Energy storage air conditioner, control method and device thereof and computer readable storage medium

Abstract

The embodiment of the invention provides an energy storage air conditioner, a control method and device of the energy storage air conditioner and a computer readable storage medium. The control method of the energy storage air conditioner comprises the steps that the Pareto boundary of the energy storage air conditioner is determined based on a multi-objective optimization model of the energy storage air conditioner and an NSGA-II algorithm; determining a weighted optimization effect of each Pareto optimal solution in the Pareto boundary based on a weight decision algorithm, and taking the Pareto optimal solution with the highest weighted optimization effect as an optimal solution of the Pareto boundary; and the energy storage air conditioner is controlled to operate according to the operation parameters in the optimal solution of the Pareto boundary.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioners, and in particular to an energy storage air conditioner and a control method, device, and computer-readable storage medium thereof. Background Art

[0002] Some energy storage air conditioners operate in areas with drastic temperature changes, such as large temperature differences between day and night, and require multiple adjustments to the operating conditions of the energy storage air conditioners in a short period of time. The control methods in related technologies are relatively rough, and the energy storage air conditioners cannot adjust the operating conditions in time with real-time environmental changes, so they are prone to deviate from the optimal operating conditions, resulting in low energy efficiency and high power consumption of the energy storage air conditioners. Summary of the invention

[0003] The embodiments of the present application provide an energy storage air conditioner and a control method, device, and computer-readable storage medium thereof, which can quickly adjust the operating parameters of the energy storage air conditioner according to real-time environmental changes, so that the energy storage air conditioner always operates in the optimal working condition, thereby reducing the operating power consumption of the energy storage air conditioner and improving the operating energy efficiency of the energy storage air conditioner.

[0004] In a first aspect, an embodiment of the present application provides a method for controlling an energy storage air conditioner, comprising: determining the Pareto frontier of the energy storage air conditioner based on a multi-objective optimization model of the energy storage air conditioner and an NSGA-II algorithm; determining the weighted optimization effect of each Pareto optimal solution in the Pareto frontier based on a weighted decision algorithm, and taking the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto frontier; and controlling the operation of the energy storage air conditioner according to the operating parameters in the optimal solution of the Pareto frontier.

[0005] In some embodiments, the weighted optimization effect of each Pareto optimal solution in the Pareto frontier is determined based on a weighted decision algorithm, and the Pareto optimal solution with the highest weighted optimization effect is used as the optimal solution of the Pareto frontier, including: constructing a decision matrix according to the overall objective function of the Pareto frontier; normalizing the decision matrix to obtain a normalized decision matrix; determining the weight value of each of the overall objective functions according to the normalized decision matrix; determining the weighted optimization effect matrix of the Pareto frontier according to the weight value and the normalized decision matrix, each individual in the weighted optimization effect matrix represents the weighted optimization effect of a Pareto optimal solution; sorting the individuals in the weighted optimization effect matrix of the Pareto frontier in descending order, and taking the individual ranked first after sorting as the optimal solution of the Pareto frontier.

[0006] In some embodiments, the weight value of each of the entire objective functions is determined according to the normalized decision matrix, including: determining the divergence value of each of the entire objective functions according to the normalized decision matrix; determining the entropy weight of the objective function according to the divergence value of the objective function, and using the entropy weight as the weight value of the objective function.

[0007] In some embodiments, the Pareto frontier of the energy storage air conditioner is determined based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm, including: randomly generating an initial population according to the multi-objective optimization model; performing the following iterative operations on the initial population: performing proportional selection, crossover and mutation on individuals in the initial population to obtain a parent population and a child population; merging the parent population and the child population, and performing elite competition on the individuals in the merged population to obtain an elite population, wherein the number of individuals in the elite population is consistent with that in the initial population; in response to determining that the current number of iterations is less than the maximum number of iterations, updating the initial population according to the elite population; in response to determining that the current number of iterations is equal to the maximum number of iterations, using the elite population as the Pareto frontier of the energy storage air conditioner.

[0008] In some embodiments, individuals in the initial population are subjected to proportional selection, crossover and mutation to obtain a parent population and a child population, including: determining a non-dominated level and a crowding degree of each individual in the initial population; selecting excellent individuals in the initial population according to the non-dominated level and the crowding degree, and forming a parent population with the excellent individuals; and performing crossover and mutation on the parent population to obtain a child population.

[0009] In some embodiments, selecting excellent individuals in the initial population according to the non-dominated level and the crowding degree includes: selecting excellent individuals in the initial population according to the non-dominated level and the crowding degree based on a binary bidding method.

[0010] In some embodiments, before determining the Pareto boundary of the energy storage air conditioner based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm, the energy storage air conditioner control method includes: establishing a multi-objective optimization model of the energy storage air conditioner according to the objective function and decision variables of the energy storage air conditioner.

