Energy consumption optimization method, device, equipment, medium and product of heating ventilation air conditioning system

Abstract

The invention discloses an energy consumption optimization method, device and equipment of a heating ventilation air conditioning system, a medium and a product, and relates to the technical field of automatic control. Comprising the steps of obtaining a total power fitting equation according to a first power fitting equation of a target water chilling unit, a second power fitting equation of a target cooling water pump, a third power fitting equation of a target chilled water pump and a fourth power fitting equation of a target cooling tower, performing parameter integration according to the first to-be-optimized operation parameter, the second to-be-optimized operation parameter, the third to-be-optimized operation parameter and the fourth to-be-optimized operation parameter to obtain a global to-be-optimized operation parameter; and optimizing the total power fitting equation, determining a target operation parameter value corresponding to the global to-be-optimized operation parameter when the total power is lowest, and controlling the operation of the target heating ventilation air conditioning system based on the target operation parameter value. According to the method, the effect of optimizing the energy consumption of the heating ventilation air-conditioning system is achieved, the technical blank of the industry is filled, and the energy consumption of the heating ventilation air-conditioning system can be practically and effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology, and in particular to a method, apparatus, equipment, medium and product for optimizing energy consumption in heating, ventilation and air conditioning systems. Background Technology

[0002] The HVAC system, a crucial component of the auxiliary systems in lithium battery manufacturing plants, holds immense energy-saving potential and is a key pathway to improving the plant's energy efficiency. The HVAC system is a complex system comprised of multiple devices, primarily including chillers, pumps, cooling towers, and various valves. These devices are interconnected through a piping network, forming a coupled relationship and influencing each other.

[0003] Currently, there is a lack of a practical and feasible method for optimizing the energy consumption of HVAC systems in the auxiliary systems of lithium battery manufacturing plants, resulting in high energy consumption of HVAC systems. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for optimizing energy consumption in HVAC systems, in order to solve the problem of high energy consumption in HVAC systems due to the lack of a practical and feasible energy consumption optimization method.

[0005] According to one aspect of the present invention, an energy consumption optimization method for a heating, ventilation, and air conditioning system is provided, the method comprising:

[0006] Determine the first operating parameters to be optimized for the target chiller unit in the target HVAC system, and obtain the first power fitting equation for the target chiller unit based on the first operating parameters to be optimized;

[0007] Determine the second operating parameter to be optimized for the target cooling water pump in the target HVAC system, and obtain the second power fitting equation for the target cooling water pump based on the second operating parameter to be optimized.

[0008] The third operating parameter to be optimized for the target chilled water pump in the target HVAC system is determined, and the third power fitting equation corresponding to the target chilled water pump is obtained based on the third operating parameter to be optimized.

[0009] Determine the fourth operating parameter to be optimized for the target cooling tower in the target HVAC system, and obtain the fourth power fitting equation for the target cooling tower based on the fourth operating parameter to be optimized;

[0010] Based on the first power fitting equation, the second power fitting equation, the third power fitting equation, and the fourth power fitting equation, the total power fitting equation corresponding to the target HVAC system is obtained. Then, based on the first operating parameter to be optimized, the second operating parameter to be optimized, the third operating parameter to be optimized, and the fourth operating parameter to be optimized, the global operating parameters to be optimized corresponding to the target HVAC system are integrated to obtain the global operating parameters to be optimized for the target HVAC system.

[0011] The total power fitting equation is optimized to determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and the operation of the target HVAC system is controlled based on the target operating parameter value.

[0012] According to another aspect of the present invention, an energy consumption optimization device for a heating, ventilation, and air conditioning system is provided, the device comprising:

[0013] The first power fitting equation determination module is used to determine the first operating parameters to be optimized for the target chiller unit in the target HVAC system, and to obtain the first power fitting equation for the target chiller unit based on the first operating parameters to be optimized.

[0014] The second power fitting equation determination module is used to determine the second operating parameter to be optimized corresponding to the target cooling water pump in the target HVAC system, and to obtain the second power fitting equation corresponding to the target cooling water pump based on the second operating parameter to be optimized.

[0015] The third power fitting equation determination module is used to determine the third operating parameter to be optimized for the target chilled water pump in the target HVAC system, and to obtain the third power fitting equation for the target chilled water pump based on the third operating parameter to be optimized.

[0016] The fourth power fitting equation determination module is used to determine the fourth operating parameter to be optimized corresponding to the target cooling tower in the target HVAC system, and to obtain the fourth power fitting equation corresponding to the target cooling tower based on the fourth operating parameter to be optimized.

[0017] The global operating parameter determination module is used to obtain the total power fitting equation corresponding to the target HVAC system based on the first power fitting equation, the second power fitting equation, the third power fitting equation, and the fourth power fitting equation, and to integrate the parameters based on the first operating parameter to be optimized, the second operating parameter to be optimized, the third operating parameter to be optimized, and the fourth operating parameter to be optimized to obtain the global operating parameters to be optimized corresponding to the target HVAC system.

[0018] The target operating parameter value determination module is used to optimize the total power fitting equation, determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and control the operation of the target HVAC system based on the target operating parameter value.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method described in any one of the present invention.

[0024] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in any one of the present invention.

[0025] The beneficial effects of this invention are as follows: By constructing power fitting equations corresponding to the target chiller, target cooling water pump, target chilled water pump, and target cooling tower in the target HVAC system, the total power fitting equation and global operating parameters to be optimized for the target HVAC system are obtained. Finally, the optimization results of the total power fitting equation are used to determine the target operating parameter value corresponding to the global operating parameters to be optimized when the total power is at its lowest. Based on the target operating parameter value, the operation of the target HVAC system is controlled, thereby achieving the effect of optimizing the energy consumption of the HVAC system, filling the technical gap in the industry, and effectively reducing the energy consumption of the HVAC system.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart of an energy consumption optimization method for a heating, ventilation, and air conditioning system provided in Embodiment 1 of the present invention;

[0029] Figure 2 This is a flowchart of a total power fitting equation optimization method provided in Embodiment 2 of the present invention;

[0030] Figure 3 This is a flowchart of a first method for generating updated running parameter values ​​provided in Embodiment 3 of the present invention;

[0031] Figure 4 This is a flowchart of a second method for generating updated running parameter values ​​provided in Embodiment 4 of the present invention;

[0032] Figure 5 This is a schematic diagram of the structure of an energy consumption optimization device for a heating, ventilation, and air conditioning system provided in Embodiment 5 of the present invention;

[0033] Figure 6 This is a schematic diagram of the structure of an electronic device for implementing the energy consumption optimization method of the HVAC system according to an embodiment of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," "third," "fourth," "initial," "updated," "iterative," "to be optimized," "target," "potential," "variation," "experiment," and "auxiliary," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] Example 1

[0037] Figure 1 This is a flowchart of an energy consumption optimization method for a heating, ventilation, and air conditioning (HVAC) system according to Embodiment 1 of the present invention. This embodiment is applicable to the situation of optimizing the energy consumption of an HVAC system in the auxiliary systems of a lithium battery manufacturing plant. This method can be executed by an energy consumption optimization device for the HVAC system, which can be implemented in hardware and / or software. Figure 1 As shown, the method includes:

[0038] S101. Determine the first operating parameters to be optimized for the target chiller unit in the target HVAC system, and obtain the first power fitting equation for the target chiller unit based on the first operating parameters to be optimized.

[0039] The target HVAC system refers to the actual operating HVAC system to be optimized in a specific building or industrial setting (such as the auxiliary systems of a lithium battery manufacturing plant). This system consists of core equipment such as chillers, cooling water pumps, chilled water pumps, and cooling towers, and achieves temperature control through refrigerant circulation.

