Air conditioning system carbon efficiency / energy efficiency management method and system, storage medium

Abstract

The present application relates to a kind of carbon efficiency / energy efficiency management method and system of air conditioning system, storage medium, the method uses mode operation analysis algorithm, carbon emission coefficient learning algorithm, pattern recognition algorithm, operation optimization algorithm is combined, algorithm is trained based on system historical operation data, improve the accuracy of algorithm;Determine system operation mode based on real-time operation data of system, calculate the dynamic evaluation parameter of system carbon emission, increase the intuitiveness of system carbon emission efficiency evaluation, by application data driven, algorithm has the ability of continuous optimization of operation accumulation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, in particular to an air conditioning system carbon efficiency / energy efficiency management method and system and a storage medium. BACKGROUND

[0002] With the development of society, the energy consumption of air conditioning systems has reached half of the building energy consumption. Central air conditioning is widely used, and air conditioning energy saving is increasingly important for reducing air conditioning system energy consumption and improving system carbon efficiency. The current mainstream air conditioning system uses a simple self-control strategy, and the control scheme is directly based on the energy consumption of the system, without calculating and evaluating the carbon efficiency. The modeling technology and adjustment scheme used do not fully apply data-driven methods, and the model accuracy is insufficient. SUMMARY

[0003] In view of the current carbon emission efficiency optimization problem under complex operating conditions of the cold machine, the present application provides an air conditioning system carbon efficiency / energy efficiency management method. Based on the historical operating data of the air conditioning system, the mode classification of the cold machine is realized, the equivalent carbon emissions generated by the operating energy consumption of the cold machine are converted, and the algorithm model can cope with the common operating scenarios of the central air conditioning system. After collecting the operating data, the optimization of the cold machine for the purpose of reducing carbon emissions is achieved, and with the accumulation of historical data in the system, the accuracy of the algorithm model is improved.

[0004] The solution to the above technical problem is as follows: an air conditioning system carbon efficiency / energy efficiency management method, comprising the following steps:

[0005] Based on the historical operating data of each cold machine in the air conditioning system, the mode classification of the cold machine is realized, and the operating mode label of the cold machine is obtained; the operating data includes various operating parameters;

[0006] The operating parameters mainly include the actual power consumption of the cold machine, the actual refrigerating capacity of the unit, the unit load rate, the compressor operating frequency, the indoor temperature, etc.; and the meteorological information of the system, including the outdoor dry-bulb temperature and the wet-bulb temperature. The data should be hourly data records collected at equal time intervals, and the recording interval is within 30 minutes.

[0007] Based on the related parameters of the cold machine and the operating mode label, the carbon emission coefficient learning is performed to determine the carbon emission coefficient corresponding to each operating mode label;

[0008] Based on the operating mode label and the historical operating data, the mode recognition learning is performed to obtain the trained mode recognition algorithm;

[0009] New specified parameters are randomly generated based on the real-time operating data of each chiller. Other parameters in the real-time operating data and the new specified parameters are input into a pattern recognition algorithm to obtain the real-time operating mode label of each chiller. The corresponding carbon emission coefficient is obtained based on the real-time operating mode label of each chiller. Based on the carbon emission coefficient corresponding to the real-time operating mode label of each chiller, the operating parameters are optimized through a pre-built optimization model.

[0010] The system feeds back the optimized operating parameters of each chiller to the air conditioning system and adjusts the real-time operating status of each chiller.

[0011] Preferably, the step of classifying the operating modes based on historical operating data of each chiller in the air conditioning system to obtain operating mode labels for the chillers specifically includes:

[0012] Based on the historical operating data of each chiller in the air conditioning system, the operating mode is classified by the K-means model to obtain the operating mode label of the chiller.

[0013] Preferably, based on the historical operating data of each chiller in the air conditioning system, a K-means model is used for pattern operation analysis and learning to obtain the chiller's operating pattern label, specifically including:

[0014] Input the historical operating data of each chiller in the air conditioning system into the K-means model to generate a sample set T = {x} u} 1≤u≤N x u ∈R n Let be the feature vector of the u-th sample in the sample set. First, randomly select K samples from the sample set T as initial cluster centers. Then, calculate the distance between each sample and each cluster center, and assign each sample to the nearest cluster center. Each cluster center represents a category. At this point, the u-th sample in the sample set is assigned the initial running mode label y′. u ∈{c1, c2, ... c K};

[0015] Calculate the sum of distances D from all samples to the centroid of their respective clusters, using the following formula:

[0016]

[0017] Where C i Let be the centroid of the i-th cluster; the dist function is the set distance metric; once all samples have been assigned initial running mode labels, the cluster center of each cluster will be recalculated based on the existing objects in the cluster;

[0018] Return to the step of calculating the distance between each sample and each cluster center, until the cluster centers of each cluster no longer change, and each sample is assigned to the final running mode label y. u∈{c1, c2, ... c K}

[0019] Preferably, the carbon emission coefficient is learned based on the relevant parameters and operating mode labels of the chiller to determine the carbon emission coefficient corresponding to each operating mode label. The specific calculation formula is as follows:

[0020]

[0021] Where βi is the carbon emission coefficient corresponding to the i-th operating mode label; i is the operating mode label; βr is the base operating mode carbon emission coefficient; and COP is the carbon emission coefficient of the base operating mode. r COP is the reference energy efficiency for the baseline operating mode. i The reference energy efficiency is the label for the i-th operating mode.

[0022] Among them, COP i The calculation formula is:

[0023]

[0024] In the formula, u is the sequence number of the u-th sample system operation data record, Q j Let P be the actual cooling capacity of the system in the j-th record, P be the actual power of the system in the u-th record, and h be the total number of records tagged with the i-th operating mode.

[0025] Among them, COP r The setting method is as follows: Based on the nominal cooling capacity and energy efficiency rating indicated on the nameplate of the chiller, read the COP of each chiller according to the national standard (GB19577-2004) for unit cooling capacity and energy efficiency, and take the minimum value obtained from the readings of each chiller as the benchmark reference COP. r .