[0011] In a second aspect, an embodiment of the present application provides a control device for an energy storage air conditioner, comprising: a multi-objective optimization genetic circuit, configured to determine the Pareto boundary of the energy storage air conditioner based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm; a weight decision circuit, configured to determine the weighted optimization effect of each Pareto optimal solution in the Pareto boundary based on the weight decision algorithm, and to use the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto boundary; and an operation control circuit, configured to control the operation of the energy storage air conditioner according to the operating parameters in the optimal solution of the Pareto boundary.

[0012] In a third aspect, an embodiment of the present application provides an energy storage air conditioner, comprising: a memory storing a computer program; and a processor, wherein when the computer program is executed by the processor, the energy storage air conditioner control method as described in any of the above embodiments is implemented.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is loaded by a processor to execute the steps in the above-described energy storage air conditioner control method.

[0014] The energy storage air conditioner control method provided in the embodiment of the present application can quickly determine the Pareto optimal solutions of multiple optimization objectives according to real-time environmental changes, and weightedly sort the optimization effects of all the obtained Pareto optimal solutions based on the weighted decision algorithm, and then determine the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto boundary, so that the energy storage air conditioner always operates in the best operating conditions that match the real-time environmental changes, thereby effectively reducing the operating power consumption of the energy storage air conditioner and improving the operating energy efficiency of the energy storage air conditioner. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 is a flow chart of a method for controlling an energy storage air conditioner provided in some embodiments of the present application;

[0017] Figure 2 is a partial flow chart of a method for controlling an energy storage air conditioner provided in some embodiments of the present application;

[0018] Figure 3 is another partial flow chart of the energy storage air conditioner control method provided by some embodiments of the present application;

[0019] Figure 4 is another partial flow chart of the energy storage air conditioner control method provided in some embodiments of the present application;

[0020] Figure 5 is another partial flow chart of the energy storage air conditioner control method provided in some embodiments of the present application;

[0021] Figure 6 is a structural diagram of an energy storage air conditioner provided in some embodiments of the present application;

[0022] Figure 7 This is a flow path structure diagram of the energy storage air conditioner provided in some embodiments of the present application when performing cooling.

[0023] Description of main component symbols:

[0024] 1-energy storage air conditioner, 10-processor, 20-memory, 30-refrigerant circuit, 31-compressor, 32-condenser, 33-electronic expansion valve, 34-first temperature sensor, 40-refrigerant circuit, 41-refrigerant circulation pump, 42-main flow, 43-natural cooling bypass, 431-natural cooling heat exchanger, 44-three-way stop valve, 45-electric heater, 46-second temperature sensor, 50-water side heat exchanger, 60-outdoor fan. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0027] “A and / or B” includes the following three combinations: A only, B only, and a combination of A and B.

[0028] The use of "suitable for" or "configured to" in this application is meant to be open and inclusive language, which does not exclude devices that are suitable for or configured to perform additional tasks or steps. In addition, the use of "based on" is meant to be open and inclusive, because the process, step, calculation or other action "based on" one or more stated conditions or values ​​can be based on additional conditions or values ​​beyond the stated values ​​in practice.

[0029] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0030] like Figure 1 As shown, in the first aspect, an embodiment of the present application provides a method for controlling an energy storage air conditioner, which includes S10 to S30, and can quickly adjust the operating parameters of the energy storage air conditioner 1 according to real-time environmental changes, so that the energy storage air conditioner 1 always operates in the optimal working condition, thereby reducing the operating power consumption of the energy storage air conditioner 1 and improving the operating energy efficiency of the energy storage air conditioner 1.

[0031] S10: Determine the Pareto frontier of the energy storage air conditioner 1 based on the multi-objective optimization model of the energy storage air conditioner 1 and the NSGA-II algorithm.

[0032] NSGA-II algorithm (Non-dominated Sorting Genetic Algorithms) is a multi-objective genetic algorithm with the advantages of fast running speed and good convergence. Here, according to the characteristics of the NSGA-II algorithm, a multi-objective optimization model of the energy storage air conditioner 1 can be established in advance. The multi-objective optimization model can set multiple optimization objectives of the energy storage air conditioner 1, and use the various parameters required for optimizing the above multiple optimization objectives based on the NSGA-II algorithm as decision variables, and set multiple objective functions for optimizing the above optimization objectives based on the above decision variables. The various parameters may include parameter types such as real-time environmental parameters and real-time operating parameters of the energy storage air conditioner 1. During the operation of the energy storage air conditioner 1, the decision variables in the multi-objective optimization model can be updated according to real-time data; when receiving new real-time data, troubleshooting such as manual maintenance and intelligent alarm can be performed first, and then the received real-time data can be optimized after troubleshooting.