[0040] The target chiller unit is the core cooling device in the target HVAC system, serving as a central component and a major energy consumer. Its internal components mainly include an evaporator, compressor, condenser, and expansion valve. Within the target chiller unit, the refrigerant undergoes a series of cycles to achieve the cooling effect. First, the refrigerant is compressed in the compressor, changing from a low-temperature, low-pressure state to a high-temperature, high-pressure state. Then, it enters the condenser and exchanges heat with the cooling water, transforming into a high-temperature, high-pressure liquid. After being depressurized by the expansion valve, the refrigerant becomes a low-temperature, low-pressure liquid. In the evaporator, the refrigerant exchanges heat with the chilled water, absorbing heat and vaporizing, thereby cooling the chilled water. Finally, the refrigerant returns to the compressor in a low-temperature, low-pressure gaseous state, and the cycle begins again for continuous cooling.

[0041] The first set of operating parameters to be optimized refers to the adjustable operational variables in the target chiller unit that directly affect its power consumption. By adjusting these parameters, the operating state of the target chiller unit can be changed, thereby achieving energy efficiency optimization.

[0042] The first set of operating parameters to be optimized includes at least one of the following: chilled water outlet temperature, chilled water return temperature, cooling water outlet temperature, cooling water return temperature, and chiller unit cooling capacity. Chilled water outlet temperature refers to the temperature at which the target chiller unit's evaporator outlet supplies water to the chilled water circulation system; it is the final temperature of the refrigerant generated by the refrigeration system transferred to the chilled water. Chilled water return temperature refers to the temperature of the chilled water that returns to the target chiller unit's evaporator after absorbing heat through the terminal heat exchange equipment. Cooling water outlet temperature refers to the temperature of the hot water supplied from the target chiller unit's condenser outlet to the target cooling tower; it is the outlet water temperature at which the refrigerant releases heat in the condenser. Cooling water return temperature refers to the temperature of the cooling water that returns to the target chiller unit's condenser after the target cooling tower has discharged heat to the atmosphere. Chiller unit cooling capacity refers to the amount of heat removed from the chilled water by the target chiller unit per unit time.

[0043] The first power fitting equation is a regression model that describes the mathematical relationship between the operating parameters and power of the target chiller unit. It is usually in the form of a nonlinear polynomial or exponential function.

[0044] In one implementation, during the process of constructing the first power fitting equation corresponding to the target chiller unit, it is determined from the performance curve data that the cooling capacity and efficiency differ significantly with changes in operating conditions (i.e., inlet and outlet water temperatures). Based on the current inlet water temperature and the set chilled water outlet temperature, the corresponding cooling capacity and efficiency data are extracted from the operating condition data table provided by the manufacturer to determine the operating status of the chiller unit.

[0045] ;

[0046] ;

[0047] in, The target is the actual efficiency of the chiller unit. The target chiller unit's maximum cooling capacity. The target chiller unit's rated cooling capacity, The target chiller unit's rated cooling capacity ratio, For the target chiller unit's rated efficiency, This is the efficiency correction factor.

[0048] Then, the cooling capacity of the chiller unit is calculated:

[0049] ;

[0050] in, For the cooling capacity of the chiller unit, For the specific heat of the medium, This refers to the chilled water flow rate. Set the outlet water temperature for the chilled water. This refers to the temperature of the chilled water return.

[0051] Next, calculate the target chiller unit's energy consumption and load factor:

[0052] ;

[0053] ;

[0054] in, For unit load rate, The target is the energy consumption of the chiller unit.

[0055] Finally, calculate the cooling water outlet temperature: when hour:

[0056] ;

[0057] when hour: ;

[0058] in, Indicates the chilled water outlet temperature. This refers to the chilled water return temperature. This represents the cooling water flow rate.

[0059] From the above mechanism formula, the theoretical relationship of each of the first operating parameters to be optimized of the target chiller unit can be obtained. Combined with the relationship between the chiller unit power and the chilled water outlet temperature, chilled water return temperature, cooling water outlet temperature, cooling water return temperature and chiller unit cooling capacity in the actual data, the first power fitting equation corresponding to the target chiller unit can be obtained.

[0060] Optionally, based on the first operating parameters to be optimized for the chilled water return system, the first power fitting equation corresponding to the target chiller unit for chilled water return is obtained, including:

[0061] The first power fitting equation for chilled water recirculation is expressed by the following equation:

[0062] ;

[0063] in, Indicates the chiller unit power of the target chiller unit; Indicates the temperature of the chilled water outlet; This represents the temperature difference of the chilled water obtained based on the chilled water outlet temperature and the chilled water return temperature; This indicates the temperature difference of the cooling water obtained based on the cooling water outlet temperature and the cooling water return temperature; This indicates the cooling capacity of the chiller unit; This represents the fitted parameters.

[0064] Optional, - The values ​​are 0.033134, -0.074025, -0.080639, 0.039043, 0.10937, 0.69327, 0.028899, 0.064956, 0.056483, 0.0021449, and 0.20904, respectively.

[0065] S102. Determine the second operating parameter to be optimized for the target cooling water pump in the target HVAC system, and obtain the second power fitting equation for the target cooling water pump based on the second operating parameter to be optimized.

[0066] S103. Determine the third operating parameter to be optimized for the target chilled water pump in the target HVAC system, and obtain the third power fitting equation for the target chilled water pump based on the third operating parameter to be optimized.

[0067] The target cooling water pump refers to the cooling water pump equipment selected as the focus during the optimization process. The cooling water pump is a core component of the target HVAC system, responsible for circulating cooling water to help the target chiller unit dissipate heat. The target chilled water pump refers to the chilled water pump equipment selected as the key focus during the optimization process. The target chilled water pump is one of the core components of the system, responsible for circulating chilled water to the terminal equipment to absorb heat within the building, and then returning it to the target chiller unit for recooling.

[0068] The target cooling water pumps and target chilled water pumps can precisely control flow rates by adjusting pump speed, achieving soft starts, reducing peak current during motor startup, and helping to extend equipment lifespan. Furthermore, the target cooling water pumps and target chilled water pumps can dynamically adjust the chilled water supply according to changes in system load, ensuring a balance between cooling supply and demand, thereby reducing overall energy consumption. The performance of the target cooling water pumps and target chilled water pumps is closely related to parameters such as flow rate, head, and power, which together determine the pump's operating efficiency.

[0069] The second set of operating parameters to be optimized are adjustable operational variables in the target cooling water pump that directly affect its power consumption. Adjusting these parameters can change the operating state of the target cooling water pump, thus achieving energy efficiency optimization. The third set of operating parameters to be optimized are adjustable operational variables in the target chilled water pump that directly affect its power consumption. Adjusting these parameters can also change the operating state of the target chilled water pump, thereby achieving energy efficiency optimization.

[0070] The second operating parameter to be optimized includes the cooling water pump frequency, which refers to the frequency of the AC power supply driving the cooling water pump motor, and is adjusted by a frequency converter. This frequency directly controls the speed of the pump motor, thereby changing the cooling water flow rate, head, and energy consumption. The third operating parameter to be optimized includes the chilled water pump frequency, which refers to the frequency of the AC power supply driving the chilled water pump motor, and is adjusted by a frequency converter. This frequency directly controls the speed of the pump motor, thereby changing the chilled water flow rate, head, and energy consumption.

[0071] The second power fitting equation is a mathematical model describing the relationship between the power of the "target cooling water pump" and the "second operating parameter to be optimized." This equation is obtained by fitting historical operating data or experimental data and is used to predict the power value under different parameter values. Its core purpose is to quickly calculate the energy consumption contribution of the target cooling water pump during the optimization process without requiring real-time physical testing. The third power fitting equation is also a mathematical model describing the relationship between the power of the "target chilled water pump" and the "third operating parameter to be optimized." This equation is obtained by fitting historical operating data or experimental data and is used to predict the power value under different parameter values. Its core purpose is to quickly calculate the energy consumption contribution of the target chilled water pump during the optimization process without requiring real-time physical testing.

