Carbon footprint analysis method and device for an electrical device

Abstract

The application discloses a carbon efficiency analysis method and device for an electrical equipment. The method comprises the following steps: simulating a first carbon consumption parameter corresponding to a plurality of input variable groups by using a preset white-box model; forming a training set by combining the input variable groups with the first carbon consumption parameter groups; training a data fitting model to obtain a black-box model; generating the training set of the black-box model by using the white-box model, thereby solving the problem of insufficient data quantity when training the current black-box model; predicting a target input variable value of the electrical equipment according to a real carbon consumption parameter of the electrical equipment by using the black-box model, thereby inversely deducing the target input variable value by using the black-box model, thereby solving the problem that the current model input needs complete input variables; the black-box model has higher calculation efficiency than the white-box model, thereby improving the carbon efficiency analysis efficiency; and finally, if the target input variable value is within a preset reference value range, it is determined that the electrical equipment has a carbon efficiency problem, thereby realizing carbon efficiency analysis and reducing the implementation difficulty of the carbon efficiency analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of carbon efficiency analysis, and particularly relates to a carbon efficiency analysis method and device for an electrical equipment. BACKGROUND

[0002] The carbon efficiency problem of an electrical equipment is usually evaluated by changing the input parameters of a carbon consumption model and observing the change of carbon emission values output by the carbon consumption model to determine the carbon saving potential of the equipment. At present, the carbon consumption model includes a white box model and a black box model. The white box model is an equipment model constructed by a software tool based on physical laws, and the black box model is an equipment model constructed by data fitting.

[0003] However, the current carbon consumption model needs complete input variables to obtain carbon consumption output, and the input variables are difficult to obtain in actual situations, such as the comprehensive performance coefficient of a cold machine, the degradation coefficient of a cold machine or the shape coefficient. At the same time, the calculation time of the white box model is long and very time-consuming, and the data amount required for the black box model in the fitting stage is insufficient, and the model effect is not good. It can be seen that the current carbon efficiency analysis method for electrical equipment has the problem of great implementation difficulty. SUMMARY

[0004] The present application provides a carbon efficiency analysis method and device for an electrical equipment to solve the technical problem of great implementation difficulty of the current carbon efficiency analysis method for electrical equipment.

[0005] In order to solve the above technical problem, in a first aspect, the present application provides a carbon efficiency analysis method for an electrical equipment, comprising:

[0006] simulating first carbon consumption parameters corresponding to a plurality of input variable groups by using a preset white box model;

[0007] forming a training set by combining the input variable groups and the first carbon consumption parameters, training a data fitting model to obtain a black box model;

[0008] predicting target input variable values of the electrical equipment according to actual carbon consumption parameters of the electrical equipment by using the black box model;

[0009] if the target input variable values are within a preset reference value range, determining that the electrical equipment has a carbon efficiency problem.

[0010] The application simulates first carbon consumption parameters corresponding to a plurality of input variable groups by using a preset white box model, and forms a training set by combining the input variable groups and the first carbon consumption parameters, trains a data fitting model, obtains a black box model, uses the white box model to generate the training set of the black box model, thereby solving the problem of insufficient data quantity when training the current black box model; then, the black box model is used to predict target input variable values of the power consumption equipment according to real carbon consumption parameters of the power consumption equipment, so as to inversely deduce the target input variable values such as the comprehensive performance coefficient of the cold machine and the cold machine degradation coefficient of the power consumption equipment according to the real carbon consumption parameters by using the black box model, thereby solving the problem that complete input variables are required for the current model input, and the calculation efficiency of the black box model is higher than that of the white box model, thereby improving the carbon efficiency analysis efficiency; finally, if the target input variable values are within a preset reference value range, it is determined that the power consumption equipment has a carbon efficiency problem, thereby realizing carbon efficiency analysis and reducing the implementation difficulty of the carbon efficiency analysis.

[0011] As preferred, the white box model is used to simulate first carbon consumption parameters corresponding to a plurality of input variable groups, including:

[0012] The plurality of input parameters of the power consumption equipment are subjected to data processing to obtain a plurality of input variable groups.