[0033] The type of optimization target can be determined according to actual needs, and may include, for example, the energy efficiency ratio of the energy storage air conditioner 1, the total operating power consumption, etc., which is not limited in the embodiments of the present application; in some embodiments, multiple optimization targets may include the energy efficiency ratio and total operating power consumption of the energy storage air conditioner 1.

[0034] The type of decision variable can be determined according to actual needs, and this embodiment of the present application does not limit this. Figure 7 As shown, in some embodiments, the energy storage air conditioner 1 may include a refrigerant circuit 30, a coolant circuit 40 and an outdoor fan 60. The refrigerant circuit 30 and the coolant circuit 40 are connected for heat exchange via a water-side heat exchanger 50. The refrigerant circuit 30 is provided with a compressor 31, a condenser 32 and an electronic expansion valve 33, and the outdoor fan 60 and the condenser 32 are correspondingly arranged; the coolant circuit 40 is provided with a coolant circulation pump 41, which is used to drive the coolant to circulate in the coolant circuit 40. Here, the decision variables may include outdoor ambient temperature, refrigerant mass flow rate, outdoor fan air volume / outdoor fan speed, suction pressure and exhaust pressure of compressor 31, suction temperature and exhaust temperature of compressor 31, condenser outlet temperature and refrigerant inlet temperature of water side heat exchanger 50; exemplarily, the outdoor ambient temperature can be determined by real-time measurement by a temperature sensor arranged on the outdoor side, the refrigerant mass flow rate can be determined by real-time measurement by a flowmeter arranged in the refrigerant circuit 40, the condenser outlet temperature can be regarded as the temperature of the refrigerant when it flows out of the condenser 32, and can be determined by real-time measurement by a temperature sensor arranged at the refrigerant outlet end of the condenser 32, and the refrigerant inlet temperature of the water side heat exchanger 50 can be regarded as the temperature before the refrigerant enters the water side heat exchanger 50, and can be determined by real-time measurement by a temperature sensor arranged at the refrigerant inlet end of the water side heat exchanger 50.

[0035] The Pareto frontier of the energy storage air conditioner 1 can be determined by solving the multi-objective optimization model based on the NSGA-II algorithm. Here, the Pareto frontier of the energy storage air conditioner 1 refers to the set of all Pareto optimal solutions obtained by optimizing the above-mentioned multiple optimization objectives. The Pareto frontier includes multiple Pareto optimal solutions, each of which includes multiple objective functions, and the multiple objective functions are equal in number to the above-mentioned multiple optimization objectives and have a one-to-one correspondence, and each objective function is used to optimize an optimization objective. The optimization effect of each Pareto optimal solution on at least one optimization objective is better than that of other Pareto optimal solutions, and the optimization effect on other optimization objectives is equivalent to or inferior to that of other Pareto optimal solutions; in other words, among the multiple objective functions included in each Pareto optimal solution, the optimization effect of at least one objective function on the corresponding optimization objective is better than that of the same objective function in other Pareto optimal solutions, that is, the optimal objective function corresponding to the current real-time environmental conditions and a certain optimization objective, and the optimization effect of the remaining objective functions on the corresponding optimization objectives is equivalent to or inferior to the same objective functions in other Pareto optimal solutions. After the Pareto optimal solution is determined, the coefficients of each objective function included in the Pareto optimal solution and the best operating parameters on the optimization target corresponding to the optimal objective function can be determined, which are the operating parameters in the Pareto optimal solution.

[0036] S20: Determine the weighted optimization effect of each Pareto optimal solution in the Pareto frontier based on the weighted decision algorithm, and take the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto frontier.

[0037] The weighted decision algorithm can be pre-set in the control system of the energy storage air conditioner 1 to determine the weighted optimization effect of each Pareto optimal solution in the Pareto boundary. Here, based on the weighted decision algorithm, the weight values ​​of all objective functions in each Pareto optimal solution in the Pareto boundary can be determined first, and then the weighted optimization effect of the Pareto optimal solution on the energy storage air conditioner 1 is weightedly calculated according to each objective function and its weight value in the same Pareto optimal solution, and the Pareto optimal solution with the highest weighted optimization effect in the Pareto boundary is determined. After determining the Pareto optimal solution with the highest weighted optimization effect in the Pareto boundary, the Pareto optimal solution can be used as the optimal solution of the Pareto boundary. The optimal solution of the Pareto boundary thus obtained has a significantly better comprehensive optimization effect on the energy storage air conditioner 1 under the current real-time environmental conditions than any other Pareto optimal solution, so that the best optimization effect can be achieved under the current real-time environmental changes.

[0038] S30: Controlling the operation of the energy storage air conditioner 1 according to the operating parameters in the optimal solution.