[0072] In one embodiment, the operating formulas for the target cooling water pump and the target chilled water pump (hereinafter collectively referred to as pumps) at the rated frequency include the flow-head equation, the flow-efficiency equation, and the power equation, as shown below:

[0073] ;

[0074] ;

[0075] ;

[0076] in, The rated head of the water pump, These are the parameters for fitting the flow-head characteristic curve. For pump efficiency, Set the flow rate for the water pump. The parameters are used to fit the flow-efficiency characteristic curve. For water pump power, This represents the actual head of the water pump.

[0077] When a water pump operates at a variable frequency, the relationship between its flow rate, head, power, and rated power is as shown in the following formula.

[0078] ;

[0079] in, For water pump frequency, This is the rated frequency of the water pump.

[0080] The pump frequency ratio, also known as the pump speed ratio, is n. Based on the above formula, the pump flow rate-head curve is shown below.

[0081] ;

[0082] Meanwhile, the operation of the water pump is also related to the pipe network impedance. The expression for the pipe network impedance in the target HVAC system is:

[0083] ;

[0084] in, For the target HVAC system equipment impedance, For the target HVAC system piping impedance, The impedance of the terminal pipes in the target HVAC system.

[0085] Therefore, the actual operating point of a water pump is the intersection of its flow-head characteristic curve and the pipeline characteristic curve. However, a water pump only has one characteristic curve, and its operating point can be solved by directly solving a set of equations. Furthermore, a water pump will have different characteristic curves when operating at different frequencies.

[0086] Substitute the target flow rate of the water pump into the pipeline characteristic curve equation to calculate the head of the current water pump operating point:

[0087] ;

[0088] Then, the current pump speed ratio is calculated:

[0089] ;

[0090] Finally, the energy consumption of the water pump is calculated based on the speed ratio.

[0091] ;

[0092] in, Where n is the rated power of the water pump and n is the pump speed ratio.

[0093] It can be seen that the power of the water pump at each moment is determined by the current water pump speed ratio, that is, by the current water pump frequency. Therefore, a water pump power-water pump frequency energy consumption model is established based on a quadratic polynomial, which yields the second power fitting equation for the target cooling water pump and the third power fitting equation for the target chilled water pump.

[0094] Optionally, a second power fitting equation corresponding to the target cooling water pump is obtained based on the second operating parameter to be optimized, including:

[0095] The second power fitting equation is expressed by the following equation:

[0096] ;

[0097] in, Indicates the cooling water pump power of the target cooling water pump; Indicates the frequency of the cooling water pump; Represents the fitting parameters. Optional. The values ​​are -0.002983, 0.97692, and 0.026095, respectively.

[0098] Optionally, a third power fitting equation corresponding to the target chilled water pump is obtained based on the third operating parameter to be optimized, including:

[0099] The third power fitting equation is expressed by the following equation:

[0100] ;

[0101] in, Indicates the chilled water pump power of the target chilled water pump; Indicates the frequency of the chilled water pump; Represents the fitting parameters. Optional. The values ​​are -0.0046777, 0.74826, and 0.266, respectively.

[0102] S104. Determine the fourth operating parameter to be optimized for the target cooling tower in the target HVAC system, and obtain the fourth power fitting equation for the target cooling tower based on the fourth operating parameter to be optimized.

[0103] Among them, the target cooling tower refers to the cooling tower equipment selected as the core of optimization in the target HVAC system. The target cooling tower promotes the contact between air and water by spraying cooling water and cooperating with a fan, so as to achieve effective heat dissipation and water temperature reduction.

[0104] The fourth set of operating parameters to be optimized is a set of adjustable variables that directly affect the performance and energy consumption of the target cooling tower. These parameters need to be dynamically adjusted through algorithms to minimize the energy consumption of the target cooling tower. The fourth set of operating parameters to be optimized includes the cooling tower frequency, which refers to the power frequency of the cooling tower fan motor adjusted by the frequency converter. This parameter directly controls the speed of the fan blades, thereby changing the cooling tower power.

[0105] In one implementation, the focus of the mechanistic model is on simulating the heat exchange between cooling water and air, with evaporative cooling being the primary heat dissipation method. To simplify the model, it is based on Brown's classical cooling tower heat transfer theory. The modeling process for the target cooling tower employs an iterative approximation method. First, the wet-bulb temperature of the air exiting the tower after heat exchange is assumed. Then, based on the temperature difference between the wet-bulb temperatures of the air at the inlet and outlet of the cooling tower, the heat absorbed by the air during the heat exchange process is determined by calculating the enthalpy difference, as shown in the following formula:

[0106] ;

[0107] in, Heat absorbed by the air The rated air volume of the fan. This is the enthalpy value of the moist air exiting the tower. This represents the enthalpy of the humid air entering the tower.

[0108] The enthalpy of moist air can be calculated using a fitting formula for wet-bulb temperature, as shown in the following equation.

[0109] ;

[0110] in, The wet-bulb temperature of the air. These are the fitting parameters.

[0111] The formula for calculating the heat exchange between water and air is shown below.

[0112] ;

[0113] in, It is used for water-air heat exchange.

[0114] Compare the heat exchange between water and air with the heat absorbed by the air. If the assumed wet-bulb temperature of the outlet air is too high, it needs to be lowered before calculation; conversely, if the assumed wet-bulb temperature of the outlet air is too low, the assumed wet-bulb temperature of the outlet air should be increased until... and If the error is within an acceptable range, the iteration ends.

[0115] It is evident that, for the target cooling tower, the current power is primarily determined by its power output. Therefore, a fourth power fitting equation is constructed based on the cooling tower frequency.

[0116] Optionally, a fourth power fitting equation corresponding to the target cooling tower is obtained based on the fourth operating parameter to be optimized, including:

[0117] The fourth power fitting equation is expressed by the following equation:

[0118] ;

[0119] in, Indicates the cooling tower power of the target cooling tower; Indicates the frequency of the cooling tower; This represents the fitted parameters.

[0120] S105. Based on the first power fitting equation, the second power fitting equation, the third power fitting equation, and the fourth power fitting equation, the total power fitting equation corresponding to the target HVAC system is obtained. Then, based on the first, second, third, and fourth operating parameters to be optimized, the parameters are integrated to obtain the global operating parameters to be optimized for the target HVAC system.

[0121] The total power fitting equation is a multivariate mathematical model that describes the quantitative relationship between the total power of the entire target HVAC system and all parameters to be optimized by superimposing the power equations of the target chiller, target cooling water pump, target chilled water pump and target cooling tower (the first to fourth power fitting equations).

[0122] Parameter integration refers to the process of merging the scattered first, second, third, and fourth operating parameters to be optimized into a unified vector. This resolves the coupling constraints between parameters of multiple devices and provides a feasible region for global optimization. The global operating parameters to be optimized are a multi-dimensional vector formed after parameter integration, containing all adjustable operating parameters. The optimization objective is to find the global operating parameters that minimize the total power corresponding to the total power fitting equation.

[0123] For example, suppose the first power fitting equation is: The second power fitting equation is: The third power fitting equation is The fourth power fitting equation is Then the total power fitting equation can be expressed as:

[0124] ;

[0125] For example, assuming the first running parameter to be optimized is represented as x1, the second running parameter to be optimized is represented as x2, the third running parameter to be optimized is represented as x3, and the fourth running parameter to be optimized is represented as x4, then the global running parameter to be optimized can be represented as x = [x1, x2, x3, x4].