[0026] Where, β r The setting method is as follows: refer to the equivalent carbon emissions per kilowatt-hour of electricity provided by the local power generation department, or refer to the index calculation unit proposed in the provincial greenhouse gas inventory compilation guidelines, with the unit being Kg / (kW.h).

[0027] Preferably, the step of performing pattern recognition learning based on operating mode labels and historical operating data to obtain a trained pattern recognition algorithm specifically includes:

[0028] A training sample set T = {(x} is constructed based on operation mode labels and historical operation data. u y u )} 1≤u≤N y u ∈{+1, -1}, x u ∈R n R n Refers to the real number vector space;

[0029] The SVM model employs a radial basis function kernel. The input training sample set is used to optimize and train the SVM model using soft margin maximization and kernel trick techniques, with the following parameter ranges as constraints:

[0030]

[0031] sty u ( <w,φ(x u )>+b)-1≥0, u=1, 2,...,N

[0032] ξ u ≥0, u=1,2,...,N

[0033] In the formula, x u Let y be the feature vector of the u-th sample in the training set; u Let be the operating mode label of the u-th sample in the training set, and N be the total number of categories of the samples; φ() is the nonlinear mapping from the original input space to the high-dimensional feature space. The nonlinear support vector machine maps the input to feature vectors through this mapping, w is the normal vector of the hyperplane in the feature space, b is the bias of the hyperplane, <, > denote the inner product of two vectors, and ξ u C is a slack variable, and C is a penalty parameter;

[0034] The trained pattern recognition algorithm SVM model is as follows:

[0035] i = SVM(x,θ)

[0036] In the formula, i is the operating mode label, x is the load rate parameter in the chiller operating data, and θ is the meteorological parameter and other operating parameters in the chiller operating data.

[0037] Preferably, the step involves randomly generating new specified parameters based on the real-time operating data of each chiller, inputting other parameters from the real-time operating data and the new specified parameters into a pattern recognition algorithm to obtain a real-time operating mode label for each chiller; obtaining the carbon emission coefficient corresponding to the real-time operating mode label based on the real-time operating mode label of each chiller; and optimizing the operating parameters using a pre-built optimization model based on the carbon emission coefficient corresponding to the real-time operating mode label of each chiller; specifically including:

[0038] An optimization model is constructed with the objective of minimizing carbon emissions. The loss function in the optimization model is expressed as follows:

[0039]

[0040] Where n is the chiller serial number, m is the total number of chillers, i is the operating mode label of the output result based on SVM(x',θ), and k is the number of chillers. i,nThe carbon emission coefficient P corresponding to the nth refrigeration unit under the i-th operating mode label. n Let x' be the rated power of the nth refrigeration unit. n The load rate is randomly generated for the nth chiller unit selected through the selection process;

[0041] Near the real-time load factor x of the nth chiller unit, generate w new chiller load factors x' randomly. Input other parameters from the real-time operating data of the nth chiller unit and the w new load factors x' into a pattern recognition algorithm SVM(x',θ) to obtain w operating mode labels i for the nth chiller unit. Based on the operating mode label i, obtain the corresponding carbon emission coefficient k. i,n ;

[0042] Input the carbon emission coefficient corresponding to the operating mode label i of the nth chiller in group w into the optimization model, and select the load factor x” that minimizes the loss function of the nth chiller from the w load factors x”. n and output x” n These are the optimized and adjusted operating parameters for the nth refrigeration unit.

[0043] Preferably, the carbon emission coefficient corresponding to the operating mode label i of the nth chiller in the input w group is fed into the optimization model, and the load factor x” that satisfies the minimum loss function of the nth chiller is selected from the w load factors x”. n and output x” n The optimized and adjusted operating parameters for the nth refrigeration unit; specifically including:

[0044] Input the carbon emission coefficient corresponding to the operating mode label i of the nth refrigeration unit in group w into the optimization model;

[0045] From w load factors x', select the load factor x” that minimizes the loss function of the nth chiller unit. n , and x” n Complete output adjustment load rate x” n Before and after, the total cooling capacity output of all chillers in the air conditioning system remains unchanged, and output x” n These are the optimized operating parameters for the nth refrigeration unit; the constraint expressions are as follows:

[0046]

[0047] Among them, Q n Let x be the rated cooling capacity of the nth chiller. n Adjust the load factor before the nth chiller, x” n The load rate of the nth chiller is adjusted.

[0048] Setting this constraint theoretically ensures that the overall cooling capacity of the system remains unchanged before and after load rate adjustments, thereby indirectly ensuring that the environmental comfort at the system's terminals is basically within a suitable range.

[0049] The present invention also provides a carbon efficiency / energy efficiency management system for an air conditioning system, comprising:

[0050] The mode operation analysis and learning module is used to classify the operation modes based on the historical operation data of each chiller in the air conditioning system and obtain the operation mode labels of the chillers; the operation data includes a variety of operation parameters;

[0051] The carbon emission coefficient learning module is used to learn the carbon emission coefficient based on the relevant parameters and operating mode labels of the chiller, and to determine the carbon emission coefficient corresponding to each operating mode label.

[0052] The pattern recognition algorithm training module is used to learn patterns based on running mode labels and historical running data to obtain a trained pattern recognition algorithm.

[0053] The optimization algorithm operation module is used to randomly generate new specified parameters based on the real-time operation data of each chiller, input other parameters in the real-time operation data and the new specified parameters into the pattern recognition algorithm to obtain the real-time operation mode label of each chiller; obtain the corresponding carbon emission coefficient based on the real-time operation mode label of each chiller; and optimize the operation parameters through a pre-built optimization model based on the carbon emission coefficient corresponding to the real-time operation mode label of each chiller.

[0054] The system control module is used to feed back the optimized operating parameters of each chiller to the air conditioning system and to control the real-time operating status of each chiller.

[0055] Preferably, the step of classifying the operating modes based on historical operating data of each chiller in the air conditioning system to obtain operating mode labels for the chillers specifically includes:

[0056] Based on the historical operating data of each chiller in the air conditioning system, the operating mode is classified by the K-means model to obtain the operating mode label of the chiller.

