , c 2 ;

[0031] Determine the formula 1 as the energy consumption model of the chilled water pump.

[0032] Optionally, the establishment of the cooling water pump energy consumption model is achieved through the following formula:

[0033]

[0034] Formula 5: H e = a 2 G w,c 2 + b 2 f e G w,c + c 2 f e 2 ;

[0035] Formula 6: y e (G w,c ) = f e ;

[0036] Wherein, the P c is the input power of the acquired historical chilled water pump; the H e is the head of the acquired historical chilled water pump; the G w,c is the flow rate of the acquired historical chilled water; the f e is the frequency percentage of the acquired historical chilled water pump;

[0037] Substitute the P c , the H e , the G w,c and the f e into the formulas 4, 5, and 6 to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 ;

[0038] Determine the formula 4 as the energy consumption model of the cooling water pump.

[0039] Optionally, the establishment of the host model includes:

[0040] According to the host evaporator model formula 7, Q e , Δt w,e , t w,e,L , te and G w,e fit the coefficient C 1 , C 2 , C 3 ;

[0041] Formula 7:

[0042] Obtain the total heat transfer coefficient model of the host evaporator:

[0043] According to the host condenser model formula 8 and Q c , Δt w,c , t w,c,E , t C and G w,C , fit the coefficient D 1 , D 2 , D 3 ;

[0044] Formula 8:

[0045] Obtain the total heat transfer coefficient model of the host condenser:

[0046] According to the host COP energy efficiency model formula 9, Q e , Q o , COP, t c and t e , fit the coefficient E 1 , E 2 ;

[0047] Formula 9:

[0048] According to the total heat transfer coefficient model of the host evaporator and the total heat transfer coefficient model of the host condenser, obtain the host model;

[0049] wherein, the Q e is the obtained historical evaporation side load, the Δt w,e is the obtained historical chilled water supply and return temperature difference, the t w,e,L is the obtained historical chilled water supply temperature, the t e is the obtained historical host evaporation temperature, the G w,e is the obtained historical chilled water flow rate, the Q c is the obtained historical condensation side load, the Δt w,c is the obtained historical cooling water supply and return temperature difference, the t w,c,E is the obtained historical cooling water return temperature, the t CFor the obtained historical host condensation temperature, the G w,C For the obtained historical cooling water flow rate, the Q o For the obtained historical rated cooling capacity of the host, the COP is the obtained historical energy efficiency of the host.

[0050] Optionally, obtaining the host model according to the total heat transfer coefficient model of the host evaporator and the total heat transfer coefficient model of the host condenser includes:

[0051] Obtaining the cooling capacity Q of the host e , the set chilled water supply temperature t′ w,e,L , the set chilled water supply and return temperature difference △t′ w,e , the set cooling water return temperature t′ w,c,E and the set cooling water supply and return temperature difference △t′ w,c ;

[0052] Based on the Q e and the △t′ w,e , calculate the chilled water flow rate: G′ w,e =Q e / △t′ w,e ;

[0053] Based on the total heat transfer coefficient model of the host evaporator, calculate the heat transfer coefficient UA′ of the evaporator e ;

[0054] Based on the heat transfer coefficient UA′ of the evaporator e , calculate the evaporation temperature

[0055] Assumption step: The assumption step includes: assuming a condensation temperature t′ c , calculate COP′ through the host energy efficiency model formula 9; based on the COP′, calculate the condensation load in sequence Cooling water flow rate Based on the total heat transfer coefficient model of the host condenser, calculate the heat transfer coefficient UA′ of the condenser c ; based on the UA′ c , calculate the theoretical value t″ of the condensation temperature c = When |t′ c -t″ c |>ε, it is not convergent, repeat the assumption step until |t′ c -t″ c |≤ε;

[0056] Obtain the host power as the host model.

[0057] Optionally, establishing a cooling tower fan performance model includes:

[0058] According to the cooling tower fan performance model formula 10, t w,c,E , T wb , G w,c , N, and △t w,c fit a 3 , b 3 , c 3 , d 3 ;

[0059] Formula 10:

[0060] According to the △t′ w,c and the G′ c corresponding when |t′ c -t″ w,c | ≤ ε, the actual outdoor wet bulb temperature T′ wb , and the formula 10, calculate the cooling return water temperature t″ w,c,E at different numbers N of cooling towers in operation;

[0061] According to the t″ w,c,E , determine the minimum number N of cooling towers in operation that satisfies t″ w,c,E ≤ t′ w,c,E ; t,min ;

[0062] According to the N t,min , determine the cooling tower fan power P t,min = N t,min P t , where the P t is the input power when the cooling tower fan is in operation, N is the number of cooling tower fans in operation, t w,c,E is the historical cooling return water temperature obtained, T wb is the historical outdoor wet bulb temperature obtained, G w,c is the historical cooling water flow obtained, and △t w,c is the historical cooling supply - return water temperature difference obtained.

[0063] Optionally, before obtaining the historical data of the cooling load per unit time in the first preset time period of the air - conditioning system to be optimized and inputting the historical data of the cooling load into the cooling load prediction model to output the predicted cooling load data per unit time in the future second preset time period, the method further includes:

[0064] Obtain training data;

[0065] Training the initial cooling load prediction model based on the training data to obtain the cooling load prediction model;

[0066] Wherein, the training data is: multiple groups of sample data, and each group of sample data includes: the historical sample data of the cooling load for each unit time within a first preset time period, and the corresponding historical sample data of the cooling load for each unit time within a second preset time period. Wherein, the first preset time period is greater than the second preset time period, and on the time axis, the second preset time period is included in the first preset time period, and the right endpoint of the second preset time period coincides with the right endpoint of the first preset time period on the time axis.