[0126] S106. Optimize the total power fitting equation, determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and control the operation of the target HVAC system based on the target operating parameter value.

[0127] The optimization of the total power fitting equation refers to the process of using mathematical algorithms to search for the parameter combination that minimizes the total power fitting equation (i.e., minimizes the total power of the target HVAC system) within the feasible region of the globally unoptimized operating parameters. Essentially, it is solving a global minimum problem under multivariable constraints. The target operating parameter values ​​are the globally optimal solutions output by the optimization algorithm, representing the set of operating parameter values ​​that minimize the total energy consumption of the target HVAC system under the current operating conditions.

[0128] In one implementation, a target optimization algorithm is used to optimize the total power fitting equation, determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and control the operation of the target HVAC system based on the target operating parameter value.

[0129] This invention constructs power fitting equations for the target chiller, target cooling water pump, target chilled water pump, and target cooling tower in the target HVAC system, thereby obtaining the total power fitting equation and global operating parameters to be optimized for the target HVAC system. Finally, the optimization results of the total power fitting equation are used to determine the target operating parameter value corresponding to the global operating parameters to be optimized when the total power is minimized. The operation of the target HVAC system is controlled based on the target operating parameter value, thereby achieving the effect of optimizing the energy consumption of the HVAC system, filling a technological gap in the industry, and effectively reducing the energy consumption of the HVAC system.

[0130] Optionally, when there are multiple target chiller units, the total power fitting equation of the chiller units can be expressed as:

[0131] ;

[0132] in, This indicates the number of target chiller units that are in operation. This represents the chiller power of the i-th target chiller unit. This represents the load rate of the i-th target chiller unit. This refers to the rated cooling capacity of a single target chiller unit. It is the penalty coefficient. It is the target total cooling capacity of all target chiller units.

[0133] Target number of chiller units in operation Determined in the following manner:

[0134] ;

[0135] in, It is the target total cooling capacity of all target chiller units. This refers to the rated cooling capacity of a single target chiller unit. It is the maximum load rate that a single chiller unit is allowed to operate at.

[0136] Example 2

[0137] Figure 2 This is a flowchart of a method for optimizing the total power fitting equation according to Embodiment 2 of the present invention. This embodiment further optimizes and expands the above embodiment's "optimizing the total power fitting equation and determining the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is minimum", and can be combined with the above optional implementation methods. Figure 2 As shown, the method includes:

[0138] S201. Obtain the target fitness equation based on the total power fitting equation, and determine the parameter value constraint range corresponding to the global operating parameters to be optimized.

[0139] The target fitness equation is an evaluation function that transforms the total power fitting equation into a maximization problem; the two are inverse functions of each other. Its core function is to quantify the "energy-saving superiority" of any global operating parameter to be optimized, allowing the algorithm to directly seek the optimal solution. The target fitness equation and the total power fitting equation are inverse functions of each other. For example, the relationship between the target fitness equation f(x) and the total power fitting equation p(x) can be expressed as: f(x) = C / p(x), where C is a constant scaling factor.

[0140] The parameter value constraint range is the feasible domain boundary of the global operating parameters to be optimized. Optionally, the lower limit of chilled water outlet temperature is 7.5℃, and the upper limit is 9.5℃; the lower limit of chilled water return temperature is 10℃, and the upper limit is 16℃; the lower limit of cooling water outlet temperature is 27℃, and the upper limit is 30℃; the lower limit of cooling water return temperature is 25℃, and the upper limit is 30℃; the lower limit of chilled water pump frequency is 30Hz, and the upper limit is 46Hz; the lower limit of cooling pump frequency is 35Hz, and the upper limit is 50Hz; and the lower limit of cooling tower frequency is 25Hz, and the upper limit is 50Hz.

[0141] S202. Generate initial operating parameter values ​​based on the parameter value constraint range, and calculate the initial fitness value based on the initial operating parameter values ​​through the target fitness equation.

[0142] The initial operating parameter values ​​are the first set of feasible operating parameter values ​​generated based on the parameter value constraints when the optimization algorithm starts, representing the baseline operating state of the target HVAC system before optimization. The initial fitness value is the first fitness value calculated by substituting the initial operating parameter values ​​into the target fitness equation.

[0143] S203. The initial running parameter values ​​are processed by the artificial fish swarm algorithm to obtain the first updated running parameter values, and the first updated running parameter values ​​are processed by the differential evolution algorithm to obtain the second updated running parameter values.

[0144] The first updated running parameter value refers to the set of updated parameter values ​​obtained after applying the artificial fish swarm algorithm, representing the result of preliminary optimization from the initial parameter values ​​using the artificial fish swarm algorithm. It serves as an intermediate output of the algorithm flow, providing a starting point for subsequent differential evolution algorithms. The second updated running parameter value refers to the set of further updated parameter values ​​obtained after applying the differential evolution algorithm, representing the result of deep optimization from the "first updated running parameter values" using the differential evolution algorithm. It serves as a key output of the iterative process, used to calculate the "updated fitness value" and guide subsequent optimization.

[0145] S204. The updated fitness value is calculated by the target fitness equation based on the second updated running parameter value. The initial fitness value is updated according to the relationship between the updated fitness value and the initial fitness value to obtain the iterative fitness value.

[0146] The updated fitness value refers to the new fitness value calculated by substituting the second update running parameter value into the target fitness equation. Updating the initial fitness value refers to the process of selecting the better value to replace the original value by comparing the updated fitness value with the initial fitness value. The iterative fitness value refers to the current best fitness value retained after each complete iteration. It is the result of "updating the initial fitness value".

[0147] Optionally, the initial fitness value is updated based on the relationship between the updated fitness value and the initial fitness value to obtain the iterative fitness value, including:

[0148] Determine the maximum update fitness value among the update fitness values, and determine the maximum initial fitness value among the initial fitness values; if the maximum update fitness value is greater than the maximum initial fitness value, use the maximum update fitness value as the iteration fitness value.

[0149] The maximum updated fitness value refers to the maximum fitness value among all updated running parameter values ​​in the current iteration. The maximum initial fitness value refers to the maximum fitness value among all initial running parameter values ​​in the initial stage of the algorithm.

[0150] In one implementation, a maximum update fitness value is determined from the updated fitness values, and a maximum initial fitness value is determined from the initial fitness values. Further, the maximum update fitness value and the maximum initial fitness value are compared. If the maximum initial fitness value is greater than or equal to the maximum update fitness value, the maximum initial fitness value is kept unchanged and used as the iterative fitness value; if the maximum update fitness value is greater than the maximum initial fitness value, the maximum update fitness value is used as the iterative fitness value.

[0151] By determining the maximum updated fitness value among the updated fitness values, and the maximum initial fitness value among the initial fitness values; and by using the maximum updated fitness value as the iterative fitness value when the maximum updated fitness value is greater than the maximum initial fitness value, the following advantages are achieved:

[0152] Firstly, to avoid the degradation of solution quality due to random search during the optimization process, we ensure that the output of each iteration is better than or equal to the previous iteration, thus ensuring that the solution quality improves monotonically.

[0153] Secondly, when a newly generated solution falls into a locally degraded state due to random disturbances, the algorithm automatically reverts to the previous generation's optimal solution, thereby enhancing the algorithm's ability to resist interference.

[0154] S205. Based on the artificial fish swarm algorithm and the differential evolution algorithm, the second update running parameter value is iteratively processed, and when the iteration termination condition is met, the iteration fitness value corresponding to the last iteration is obtained as the maximum iteration fitness value.

[0155] The iterative process refers to the optimization process of repeatedly executing the artificial fish swarm algorithm, differential evolution algorithm, fitness value evaluation, and fitness value comparison and update based on the second updated running parameter values. The iteration termination condition refers to the preset rules for stopping the iteration, ensuring that the algorithm outputs a reliable solution within reasonable resources. The maximum iterative fitness value refers to the iterative fitness value retained in the last round when the iteration terminates, i.e., the historical maximum fitness value.