[0039] After determining the optimal solution of the Pareto boundary, the operation of the energy storage air conditioner 1 can be controlled according to the operating parameters in the optimal solution, so that the energy storage air conditioner 1 can quickly adjust to the optimal operating condition matching the real-time environmental changes according to the real-time environmental changes, so that the energy storage air conditioner 1 has lower operating energy consumption and higher operating energy efficiency under real-time environmental conditions, thereby achieving better high-efficiency and energy-saving operation effects.

[0040] Compared with the related art, the energy storage air conditioner control method provided in the embodiment of the present application can quickly determine the Pareto optimal solutions of multiple optimization objectives according to real-time environmental changes, and weightedly sort the optimization effects of all the obtained Pareto optimal solutions based on the weight decision algorithm, and then determine the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto boundary, so that the energy storage air conditioner 1 always operates in the optimal operating conditions that match the real-time environmental changes, thereby effectively reducing the operating power consumption of the energy storage air conditioner 1 and improving the operating energy efficiency of the energy storage air conditioner 1.

[0041] like Figure 2 As shown, in some embodiments, S20 may include S21-S25.

[0042] S21: Construct a decision matrix based on the overall objective function of the Pareto frontier.

[0043] Here, each Pareto optimal solution in the Pareto frontier corresponds to a different objective function, and the overall objective function of the Pareto frontier is the set of objective functions corresponding to each Pareto optimal solution in the Pareto frontier. Based on the set of objective functions, a decision matrix can be constructed, and each individual in the decision matrix is ​​an objective function.

[0044] S22: Normalize the decision matrix to obtain a normalized decision matrix.

[0045] Here, normalizing the decision matrix means changing each individual in the decision matrix into a decimal between (0, 1), thereby obtaining a normalized form of the decision matrix, i.e., a normalized decision matrix. Accordingly, each individual in the normalized decision matrix is ​​a normalized form of an objective function.

[0046] Exemplarily, the decision matrix can be normalized according to the following formula:

[0047]

[0048]

[0049] Among them, R ij is the decision matrix, r ij is the jth objective function of the ith Pareto optimal solution in the Pareto frontier; ij is the normalized decision matrix, pij For r ij The normalized form of .

[0050] S23: Determine the weight value of each of the overall objective functions according to the normalized decision matrix.

[0051] After obtaining the normalized decision matrix, the weight values ​​of the above-mentioned various objective functions can be determined according to the normalized decision matrix; in this way, the weight values ​​of each objective function in each Pareto optimal solution are determined. Here, the specific calculation method for determining the weight values ​​of each objective function according to the normalized decision matrix can be determined according to actual needs, and the embodiments of the present application are not limited to this.

[0052] S24: Determine a weighted optimization effect matrix of the Pareto frontier according to the weight values ​​and the normalized decision matrix.

[0053] Here, each individual in the weighted optimization effect matrix of the Pareto frontier corresponds to a Pareto optimal solution in the Pareto frontier, and each individual can represent the weighted optimization effect of the Pareto optimal solution corresponding to the individual. Exemplarily, a weight matrix can be constructed according to the weight values ​​of each in the overall objective function, and then the product matrix of the normalized decision matrix and the weight matrix can be obtained, and the product matrix is ​​used as the weighted optimization effect matrix of the Pareto frontier.

[0054] S25: Sort the individuals in the weighted optimization effect matrix of the Pareto frontier in descending order, and take the individual that ranks first after sorting as the optimal solution of the Pareto frontier.

[0055] All individuals in the weighted optimization effect matrix of the Pareto frontier are sorted in descending order from large to small according to the numerical value. The Pareto optimal solution corresponding to the individual ranked first after sorting is the Pareto optimal solution with the highest weighted optimization effect in the Pareto frontier, so that the Pareto optimal solution can be used as the optimal solution of the Pareto frontier.

[0056] By setting S21~S25, the weight value of each objective function in each Pareto optimal solution can be determined more accurately, and then the weighted optimization effect of each Pareto optimal solution on the energy storage air conditioner can be calculated according to each objective function and its weight value. Therefore, the Pareto optimal solution with the highest weighted optimization effect can be accurately used as the optimal solution of the Pareto boundary, which significantly improves the control accuracy of the energy storage air conditioner and ensures that the energy storage air conditioner always operates in the best operating conditions that match the real-time environmental changes.

[0057] like Figure 3 As shown, in some examples, S23 may include S231-S232.

[0058] S231: Determine the divergence value of each of the entire objective functions according to the normalized decision matrix.

[0059] Here, the information entropy of each objective function can be determined according to the normalized decision matrix, and the sum of the information entropy and the divergence value of the objective function is 1, so the divergence value of the objective function is equal to the difference between 1 and the information entropy of the objective function. Exemplarily, the divergence value of the objective function can be determined in sequence according to the following formulas:

[0060]

[0061] Among them, d ij is the divergence value of the objective function, P ij is the normalized decision matrix.

[0062] S232: Determine the entropy weight of the objective function according to the divergence value of the objective function, and use the entropy weight as the weight value of the objective function.