[0067] In a second aspect, an embodiment of the present application provides an operating parameter optimization device for an air conditioning system, and the device includes:

[0068] An acquisition module, configured to acquire the historical cooling load data for each unit time within a first preset time period of the air conditioning system to be optimized, input the historical cooling load data into the cooling load prediction model, and output the predicted cooling load data for each unit time within a future second preset time period;

[0069] An execution module, configured to perform proportional distribution on the cooling load data based on the rated cooling capacity of each main unit of the air conditioning system to be optimized, so as to predict the cooling capacity of each main unit for each unit time within the future second preset time period; solve the energy-saving optimization model based on the preset energy-saving optimization model and the cooling capacity of each main unit for each unit time within the future second preset time period, and obtain the output of the energy-saving optimization model. The solution of the energy-saving optimization model is: under the premise of satisfying the constraint conditions of the energy-saving optimization model, find the operating state of the equipment in the air conditioning system to be optimized for each unit time within the future second preset time period and the parameter setting value of the air conditioning system to be optimized for each unit time within the future second preset time period that minimize the objective function of the energy-saving optimization model, as the output of the energy-saving optimization model. The objective function is used to represent the total energy consumption of the air conditioning system to be optimized.

[0070] In a third aspect, an embodiment of the present application provides a network device, including: a processor, a memory, and a program stored on the memory and executable on the processor. When the program is executed by the processor, the steps of an operating parameter optimization method for an air conditioning system as described in the first aspect are implemented.

[0071] Fourthly, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of an operation parameter optimization method for an air-conditioning system as described in the first aspect are implemented.

[0072] Fifthly, an embodiment of the present application provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps of an operation parameter optimization method for an air-conditioning system as described in the first aspect are implemented.

[0073] In the embodiment of the present application, by deeply combining the equipment mechanism and operation data of the heating, ventilation, and air-conditioning (HVAC) system, an operation parameter optimization method for an air-conditioning system is constructed. This method establishes a cooling load prediction model, and with the goal of minimizing the operation power of the HVAC system, an energy-saving optimization model is established. Through dynamic adjustment, the optimal control of the HVAC system is achieved, significantly improving energy efficiency, reducing energy consumption costs, and maximizing the economic benefits of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0075] Figure 1 is a flowchart of an operation parameter optimization method for an air-conditioning system provided by an embodiment of the present application;

[0076] Figure 2 is a structural block diagram of an air-conditioning system provided by an embodiment of the present application;

[0077] Figure 3 is a flowchart of an operation parameter optimization method for an air-conditioning system provided by an embodiment of the present application;

[0078] Figure 4 is a schematic diagram of the relationship between the power and frequency percentage of a chilled water pump and a cooling water pump provided by an embodiment of the present application;

[0079] Figure 5 is a structural block diagram of an operation parameter optimization device for an air-conditioning system provided by an embodiment of the present application;

[0080] Figure 6 is a structural block diagram of a network device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0081] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0082] Figure 1 A method for optimizing the operating parameters of an air-conditioning system according to an embodiment of the present application is shown. Figure 1 The method shown can be applied to Figure 2 the air-conditioning system shown, such as Figure 1 as shown, the method includes:

[0083] Step S101: Obtain the historical cooling load data of each unit time within a first preset time period of the air-conditioning system to be optimized, input the historical cooling load data into a cooling load prediction model, and output the predicted cooling load data of each unit time within a future second preset time period.

[0084] Step S102: Based on the rated cooling capacity of each main unit of the air-conditioning system to be optimized, proportionally allocate the cooling load data to predict the cooling capacity of each main unit within each unit time of the future second preset time period.

[0085] Step S103: Based on a preset energy-saving optimization model and the cooling capacity of each main unit within each unit time of the future second preset time period, solve the energy-saving optimization model to obtain the output of the energy-saving optimization model.

[0086] In step S101, the system first collects the historical cooling load data of the air-conditioning system to be optimized within the first preset time period. The cooling load refers to the refrigeration capacity required by the air-conditioning system at a specific time. Then, this historical data is input into a cooling load prediction model, which analyzes past data to predict the cooling load changes in a future period (the second preset time period). Finally, the cooling load prediction model outputs the predicted cooling load data for each time unit in the future (for example, it can output the predicted cooling load data per minute within the next hour), and these data will be used for subsequent optimization processes.

[0087] In step S102, the system proportionally allocates the predicted cooling load data according to the rated cooling capacity of each air-conditioning host (i.e., the maximum cooling capacity that each host can provide under the optimal working condition). The system will reasonably allocate the required cooling capacity for each future time unit according to the capabilities of each host. For example, if the rated cooling capacity of a host accounts for 50% of the total rated cooling capacity, then when allocating the cooling load, this host will undertake 50% of the cooling load. This process ensures that the future working load distribution of each host is reasonable and helps to improve the overall efficiency of the system.

[0088] In step S103, the solution of the energy-saving optimization model is as follows: on the premise of satisfying the constraint conditions of the energy-saving optimization model, find the operating state of the equipment in the to-be-optimized air-conditioning system for each unit time within the second preset time period in the future and the parameter setting values of the to-be-optimized air-conditioning system for each unit time within the second preset time period in the future, which are used as the output of the energy-saving optimization model. The objective function is used to represent the total energy consumption of the to-be-optimized air-conditioning system.

[0089] In a possible implementation manner, the operating state of the equipment in the to-be-optimized air-conditioning system for each unit time within the second preset time period in the future includes: the starting state x of the i-th host i , the starting state y of the i-th chilled water pump i , the starting state z of the i-th cooling water pump i and the starting state k of the i-th cooling tower fan i ; the parameter setting values of the air-conditioning system for each unit time within the second preset time period in the future include: the chilled water supply-return temperature difference △t w,e , the cooling return water temperature t w,c,L , the cooling water supply-return temperature difference △t w,c , the chilled water supply temperature t of the i-th host i w,e,L , where i is a positive integer.

[0090] In this step, the system uses a preset energy-saving optimization model to analyze the cooling capacity of each host within the second preset time period in the future. The energy-saving optimization model usually contains a series of algorithms and rules, aiming to find the best operation strategy that minimizes energy consumption while meeting the cooling load demand. By solving the allocated cooling capacity, the model can output the optimized control strategy or operating parameters, and these outputs will guide the actual operation of the air-conditioning system to achieve the energy-saving goal and improve the overall efficiency of the system.

[0091] It should be noted that the Gurobi solver can be used to solve the energy-saving optimization model. The Gurobi solver is an efficient mathematical optimization software widely used to solve linear programming, integer programming, mixed integer programming, quadratic programming, and other types of optimization problems.