[0013] The first carbon consumption parameter corresponding to each input variable group is determined based on the white box model.

[0014] As preferred, the plurality of input parameters of the power consumption equipment are subjected to data processing to obtain a plurality of input variable groups, including:

[0015] If there are missing parameters in the plurality of input parameters, the missing values of the missing parameters are completed to obtain a plurality of complete input parameters.

[0016] Data transformation is performed on each complete input parameter to obtain a plurality of extension parameters corresponding to each complete input parameter.

[0017] The plurality of complete input parameters and the plurality of extension parameters are randomly combined to obtain a plurality of input variable groups.

[0018] As preferred, the first carbon consumption parameter corresponding to each input variable group is determined based on the white box model, including:

[0019] The plurality of input variable groups are input into the white box model, and energy consumption parameters corresponding to each input variable group are output.

[0020] The first carbon consumption parameter corresponding to each input variable group is generated according to the energy consumption parameters and a preset carbon emission factor.

[0021] As preferred, the black box model is used to predict target input variable values of the power consumption equipment according to real carbon consumption parameters of the power consumption equipment, including:

[0022] Determine, by using the black-box model, second carbon consumption parameters corresponding to a plurality of random input variable groups;

[0023] If a difference between the target carbon consumption parameter and the real carbon consumption parameter is less than a preset difference value, the random input variable group corresponding to the target carbon consumption parameter is taken as a target input variable group, the target carbon consumption parameter is one of the second carbon consumption parameters, and the target variable group contains target input variable values.

[0024] Preferably, the determining, by using the black-box model, of the second carbon consumption parameters corresponding to the plurality of random input variable groups comprises:

[0025] Randomly generating a first random input variable group based on a preset constraint range of the target input variable values;

[0026] Determining, by using the black-box model, a second carbon consumption parameter corresponding to the first random input variable group;

[0027] If a difference between the second carbon consumption parameter and the real carbon consumption parameter is not less than the preset difference value, selecting, by using a preset optimization algorithm, a second random input variable group based on a preset constraint range;

[0028] Determining, by using the black-box model, a second carbon consumption parameter corresponding to the second random input variable group, until a difference between the second carbon consumption parameter and the real carbon consumption parameter is less than the preset difference value.

[0029] Preferably, if the target input variable values are within a preset reference value range, the determining of the existence of the carbon efficiency problem of the power consumption equipment further comprises:

[0030] Obtaining sensor data of the power consumption equipment;

[0031] Performing data analysis on the sensor data based on a preset carbon efficiency analysis strategy to determine a carbon efficiency problem type of the power consumption equipment.

[0032] In a second aspect, the application provides a carbon efficiency analysis device of a power consumption equipment, comprising:

[0033] A simulation module configured to simulate, by using a preset white-box model, first carbon consumption parameters corresponding to a plurality of input variable groups;

[0034] A training module configured to form a training set by combining the input variable groups and the first carbon consumption parameters, train a data fitting model, and obtain a black-box model;

[0035] A prediction module configured to predict, by using the black-box model, target input variable values of the power consumption equipment according to a real carbon consumption parameter of the power consumption equipment;

[0036] A determination module configured to determine that the power consumption equipment has a carbon efficiency problem if the target input variable values are within a preset reference value range.

[0037] In a third aspect, the present application provides a computer device, comprising a processor and a memory, the memory being configured to store a computer program, the computer program being configured to implement the carbon efficiency analysis method of the power consuming device according to the first aspect when executed by the processor.

[0038] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, the computer program being configured to implement the carbon efficiency analysis method of the power consuming device according to the first aspect when executed by a processor.

[0039] It should be noted that the beneficial effects of the second aspect to the fourth aspect described above can refer to the related description of the first aspect, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A flowchart of the carbon efficiency analysis method of the power consuming device according to the embodiments of the present application is shown in the figure.