[0057] Preferably, based on the historical operating data of each chiller in the air conditioning system, a K-means model is used for pattern operation analysis and learning to obtain the chiller's operating pattern label, specifically including:

[0058] Input the historical operating data of each chiller in the air conditioning system into the K-means model to generate a sample set T = {x} u} 1≤u≤N x u ∈R nLet be the feature vector of the u-th sample in the sample set. First, randomly select K samples from the sample set T as initial cluster centers. Then, calculate the distance between each sample and each cluster center, and assign each sample to the nearest cluster center. Each cluster center represents a category. At this point, the u-th sample in the sample set is assigned the initial running mode label y′. u ∈{c1, c2, ... c K};

[0059] Calculate the sum of distances D from all samples to the centroid of their respective clusters, using the following formula:

[0060]

[0061] Where C i Let be the centroid of the i-th cluster; the dist function is the set distance metric; once all samples have been assigned initial running mode labels, the cluster center of each cluster will be recalculated based on the existing objects in the cluster;

[0062] Return to the step of calculating the distance between each sample and each cluster center, until the cluster centers of each cluster no longer change, and each sample is assigned to the final running mode label y. u ∈{c1, c2, ... c K}

[0063] Preferably, the carbon emission coefficient is learned based on the relevant parameters and operating mode labels of the chiller to determine the carbon emission coefficient corresponding to each operating mode label. The specific calculation formula is as follows:

[0064]

[0065] Where βi is the carbon emission coefficient corresponding to the i-th operating mode label; i is the operating mode label; βr is the base operating mode carbon emission coefficient; and COP is the carbon emission coefficient of the base operating mode. r COP is the reference energy efficiency for the baseline operating mode. i The reference energy efficiency is the label for the i-th operating mode.

[0066] Among them, COP i The calculation formula is:

[0067]

[0068] In the formula, u is the sequence number of the u-th sample system operation data record, Q j Let P be the actual cooling capacity of the system in the j-th record, P be the actual power of the system in the u-th record, and h be the total number of records tagged with the i-th operating mode.

[0069] Preferably, the step of performing pattern recognition learning based on operating mode labels and historical operating data to obtain a trained pattern recognition algorithm specifically includes:

[0070] A training sample set T = {(x} is constructed based on operation mode labels and historical operation data. u y u )} 1≤u≤N y u ∈{+1, -1}, x u ∈R n R n Refers to the real number vector space;

[0071] The SVM model employs a radial basis function kernel. The input training sample set is used to optimize and train the SVM model using soft margin maximization and kernel trick techniques, with the following parameter ranges as constraints:

[0072]

[0073] sty u ( <w,φ(x u )>+b)-1≥0, u=1, 2,...,N

[0074] ξ u ≥0, u=1,2,...,N

[0075] In the formula, x u Let y be the feature vector of the u-th sample in the training set; u Let be the operating mode label of the u-th sample in the training set, and N be the total number of categories of the samples; φ() is the nonlinear mapping from the original input space to the high-dimensional feature space. The nonlinear support vector machine maps the input to feature vectors through this mapping, w is the normal vector of the hyperplane in the feature space, b is the bias of the hyperplane, <, > denote the inner product of two vectors, and ξ u C is a slack variable, and C is a penalty parameter;

[0076] The trained pattern recognition algorithm SVM model is as follows:

[0077] i = SVM(x,θ)

[0078] In the formula, i is the operating mode label, x is the load rate parameter in the chiller operating data, and θ is the meteorological parameter and other operating parameters in the chiller operating data.

[0079] Preferably, the step involves randomly generating new specified parameters based on the real-time operating data of each chiller, inputting other parameters from the real-time operating data and the new specified parameters into a pattern recognition algorithm to obtain a real-time operating mode label for each chiller; obtaining the carbon emission coefficient corresponding to the real-time operating mode label based on the real-time operating mode label of each chiller; and optimizing the operating parameters using a pre-built optimization model based on the carbon emission coefficient corresponding to the real-time operating mode label of each chiller; specifically including:

[0080] An optimization model is constructed with the objective of minimizing carbon emissions. The loss function in the optimization model is expressed as follows:

[0081]

[0082] Where n is the chiller serial number, m is the total number of chillers, i is the operating mode label of the output result based on SVM(x',θ), and k is the number of chillers. i,n The carbon emission coefficient P corresponding to the nth refrigeration unit under the i-th operating mode label. n Let x' be the rated power of the nth refrigeration unit. n The load rate is randomly generated for the nth chiller unit selected through the selection process;

[0083] Near the real-time load factor x of the nth chiller unit, generate w new chiller load factors x' randomly. Input other parameters from the real-time operating data of the nth chiller unit and the w new load factors x' into a pattern recognition algorithm SVM(x',θ) to obtain w operating mode labels i for the nth chiller unit. Based on the operating mode label i, obtain the corresponding carbon emission coefficient k. i,n ;

[0084] Input the carbon emission coefficient corresponding to the operating mode label i of the nth chiller in group w into the optimization model, and select the load factor x” that minimizes the loss function of the nth chiller from the w load factors x”. n and output x” n These are the optimized and adjusted operating parameters for the nth refrigeration unit.

[0085] Preferably, the carbon emission coefficient corresponding to the operating mode label i of the nth chiller in the input w group is fed into the optimization model, and the load factor x” that satisfies the minimum loss function of the nth chiller is selected from the w load factors x”. n and output x” n The optimized and adjusted operating parameters for the nth refrigeration unit; specifically including:

[0086] Input the carbon emission coefficient corresponding to the operating mode label i of the nth refrigeration unit in group w into the optimization model;

[0087] From w load factors x', select the load factor x” that minimizes the loss function of the nth chiller unit. n , and x” n Complete output adjustment load rate x” n Before and after, the total cooling capacity output of all chillers in the air conditioning system remains unchanged, and output x” n These are the optimized operating parameters for the nth refrigeration unit; the constraint expressions are as follows:

[0088]

[0089] Among them, Q n Let x be the rated cooling capacity of the nth chiller. n Adjust the load factor before the nth chiller, x” n The load rate of the nth chiller is adjusted.