[0156] In one implementation, the second updated running parameter value is iteratively processed based on the artificial fish swarm algorithm and the differential evolution algorithm, and after each round of iteration, it is evaluated whether the iteration termination condition is met. The iteration termination condition includes, but is not limited to: the number of iterations reaches a preset threshold, and / or the fitness value is in a stable state.

[0157] If the iteration termination condition is met, the iteration fitness value corresponding to the last iteration is obtained as the maximum iteration fitness value, i.e., the historical maximum fitness value.

[0158] S206. Determine the optimal operating parameter value corresponding to the maximum iteration fitness value, and use it as the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest.

[0159] The optimal running parameter value refers to the set of global running parameter values ​​to be optimized when the algorithm iteration terminates, corresponding to the maximum iteration fitness value.

[0160] The target fitness equation is obtained by fitting the total power equation, and the parameter value constraint range corresponding to the global operating parameters to be optimized is determined. Initial operating parameter values ​​are generated based on the parameter value constraint range, and the initial fitness value is calculated using the target fitness equation based on the initial operating parameter values. The initial operating parameter values ​​are processed using the artificial fish swarm algorithm to obtain the first updated operating parameter value, and then processed using the differential evolution algorithm to obtain the second updated operating parameter value. The updated fitness value is calculated using the target fitness equation based on the second updated operating parameter value, and the initial fitness value is updated according to the relationship between the updated fitness value and the initial fitness value to obtain the iterative fitness value. The second updated operating parameter value is iteratively processed based on the artificial fish swarm algorithm and the differential evolution algorithm, and when the iteration termination condition is met, the iterative fitness value corresponding to the last iteration is obtained as the maximum iterative fitness value. The optimal operating parameter value corresponding to the maximum iterative fitness value is determined as the target operating parameter value corresponding to the global operating parameters to be optimized when the total power is minimum. The beneficial effects are:

[0161] Firstly, through iterative calculation, solutions with strong adaptability are selectively retained while solutions with poor adaptability are eliminated, thereby driving the search process to gradually approach the global optimal solution.

[0162] Secondly, this study combines the artificial fish swarm algorithm with differential evolution, leveraging the advantages of both. The introduction of differential evolution, on the one hand, expands the search space and maintains solution diversity, helping the artificial fish swarm algorithm escape local optima and facilitating the discovery of the global optimum; on the other hand, it enhances the algorithm's robustness and improves search efficiency by guiding the search direction. This hybrid strategy of artificial fish swarming and differential evolution encourages individuals to explore new solution spaces, effectively avoiding getting trapped in local optima while accelerating the convergence speed of the global optimum.

[0163] Example 3

[0164] Figure 3This is a flowchart of a method for generating a first updated running parameter value according to Embodiment 3 of the present invention. This embodiment further optimizes and expands the "processing of the initial running parameter value using an artificial fish swarm algorithm to obtain the first updated running parameter value" in the above embodiments, and can be combined with the above optional implementation methods. Figure 3 As shown, the method includes:

[0165] S301. The initial running parameter values ​​are processed by the foraging behavior operation in the artificial fish swarm algorithm to obtain the first potential running parameter values, and the first fitness value is calculated by the target fitness equation based on the first potential running parameter values.

[0166] Here, foraging behavior refers to simulating the process of fish randomly searching for food. The algorithm randomly generates new solutions near the initial operating parameter values ​​to explore unknown areas. The first potential operating parameter value refers to the new parameter value obtained after processing the initial operating parameter value by applying the foraging behavior operation. It represents a temporary optimization candidate solution and is the result of random exploration. The first fitness value refers to the value obtained by substituting the first potential operating parameter value into the target fitness equation. It quantifies the quality of the first potential operating parameter value; the higher the first fitness value, the better the first potential operating parameter value.

[0167] In one implementation, for the initial operating parameter values Process according to the following formula:

[0168] ;

[0169] Randomly select an operating parameter value from a position smaller than its field of vision. Calculate Then to Move one step in random direction:

[0170] ;

[0171] in, According to The calculated fitness value, According to The calculated fitness value.

[0172] Otherwise, randomly select a state again; after several attempts, if a state that meets the conditions is still not found... Then, randomly choose a direction and move one step:

[0173] .

[0174] S302. The initial running parameter values ​​are processed by the swarming behavior operation in the artificial fish swarm algorithm to obtain the second potential running parameter values, and the second fitness value is calculated by the target fitness equation based on the second potential running parameter values.

[0175] Among them, the swarming behavior operation refers to simulating the collective behavior of fish gathering together for safety or efficiency. It generates new solutions by calculating the average position of neighboring fish, avoiding individual isolation and accelerating convergence to a possible optimal region. The second potential operating parameter value refers to the new parameter value obtained after processing the initial operating parameter value by applying the swarming behavior operation. It represents a candidate solution generated based on group consensus, reflecting the algorithm's exploration of local optima. The second fitness value refers to the numerical value obtained by substituting the second potential operating parameter value into the target fitness equation. It evaluates the quality of the swarming solution; a high value indicates that the region may contain a global optimum or a relatively good solution.

[0176] In one implementation, for the initial running parameter value Artificial fish, in its neighborhood The number nf of other operating parameter values ​​within the range and the center position of all operating parameter values. Perform a search, if This means The area was not crowded and had a sufficient food concentration, so the operating parameter values ​​were adjusted towards... Move one step in the direction shown in the formula below; otherwise, perform a foraging behavior operation.

[0177] .

[0178] S303. The initial running parameter values ​​are processed by the tail-chasing behavior operation in the artificial fish swarm algorithm to obtain the third potential running parameter values, and the third fitness value is calculated by the target fitness equation based on the third potential running parameter values.

[0179] The "tail-chasing" behavior simulates the behavior of an individual fish in a school following a leading fish with higher fitness, focusing on the vicinity of known excellent solutions and avoiding ineffective searches. The third potential running parameter value is a new parameter value obtained by processing the initial running parameter value through the tail-chasing behavior. It represents a new candidate solution generated by following the best neighbor, aiming to quickly improve the solution by directly utilizing known information. The third fitness value is a numerical value obtained by substituting the third potential running parameter value into the target fitness equation. It quantifies the quality of the solution obtained through the following behavior; a high value indicates that the solution may be close to the global optimum.

[0180] In one implementation, for the initial running parameter value Artificial fish, in its neighborhood Search for the number of other operating parameter values ​​(nf) within the range and their fitness values, and find the operating parameter value with the smallest fitness value. ,if This indicates the running parameter value. The area was not crowded and had a sufficient food concentration, allowing the initial operating parameter values ​​to be... Follow the running parameter values Move one step in the direction as shown in the formula below; otherwise, perform a foraging behavior operation.

[0181] .

[0182] S304. Based on the relationship between the first fitness value, the second fitness value, and the third fitness value, determine the first update operating parameter value from the first potential operating parameter value, the second potential operating parameter value, and the third potential operating parameter value.

[0183] In one implementation, the size relationship between the first fitness value, the second fitness value, and the third fitness value is determined, and the potential running parameter value corresponding to the maximum fitness value is selected as the first update running parameter value according to the size relationship.

[0184] For example, if the first fitness value is determined to be the maximum fitness value based on the size relationship, then the first potential operating parameter value is determined to be the first updated operating parameter value; if the second fitness value is determined to be the maximum fitness value based on the size relationship, then the second potential operating parameter value is determined to be the first updated operating parameter value; if the third fitness value is determined to be the maximum fitness value based on the size relationship, then the third potential operating parameter value is determined to be the first updated operating parameter value.