[0063] Here, the sum of the divergence values ​​of all objective functions may be determined first, and the entropy weight of each objective function is equal to the quotient of the divergence value of the objective function and the sum of the divergence values ​​of all objective functions. Exemplarily, the weight values ​​of the objective functions may be determined in sequence according to the following formula:

[0064]

[0065] Among them, w j is the weight value of the objective function.

[0066] By setting S231~S232, the weight value of each objective function in each Pareto optimal solution can be determined more accurately, and then the weighted optimization effect of each Pareto optimal solution on the energy storage air conditioner 1 can be calculated according to each objective function and its weight value, so that the Pareto optimal solution with the highest weighted optimization effect can be accurately used as the optimal solution of the Pareto boundary, which significantly improves the control accuracy of the energy storage air conditioner 1 and ensures that the energy storage air conditioner 1 always operates in the optimal operating conditions that match the real-time environmental changes.

[0067] like Figure 4 As shown, in some embodiments, S10 may include S11-S12.

[0068] S11: Randomly generate an initial population according to the multi-objective optimization model.

[0069] Exemplarily, multiple initial solutions for optimizing the above multiple optimization objectives can be randomly generated according to the optimization objectives, decision variables and objective functions in the multi-objective optimization model, and the optimization effects of different initial solutions are different. Each initial solution includes the above multiple objective functions, and when the initial solution is randomly generated, the coefficients of each objective function in the initial solution are randomly generated.

[0070] S12: Perform the following iterative operations S121 to S124 on the initial population.

[0071] S121: Perform proportional selection, crossover and mutation on the individuals in the initial population to obtain the parent population and the offspring population.

[0072] Here, excellent individuals can be selected in the initial population according to a preset ratio, and crossover and mutation can be performed on the excellent individuals to obtain a parent population and a child population. Exemplarily, the crossover probability and mutation probability can be pre-set in the control system of the energy storage air conditioner 1, and the excellent individuals can be controlled to crossover and randomly mutate based on the crossover probability and mutation probability.

[0073] S122: The parent population and the child population are merged, and individuals in the merged population are subjected to elite competition to obtain an elite population.

[0074] Here, the number of individuals in the elite population and the initial population can be the same. Based on the elite competition strategy, the individuals in the merged population, that is, the individuals in the parent population and the child population, can compete together to produce the next generation population, which is conducive to the excellent individuals in the parent population entering the next generation and being retained, avoiding the excellent individuals in the parent population from being destroyed due to crossover and mutation, and quickly improving the level of the next generation population. Exemplarily, before the individuals in the merged population are subjected to elite competition, the non-dominated rank and crowding degree in the merged population can be determined first, and then the individuals in the merged population can be subjected to elite competition based on the non-dominated rank and crowding degree.

[0075] S123: In response to determining that the current number of iterations is less than the maximum number of iterations, updating the initial population according to the elite population.

[0076] Before performing the iterative operation, the maximum number of iterations can be pre-set, and the maximum number of iterations can be used as the judgment condition for ending the iterative operation; and the current number of iterations is the cumulative number of iterations performed on the initial population in the current iterative operation. When it is determined that the current number of iterations is less than the maximum number of iterations, it can be determined that the condition for ending the iterative operation has not been met. At this time, the initial population can be updated to the elite population determined in S122, and the iterative operations of S121 to S124 are performed again based on the updated initial population.

[0077] S124: In response to determining that the current number of iterations is equal to the maximum number of iterations, the elite population is used as the Pareto frontier of the energy storage air conditioner 1.

[0078] When it is determined that the current number of iterations is equal to the maximum number of iterations, it can be determined that the condition for ending the iteration operation has been met. At this time, the elite population determined in S122 can be output as the final elite population, and the final elite population is used as the Pareto frontier of the energy storage air conditioner 1.

[0079] like Figure 5 As shown, in some examples, S121 may include S1211 to S1212.

[0080] S1211: Determine the non-dominated level and crowding degree of each individual in the initial population.

[0081] Here, the non-dominance relationship of each individual in the initial population can be defined, and non-dominance levels can be assigned to each individual based on the non-dominance relationship and non-dominance sorting can be performed. Here, the crowding degree of each individual in the initial population can be calculated using a preset crowding degree algorithm.

[0082] S1212: Select excellent individuals from the initial population according to the non-dominated level and the crowding degree, and use the excellent individuals to form the parent population.

[0083] Here, individuals with higher non-dominance levels can be preferentially selected as excellent individuals; if the non-dominance levels of two individuals are the same, the individual with smaller crowding degree is selected as the excellent individual. After selecting excellent individuals from the initial population, the selected excellent individuals can be formed into the parent population.

[0084] S1213: Perform crossover and mutation on the parent population to obtain the offspring population.