[0090] The present invention also provides a computer storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the air conditioning system carbon efficiency / energy efficiency management method described above.

[0091] The present invention also provides an electronic device, including a memory and a processor: the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, wherein when the computer-executable instructions are executed by the processor, the steps of the air conditioning system carbon efficiency / energy efficiency management method described above are implemented.

[0092] The beneficial effects of this invention are: the method provided by this invention determines the system operation mode based on system operation data and calculates dynamic evaluation parameters of system carbon emissions, increasing the intuitiveness of system carbon emission efficiency evaluation. By applying data-driven approaches and accumulating operational data in the system, the algorithm model has the ability to continuously optimize based on operational accumulation, thereby improving accuracy and reliability.

[0093] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0094] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0095] Figure 1 This is a simplified flowchart of the method described in Embodiment 1 of the present invention;

[0096] Figure 2 This is a flowchart illustrating the operation and optimization of the method described in Embodiment 1 of the present invention;

[0097] Figure 3 This is a simplified flowchart of the system operation described in Embodiment 2 of the present invention. Detailed Implementation

[0098] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0099] Example 1

[0100] like Figures 1-2 As shown, a carbon efficiency / energy efficiency management method for an air conditioning system includes the following steps:

[0101] Based on the historical operating data of each chiller in the air conditioning system, the operating modes are classified to obtain the operating mode labels of the chillers. The specific steps are as follows:

[0102] Input the historical operating data of each chiller in the air conditioning system into the K-means model to generate a sample set T = {x} u} 1≤u≤N x u ∈R n Let be the feature vector of the u-th sample in the sample set. First, randomly select K samples from the sample set T as initial cluster centers. Then, calculate the distance between each sample and each cluster center, and assign each sample to the nearest cluster center. Each cluster center represents a category. At this point, the u-th sample in the sample set is assigned the initial running mode label y′. u ∈{c1, c2, ... c K};

[0103] Calculate the sum of distances D from all samples to the centroid of their respective clusters, using the following formula:

[0104]

[0105] Among them, C i Let be the centroid of the i-th cluster; the dist function is the set distance metric; once all samples have been assigned initial running mode labels, the cluster center of each cluster will be recalculated based on the existing objects in the cluster;

[0106] Return to the step of calculating the distance between each sample and each cluster center, until the cluster centers of each cluster no longer change, and each sample is assigned to the final running mode label y. u ∈{c1, c2, ... c K}

[0107] The system operation data includes various key operating parameters of the chiller. These mainly include the chiller's actual power consumption, actual cooling capacity, load rate, compressor operating frequency, and indoor temperature; as well as meteorological information, including outdoor dry-bulb and wet-bulb temperatures. The data should be hourly records at equal time intervals, with each record interval within 30 minutes.

[0108] Based on the relevant parameters and operating mode labels of the chiller, carbon emission coefficients are learned to determine the carbon emission coefficients corresponding to each operating mode label. The specific calculation formula is as follows:

[0109]

[0110] Where βi is the carbon emission coefficient corresponding to the i-th operating mode label; i is the operating mode label; βr is the base operating mode carbon emission coefficient; and COP is the carbon emission coefficient of the base operating mode. r COP is the reference energy efficiency for the baseline operating mode. i The reference energy efficiency is the label for the i-th operating mode.

[0111] Among them, COP i The calculation formula is:

[0112]

[0113] In the formula, u is the sequence number of the u-th sample system operation data record, Q j Let P be the actual cooling capacity of the system in the j-th record, P be the actual power of the system in the u-th record, and h be the total number of records tagged with the i-th operating mode.

[0114] Among them, COP r The setting method is as follows: Based on the nominal cooling capacity and energy efficiency rating indicated on the nameplate of the chiller, read the COP of each chiller according to the national standard (GB19577-2004) for unit cooling capacity and energy efficiency, and take the minimum value obtained from the readings of each chiller as the benchmark reference COP. r .

[0115] Where, β r The setting method is as follows: refer to the equivalent carbon emissions per kilowatt-hour of electricity provided by the local power generation department, or refer to the index calculation unit proposed in the provincial greenhouse gas inventory compilation guidelines, with the unit being Kg / (kW.h).

[0116] Finally, the calculated coefficients for the obtained patterned carbon emission factors are recorded in the following Table 1:

[0117] Table 1

[0118] Operating mode Carbon emission factor Mode 1 ​ Mode 2 [ k2 ] Mode 3 [ k3 ] ... ...

[0119] Based on the operating mode labels and historical operating data, pattern recognition learning is performed to obtain a trained pattern recognition algorithm. The specific steps are as follows:

[0120] A training sample set T = {(x} is constructed based on operation mode labels and historical operation data. u y u )} 1≤u≤N y u ∈{+1, -1}, x u ∈R n R n Refers to the real number vector space;

[0121] The SVM model employs a radial basis function kernel. The input training sample set is used to optimize and train the SVM model using soft margin maximization and kernel trick techniques, with the following parameter ranges as constraints:

[0122]

[0123] sty u ( <w,φ(x u )>+b)-1≥0, u=1, 2,...,N

[0124] ξ u ≥0, u=1,2,...,N

[0125] In the formula, x u Let y be the feature vector of the u-th sample in the training set; u Let be the operating mode label of the u-th sample in the training set, and N be the total number of categories of the samples; φ() is the nonlinear mapping from the original input space to the high-dimensional feature space. The nonlinear support vector machine maps the input to feature vectors through this mapping, w is the normal vector of the hyperplane in the feature space, b is the bias of the hyperplane, <, > denote the inner product of two vectors, and ζ u C is a slack variable, and C is a penalty parameter;

[0126] The trained pattern recognition algorithm SVM model is as follows:

[0127] i = SVM(x,θ)

[0128] In the formula, i is the operating mode label, x is the load rate parameter in the chiller operating data, and θ is the meteorological parameter and other operating parameters in the chiller operating data.