[0185] The initial operating parameter values ​​are processed using the foraging behavior operation in the artificial fish swarm algorithm to obtain a first potential operating parameter value, and the first fitness value is calculated based on the first potential operating parameter value using the target fitness equation. The initial operating parameter values ​​are then processed using the swarming behavior operation in the artificial fish swarm algorithm to obtain a second potential operating parameter value, and the second fitness value is calculated based on the second potential operating parameter value using the target fitness equation. The initial operating parameter values ​​are then processed using the tailing behavior operation in the artificial fish swarm algorithm to obtain a third potential operating parameter value, and the third fitness value is calculated based on the third potential operating parameter value using the target fitness equation. Based on the relationship between the first, second, and third fitness values, a first updated operating parameter value is determined from the first, second, and third potential operating parameter values. The beneficial effects are:

[0186] Three behavioral operations cover the complete search logic, generating potential runtime parameter values ​​from different dimensions. By comparing the fitness values ​​of the three in real time, the algorithm can dynamically select the optimal direction to update the runtime parameter values, significantly reducing the risk of getting trapped in local optima, making it particularly suitable for complex multi-peak optimization problems.

[0187] Example 4

[0188] Figure 4 This is a flowchart of a second updated running parameter value generation method provided in Embodiment 4 of the present invention. This embodiment further optimizes and extends the above embodiment's "processing the first updated running parameter value using a differential evolution algorithm to obtain the second updated running parameter value," and can be combined with the above-mentioned optional implementation methods. For example... Figure 4 As shown, the method includes:

[0189] S401. The first updated running parameter value is processed by the mutation operation in the differential evolution algorithm to obtain the mutated running parameter value.

[0190] The mutation operation refers to generating a new solution by applying a differential perturbation to the first updated running parameter value. The mutated running parameter value refers to the intermediate candidate running parameter value generated through the mutation operation.

[0191] In one implementation, for the first updated running parameter value A new mutation runtime parameter value It can be generated through the following mutation equation:

[0192] ;

[0193] in, and It is a set of distinct integers randomly selected from the range [1,N], and each integer is different from the index i; the variation factor F is used to adjust the size of the difference vector.

[0194] S402. The first updated running parameter value and the mutated running parameter value are processed by the crossover operation in the differential evolution algorithm to obtain the experimental running parameter value.

[0195] The crossover operation refers to the process of mixing the mutated run parameter values ​​and the first updated run parameter values ​​to generate a composite solution. The test run parameter values ​​refer to the final candidate run parameter values ​​output by the crossover operation.

[0196] In one implementation, the crossover operation equation is:

[0197] ;

[0198] in, express A random integer within; It is a uniformly distributed random number on [1,D]; CR is the crossover probability, which takes values ​​in the interval (0,1).

[0199] S403. The experimental running parameter values ​​and the first updated running parameter values ​​are processed by the selection operation in the differential evolution algorithm to obtain the second updated running parameter values.

[0200] The selection operation refers to the operation of selecting and determining the second updated operating parameter value from the experimental operating parameter value and the first updated operating parameter value by comparing their respective fitness values.

[0201] The first updated running parameter value is processed by the mutation operation in the differential evolution algorithm to obtain the mutated running parameter value; the first updated running parameter value and the mutated running parameter value are processed by the crossover operation in the differential evolution algorithm to obtain the experimental running parameter value; the experimental running parameter value and the first updated running parameter value are processed by the selection operation in the differential evolution algorithm to obtain the second updated running parameter value. The beneficial effect is that, through the three-stage architecture of mutation, crossover and selection operations, efficient search is achieved while ensuring global convergence.

[0202] Optionally, the experimental running parameter values ​​and the first updated running parameter values ​​are processed through the selection operation in the differential evolution algorithm to obtain the second updated running parameter values, including:

[0203] S4031. The experimental fitness value is calculated using the target fitness equation based on the experimental operation parameter values, and the auxiliary fitness value is calculated using the target fitness equation based on the first update operation parameter values.

[0204] The experimental fitness value is a quantitative score calculated by substituting the experimental running parameter values ​​into the target fitness equation. The auxiliary fitness value is a quantitative score calculated by substituting the first updated running parameter values ​​into the same target fitness equation.

[0205] S4032. If the experimental fitness value is greater than the auxiliary fitness value, the experimental running parameter value shall be used as the second updated running parameter value.

[0206] S4033. If the auxiliary fitness value is greater than the experimental fitness value, the first update running parameter value shall be used as the second update running parameter value.

[0207] In one implementation, the experimental fitness value and the auxiliary fitness value are compared. If the experimental fitness value is greater than the auxiliary fitness value, the experimental running parameter value is used as the second updated running parameter value; if the auxiliary fitness value is greater than the experimental fitness value, the first updated running parameter value is used as the second updated running parameter value.

[0208] The experimental fitness value is calculated using the target fitness equation based on the experimental running parameter values, and the auxiliary fitness value is calculated using the target fitness equation based on the first updated running parameter values. If the experimental fitness value is greater than the auxiliary fitness value, the experimental running parameter value is used as the second updated running parameter value. If the auxiliary fitness value is greater than the experimental fitness value, the first updated running parameter value is used as the second updated running parameter value. The beneficial effect is that it ensures that the quality of the solution in each iteration does not decrease monotonically, thus mathematically avoiding the risk of population degradation.

[0209] Example 5

[0210] Figure 5 This is a schematic diagram of the structure of an energy consumption optimization device for a heating, ventilation, and air conditioning system provided in Embodiment 5 of the present invention. It is applicable to situations where energy consumption optimization is performed on the heating, ventilation, and air conditioning system in the auxiliary systems of a lithium battery manufacturing plant, such as... Figure 5 As shown, the device includes:

[0211] The first power fitting equation determination module 51 is used to determine the first operating parameters to be optimized for the target chiller unit in the target HVAC system, and to obtain the first power fitting equation for the target chiller unit based on the first operating parameters to be optimized.

[0212] The second power fitting equation determination module 52 is used to determine the second operating parameters to be optimized for the target cooling water pump in the target HVAC system, and to obtain the second power fitting equation for the target cooling water pump based on the second operating parameters to be optimized.

[0213] The third power fitting equation determination module 53 is used to determine the third operating parameter to be optimized for the target chilled water pump in the target HVAC system, and to obtain the third power fitting equation for the target chilled water pump based on the third operating parameter to be optimized.

[0214] The fourth power fitting equation determination module 54 is used to determine the fourth operating parameter to be optimized corresponding to the target cooling tower in the target HVAC system, and to obtain the fourth power fitting equation corresponding to the target cooling tower based on the fourth operating parameter to be optimized.

[0215] The global operating parameter determination module 55 is used to obtain the total power fitting equation corresponding to the target HVAC system based on the first power fitting equation, the second power fitting equation, the third power fitting equation, and the fourth power fitting equation, and to integrate the parameters based on the first operating parameter to be optimized, the second operating parameter to be optimized, the third operating parameter to be optimized, and the fourth operating parameter to be optimized to obtain the global operating parameters to be optimized corresponding to the target HVAC system.

[0216] The target operating parameter value determination module 56 is used to optimize the total power fitting equation, determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and control the operation of the target HVAC system based on the target operating parameter value.

[0217] Optionally, the target operating parameter value determination module 56 is specifically used for:

[0218] The target fitness equation is obtained based on the total power fitting equation, and the parameter value constraint range corresponding to the global operating parameters to be optimized is determined; wherein, the target fitness equation and the total power fitting equation are inverse functions of each other;

[0219] Initial operating parameter values ​​are generated based on the parameter value constraint range, and initial fitness values ​​are calculated based on the initial operating parameter values ​​using the target fitness equation.