[0092] In summary, in the embodiments of the present application, by deeply combining the equipment mechanism and operation data of the HVAC system, an operation parameter optimization method for an air-conditioning system is constructed. This method establishes a cooling load prediction model and an energy-saving optimization model with the goal of minimizing the operating power of the HVAC system, and realizes the optimal control of the HVAC system through dynamic adjustment, significantly improving energy efficiency, reducing energy consumption costs, and maximizing the economic benefits of users.

[0093] In a possible implementation, before obtaining the cooling load historical data of each unit time within the first preset time period of the air-conditioning system to be optimized and inputting the cooling load historical data into the cooling load prediction model to output the predicted cooling load data of each unit time within the future second preset time period, the method further includes: obtaining training data; training the initial cooling load prediction model based on the training data to obtain the cooling load prediction model; where the training data is: multiple groups of sample data, and each group of sample data includes: the cooling load historical sample data of each unit time within the first preset time period, and the corresponding cooling load historical sample data of each unit time within the second preset time period, where the first preset time period is greater than the second preset time period, and the second preset time period is included in the first preset time period on the time axis, and the right endpoint of the second preset time period coincides with the right endpoint of the first preset time period on the time axis.

[0094] It should be noted that in a specific application scenario, the operation data of the HVAC system for at least one month can be collected and the stable operating condition data can be screened out. Specifically, the historical operation data of the HVAC system with a sampling interval of 1 min can be collected, including the host condensation temperature t c 、the host evaporation temperature t e 、the host input power P chiller 、the chilled water supply temperature t w,e,L 、the chilled water supply and return temperature difference △t w,e 、the chilled water flow rate G w,e 、the chilled water pump frequency percentage f e 、the chilled water pump input power P e 、the chilled water pump head H e 、the cooling water return temperature t w,c,E 、the cooling water supply and return temperature difference △t w,c 、the cooling water flow rate G w,c 、the cooling water pump head H c 、the cooling water pump frequency percentage f c, the input power P of the cooling water pump c and the outdoor wet-bulb temperature T wb ; Calculate the evaporation-side load Q through Q e = cG w,e △t w,e Calculate the evaporation-side load Q e , Calculate the condensation-side load Q through Q c = cG w,c △t w,c Calculate the condensation-side load Q c , Screen out the data with the fluctuations of Q e and Q c not exceeding 10% within 30 minutes as the stable operating condition data. c is the specific heat capacity of water, and use the evaporation-side load Q in the stable operating condition data e as the training data of the cooling load prediction model. The input of the cooling load prediction model is the cooling load per 1 minute in the most recent three hours (the first preset time period), and the output is the cooling load per 1 minute in the most recent one hour (the second preset time period), and the ARIMA model can be used to establish the cooling load prediction model.

[0095] Among them, ARIMA (Autoregressive Integrated Moving Average Model) is a statistical method for time series prediction, which is widely used in fields such as economy and finance. Its core is to predict future trends through historical data.

[0096] In a possible implementation, before solving the energy-saving optimization model based on the preset energy-saving optimization model and the refrigeration capacity of each host in each unit time in the future second preset time period to obtain the output of the energy-saving optimization model, the method further includes: establishing an energy-saving optimization model, and establishing the energy-saving optimization model as Figure 3 shown, including:

[0097] Step S301, establish a host model, a cooling water pump energy consumption model, a chilled water pump energy consumption model, and a cooling tower fan performance model;

[0098] Step S302, based on the host model, the cooling water pump energy consumption model, the chilled water pump energy consumption model, and the cooling tower fan performance model, establish an energy-saving optimization model.

[0099] In a possible implementation, the chilled water pump energy consumption model is established through the following formula:

[0100]

[0101] Formula 2: H e = a 2 G w,e 2 + b 2 f e G w,e + c2 f e 2 ;

[0102] Formula 3: y e (G w,e ) = f e ;

[0103] where P e is the acquired historical input power of the chilled water pump, H e is the acquired historical head of the chilled water pump, G w,e is the acquired historical chilled water flow rate, and f e is the acquired historical frequency percentage of the chilled water pump;

[0104] Substitute P e , H e , G w,e and f e into Formulas 1, 2, and 3 to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 ;

[0105] Determine Formula 1 as the energy consumption model of the chilled water pump.

[0106] The fitting method can be the least squares method.

[0107] Thus, by substituting the input power P e , head H e , flow rate G w,e and frequency percentage f e in the historical data into Formulas 1, 2, and 3, and using the least squares method to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 , the finally established energy consumption model of the chilled water pump can more accurately reflect the energy consumption characteristics of the chilled water pump, providing a basis for optimizing the operation of the pump and subsequently reducing the overall energy consumption of the air conditioning system.

[0108] And Figure 4 shows the relationship between the power and frequency percentage of the chilled water pump.

[0109] In a possible implementation, the energy consumption model of the cooling water pump is established through the following formula:

[0110]

[0111] Formula 5: H e = a 2 G w,c 2 + b 2 f e G w,c + c 2 f e 2 ;

[0112] Formula 6: y e (G w,c ) = f e ;

[0113] where P c is the acquired historical input power of the chilled water pump; H e is the acquired historical head of the chilled water pump; G w,c is the acquired historical chilled water flow rate; f e is the acquired historical frequency percentage of the chilled water pump;

[0114] Substitute P c , H e , G w,c and f e into Formulas 4, 5, and 6 to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 ;

[0115] Determine Formula 4 as the energy consumption model of the cooling water pump.

[0116] Thus, by substituting the input power P c , head H e , flow rate G w,c and frequency percentage f e of the cooling water pump in the historical data into Formulas 4, 5, and 6, and using the least squares method to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 , the finally established energy consumption model of the cooling water pump can effectively describe the energy consumption characteristics of the cooling water pump, providing a basis for optimizing the operation efficiency of the pump and subsequently reducing the overall energy consumption of the air conditioning system.

[0117] And Figure 4Shows the relationship between the power of the cooling water pump and the percentage of frequency.