[0129] New specified parameters are randomly generated based on the real-time operating data of each chiller. Other parameters from the real-time operating data and the new specified parameters are input into a pattern recognition algorithm to obtain a real-time operating mode label for each chiller. The carbon emission coefficient corresponding to each real-time operating mode label is then obtained. Based on the carbon emission coefficient corresponding to each chiller's real-time operating mode label, the operating parameters are optimized using a pre-built optimization model.

[0130] The specific steps are as follows;

[0131] An optimization model is constructed with the objective of minimizing carbon emissions. The loss function in the optimization model is expressed as follows:

[0132]

[0133] Where n is the chiller serial number, m is the total number of chillers, i is the operating mode label of the output result based on SVM(x',θ), and k is the number of chillers. i,n The carbon emission coefficient P corresponding to the nth refrigeration unit under the i-th operating mode label. n Let x' be the rated power of the nth refrigeration unit. n The load rate is randomly generated for the nth chiller unit selected through the selection process;

[0134] Near the real-time load factor x of the nth chiller unit, generate w new chiller load factors x' randomly. Input other parameters from the real-time operating data of the nth chiller unit and the w new load factors x' into a pattern recognition algorithm SVM(x',θ) to obtain w operating mode labels i for the nth chiller unit. Based on the operating mode label i, obtain the corresponding carbon emission coefficient k. i,n ;

[0135] Input the carbon emission coefficient corresponding to the operating mode label i of the nth chiller in group w into the optimization model, and select the load factor x” that minimizes the loss function of the nth chiller from the w load factors x”. n , and x” n Complete output adjustment load rate x” n Before and after, the total cooling capacity output of all chillers in the air conditioning system remains unchanged under the constraint condition; the expression for the constraint condition is as follows:

[0136]

[0137] Among them, Q n Let x be the rated cooling capacity of the nth chiller. n Adjust the load factor before the nth chiller, x” n The load rate of the nth chiller is adjusted.

[0138] Output x” nThese are the optimized and adjusted operating parameters for the nth refrigeration unit.

[0139] The system feeds back the optimized operating parameters of each chiller to the air conditioning system and adjusts the real-time operating status of each chiller.

[0140] Example 2

[0141] An air conditioning system carbon efficiency / energy efficiency management system, such as Figure 3 As shown, it includes:

[0142] The mode operation analysis and learning module is used to classify the operation modes based on the historical operation data of each chiller in the air conditioning system and obtain the operation mode labels of the chillers; the operation data includes a variety of operation parameters;

[0143] The carbon emission coefficient learning module is used to learn the carbon emission coefficient based on the relevant parameters and operating mode labels of the chiller, and to determine the carbon emission coefficient corresponding to each operating mode label.

[0144] The pattern recognition algorithm training module is used to learn patterns based on running mode labels and historical running data to obtain a trained pattern recognition algorithm.

[0145] The optimization algorithm operation module is used to randomly generate new specified parameters based on the real-time operation data of each chiller, input other parameters in the real-time operation data and the new specified parameters into the pattern recognition algorithm to obtain the real-time operation mode label of each chiller; obtain the corresponding carbon emission coefficient based on the real-time operation mode label of each chiller; and optimize the operation parameters through a pre-built optimization model based on the carbon emission coefficient corresponding to the real-time operation mode label of each chiller.

[0146] The system control module is used to feed back the optimized operating parameters of each chiller to the air conditioning system and to control the real-time operating status of each chiller.

[0147] The method involves classifying the operating modes based on historical operating data of each chiller in the air conditioning system to obtain operating mode labels for the chillers, specifically including:

[0148] Based on the historical operating data of each chiller in the air conditioning system, the operating mode is classified by the K-means model to obtain the operating mode label of the chiller.

[0149] The method involves using historical operating data from each chiller in the air conditioning system and performing pattern operation analysis and learning through a K-means model to obtain chiller operating pattern labels, specifically including:

[0150] Input the historical operating data of each chiller in the air conditioning system into the K-means model to generate a sample set T = {x} u} 1≤u≤N x u ∈R nLet be the feature vector of the u-th sample in the sample set. First, randomly select K samples from the sample set T as initial cluster centers. Then, calculate the distance between each sample and each cluster center, and assign each sample to the nearest cluster center. Each cluster center represents a category. At this point, the u-th sample in the sample set is assigned the initial running mode label y′. u ∈{c1, c2, ... c K};

[0151] Calculate the sum of distances D from all samples to the centroid of their respective clusters, using the following formula:

[0152]

[0153] Where C i Let be the centroid of the i-th cluster; the dist function is the set distance metric; once all samples have been assigned initial running mode labels, the cluster center of each cluster will be recalculated based on the existing objects in the cluster;

[0154] Return to the step of calculating the distance between each sample and each cluster center, until the cluster centers of each cluster no longer change, and each sample is assigned to the final running mode label y. u ∈{c1, c2, ... c K}

[0155] Based on the relevant parameters and operating mode labels of the chiller, carbon emission coefficients are learned to determine the carbon emission coefficients corresponding to each operating mode label. The specific calculation formula is as follows:

[0156]

[0157] Where βi is the carbon emission coefficient corresponding to the i-th operating mode label; i is the operating mode label; βr is the base operating mode carbon emission coefficient; and COP is the carbon emission coefficient of the base operating mode. r COP is the reference energy efficiency for the baseline operating mode. i The reference energy efficiency is the label for the i-th operating mode.

[0158] Among them, COP i The calculation formula is:

[0159]

[0160] In the formula, u is the sequence number of the u-th sample system operation data record, Q j Let P be the actual cooling capacity of the system in the j-th record, P be the actual power of the system in the u-th record, and h be the total number of records tagged with the i-th operating mode.