[0041] Figure 2 A structural diagram of the carbon efficiency analysis device according to the embodiments of the present application is shown in the figure.

[0042] Figure 3 A structural diagram of the computer device according to the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0044] As described in the related art, the current carbon consumption model needs complete input variables to obtain carbon consumption output, and the input variables are difficult to obtain in actual situations, such as cold machine comprehensive performance coefficient, cold machine degradation coefficient or body shape coefficient. At the same time, the calculation time of the white box model is longer and very time-consuming; the amount of data required for the black box model in the fitting stage is insufficient, and the model effect is not good. It can be seen that the current carbon efficiency analysis method of the power consuming device has the problem of difficult implementation.

[0045] To this end, the embodiment of the present application provides a carbon efficiency analysis method of an electrical equipment. The method comprises the following steps: simulating a first carbon consumption parameter corresponding to a plurality of input variable groups by using a preset white-box model; forming a training set by combining the input variable groups and the first carbon consumption parameter group; training a data fitting model to obtain a black-box model; and generating the training set of the black-box model by using the white-box model, thereby solving the problem of insufficient data quantity when training the current black-box model. Then, the black-box model is used to predict a target input variable value of the electrical equipment according to a real carbon consumption parameter of the electrical equipment, thereby inversely deducing the target input variable value of the electrical equipment, such as a cold machine comprehensive performance coefficient and a cold machine degradation coefficient, by using the black-box model according to the real carbon consumption parameter, thereby solving the problem that the current model input needs complete input variables. Meanwhile, compared with the white-box model, the black-box model has higher calculation efficiency, thereby improving the carbon efficiency analysis efficiency. Finally, if the target input variable value is within a preset reference value range, it is determined that the electrical equipment has a carbon efficiency problem, thereby realizing carbon efficiency analysis and reducing the implementation difficulty of carbon efficiency analysis.

[0046] Please refer to Figure 1 , Figure 1 The embodiment of the present application provides a flowchart of a carbon efficiency analysis method of an electrical equipment. The carbon efficiency analysis method of the electrical equipment of the embodiment of the present application can be applied to a computer equipment, which includes but is not limited to a smart phone, a notebook computer, a tablet computer, a desktop computer, a physical server and a cloud server and the like. As shown in Figure 1 The carbon efficiency analysis method of the electrical equipment of the embodiment comprises steps S101 to S104, which are described in detail as follows:

[0047] In step S101, a first carbon consumption parameter corresponding to a plurality of input variable groups is simulated by using a preset white-box model.

[0048] In this step, the white-box model is a device model constructed by a standardized software tool based on the physical law of the electrical equipment, and the standardized software tool includes but is not limited to Equest, Energyplus or Dest and the like. The input variable group is a set of influence factors affecting the carbon emission efficiency performance of the electrical equipment, and each input variable group includes a plurality of input parameters, such as a cold machine comprehensive performance coefficient (COP), a cold machine degradation coefficient, a wind system type, a water system type, a supply air temperature and a fan efficiency and the like. The first carbon consumption parameter can be the carbon consumption of the electrical equipment.

[0049] Optionally, the input variable groups are input into the white-box model by using the standardized software tool, and the standardized software tool automatically outputs the first carbon consumption parameter corresponding to each input variable group.

[0050] It can be understood that in actual situations, the cold machine comprehensive COP and the cold machine degradation coefficient are difficult to obtain, so the embodiment uses preset prior knowledge to simulate the cold machine comprehensive COP and the cold machine degradation coefficient. For input parameters that can be obtained in actual situations, they can be obtained in actual situations or simulated. The input parameters obtained in actual situations and the simulated input parameters are combined into an input variable group.

[0051] In step S102, the input variable group and the first carbon consumption parameter form a training set, and a data fitting model is trained to obtain a black box model.

[0052] In this step, the data fitting model includes but is not limited to a data model constructed by a data fitting algorithm such as multiple linear regression, kernel method or neural network. Each input variable group corresponds to a first carbon consumption parameter, and the two are one-to-one corresponding to form a training set.