[0085] Here, individuals in the parent population can be crossovered and randomly mutated based on the preset crossover probability and mutation probability to obtain the offspring population.

[0086] Exemplarily, S1212 may include S12121.

[0087] S12121: Based on the binary bidding method, excellent individuals in the initial population are selected according to non-dominated sorting and crowding.

[0088] In some embodiments, before S10, the energy storage air conditioner control method includes S00.

[0089] S00: Establishing a multi-objective optimization model of the energy storage air conditioner 1 according to the objective function and decision variables of the energy storage air conditioner 1.

[0090] Here, the corresponding type and number of objective functions can be determined based on the historical operating data and / or experimental test data of the energy storage air conditioner 1 and the type and number of optimization targets required by the energy storage air conditioner 1, and the specific values ​​of the coefficients of the objective function can be determined according to the solution of S10. In some examples, the multiple optimization targets may include the energy efficiency ratio and the total operating power consumption of the energy storage air conditioner 1. In some examples, the decision variables may include the outdoor ambient temperature, the mass flow rate of the refrigerant, the air volume of the outdoor fan, the suction pressure and exhaust pressure of the compressor 31, the suction temperature and exhaust temperature of the compressor 31, the condenser outlet temperature, and the refrigerant inlet temperature of the water side heat exchanger 50.

[0091] In a second aspect, an embodiment of the present application provides a control device for an energy storage air conditioner, which includes: a multi-objective optimization genetic circuit, configured to determine the Pareto frontier of the energy storage air conditioner 1 based on the multi-objective optimization model of the energy storage air conditioner 1 and the NSGA-II algorithm; a weight decision circuit, configured to determine the weighted optimization effect of each Pareto optimal solution in the Pareto frontier based on the weight decision algorithm, and use the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto frontier; an operation control circuit, configured to control the operation of the energy storage air conditioner 1 according to the operating parameters in the optimal solution.

[0092] like Figure 6 As shown, in the third aspect, an embodiment of the present application provides an energy storage air conditioner 1, which includes a processor 10 and a memory 20, and the memory 20 stores a computer program, which, when executed by the processor 10, implements the energy storage air conditioner control method described in any of the above embodiments.

[0093] The processor 10 is connected to the memory 20, and can perform various actions and processes according to the program stored in the memory 20. Specifically, the processor 10 can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 10 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can be an X86 architecture or an ARM architecture.

[0094] The memory 20 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronously linked dynamic random access memory (SLDRAM), and direct memory bus random access memory (DRRAM). It should be noted that the memory 20 of the method described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0095] like Figure 7 As shown, in some embodiments, the energy storage air conditioner 1 may include a refrigerant circuit 30, a secondary coolant circuit 40 and an outdoor fan 60. The refrigerant circuit 30 and the secondary coolant circuit 40 are connected for heat exchange through a water-side heat exchanger 50. The refrigerant circuit 30 is provided with a compressor 31, a condenser 32 and an electronic expansion valve 33, and the outdoor fan 60 and the condenser 32 are arranged correspondingly; the secondary coolant circuit 40 is provided with a secondary coolant circulation pump 41, and the secondary coolant circulation pump 41 is used to drive the secondary coolant to circulate in the secondary coolant circuit 40. Here, the water-side heat exchanger 50 has a refrigerant flow channel and a secondary coolant flow channel isolated from each other, the refrigerant flow channel is connected to the refrigerant circuit 30, and the refrigerant can flow through, and the secondary coolant flow channel is connected to the secondary coolant circuit 40, and the secondary coolant can flow through, so that the refrigerant and the secondary coolant can exchange heat in the water-side heat exchanger 50.

[0096] In some examples, the brine circuit 40 may include a main flow path 42 and a natural cooling bypass 43 arranged in parallel. The main flow path 42 and the natural cooling bypass 43 are connected in parallel to form a parallel flow path structure, which may be connected to the water side heat exchanger 50 and / or the brine circulation pump 41, or the water side heat exchanger 50 may also be arranged on the main flow path 42. Exemplarily, one end of the parallel flow path structure can be connected to the water side heat exchanger 50, and the other end can be connected to the refrigerant circulation pump 41; another exemplary embodiment, the parallel flow path structure can be connected to the refrigerant circulation pump 41 through the water side heat exchanger 50, so that the parallel flow path structure and the refrigerant circulation pump 41 are respectively located at opposite ends of the water side heat exchanger 50; another exemplary embodiment, the parallel flow path structure can be connected to the water side heat exchanger 50 through the refrigerant circulation pump 41, so that the parallel flow path structure and the water side heat exchanger 50 are respectively located at opposite ends of the refrigerant circulation pump 41; another exemplary embodiment, the water side heat exchanger 50 can be arranged on the mainstream path 42, so that the water side heat exchanger 50 and the natural cooling bypass 43 are arranged in parallel.