[0161] The process of learning a pattern recognition algorithm based on operating mode labels and historical operating data to obtain a trained pattern recognition algorithm specifically includes:

[0162] A training sample set T = {(x} is constructed based on operation mode labels and historical operation data. u y u )} 1≤u≤N y u ∈{+1, -1}, x u ∈R n R n Refers to the real number vector space;

[0163] The SVM model employs a radial basis function kernel. The input training sample set is used to optimize and train the SVM model using soft margin maximization and kernel trick techniques, with the following parameter ranges as constraints:

[0164]

[0165] sty u ( <w,φ(x u )>+b)-1≥0, u=1, 2,...,N

[0166] ξ u ≥0, u=1,2,...,N

[0167] In the formula, x u Let y be the feature vector of the u-th sample in the training set; u Let be the operating mode label of the u-th sample in the training set, and N be the total number of categories of the samples; φ() is the nonlinear mapping from the original input space to the high-dimensional feature space. The nonlinear support vector machine maps the input to feature vectors through this mapping, w is the normal vector of the hyperplane in the feature space, b is the bias of the hyperplane, <, > denote the inner product of two vectors, and ξ u C is a slack variable, and C is a penalty parameter;

[0168] The trained pattern recognition algorithm SVM model is as follows:

[0169] i = SVM(x,θ)

[0170] In the formula, i is the operating mode label, x is the load rate parameter in the chiller operating data, and θ is the meteorological parameter and other operating parameters in the chiller operating data.

[0171] The process involves randomly generating new specified parameters based on the real-time operating data of each chiller, inputting other parameters from the real-time operating data and the new specified parameters into a pattern recognition algorithm to obtain a real-time operating mode label for each chiller; obtaining the carbon emission coefficient corresponding to the real-time operating mode label based on the real-time operating mode label of each chiller; and optimizing the operating parameters using a pre-built optimization model based on the carbon emission coefficient corresponding to the real-time operating mode label of each chiller. Specifically, this includes:

[0172] An optimization model is constructed with the objective of minimizing carbon emissions. The loss function in the optimization model is expressed as follows:

[0173]

[0174] Where n is the chiller serial number, m is the total number of chillers, i is the operating mode label of the output result based on SVM(x',θ), and k is the number of chillers. i,n The carbon emission coefficient P corresponding to the nth refrigeration unit under the i-th operating mode label. n Let x' be the rated power of the nth refrigeration unit. n The load rate is randomly generated for the nth chiller unit selected through the selection process;

[0175] Near the real-time load factor x of the nth chiller unit, generate w new chiller load factors x' randomly. Input other parameters from the real-time operating data of the nth chiller unit and the w new load factors x' into a pattern recognition algorithm SVM(x',θ) to obtain w operating mode labels i for the nth chiller unit. Based on the operating mode label i, obtain the corresponding carbon emission coefficient k. i,n ;

[0176] Input the carbon emission coefficient corresponding to the operating mode label i of the nth chiller in group w into the optimization model, and select the load factor x” that minimizes the loss function of the nth chiller from the w load factors x”. n and output x” n These are the optimized and adjusted operating parameters for the nth refrigeration unit.

[0177] The carbon emission coefficient corresponding to the operating mode label i of the nth chiller in the input w group is fed into the optimization model, and the load factor x” that satisfies the minimum loss function of the nth chiller is selected from the w load factors x”. n and output x” n The optimized and adjusted operating parameters for the nth refrigeration unit; specifically including:

[0178] Input the carbon emission coefficient corresponding to the operating mode label i of the nth refrigeration unit in group w into the optimization model;

[0179] From w load factors x', select the load factor x” that minimizes the loss function of the nth chiller unit. n , and x” n Complete output adjustment load rate x” n Before and after, the total cooling capacity output of all chillers in the air conditioning system remains unchanged, and output x” n These are the optimized operating parameters for the nth refrigeration unit; the constraint expressions are as follows:

[0180]

[0181] Among them, Q n Let x be the rated cooling capacity of the nth chiller. n Adjust the load factor before the nth chiller, x” n The load rate of the nth chiller is adjusted.

[0182] Example 3

[0183] A computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the air conditioning system carbon efficiency / energy efficiency management method as described in Example 1.

[0184] Example 4

[0185] An electronic device includes a memory and a processor: the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, wherein when the computer-executable instructions are executed by the processor, the steps of the air conditioning system carbon efficiency / energy efficiency management method as described in Embodiment 1 are implemented.

[0186] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce implementations of the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application. Obviously, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and modifications.

Claims

1. A method for managing carbon efficiency / energy efficiency in an air conditioning system, characterized in that, Includes the following steps: Based on the historical operating data of each chiller in the air conditioning system, the operating mode is classified using the K-means model to obtain the operating mode label of the chiller; the operating data includes a variety of operating parameters; Based on the relevant parameters and operating mode labels of the chiller, carbon emission coefficients are learned to determine the carbon emission coefficients corresponding to each operating mode label, specifically: Where βi is the carbon emission coefficient corresponding to the i-th operating mode label; i is the operating mode label; βr is the base operating mode carbon emission coefficient; and COP is the carbon emission coefficient of the base operating mode. r COP is the reference energy efficiency for the baseline operating mode. i The reference energy efficiency for the i-th operating mode label; Among them, COP i The calculation formula is: In the formula, u is the sequence number of the u-th sample system operation data record, Q j Let P be the actual cooling capacity of the system in the j-th record, P be the actual power of the system in the u-th record, and h be the total number of records tagged with the i-th operating mode. Based on the operating mode labels and historical operating data, pattern recognition learning is performed to obtain a trained pattern recognition algorithm; New specified parameters are randomly generated based on the real-time operating data of each chiller. Other parameters in the real-time operating data and the new specified parameters are input into a pattern recognition algorithm to obtain the real-time operating mode label of each chiller. The corresponding carbon emission coefficient is obtained based on the real-time operating mode label of each chiller. Based on the carbon emission coefficient corresponding to the real-time operating mode label of each chiller, the operating parameters are optimized by pre-constructing an optimization model with the goal of minimizing carbon emissions and based on the constraint that the total cooling capacity output by all chillers in the air conditioning system remains unchanged. The system feeds back the optimized operating parameters of each chiller to the air conditioning system and adjusts the real-time operating status of each chiller.