[0053] Optionally, using the data fitting model, the input variable group of the electric equipment is predicted according to the first carbon consumption parameter in the training set, the input variable group is compared with the input variable group corresponding to the first carbon consumption parameter in the training set, and the loss function value of the data fitting model is calculated. If the loss function value is not less than the preset loss value, the model parameters of the data fitting model are updated according to the comparison result, and the above training process is repeated based on the data fitting model after the model parameters are updated, until the number of repetitions reaches the preset number, or the loss function value is less than the preset loss value. The data fitting model obtained by the last training is used as the black box model.

[0054] In step S103, using the black box model, the target input variable value of the electric equipment is predicted according to the real carbon consumption parameter of the electric equipment.

[0055] In this step, the electric equipment includes but is not limited to a cold machine, a chilled water pump, a cooling water pump and a cooling tower and the like. The real carbon consumption parameter is the product of the real energy consumption and the carbon emission factor of the electric equipment, wherein the real energy consumption and the carbon emission factor can be easily obtained in actual situations. The target input variable value is the value of the input parameter that is difficult to obtain in actual situations, for example, the value of the cold machine comprehensive COP and the cold machine degradation coefficient.

[0056] Optionally, the real carbon consumption parameter is input into the black box model, and the target input variable group including the target input variable value is output.

[0057] Optionally, in order to ensure that the black box model falls into a local extreme point, the target input variable value can be numerically constrained to ensure that the target input variable value output by the black box model is within the data constraint range, thereby improving the prediction accuracy.

[0058] Step S104, if the target input variable value is within the preset reference value range, it is determined that the power consumption equipment has a carbon efficiency problem.

[0059] In this step, the target input variable value is compared with the preset parameter value range to determine whether the power consumption equipment has energy saving space, i.e., whether the power consumption equipment has a carbon efficiency problem. Alternatively, when the target input variable value is within the preset reference value range, it is determined that the power consumption equipment has a carbon efficiency problem; when the target input variable is not within the preset reference value range, it is determined that the power consumption equipment does not have a carbon efficiency problem.

[0060] Illustratively, when the comprehensive COP of the cold machine is lower than the theoretical COP, or the cold machine degradation coefficient is less than the preset coefficient, it indicates that the cold machine operation strategy is improper or the cold machine performance is attenuated, i.e., the cold machine has a carbon efficiency problem.

[0061] It should be noted that the present application provides a brand new carbon efficiency analysis perspective. By deducing the input variable from the real carbon consumption and comparing the deduced result with the reference value for carbon efficiency diagnosis, the problem of requiring complete input variables in the current model is solved. At the same time, the simulation data of the white box model is used to fit the black box model, so as to use the black box model as an application model in the actual application process. Compared with the low calculation efficiency of the white box model, the carbon efficiency analysis efficiency is improved.

[0062] In an embodiment, in Figure 1 Based on the embodiment shown, the preset white box model is used to simulate a first carbon consumption parameter corresponding to a plurality of input variable groups, which includes:

[0063] The plurality of input parameters of the power consumption equipment are subjected to data processing to obtain a plurality of input variable groups.

[0064] Based on the white box model, a first carbon consumption parameter corresponding to each of the input variable groups is determined.

[0065] In this embodiment, data processing includes but is not limited to data cleaning, data completion and / or data transformation, etc. This embodiment simulates a plurality of input variable groups by data processing on input parameters, realizes training set expansion, increases the data amount of the training set, and solves the problem of insufficient data amount of the training set of the current black box model.

[0066] Alternatively, the data processing on the plurality of input parameters of the power consumption equipment to obtain a plurality of input variable groups includes:

[0067] If there is a missing parameter in the plurality of input parameters, the missing value of the missing parameter is completed to obtain a plurality of complete input parameters;

[0068] Data transformation is performed on each of the complete input parameters to obtain a plurality of expansion parameters corresponding to each complete input parameter.

[0069] randomly combine the plurality of complete input parameters and the plurality of extended parameters to obtain a plurality of input variable groups.