[0097] Here, the main flow path 42 and the natural cooling bypass path 43 can be selectively opened or closed, respectively, so that the brine can selectively flow into the main flow path 42 and / or the natural cooling bypass path 43. When the main flow path 42 is opened and the natural cooling bypass path 43 is closed, the brine can flow into the main flow path 42 and circulate the brine through the main flow path 42; when the main flow path 42 is closed and the natural cooling bypass path 43 is opened, the brine can flow into the natural cooling bypass path 43 and circulate the brine through the natural cooling bypass path 43; when the main flow path 42 is opened and the natural cooling bypass path 43 is opened, the brine can flow into the main flow path 42 and the natural cooling bypass path 43, respectively, and circulate the brine through the main flow path 42 and the natural cooling bypass path 43, respectively. Exemplarily, a three-way stop valve 44 may be provided at the connection between the main flow path 42 and the natural cooling bypass 43, and the three-way stop valve 44 is used to control the main flow path 42 and the natural cooling bypass 43 to be selectively connected or cut off; another exemplary embodiment, the main flow path 42 and the natural cooling bypass 43 may be provided with stop valves respectively, and the stop valves are used to control the main flow path 42 and the natural cooling bypass 43 to be selectively connected or cut off.

[0098] Here, a natural cooling heat exchanger 431 is provided on the natural cooling bypass 43, and the natural cooling heat exchanger 431 can exchange heat with the air to use the cold in the air to cool the refrigerant flowing through the natural cooling bypass 43. The type of the natural cooling heat exchanger 431 can be determined according to actual needs, and can be, for example, a fin heat exchanger, a tube heat exchanger, etc., which is not limited in the embodiment of the present application. Exemplarily, the natural cooling heat exchanger 431 can be a natural cooling coil. Exemplarily, the indoor fan can be set corresponding to the natural cooling heat exchanger 431.

[0099] In some examples, the brine circuit 40 may be provided with an electric heater 45, which may generate heat when powered on to heat the brine in the brine circuit 40. Exemplarily, when the brine circuit 40 includes a main flow path 42 and a natural cooling bypass path 43 arranged in parallel, the electric heater 45 may be arranged on the main flow path 42, or the electric heater 45 may be arranged in series with the parallel flow path structure.

[0100] Here, the energy storage air conditioner 1 may have operating modes such as full mechanical cooling mode, partial natural cooling mode, full natural cooling mode and heating mode. The above operating modes are introduced one by one here.

[0101] When the energy storage air conditioner 1 operates in the full mechanical refrigeration mode, the compressor 31 in the refrigerant circuit 30 is turned on to perform evaporative cooling on the refrigerant in the refrigerant circuit 30; the main flow path 42 is connected and the natural cooling bypass 43 is blocked, preventing the coolant from flowing into the natural cooling bypass 43, and all the coolant is used to exchange heat with the low-temperature refrigerant through the water-side heat exchanger 50, and the low-temperature refrigerant cools the coolant, and then the cooling capacity obtained from the low-temperature refrigerant is provided to the temperature control object.

[0102] When the energy storage air conditioner 1 operates in a partial natural cooling mode, the compressor 31 in the refrigerant circuit 30 is turned on to perform evaporative cooling on the refrigerant in the refrigerant circuit 30; the main flow path 42 is turned on and the natural cooling bypass 43 is turned on, so that part of the refrigerant flows into the natural cooling bypass 43 and is cooled by the natural cooling heat exchanger 431. At the same time, at least part of the refrigerant exchanges heat with the low-temperature refrigerant through the water side heat exchanger 50 and is cooled by the low-temperature refrigerant.

[0103] When the energy storage air conditioner 1 operates in the full natural cooling mode, the compressor 31 in the refrigerant circuit 30 stops running and does not perform evaporative cooling on the refrigerant in the refrigerant circuit 30; the main flow 42 is cut off and the natural cooling bypass 43 is connected, and all the refrigerant flows into the natural cooling bypass 43 and is cooled by the natural cooling heat exchanger 431, thereby providing the cooling energy obtained from the natural environment to the temperature control object.

[0104] When the energy storage air conditioner 1 is operated in the heating mode, the compressor 31 in the refrigerant circuit 30 does not perform evaporative cooling on the refrigerant in the refrigerant circuit 30; the main flow path 42 is connected and the natural cooling bypass 43 is blocked, preventing the coolant from flowing into the natural cooling bypass 43, and the electric heater 45 heats the entire coolant, and the heated coolant provides heat to the temperature control object.

[0105] In some examples, the refrigerant circuit 30 may be provided with a first temperature sensor 34, which is disposed at the refrigerant outlet of the condenser 32 and is used to measure the outlet temperature of the condenser 32. In some examples, the brine circuit 40 may be provided with a second temperature sensor 46, which is disposed at the brine inlet of the water-side heat exchanger 50 and is used to measure the brine inlet temperature of the water-side heat exchanger 50.