2. The carbon efficiency / energy efficiency management method for an air conditioning system according to claim 1, characterized in that, Based on historical operating data of each chiller in the air conditioning system, a K-means model is used for pattern operation analysis and learning to obtain the operating pattern labels of the chillers, specifically including: Input the historical operating data of each chiller in the air conditioning system into the K-means model to generate a sample set T = {x} u } 1≤u≤N x u ∈R n Let u be the feature vector of the u-th sample in the sample set; In the sample set T, K samples are randomly selected as initial cluster centers. Then, the distance between each sample and each cluster center is calculated, and each sample is assigned to the nearest cluster center. Each cluster center represents a category. At this point, the u-th sample in the sample set is assigned the initial running mode label y′. u ∈{c1,c2,...c K }; Calculate the sum of distances D from all samples to the centroid of their respective clusters, using the following formula: Where C i Let be the centroid of the i-th cluster; the dist function is the defined distance metric. Once all samples have been assigned an initial running mode label, the cluster centers of each cluster are recalculated based on the existing objects in the cluster. Return to the step of calculating the distance between each sample and each cluster center, until the cluster centers of each cluster no longer change, and each sample is assigned to the final running mode label y. u ∈{c1, c2, ... c K } 3. The air conditioning system carbon efficiency / energy efficiency management method according to claim 1, characterized in that, The process of learning a pattern recognition algorithm based on operating mode labels and historical operating data to obtain a trained pattern recognition algorithm specifically includes: A training sample set T = {(x} is constructed based on operation mode labels and historical operation data. u y u )} 1≤u≤N y u ∈{+1, -1}, x u ∈R n R n Refers to the real number vector space; The SVM model employs a radial basis function kernel. The input training sample set is used to optimize and train the SVM model using soft margin maximization and kernel trick techniques, with the following parameter ranges as constraints: s.t.y u (<w,φ(x u )>+b)-1≥0,u=1,2,…,N x u ≥0, u=1, 2,..., N In the formula, x u Let y be the feature vector of the u-th sample in the training set; u Let be the operating mode label of the u-th sample in the training set, and N be the total number of categories of the samples; φ() is the nonlinear mapping from the original input space to the high-dimensional feature space. The nonlinear support vector machine maps the input to feature vectors through this mapping, w is the normal vector of the hyperplane in the feature space, b is the bias of the hyperplane, <, > denote the inner product of two vectors, and ξ u C is a slack variable, and C is a penalty parameter; The trained pattern recognition algorithm SVM model is as follows: i = SVM(x,θ) In the formula, i is the operating mode label, x is the load rate parameter in the chiller operating data, and θ is the meteorological parameter and other operating parameters in the chiller operating data.

4. The air conditioning system carbon efficiency / energy efficiency management method according to claim 3, characterized in that, The method involves randomly generating new specified parameters based on the real-time operating data of each chiller, and inputting other parameters from the real-time operating data and the new specified parameters into a pattern recognition algorithm to obtain the real-time operating mode label of each chiller. The carbon emission coefficient corresponding to each real-time operation mode label is obtained based on the real-time operation mode label of each chiller; based on the carbon emission coefficient corresponding to each real-time operation mode label of each chiller, the operating parameters are optimized by pre-constructing an optimization model with the goal of minimizing carbon emissions and under the constraint that the total cooling capacity output by all chillers in the air conditioning system remains unchanged; specifically including: An optimization model is constructed with the objective of minimizing carbon emissions. The loss function in the optimization model is expressed as follows: Where n is the chiller serial number, m is the total number of chillers, i is the operating mode label of the output result based on SVM(x',θ), and k is the number of chillers. i,n The carbon emission coefficient P corresponding to the nth refrigeration unit under the i-th operating mode label. n Let x' be the rated power of the nth refrigeration unit. n The load rate is randomly generated for the nth chiller unit selected through the selection process; Near the real-time load factor x of the nth chiller unit, generate w new chiller load factors x' randomly. Input other parameters from the real-time operating data of the nth chiller unit and the w new load factors x' into a pattern recognition algorithm SVM(x',θ) to obtain w operating mode labels i for the nth chiller unit. Based on the operating mode label i, obtain the corresponding carbon emission coefficient k. i,n ; Input the carbon emission coefficient corresponding to the operating mode label i of the nth refrigeration unit in group w into the optimization model; From w load factors x', select the load factor x” that minimizes the loss function of the nth chiller unit. n , and x” n Complete output adjustment load rate x” n Before and after, the total cooling capacity output of all chillers in the air conditioning system remains unchanged, and output x” n These are the optimized operating parameters for the nth refrigeration unit; the constraint expressions are as follows: Among them, Q n Let x be the rated cooling capacity of the nth chiller. n Adjust the load factor before the nth chiller, x” n The load rate of the nth chiller is adjusted.

5. An air conditioning system carbon efficiency / energy efficiency management system implementing the method as described in claim 1, characterized in that, include: The mode operation analysis and learning module is used to classify the operation modes of each chiller in the air conditioning system based on historical operating data of each chiller using a K-means model, and obtain the operating mode labels of the chillers; the operating data includes a variety of operating parameters; The carbon emission coefficient learning module is used to learn the carbon emission coefficient based on relevant parameters and operating mode labels of the chiller, and to determine the carbon emission coefficient corresponding to each operating mode label. Specifically: Where βi is the carbon emission coefficient corresponding to the i-th operating mode label; i is the operating mode label; βr is the base operating mode carbon emission coefficient; and COP is the carbon emission coefficient of the base operating mode. r COP is the reference energy efficiency for the baseline operating mode. i The reference energy efficiency for the i-th operating mode label; Among them, COP i The calculation formula is: In the formula, u is the sequence number of the u-th sample system operation data record, Q j Let P be the actual cooling capacity of the system in the j-th record, P be the actual power of the system in the u-th record, and h be the total number of records tagged with the i-th operating mode. The pattern recognition algorithm training module is used to learn patterns based on running mode labels and historical running data to obtain a trained pattern recognition algorithm. The optimization algorithm execution module is used to randomly generate new specified parameters based on the real-time operating data of each chiller. It inputs other parameters from the real-time operating data and the new specified parameters into the pattern recognition algorithm to obtain the real-time operating mode label of each chiller. Based on the real-time operating mode label of each chiller, it obtains the corresponding carbon emission coefficient. Based on the carbon emission coefficient corresponding to the real-time operating mode label of each chiller, it optimizes the operating parameters by pre-constructing an optimization model with the goal of minimizing carbon emissions and based on the constraint that the total cooling capacity output by all chillers in the air conditioning system remains unchanged. The system control module is used to feed back the optimized operating parameters of each chiller to the air conditioning system and to control the real-time operating status of each chiller.