[0220] The initial operating parameter values ​​are processed using an artificial fish swarm algorithm to obtain the first updated operating parameter values, and the first updated operating parameter values ​​are processed using a differential evolution algorithm to obtain the second updated operating parameter values.

[0221] The updated fitness value is calculated based on the second updated running parameter value using the target fitness equation. The initial fitness value is then updated based on the relationship between the updated fitness value and the initial fitness value to obtain the iterative fitness value.

[0222] The second updated running parameter value is iteratively processed based on the artificial fish swarm algorithm and the differential evolution algorithm, and when the iteration termination condition is met, the iteration fitness value corresponding to the last iteration is obtained as the maximum iteration fitness value.

[0223] The optimal operating parameter value corresponding to the maximum iteration fitness value is determined as the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest.

[0224] Optionally, the target operating parameter value determination module 56 is further used for:

[0225] The initial operating parameter values ​​are processed by the foraging behavior operation in the artificial fish swarm algorithm to obtain the first potential operating parameter values, and the first fitness value is calculated by the target fitness equation based on the first potential operating parameter values.

[0226] The initial operating parameter values ​​are processed by the swarming behavior operation in the artificial fish swarm algorithm to obtain the second potential operating parameter values, and the second fitness value is calculated by the target fitness equation based on the second potential operating parameter values.

[0227] The initial operating parameter values ​​are processed by the tail-chasing behavior operation in the artificial fish swarm algorithm to obtain the third potential operating parameter values, and the third fitness value is calculated by the target fitness equation based on the third potential operating parameter values.

[0228] Based on the relationship between the first fitness value, the second fitness value, and the third fitness value, the first updated operating parameter value is determined from the first potential operating parameter value, the second potential operating parameter value, and the third potential operating parameter value.

[0229] Optionally, the target operating parameter value determination module 56 is further used for:

[0230] The first updated running parameter value is processed by the mutation operation in the differential evolution algorithm to obtain the mutated running parameter value;

[0231] The first updated running parameter value and the mutated running parameter value are processed by the crossover operation in the differential evolution algorithm to obtain the experimental running parameter value;

[0232] The experimental running parameter value and the first updated running parameter value are processed by the selection operation in the differential evolution algorithm to obtain the second updated running parameter value.

[0233] Optionally, the target operating parameter value determination module 56 is further used for:

[0234] The experimental fitness value is calculated using the target fitness equation based on the experimental running parameter value, and the auxiliary fitness value is calculated using the target fitness equation based on the first updated running parameter value.

[0235] If the experimental fitness value is greater than the auxiliary fitness value, the experimental running parameter value is used as the second updated running parameter value;

[0236] If the auxiliary fitness value is greater than the experimental fitness value, the first update running parameter value is used as the second update running parameter value.

[0237] Optionally, the target operating parameter value determination module 56 is further used for:

[0238] Determine the maximum update fitness value among the updated fitness values, and determine the maximum initial fitness value among the initial fitness values;

[0239] If the maximum update fitness value is greater than the maximum initial fitness value, the maximum update fitness value is used as the iterative fitness value.

[0240] Optionally, the first operating parameter to be optimized includes at least one of chilled water outlet temperature, chilled water return temperature, cooling water outlet temperature, cooling water return temperature, and chiller unit cooling capacity;

[0241] The first power fitting equation determination module 51 is specifically used for:

[0242] The first power fitting equation is expressed by the following equation:

[0243] ;

[0244] Among them, the The chiller unit power of the target chiller unit; The temperature of the chilled water outlet is indicated; This represents the temperature difference of the chilled water obtained based on the chilled water outlet temperature and the chilled water return temperature; This represents the cooling water temperature difference obtained based on the cooling water outlet temperature and the cooling water return temperature; This indicates the cooling capacity of the chiller unit; This represents the fitted parameters.

[0245] Optionally, the second operating parameter to be optimized includes the cooling water pump frequency;

[0246] The second power fitting equation determination module 52 is specifically used for:

[0247] The second power fitting equation is expressed by the following equation:

[0248] ;

[0249] Among them, the This indicates the cooling water pump power of the target cooling water pump; the This indicates the frequency of the cooling water pump; This represents the fitted parameters.

[0250] Optionally, the third operating parameter to be optimized includes the chilled water pump frequency;

[0251] The third power fitting equation determination module 53 is specifically used for:

[0252] The third power fitting equation is expressed by the following equation:

[0253] ;

[0254] Among them, the This indicates the chilled water pump power of the target chilled water pump; Indicates the frequency of the chilled water pump; This represents the fitted parameters.

[0255] Optionally, the fourth operating parameter to be optimized includes the cooling tower frequency;

[0256] The fourth power fitting equation determination module 54 is specifically used for:

[0257] The fourth power fitting equation is expressed by the following equation:

[0258] ;

[0259] Among them, the The cooling tower power of the target cooling tower is indicated; Indicates the frequency of the cooling tower; This represents the fitted parameters.

[0260] The energy consumption optimization device for HVAC systems provided in this embodiment of the invention can execute the energy consumption optimization method for HVAC systems provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0261] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0262] Example 6

[0263] Figure 6 A schematic diagram of an electronic device 60 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0264] like Figure 6 As shown, the electronic device 60 includes at least one processor 61 and a memory, such as a read-only memory (ROM) 62 and a random access memory (RAM) 63, communicatively connected to the at least one processor 61. The memory stores computer programs executable by the at least one processor. The processor 61 can perform various appropriate actions and processes based on the computer program stored in the ROM 62 or loaded from storage unit 68 into the RAM 63. The RAM 63 can also store various programs and data required for the operation of the electronic device 60. The processor 61, ROM 62, and RAM 63 are interconnected via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0265] Multiple components in electronic device 60 are connected to I / O interface 65, including: input unit 66, such as keyboard, mouse, etc.; output unit 67, such as various types of monitors, speakers, etc.; storage unit 68, such as disk, optical disk, etc.; and communication unit 69, such as network card, modem, wireless transceiver, etc. Communication unit 69 allows electronic device 60 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0266] Processor 61 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 61 performs the various methods and processes described above, such as energy consumption optimization methods for HVAC systems.

[0267] In some embodiments, the energy consumption optimization method for a heating, ventilation, and air conditioning (HVAC) system can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 68. In some embodiments, part or all of the computer program can be loaded into and / or installed on an electronic device 60 via ROM 62 and / or communication unit 69. When the computer program is loaded into RAM 63 and executed by processor 61, one or more steps of the energy consumption optimization method for an HVAC system described above can be performed. Alternatively, in other embodiments, processor 61 can be configured to perform the energy consumption optimization method for an HVAC system by any other suitable means (e.g., by means of firmware).

[0268] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0269] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0270] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0271] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0272] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0273] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0274] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0275] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for optimizing energy consumption in a heating, ventilation, and air conditioning (HVAC) system, characterized in that, The method includes: Determine the first operating parameters to be optimized for the target chiller unit in the target HVAC system, and obtain the first power fitting equation for the target chiller unit based on the first operating parameters to be optimized; Determine the second operating parameter to be optimized for the target cooling water pump in the target HVAC system, and obtain the second power fitting equation for the target cooling water pump based on the second operating parameter to be optimized. The third operating parameter to be optimized for the target chilled water pump in the target HVAC system is determined, and the third power fitting equation corresponding to the target chilled water pump is obtained based on the third operating parameter to be optimized. Determine the fourth operating parameter to be optimized for the target cooling tower in the target HVAC system, and obtain the fourth power fitting equation for the target cooling tower based on the fourth operating parameter to be optimized; Based on the first power fitting equation, the second power fitting equation, the third power fitting equation, and the fourth power fitting equation, the total power fitting equation corresponding to the target HVAC system is obtained. Then, based on the first operating parameter to be optimized, the second operating parameter to be optimized, the third operating parameter to be optimized, and the fourth operating parameter to be optimized, the global operating parameters to be optimized corresponding to the target HVAC system are integrated to obtain the global operating parameters to be optimized for the target HVAC system. The total power fitting equation is optimized to determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and the operation of the target HVAC system is controlled based on the target operating parameter value.