[0118] In a possible implementation, establishing the host model includes:

[0119] According to the host evaporator model formula 7, Q e , Δt w,e , t w,e,L , t e and G w,e to fit the coefficients C 1 , C 2 , C 3 ;

[0120] Formula 7:

[0121] Obtain the total heat transfer coefficient model of the host evaporator:

[0122] According to the host condenser model formula 8 and Q c , Δt w,c , t w,c,E , t C and G w,C , to fit the coefficients D 1 , D 2 , D 3 ;

[0123] Formula 8:

[0124] Obtain the total heat transfer coefficient model of the host condenser:

[0125] According to the host COP energy efficiency model formula 9, Q e , Q o , COP, t c and t e to fit the coefficients E 1 , E 2 ;

[0126] Formula 9:

[0127] According to the total heat transfer coefficient model of the host evaporator and the total heat transfer coefficient model of the host condenser, obtain the host model;

[0128] Among them, Q e is the obtained historical evaporation side load, Δt w,e is the obtained historical chilled water supply and return temperature difference, t w,e,L is the obtained historical chilled water supply temperature, t eFor the obtained historical host evaporation temperature, G w,e For the obtained historical chilled water flow rate, Q c For the obtained historical condensing side load, Δt w,c For the obtained historical cooling supply - return water temperature difference, t w,c,E For the obtained historical cooling return water temperature, t C For the obtained historical host condensing temperature, G w,C For the obtained historical cooling water flow rate, Q o For the obtained historical rated cooling capacity of the host, COP is the obtained historical energy efficiency of the host.

[0129] In a possible implementation, according to the total heat transfer coefficient model of the host evaporator and the total heat transfer coefficient model of the host condenser, the host model obtained includes:

[0130] Obtain the cooling capacity Q of the host e , the set value of the chilled water supply temperature t′ w,e,L , the set value of the chilled water supply - return water temperature difference △t′ w,e , the set value of the cooling return water temperature t′ w,c,E and the set value of the cooling supply - return water temperature difference △t′ w,c ;

[0131] Based on Q e and △t′ w,e , calculate the chilled water flow rate: G′ w,e = Q e / △t′ w,e ;

[0132] Based on the total heat transfer coefficient model of the host evaporator, calculate the evaporator heat transfer coefficient UA′ e ;

[0133] Based on the evaporator heat transfer coefficient UA′ e , calculate the evaporation temperature

[0134] Assumption step: The assumption step includes: Assume a condensing temperature t′ c , through the host energy efficiency model formula 9, calculate COP′; Based on COP′, calculate the condensing load in sequence cooling water flow rate Based on the total heat transfer coefficient model of the host condenser, calculate the condenser heat transfer coefficient UA′ c ; Based on UA′ c , calculate the theoretical value of the condensing temperature When |t′ c - t″ cWhen |t′| > ε, it has not converged, and the assumption step is repeated until |t′ - t″| ≤ ε; c -t″ c |≤ε;

[0135] Obtain the main engine power as the main engine model.

[0136] Thus, by combining the total heat transfer coefficient model of the main engine evaporator, the total heat transfer coefficient model of the condenser, and the main engine COP energy efficiency model, and fitting the coefficients based on historical data, the main engine model is finally established. It provides a reliable basis for optimizing the operating parameters of the main engine and improving energy efficiency.

[0137] In a possible implementation, establishing the performance model of the cooling tower fan includes:

[0138] According to the performance model formula 10 of the cooling tower fan, t w,c,E , T wb , G w,c , N, and △t w,c fit a 3 , b 3 , c 3 , d 3 ;

[0139] Formula 10:

[0140] According to △t′ and the corresponding G′ when |t′ - t′′| ≤ ε, the actual outdoor wet bulb temperature T′, and formula 10, calculate the cooling return water temperature t″ at different numbers of cooling towers N turned on w,c ; c -t′′ c |≤ε, the corresponding G′ w,c , the actual outdoor wet bulb temperature T′ wb , and formula 10, calculate the cooling return water temperature t″ at different numbers of cooling towers N turned on w,c,E ;

[0141] According to t″, determine the minimum number of cooling towers N turned on that satisfies t″ ≤ t′ w,c,E ; w,c,E ≤t′ w,c,E ; t,min ;

[0142] According to N, determine the cooling tower fan power P t,min = N t,min P t,min , where P t is the input power when the cooling tower fan is running, N is the number of cooling tower fans turned on, t t is the historical cooling return water temperature obtained, T w,c,E is the historical outdoor wet bulb temperature obtained, G wb is the historical cooling water flow obtained, △t w,c is the historical cooling water flow obtained, △t w,cis the historical temperature difference between the supply and return water for cooling obtained.

[0143] Thus, the performance model of the cooling tower fan provides a scientific basis for optimizing the operating efficiency of the cooling tower and reducing the energy consumption of the fan, which helps to achieve more efficient cooling system management and energy conservation.

[0144] It should be noted that the system needs to establish multiple performance models to accurately describe the energy consumption and performance characteristics of each component in the air conditioning system. Among them, the host model is used to describe the refrigeration capacity, energy efficiency ratio, operating status, etc. of the air conditioning host. This model can help predict the energy consumption and performance of the host under different working conditions; the cooling water pump energy consumption model is used to calculate the energy consumption of the cooling water pump under different flow and pressure conditions. This model takes into account the efficiency and hydrodynamic characteristics of the cooling water pump to accurately evaluate the energy consumption of the cooling water pump during operation; the chilled water pump energy consumption model is similar to the cooling water pump model, but focuses on the energy consumption characteristics of the chilled water pump and can evaluate the energy consumption of the chilled water circulating in the system; the performance model of the cooling tower fan is used to describe the performance of the cooling tower fan, including air volume, wind pressure and energy consumption, etc. This model can help optimize the operation of the cooling tower and ensure that it works in the best state. By establishing these models, the system can comprehensively understand the performance and energy consumption characteristics of each component and provide basic data for the establishment of subsequent energy-saving optimization models.