[0070] In the optional embodiment, since some input parameters are difficult to obtain in actual situations, when there is a missing parameter in the input parameters, the missing parameter is completed by using preset prior knowledge, and data expansion is realized by using the data transformation method. It can be understood that the preset prior knowledge is manifested in the computer device as a preset missing value range of the input parameter.

[0071] For example, the input parameters include the comprehensive COP of the electrical equipment, the deterioration coefficient, the supply air temperature and the fan efficiency, wherein the comprehensive COP and the deterioration coefficient are missing parameters, the supply air temperature is a known quantity C1 to Cn, and the fan efficiency is a known quantity D1 to Dn, the missing value of the comprehensive COP is completed as A1, and the missing value of the deterioration coefficient is completed as B1; then the input parameters are transformed, such as the comprehensive COP is transformed into A2 to An, and the deterioration coefficient is transformed into B2 to Bn; finally, the input parameters and the extended parameters are randomly combined to obtain input variable groups such as (A1, B1, C1, D1), (A1, B1, C1, D2) and (A3, B4, C2, D5), and the specific input variable groups are not described here.

[0072] Optionally, the determining, based on the white-box model, of a first carbon consumption parameter corresponding to each of the input variable groups comprises:

[0073] inputting the plurality of input variable groups into the white-box model to output an energy consumption parameter corresponding to each of the input variable groups;

[0074] generating, according to the energy consumption parameter and a preset carbon emission factor, a first carbon consumption parameter corresponding to each of the input variable groups.

[0075] In the optional embodiment, by calling the above-mentioned standardized software tool, the plurality of input variable groups are input into the white-box model, the standardized software tool outputs the energy consumption parameter, and the energy consumption parameter is multiplied by the preset carbon emission factor to obtain the first carbon consumption parameter.

[0076] It can be understood that the white-box model is based on the standardized software tool and is constructed based on the physical law of the electrical equipment, so the white-box model can analyze the first carbon consumption parameter of each input variable group based on the physical law, and the disadvantage is that the calculation efficiency is low. The present application uses the white-box model to generate the training set of the black-box model, which only calculates before the training of the black-box model, and does not need to be calculated in the actual application scenario of carbon efficiency analysis of specific electrical equipment.

[0077] In an embodiment, in Figure 1On the basis of the embodiment, the black box model is used to predict the target input variable value of the power consumption equipment according to the real carbon consumption parameter of the power consumption equipment, and the method comprises the following steps of:

[0078] The black box model is used to determine a second carbon consumption parameter corresponding to each of a plurality of random input variable groups.

[0079] If the difference between the target carbon consumption parameter and the real carbon consumption parameter is less than a preset difference value, a random input variable group corresponding to the target carbon consumption parameter is taken as a target input variable group, the target carbon consumption parameter is one of the second carbon consumption parameters, and the target variable group contains the target input variable value.

[0080] In the embodiment, the random input variable group includes randomly generated input parameters and actual input parameters of the power consumption equipment, that is, input parameters that cannot be obtained in actual situations are randomly generated, and the remaining input parameters are obtained in actual situations.

[0081] Optionally, by means of the optimization idea, an optimal point is searched for in the unknown input parameter space, so that the output result of the black box model corresponding to the input parameter of the point is closest to the real carbon consumption result.

[0082] Optionally, the black box model is used to determine a second carbon consumption parameter corresponding to each of a plurality of random input variable groups, and the method comprises the following steps of:

[0083] A first random input variable group is randomly generated based on a preset constraint range of the target input variable value.

[0084] The black box model is used to determine the second carbon consumption parameter corresponding to the first random input variable group.

[0085] If the difference between the second carbon consumption parameter and the real carbon consumption parameter is not less than a preset difference value, a second random input variable group is selected based on the preset constraint range by using a preset optimization algorithm.

[0086] The black box model is used to determine the second carbon consumption parameter corresponding to the second random input variable group, until the difference between the second carbon consumption parameter and the real carbon consumption parameter is less than a preset difference value.