6. The air conditioning system carbon efficiency / energy efficiency management system according to claim 5, characterized in that, The method involves using historical operating data of each chiller in the air conditioning system and performing pattern operation analysis and learning through a K-means model to obtain the operating pattern labels of the chillers, specifically including: Input the historical operating data of each chiller in the air conditioning system into the K-means model to generate a sample set T = {x} u } 1≤u≤N x u ∈R n Let u be the feature vector of the u-th sample in the sample set; In the sample set T, K samples are randomly selected as initial cluster centers. Then, the distance between each sample and each cluster center is calculated, and each sample is assigned to the nearest cluster center. Each cluster center represents a category. At this point, the u-th sample in the sample set is assigned the initial running mode label y′. u ∈{c1, c2, ... c K }; Calculate the sum of distances D from all samples to the centroid of their respective clusters, using the following formula: Where C i Let be the centroid of the i-th cluster; the dist function is the defined distance metric. Once all samples have been assigned an initial running mode label, the cluster centers of each cluster are recalculated based on the existing objects in the cluster. Return to the step of calculating the distance between each sample and each cluster center, until the cluster centers of each cluster no longer change, and each sample is assigned to the final running mode label y. u ∈{c1, c2, ... c K } 7. The air conditioning system carbon efficiency / energy efficiency management system according to claim 6, characterized in that, The process of learning a pattern recognition algorithm based on operating mode labels and historical operating data to obtain a trained pattern recognition algorithm specifically includes: A training sample set T = {(x} is constructed based on operation mode labels and historical operation data. u y u )} 1≤u≤N y u ∈{+1, -1}, x u ∈R n R n Refers to the real number vector space; The SVM model employs a radial basis function kernel. The input training sample set is used to optimize and train the SVM model using soft margin maximization and kernel trick techniques, with the following parameter ranges as constraints: s.t.y u (<w,φ(x u )>+b)-1≥0,u=1,2,...,N x u ≥0,u=1,2,...,N In the formula, x u Let y be the feature vector of the u-th sample in the training set; u Let be the operating mode label of the u-th sample in the training set, and N be the total number of categories of the samples; φ() is the nonlinear mapping from the original input space to the high-dimensional feature space. The nonlinear support vector machine maps the input to feature vectors through this mapping, w is the normal vector of the hyperplane in the feature space, b is the bias of the hyperplane, <, > denote the inner product of two vectors, and ξ u C is a slack variable, and C is a penalty parameter; The trained pattern recognition algorithm SVM model is as follows: i = SVM(x,θ) In the formula, i is the operating mode label, x is the load rate parameter in the chiller operating data, and θ is the meteorological parameter and other operating parameters in the chiller operating data.

8. The air conditioning system carbon efficiency / energy efficiency management system according to claim 7, characterized in that, The method involves randomly generating new specified parameters based on the real-time operating data of each chiller, and inputting other parameters from the real-time operating data and the new specified parameters into a pattern recognition algorithm to obtain the real-time operating mode label of each chiller. The carbon emission coefficient corresponding to each real-time operation mode label is obtained based on the real-time operation mode label of each chiller; based on the carbon emission coefficient corresponding to each real-time operation mode label of each chiller, the operating parameters are optimized by pre-constructing an optimization model with the goal of minimizing carbon emissions and under the constraint that the total cooling capacity output by all chillers in the air conditioning system remains unchanged; specifically including: An optimization model is constructed with the objective of minimizing carbon emissions. The loss function in the optimization model is expressed as follows: Where n is the chiller serial number, m is the total number of chillers, i is the operating mode label of the output result based on SVM(x',θ), and k is the number of chillers. i,n The carbon emission coefficient P corresponding to the nth refrigeration unit under the i-th operating mode label. n Let x' be the rated power of the nth refrigeration unit. n The load rate is randomly generated for the nth chiller unit selected through the selection process; Near the real-time load factor x of the nth chiller unit, generate w new chiller load factors x' randomly. Input other parameters from the real-time operating data of the nth chiller unit and the w new load factors x' into a pattern recognition algorithm SVM(x',θ) to obtain w operating mode labels i for the nth chiller unit. Based on the operating mode label i, obtain the corresponding carbon emission coefficient k. i,n ; Input the carbon emission coefficient corresponding to the operating mode label i of the nth refrigeration unit in group w into the optimization model; From w load factors x', select the load factor x” that minimizes the loss function of the nth chiller unit. n , and x” n Complete output adjustment load rate x” n Before and after, the total cooling capacity output of all chillers in the air conditioning system remains unchanged, and output x” n These are the optimized operating parameters for the nth refrigeration unit; the constraint expressions are as follows: Among them, Q n Let x be the rated cooling capacity of the nth chiller. n Adjust the load factor before the nth chiller, x” n The load rate of the nth chiller is adjusted.

9. A computer storage medium, wherein the computer-readable storage medium stores a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the air conditioning system carbon efficiency / energy efficiency management method as described in any one of claims 1-4.

10. An electronic device, characterized in that, Includes a memory and a processor: the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the air conditioning system carbon efficiency / energy efficiency management method as described in any one of claims 1-4.

Images