[0145] In a possible implementation, the objective function of the energy-saving optimization model is:

[0146]

[0147] where N is the number of hosts, N e is the number of chilled water pumps, N c is the number of cooling water pumps, N t is the number of cooling tower fans, R i is the total operating duration of the i-th host, the Var function represents the measure of the imbalance of the operating duration, λ is the balance coefficient, P i ,j chiller is the host model, P i,j e is the chilled water pump energy consumption model, P i,j c is the cooling water pump energy consumption model, P i,j t is the performance model of the cooling tower fan, x ij is the startup status of the i-th host at the j-th unit time, y ij is the startup status of the i-th chilled water pump at the j-th unit time, z ij the startup status of the i-th cooling water pump at the j-th unit time, and k ijis the startup status of the i-th cooling tower fan in the j-th unit time;

[0148] The decision variables of the energy-saving optimization model include: the temperature difference △t between the supply and return water of the chiller w,e , the return water temperature t of the cooling water w,c,E and the temperature difference △t between the supply and return water of the cooling water w,c , the startup status xi of the i-th host i , the supply water temperature ti of the i-th host's chilled water i w,e,L , y i is the startup status of the i-th chilled water pump, z i is the startup status of the i-th cooling water pump, k i is the startup status of the i-th cooling tower fan. Decision variables usually represent the operating parameters that can be adjusted in the energy-saving optimization model, such as the operating frequencies of each host, the flow rates of the cooling water pump and the chilled water pump, and the rotational speeds of the cooling tower fans. By optimizing these variables, the energy-saving model can formulate the best control strategy to ensure that the system can meet the cooling load demand while minimizing energy consumption as much as possible.

[0149] And the total energy consumption is the sum of the total energy consumption of each host, each cooling water pump, each chilled water pump, and each cooling tower fan in the air-conditioning system to be optimized; the constraint conditions of the energy-saving optimization model include at least one of the following: refrigeration load constraint, temperature constraint, host start-stop interval constraint, and start-stop status constraints of the host, chilled water pump, cooling water pump, and cooling tower fan.

[0150] The constraint conditions are expressed by the following formulas:

[0151] Refrigeration load constraint: Among them, 60 represents 60 minutes, j is the unit time interval, and can be set according to actual needs. Q j e is the cooling load data of each unit time in the predicted future second preset time period.

[0152] Host start-stop interval constraint: xi i,j + xi i,(j+1) +... + xi i,(j+I-1) ≤ 1. I is the start-stop interval of operation

[0153] Temperature constraint:

[0154] △t mib w,e ≤ △t w,e ≤ △t max w,e

[0155] t min w,c,E ≤ t w,c,E≤t max w,c,E

[0156] △t min w,c ≤△t w,c ≤△t max w,c

[0157]

[0158] Start-stop state constraint:

[0159]

[0160] In summary, by deeply combining the equipment mechanism and operation data of the HVAC system, an operation parameter optimization method for an air-conditioning system is constructed. This method establishes a cooling load prediction model, comprehensively considers four key parameters: chilled water supply temperature, chilled water supply-return temperature difference, cooling water return temperature, and cooling water supply-return temperature difference. With the goal of minimizing the operation power of the HVAC system, an energy-saving optimization model and related processes are established, and the optimal control of the HVAC system is achieved through dynamic adjustment, significantly improving energy efficiency, reducing energy consumption costs, and maximizing the economic benefits of users.

[0161] Figure 5 The figure shows an operation parameter optimization device for an air-conditioning system according to an embodiment of the present application, as Figure 5 shown, the device includes:

[0162] An acquisition module 501, configured to acquire the historical cooling load data of each unit time within a first preset time period of the air-conditioning system to be optimized, input the historical cooling load data into the cooling load prediction model, and output the predicted cooling load data of each unit time within a future second preset time period;

[0163] The execution module 502 is configured to proportionally allocate the cooling load data based on the rated cooling capacity of each host in the air conditioning system to be optimized, so as to predict the cooling capacity of each host per unit time in the second preset time period in the future; solve the energy-saving optimization model based on the preset energy-saving optimization model and the cooling capacity of each host per unit time in the second preset time period in the future, and obtain the output of the energy-saving optimization model. The solution of the energy-saving optimization model is as follows: on the premise of satisfying the constraint conditions of the energy-saving optimization model, find the operating state of the equipment in the air conditioning system to be optimized per unit time in the second preset time period in the future and the parameter setting values of the air conditioning system to be optimized per unit time in the second preset time period in the future that minimize the objective function of the energy-saving optimization model, and use them as the output of the energy-saving optimization model. The objective function is used to represent the total energy consumption of the air conditioning system to be optimized.

[0164] In a possible implementation manner, the operating state of the equipment in the air conditioning system to be optimized per unit time in the second preset time period in the future includes:

[0165] The starting state \(x\) of the \(i\)-th host i and the starting state \(y\) of the \(i\)-th chilled water pump i and the starting state \(z\) of the \(i\)-th cooling water pump i and the starting state \(k\) of the \(i\)-th cooling tower fan i ;

[0166] The parameter setting values of the air conditioning system per unit time in the second preset time period in the future include:

[0167] The chilled water supply-return temperature difference \(\Delta t\) w,e and the cooling water return temperature \(t\) w,c,L and the cooling water supply-return temperature difference \(\Delta t\) w,c and the chilled water supply temperature \(t\) of the \(i\)-th host i w,e,L , where \(i\) is a positive integer.

[0168] In a possible implementation manner, the execution module 502 is further configured to establish the energy-saving optimization model before solving the energy-saving optimization model based on the preset energy-saving optimization model and the cooling capacity of each host per unit time in the second preset time period in the future, and obtain the output of the energy-saving optimization model.

[0169] The execution module 502 is further configured to establish a host model, a cooling water pump energy consumption model, a chilled water pump energy consumption model, and a cooling tower fan performance model; and establish the energy-saving optimization model based on the host model, the cooling water pump energy consumption model, the chilled water pump energy consumption model, and the cooling tower fan performance model.

[0170] In a possible implementation manner, the objective function of the energy-saving optimization model is:

[0171]

[0172] wherein, N is the number of hosts, N e is the number of chilled water pumps, N c is the number of cooling water pumps, N t is the number of cooling tower fans, R i is the total operating duration of the i-th host, the Var function represents the measure of the imbalance of the operating duration, λ is the balance coefficient, the P i,j chiller is the host model, the P i,j e is the chilled water pump energy consumption model, the P i,j c is the cooling water pump energy consumption model, the P i,j t is the cooling tower fan performance model, the x ij is the startup state of the i-th host at the j-th unit time, the y ij is the startup state of the i-th chilled water pump at the j-th unit time, the z ij is the startup state of the i-th cooling water pump at the j-th unit time, and the k ij is the startup state of the i-th cooling tower fan at the j-th unit time;

[0173] The total energy consumption is the sum of the total energy consumption of each host, each cooling water pump, each chilled water pump, and each cooling tower fan of the air conditioning system to be optimized;

[0174] The constraint conditions of the energy-saving optimization model include at least one of the following: refrigeration load constraint, temperature constraint, host startup and shutdown interval constraint, and startup and shutdown state constraints of the host, the chilled water pump, the cooling water pump, and the cooling tower fan.