2. The method according to claim 1, characterized in that, The optimization of the total power fitting equation to determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is minimized includes: The target fitness equation is obtained based on the total power fitting equation, and the parameter value constraint range corresponding to the global operating parameters to be optimized is determined; wherein, the target fitness equation and the total power fitting equation are inverse functions of each other; Initial operating parameter values ​​are generated based on the parameter value constraint range, and initial fitness values ​​are calculated based on the initial operating parameter values ​​using the target fitness equation. The initial operating parameter values ​​are processed using an artificial fish swarm algorithm to obtain the first updated operating parameter values, and the first updated operating parameter values ​​are processed using a differential evolution algorithm to obtain the second updated operating parameter values. The updated fitness value is calculated based on the second updated running parameter value using the target fitness equation. The initial fitness value is then updated based on the relationship between the updated fitness value and the initial fitness value to obtain the iterative fitness value. The second updated running parameter value is iteratively processed based on the artificial fish swarm algorithm and the differential evolution algorithm, and when the iteration termination condition is met, the iteration fitness value corresponding to the last iteration is obtained as the maximum iteration fitness value. The optimal operating parameter value corresponding to the maximum iteration fitness value is determined as the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest.

3. The method according to claim 2, characterized in that, The step of processing the initial operating parameter values ​​using the artificial fish swarm algorithm to obtain the first updated operating parameter values ​​includes: The initial operating parameter values ​​are processed by the foraging behavior operation in the artificial fish swarm algorithm to obtain the first potential operating parameter values, and the first fitness value is calculated by the target fitness equation based on the first potential operating parameter values. The initial operating parameter values ​​are processed by the swarming behavior operation in the artificial fish swarm algorithm to obtain the second potential operating parameter values, and the second fitness value is calculated by the target fitness equation based on the second potential operating parameter values. The initial operating parameter values ​​are processed by the tail-chasing behavior operation in the artificial fish swarm algorithm to obtain the third potential operating parameter values, and the third fitness value is calculated by the target fitness equation based on the third potential operating parameter values. Based on the relationship between the first fitness value, the second fitness value, and the third fitness value, the first updated operating parameter value is determined from the first potential operating parameter value, the second potential operating parameter value, and the third potential operating parameter value.

4. The method according to claim 2, characterized in that, The step of processing the first updated running parameter value using the differential evolution algorithm to obtain the second updated running parameter value includes: The first updated running parameter value is processed by the mutation operation in the differential evolution algorithm to obtain the mutated running parameter value; The first updated running parameter value and the mutated running parameter value are processed by the crossover operation in the differential evolution algorithm to obtain the experimental running parameter value; The experimental running parameter value and the first updated running parameter value are processed by the selection operation in the differential evolution algorithm to obtain the second updated running parameter value.

5. The method according to claim 4, characterized in that, The step of processing the experimental running parameter values ​​and the first updated running parameter values ​​through the selection operation in the differential evolution algorithm to obtain the second updated running parameter values ​​includes: The experimental fitness value is calculated using the target fitness equation based on the experimental running parameter value, and the auxiliary fitness value is calculated using the target fitness equation based on the first updated running parameter value. If the experimental fitness value is greater than the auxiliary fitness value, the experimental running parameter value is used as the second updated running parameter value; If the auxiliary fitness value is greater than the experimental fitness value, the first update running parameter value is used as the second update running parameter value.

6. The method according to claim 2, characterized in that, Based on the relationship between the updated fitness value and the initial fitness value, the initial fitness value is updated to obtain an iterative fitness value, including: Determine the maximum update fitness value among the updated fitness values, and determine the maximum initial fitness value among the initial fitness values; If the maximum update fitness value is greater than the maximum initial fitness value, the maximum update fitness value is used as the iterative fitness value.

7. The method according to claim 1, characterized in that, The first operating parameter to be optimized includes at least one of chilled water outlet temperature, chilled water return temperature, cooling water outlet temperature, cooling water return temperature, and chiller unit cooling capacity; The step of obtaining the first power fitting equation corresponding to the target chiller unit based on the first operating parameters to be optimized includes: The first power fitting equation is expressed by the following equation: ； Among them, the The chiller unit power of the target chiller unit; The temperature of the chilled water outlet is indicated; This represents the temperature difference of the chilled water obtained based on the chilled water outlet temperature and the chilled water return temperature; This represents the cooling water temperature difference obtained based on the cooling water outlet temperature and the cooling water return temperature; This indicates the cooling capacity of the chiller unit; This represents the fitted parameters.

8. The method according to claim 1, characterized in that, The second operating parameter to be optimized includes the cooling water pump frequency; The step of obtaining the second power fitting equation corresponding to the target cooling water pump based on the second operating parameters to be optimized includes: The second power fitting equation is expressed by the following equation: ； Among them, the This indicates the cooling water pump power of the target cooling water pump; the This indicates the frequency of the cooling water pump; This represents the fitted parameters.

9. The method according to claim 1, characterized in that, The third operating parameter to be optimized includes the chilled water pump frequency; The step of obtaining the third power fitting equation corresponding to the target chilled water pump based on the third operating parameter to be optimized includes: The third power fitting equation is expressed by the following equation: ； Among them, the This indicates the chilled water pump power of the target chilled water pump; Indicates the frequency of the chilled water pump; This represents the fitted parameters.

10. The method according to claim 1, characterized in that, The fourth operating parameter to be optimized includes the cooling tower frequency; The step of obtaining the fourth power fitting equation corresponding to the target cooling tower based on the fourth operating parameter to be optimized includes: The fourth power fitting equation is expressed by the following equation: ； Among them, the The cooling tower power of the target cooling tower is indicated; Indicates the frequency of the cooling tower; This represents the fitted parameters.

11. An energy consumption optimization device for a heating, ventilation, and air conditioning system, characterized in that, The device includes: The first power fitting equation determination module is used to determine the first operating parameters to be optimized for the target chiller unit in the target HVAC system, and to obtain the first power fitting equation for the target chiller unit based on the first operating parameters to be optimized. The second power fitting equation determination module is used to determine the second operating parameter to be optimized corresponding to the target cooling water pump in the target HVAC system, and to obtain the second power fitting equation corresponding to the target cooling water pump based on the second operating parameter to be optimized. The third power fitting equation determination module is used to determine the third operating parameter to be optimized for the target chilled water pump in the target HVAC system, and to obtain the third power fitting equation for the target chilled water pump based on the third operating parameter to be optimized. The fourth power fitting equation determination module is used to determine the fourth operating parameter to be optimized corresponding to the target cooling tower in the target HVAC system, and to obtain the fourth power fitting equation corresponding to the target cooling tower based on the fourth operating parameter to be optimized. The global operating parameter determination module is used to obtain the total power fitting equation corresponding to the target HVAC system based on the first power fitting equation, the second power fitting equation, the third power fitting equation, and the fourth power fitting equation, and to integrate the parameters based on the first operating parameter to be optimized, the second operating parameter to be optimized, the third operating parameter to be optimized, and the fourth operating parameter to be optimized to obtain the global operating parameters to be optimized corresponding to the target HVAC system. The target operating parameter value determination module is used to optimize the total power fitting equation, determine the target operating parameter value corresponding to the global operating parameter to be optimized when the total power is the lowest, and control the operation of the target HVAC system based on the target operating parameter value.

12. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to perform the method of any one of claims 1-10.

14. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-10.

Images