[0106] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. The computer program is loaded by the processor 10 to execute the steps in the control method of any of the above embodiments.

[0107] Exemplarily, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks or magnetic tapes, etc.), optical disks (e.g., CDs (Compact Disks), DVDs (Digital Versatile Disks), etc.), smart cards and flash memory devices (e.g., EPROMs (Erasable Programmable Read-Only Memory), cards, sticks or key drives, etc.). The various computer-readable storage media described in the embodiments of the present application may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing and / or carrying instructions and / or data.

[0108] The above is a detailed introduction to an energy storage air conditioner and its control method, device, and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for controlling an energy storage air conditioner, characterized in that: include: Determine the Pareto frontier of the energy storage air conditioner based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm; Determine the weighted optimization effect of each Pareto optimal solution in the Pareto frontier based on a weighted decision algorithm, and take the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto frontier; The operation of the energy storage air conditioner is controlled according to the operating parameters in the optimal solution of the Pareto boundary.

2. The energy storage air conditioner control method according to claim 1, characterized in that: Determining the weighted optimization effect of each Pareto optimal solution in the Pareto frontier based on a weighted decision algorithm, and taking the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto frontier, including: Constructing a decision matrix according to the overall objective function of the Pareto frontier; Normalizing the decision matrix to obtain a normalized decision matrix; Determining the weight value of each of the overall objective functions according to the normalized decision matrix; Determining a weighted optimization effect matrix of the Pareto frontier according to the weight values ​​and the normalized decision matrix, wherein each individual in the weighted optimization effect matrix represents a weighted optimization effect of a Pareto optimal solution; The individuals in the weighted optimization effect matrix of the Pareto frontier are sorted in descending order, and the individual that ranks first after sorting is taken as the optimal solution of the Pareto frontier.

3. The energy storage air conditioner control method according to claim 2, characterized in that: Determining the weight value of each of the overall objective functions according to the normalized decision matrix includes: Determining the divergence value of each of the overall objective functions according to the normalized decision matrix; An entropy weight of the objective function is determined according to the divergence value of the objective function, and the entropy weight is used as a weight value of the objective function.

4. The energy storage air conditioner control method according to claim 1, characterized in that: Determining the Pareto frontier of the energy storage air conditioner based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm includes: Randomly generate an initial population according to the multi-objective optimization model; The following iterative operations are performed on the initial population: Performing proportional selection, crossover and mutation on individuals in the initial population to obtain a parent population and a child population; The parent population and the child population are merged, and individuals in the merged population are subjected to elite competition to obtain an elite population, wherein the number of individuals in the elite population is consistent with that in the initial population; In response to determining that the current number of iterations is less than the maximum number of iterations, updating the initial population according to the elite population; In response to determining that the current number of iterations is equal to the maximum number of iterations, the elite population is used as the Pareto frontier of the energy storage air conditioner.

5. The energy storage air conditioner control method according to claim 4, characterized in that: Proportional selection, crossover and mutation are performed on the individuals in the initial population to obtain a parent population and a child population, including: Determining the non-dominated rank and crowding degree of each individual in the initial population; Selecting excellent individuals from the initial population according to the non-dominated level and the crowding degree, and forming a parent population with the excellent individuals; The parent population is subjected to crossover and mutation to obtain a child population.

6. The energy storage air conditioner control method according to claim 5, characterized in that: Selecting excellent individuals in the initial population according to the non-dominated level and the crowding degree includes: Based on a binary bidding method, excellent individuals in the initial population are selected according to the non-dominated level and the crowding degree.

7. The energy storage air conditioner control method according to claim 1, characterized in that: Before determining the Pareto boundary of the energy storage air conditioner based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm, the energy storage air conditioner control method includes: A multi-objective optimization model of the energy storage air conditioner is established according to the objective function and decision variables of the energy storage air conditioner.

8. A control device for an energy storage air conditioner, characterized in that: include: A multi-objective optimization genetic circuit is configured to determine the Pareto frontier of the energy storage air conditioner based on the multi-objective optimization model of the energy storage air conditioner and the NSGA-II algorithm; A weight decision circuit is configured to determine the weighted optimization effect of each Pareto optimal solution in the Pareto frontier based on a weight decision algorithm, and use the Pareto optimal solution with the highest weighted optimization effect as the optimal solution of the Pareto frontier; The operation control circuit is configured to control the operation of the energy storage air conditioner according to the operation parameters in the optimal solution of the Pareto boundary.

9. An energy storage air conditioner, characterized in that: include: a memory storing a computer program; A processor, wherein when the computer program is executed by the processor, the energy storage air conditioner control method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the energy storage air conditioner control method described in any one of claims 1 to 7.

Images