[0175] In a possible implementation manner, the chilled water pump energy consumption model is established by the following formula:

[0176]

[0177] Formula 2: H e = a2 G w,e 2 +b 2 f e G w,e +c 2 f e 2 ;

[0178] Formula 3: y e (G w,e ) = f e ;

[0179] wherein, the P e is the acquired historical input power of the chilled water pump, the H e is the acquired historical head of the chilled water pump, the G w,e is the acquired historical chilled water flow rate, and the f e is the acquired historical frequency percentage of the chilled water pump;

[0180] Substitute the P e , the H e , the G w,e and the f e into the Formulas 1, 2, and 3 to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 ;

[0181] Determine the Formula 1 as the energy consumption model of the chilled water pump.

[0182] In a possible implementation, the energy consumption model of the cooling water pump is established through the following formula:

[0183]

[0184] Formula 5: H e = a 2 G w,c 2 +b 2 f e G w,c +c 2 f e 2 ;

[0185] Formula 6: y e (G w,c ) = f e ;

[0186] wherein, the Pc is the obtained historical input power of the chilled water pump; the H e is the obtained historical head of the chilled water pump; the G w,c is the obtained historical chilled water flow rate; the f e is the obtained historical frequency percentage of the chilled water pump;

[0187] Substitute the P c and the H e and the G w,c and the f e into the formulas 4, 5, and 6 to fit the coefficients a 1 , b 1 , c 1 , d 1 , a 2 , b 2 , c 2 ;

[0188] Determine the formula 4 as the cooling water pump energy consumption model.

[0189] In a possible implementation manner, the execution module 502 is further configured to fit the coefficients C e , Δt w,e , t w,e,L , t e and G w,e according to the host evaporator model formula 7, Q 1 , C 2 , C 3 ;

[0190] Formula 7:

[0191] Obtain the total heat transfer coefficient model of the host evaporator:

[0192] According to the host condenser model formula 8 and Q c , Δt w,c , t w,c,E , t C and G w,C , fit the coefficients D 1 , D 2 , D 3 ;

[0193] Formula 8:

[0194] Obtain the total heat transfer coefficient model of the host condenser:

[0195] According to the host COP energy efficiency model formula 9, Qe , Q o , COP, t c and t e to fit the coefficient E 1 , E 2 ;

[0196] Formula 9:

[0197] According to the total heat transfer coefficient model of the host evaporator and the total heat transfer coefficient model of the host condenser, the host model is obtained;

[0198] wherein, the Q e is the obtained historical evaporation side load, the Δt w,e is the obtained historical chilled water supply and return temperature difference, the t w,e,L is the obtained historical chilled water supply temperature, the t e is the obtained historical host evaporation temperature, the G w,e is the obtained historical chilled water flow rate, the Q c is the obtained historical condensation side load, the Δt w,c is the obtained historical cooling water supply and return temperature difference, the t w,c,E is the obtained historical cooling water return temperature, the t C is the obtained historical host condensation temperature, the G w,C is the obtained historical cooling water flow rate, the Q o is the obtained historical rated cooling capacity of the host, and the COP is the obtained historical energy efficiency of the host.

[0199] In a possible implementation manner, the execution module 502 is further configured to obtain the cooling capacity Q of the host e , the set value of the chilled water supply temperature t′ w,e,L , the set value of the chilled water supply and return temperature difference △t′ w,e , the set value of the cooling water return temperature t′ w,c,E and the set value of the cooling water supply and return temperature difference △t′ w,c ;

[0200] Based on the Q e and the △t′ w,e , calculate the chilled water flow rate: G′ w,e = Q e / △t′ w,e ;

[0201] Based on the total heat transfer coefficient model of the host evaporator, calculate the evaporator heat transfer coefficient UA′ e ;

[0202] Based on the evaporator heat transfer coefficient UA′ e, calculate the evaporation temperature

[0203] Assumption step: The assumption step includes: assuming a condensation temperature t′ c , through the host energy efficiency model formula 9, calculate COP′; based on the COP′, calculate the condensation load in sequence Cooling water flow Based on the host condenser total heat transfer coefficient model, calculate the condenser heat transfer coefficient UA′ c ; based on the UA′ c , calculate the theoretical value of the condensation temperature When |t′ c - t″ c | > ε, it is not convergent, and repeat the assumption step until |t′ c - t″ c | ≤ ε;

[0204] Obtain the host power As the host model.

[0205] In a possible implementation, the execution module 502 is further configured to fit a w,c,E , b wb , c w,c , d w,c according to the cooling tower fan performance model formula 10, t 3 , b 3 , c 3 , d 3 ;

[0206] Formula 10:

[0207] According to the △t′ w,c and the G′ c - t″ c | ≤ ε, the actual outdoor wet bulb temperature T′ w,c , and the formula 10, calculate the cooling return water temperature t″ wb at different numbers of cooling tower opening N; w,c,E ;

[0208] According to the t″ w,c,E , determine the minimum number of cooling tower opening N w,c,E that satisfies t″ w,c,E ≤ t′ t,min ;

[0209] According to the N t,min, determine the power P of the cooling tower fan t,min = N t,min P t , where the P t is the input power when the cooling tower fan is running, N is the number of cooling tower fans turned on, t w,c,E is the obtained historical cooling return water temperature, T wb is the obtained historical outdoor wet bulb temperature, G w,c is the obtained historical cooling water flow rate, △t w,c is the obtained historical cooling supply - return water temperature difference.

[0210] In a possible implementation, the acquisition module 501 is further configured to obtain training data before obtaining the historical cooling load data of each unit time within the first preset time period of the air - conditioning system to be optimized, inputting the historical cooling load data into the cooling load prediction model, and outputting the predicted cooling load data of each unit time within the future second preset time period; training the initial cooling load prediction model based on the training data to obtain the cooling load prediction model;

[0211] where the training data is: multiple sets of sample data, and each set of sample data includes: the historical cooling load sample data of each unit time within the first preset time period, and the corresponding historical cooling load sample data of each unit time within the second preset time period, where the first preset time period is greater than the second preset time period, and on the time axis, the second preset time period is included in the first preset time period, and the right - hand endpoint of the second preset time period coincides with the right - hand endpoint of the first preset time period on the time axis.

[0212] In summary, by deeply combining the equipment mechanism and operation data of the HVAC system, an operation parameter optimization method for an air - conditioning system is constructed. This method establishes a cooling load prediction model, comprehensively considers four key parameters: chilled water supply temperature, chilled water supply - return temperature difference, cooling return water temperature, and cooling supply - return water temperature difference, aims to minimize the operation power of the HVAC system, establishes an energy - saving optimization model and related processes, and realizes the optimal control of the HVAC system through dynamic adjustment, significantly improving energy efficiency, reducing energy consumption costs, and maximizing the economic benefits of users.

[0213] An embodiment of the present application provides a network device 60, as Figure 6 shown, the network device 60 includes: a processor 601, a memory 602, and a program stored on the memory 602 and executable on the processor 601. When the program is executed by the processor 601, it implements the steps of an operation parameter optimization method for an air - conditioning system as shown in the above - mentioned embodiment.

[0214] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of an operation parameter optimization method of an air-conditioning system as shown in the above embodiments are implemented, and the same technical effects can be achieved. To avoid repetition, details are not described herein again. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0215] The embodiments of the present application also provide a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps of an operation parameter optimization method of an air-conditioning system as shown in the above embodiments are implemented, and the same technical effects can be achieved. To avoid repetition, details are not described herein again.

[0216] It should be noted that in this document, the term "including", "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0217] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0218] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

Claims

1. A method for optimizing operating parameters of an air conditioning system, characterized in that: The method comprises: Acquire historical cooling load data per unit time of a first preset time period of the air-conditioning system to be optimized, input the historical cooling load data into a cooling load prediction model, and output predicted cooling load data per unit time of a second preset time period in the future; Based on the rated cooling capacity of each host of the air-conditioning system to be optimized, the cooling load data is distributed in equal proportion to predict the cooling capacity of each host in each unit time of the future second preset time period; Based on a preset energy-saving optimization model and the respective cooling capacity of each host in each unit time of the second preset time period in the future, the energy-saving optimization model is solved to obtain the output of the energy-saving optimization model. The solution of the energy-saving optimization model is: on the premise of satisfying the constraints of the energy-saving optimization model, the operating status of the equipment in the air-conditioning system to be optimized in each unit time of the second preset time period in the future and the parameter setting values ​​of the air-conditioning system to be optimized in each unit time of the second preset time period in the future that minimize the objective function of the energy-saving optimization model are calculated as the output of the energy-saving optimization model. The objective function is used to represent the total energy consumption of the air-conditioning system to be optimized.

2. The method according to claim 1, characterized in that: The operating status of the equipment in the air-conditioning system to be optimized in each unit time within the future second preset time period includes: The boot status of the i-th host is x i 、The startup status of the i-th chilled water pump y i 、The i-th cooling water pump startup status z i And the starting status k of the i-th cooling tower fan i ; The parameter setting values ​​of the air conditioning system in each unit time within the future second preset time period include: Chilled water supply and return temperature difference △t w,e , Cooling return water temperature t w,c,L , Cooling water supply and return temperature difference △t w,c 、The refrigeration water supply temperature of the i-th host t i w,e,L , wherein i is a positive integer.

3. The method according to claim 1, characterized in that Before solving the energy-saving optimization model based on the preset energy-saving optimization model and the respective cooling capacity of each host in each unit time of the future second preset time period to obtain the output of the energy-saving optimization model, the method further includes: The energy-saving optimization model is established, which includes: Establish host model, cooling water pump energy consumption model, chilled water pump energy consumption model and cooling tower fan performance model; The energy-saving optimization model is established based on the host model, the cooling water pump energy consumption model, the freezing water pump energy consumption model and the cooling tower fan performance model.

4. The method according to claim 3, characterized in that: The objective function of the energy-saving optimization model is: Wherein, N is the number of hosts, N e is the number of chilled water pumps, N c is the number of cooling water pumps, N t is the number of cooling tower fans, R i is the total running time of the i-th host, the Var function represents the imbalance measure of the running time, λ is the balance coefficient, and the P i,j chiller is the host model, the P i,j e is the energy consumption model of the chilled water pump, the P i,j c is the cooling water pump energy consumption model, the P i,j t is the cooling tower fan performance model, the x ij is the power-on status of the i-th host in the j-th unit time, the y ij is the startup state of the i-th chilled water pump in the j-th unit time, the z ij The startup state of the i-th cooling water pump in the j-th unit time, and the k ij is the startup status of the i-th cooling tower fan in the j-th unit time; The total energy consumption is the sum of the total energy consumption of each host, the total energy consumption of each cooling water pump, the total energy consumption of each freezing water pump and the total energy consumption of each cooling tower fan of the air conditioning system to be optimized; The constraints of the energy-saving optimization model include at least one of the following: refrigeration load constraint, temperature constraint, host start / stop interval constraint, and start / stop state constraint of the host, the chilled water pump, the cooling water pump, and the cooling tower fan.

5. The method according to claim 3, characterized in that: The energy consumption model of the chilled water pump is established through the following formula: Formula 2: H e =a2G w,e 2 +b2f e G w,e +c2f e 2 ; Formula 3: y e (G w,e ) = f e ; Among them, the P e is the historical chilled water pump input power obtained, the H e is the historical chilled water pump head obtained, the G w,e is the historical chilled water flow rate obtained, the f e is the historical chilled water pump frequency percentage obtained; The P e , the H e , the G w,e and the f e Substitute into the above formulas 1, 2, and 3 to fit the coefficients a1, b1, c1, d1, a2, b2, and c2; Formula 1 is determined as the energy consumption model of the chilled water pump.

6. The method according to claim 3, characterized in that The energy consumption model of the cooling water pump is established through the following formula: Formula 5: H e =a2G w,c 2 +b2f e G w,c +c2f e 2 ; Formula 6: y e (G w,c ) = f e ; Among them, the P c is the historical chilled water pump input power obtained; e is the historical chilled water pump head obtained; the G w,c is the historical chilled water flow rate obtained; the f e is the historical chilled water pump frequency percentage obtained; The P c , the H e , the G w,c and the f e Substitute into the above formulas 4, 5, and 6 to fit the coefficients a1, b1, c1, d1, a2, b2, and c2; Formula 4 is determined as the cooling water pump energy consumption model.

7. The method according to claim 3, characterized in that Building a host model includes: According to the host evaporator model formula 7, Q e , Δt w,e ,t w,e,L ,t e and G w,e Fit the coefficients C1, C2, and C3; Get the total heat transfer coefficient model of the main engine evaporator: According to the host condenser model formula 8 and Q c , Δt w,c ,t w,c,E ,t C and G w,C , fitting coefficients D1, D2, D3; The total heat transfer coefficient model of the main engine condenser is obtained: According to the host COP energy efficiency model formula 9, Q e , Q o , COP, t c and t e Fit the coefficients E1 and E2; Formula 9: Obtaining the host model according to the host evaporator total heat transfer coefficient model and the host condenser total heat transfer coefficient model; Among them, the Q e is the historical evaporation side load obtained, the Δt w,e is the historical refrigeration supply and return water temperature difference, the t w,e,L is the historical chilled water supply temperature obtained, the t e is the historical host evaporation temperature obtained, the G w,e is the historical chilled water flow rate, the Q c is the historical condensing side load obtained, the Δt w,c is the historical cooling supply and return water temperature difference, the t w,c,E is the historical cooling return water temperature obtained, the t C is the historical host condensing temperature obtained, the G w,C is the historical cooling water flow rate obtained, the Q o is the historical host rated cooling capacity obtained, and the COP is the historical host energy efficiency obtained.

8. The method according to claim 7, characterized in that According to the total heat transfer coefficient model of the host evaporator and the total heat transfer coefficient model of the host condenser, the host model is obtained, including: Get the host cooling capacity Q e , set value chilled water supply temperature t′ w,e,L , set value refrigeration supply and return water temperature difference △t′ w,e , set value cooling return water temperature t′ w,c,E And the set value cooling supply and return water temperature difference △t′ w,c ; Based on the Q e With the △t′ w,e , calculate the chilled water flow: G′ w,e =Q e / △t′ w,e ; Based on the host evaporator total heat transfer coefficient model, the evaporator heat transfer coefficient UA′ is calculated e ; Based on the evaporator heat transfer coefficient UA′ e , calculate the evaporation temperature Assumption step: The assumption step includes: assuming a condensation temperature t' c , COP′ is calculated by the host energy efficiency model formula 9; based on the COP′, the condensing load is calculated in turn Cooling water flow Based on the host condenser total heat transfer coefficient model, the condenser heat transfer coefficient UA′ is calculated c ; Based on the UA′ c , calculate the theoretical value of condensation temperature When |t′ c -t"′ c When |>ε, it has not converged, and the above assumption steps are repeated until |t′ c -t′′ c |≤ε; Get host power as the host model.

9. The method according to claim 3, characterized in that: Building a cooling tower fan performance model includes: According to the cooling tower fan performance model formula 10, t w,c,E 、T wb , G w,c , N and △t w,c Fit a3, b3, c3, d3; According to the Δt′ w,c With the |t′ c -t″ c |≤ε, the corresponding G′ w,c , the actual outdoor wet bulb temperature T′ wb , and the formula 10, calculate the cooling return water temperature t″ under different cooling tower opening numbers N w,c,E ; According to the t″ w,c,E , determine whether t″ is satisfied w,c,E ≤t′ w,c,E The minimum number of cooling towers to be opened is N t,min ; According to the N t,min , determine the cooling tower fan power P t,min =N t,min P t , wherein the P t is the input power of the cooling tower fan when it is running, N is the number of cooling tower fans turned on, t w,c,E is the historical cooling return water temperature, T wb is the historical outdoor wet-bulb temperature, G w,c is the historical cooling water flow, △t w,c The historical cooling supply and return water temperature difference is obtained.

10. The method according to any one of claims 1 to 9, characterized in that Before obtaining historical cooling load data per unit time of the air-conditioning system to be optimized within a first preset time period, inputting the historical cooling load data into a cooling load prediction model, and outputting predicted cooling load data per unit time within a future second preset time period, the method further includes: Get training data; Training the initial cooling load prediction model based on the training data to obtain the cooling load prediction model; Wherein, the training data is: multiple groups of sample data, each group of sample data includes: historical sample data of cooling load per unit time in a first preset time period, and historical sample data of cooling load per unit time in a corresponding second preset time period, wherein the first preset time period is greater than the second preset time period, and the second preset time period is on the time axis and is included in the first preset time period, and the right endpoint of the second preset time period coincides with the right endpoint of the first preset time period on the time axis.

11. An operating parameter optimization device for an air conditioning system, characterized in that: The device comprises: An acquisition module, used for acquiring historical cooling load data of each unit time within a first preset time period of the air-conditioning system to be optimized, inputting the historical cooling load data into a cooling load prediction model, and outputting predicted cooling load data of each unit time within a second preset time period in the future; An execution module is used to distribute the cooling load data in equal proportion based on the rated cooling capacity of each host of the air-conditioning system to be optimized, so as to predict the cooling capacity of each host per unit time in the second preset time period in the future; based on a preset energy-saving optimization model and the cooling capacity of each host per unit time in the second preset time period in the future, solve the energy-saving optimization model to obtain the output of the energy-saving optimization model, and the solution of the energy-saving optimization model is: on the premise of satisfying the constraints of the energy-saving optimization model, find the operating status of the equipment in the air-conditioning system to be optimized per unit time in the second preset time period in the future and the parameter setting value of the air-conditioning system to be optimized per unit time in the second preset time period in the future that minimizes the objective function of the energy-saving optimization model, as the output of the energy-saving optimization model, and the objective function is used to represent the total energy consumption of the air-conditioning system to be optimized.

12. A network device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of a method for optimizing operating parameters of an air-conditioning system as described in any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for optimizing operating parameters of an air-conditioning system according to any one of claims 1 to 10 are implemented.

14. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of a method for optimizing operating parameters of an air-conditioning system as described in any one of claims 1 to 10.

Images