[0087] In the optional embodiment, some constraints are imposed on the input parameters to ensure that the optimization process of the input parameters falls into a local extreme point. For example, when the unknown input parameters are the comprehensive COP of the cold machine and the degradation coefficient of the cold machine, the preset optimization method is a particle swarm algorithm, and the preset constraint range includes that the COP is 4 to 7 and the degradation coefficient is 0.7 to 1.

[0088] In an embodiment, in Figure 1On the basis of the embodiment shown, after determining that the power consumption equipment has a carbon efficiency problem, if the target input variable value is within a preset reference value range, the method further includes:

[0089] Obtaining sensor data of the power consumption equipment;

[0090] Based on a preset carbon efficiency analysis strategy, performing data analysis on the sensor data to determine a carbon efficiency problem type of the power consumption equipment.

[0091] In this embodiment, when more detailed sub-item energy consumption data (i.e., sensor data) can be given, further device carbon efficiency analysis is performed. Exemplarily, the preset carbon efficiency analysis strategy is:

[0092]

[0093] Where T is temperature, Q is flow rate, E is power, and f is frequency. ce is condenser inlet, ee is evaporator inlet, el is evaporator outlet, LV is limit condition, chw is chilled water, s is simulation condition, rated is rated condition, b is branch, cw is cooling water, and ctf is cooling tower fan.

[0094] In order to perform the carbon efficiency analysis method of the power consumption equipment corresponding to the above-mentioned method embodiment, to realize the corresponding functions and technical effects. Referring to Figure 2 , Figure 2 A structural block diagram of a carbon efficiency analysis device for power consumption equipment provided by an embodiment of the present application is shown. For ease of illustration, only parts related to the present embodiment are shown. The carbon efficiency analysis device for power consumption equipment provided by the present embodiment includes:

[0095] A simulation module 201 is configured to simulate a first carbon consumption parameter corresponding to a plurality of input variable groups by using a preset white box model.

[0096] A training module 202 is configured to form a training set by combining the input variable groups and the first carbon consumption parameter groups, train a data fitting model, and obtain a black box model.

[0097] A prediction module 203 is configured to predict a target input variable value of the power consumption equipment according to a real carbon consumption parameter of the power consumption equipment by using the black box model.

[0098] A determination module 204 is configured to determine that the power consumption equipment has a carbon efficiency problem if the target input variable value is within a preset reference value range.

[0099] In an embodiment, in Figure 2 On the basis of the embodiment shown, the simulation module 201 includes:

[0100] a processing unit, configured to perform data processing on a plurality of input parameters of the electrical equipment to obtain a plurality of input variable groups;

[0101] a first determining unit, configured to determine, based on the white-box model, a first carbon consumption parameter corresponding to each of the input variable groups.

[0102] Optionally, the processing unit is specifically configured to:

[0103] if there is a missing parameter in the plurality of input parameters, complete the missing value of the missing parameter to obtain a plurality of complete input parameters;

[0104] perform data transformation on each of the complete input parameters to obtain a plurality of extended parameters corresponding to each of the complete input parameters;

[0105] randomly combine the plurality of complete input parameters and the plurality of extended parameters to obtain the plurality of input variable groups.

[0106] Optionally, the determining unit is specifically configured to:

[0107] input the plurality of input variable groups into the white-box model to output an energy consumption parameter corresponding to each of the input variable groups;

[0108] generate, according to the energy consumption parameter and a preset carbon emission factor, a first carbon consumption parameter corresponding to each of the input variable groups.

[0109] In an embodiment, based on the embodiment shown in Figure 2 The prediction module 203, based on the embodiment shown in

[0110] a second determining unit, configured to determine, by using the black-box model, a second carbon consumption parameter corresponding to a plurality of random input variable groups;

[0111] a unit configured to, if a difference between a target carbon consumption parameter and the real carbon consumption parameter is less than a preset difference value, take a random input variable group corresponding to the target carbon consumption parameter as a target input variable group, the target carbon consumption parameter being one of the second carbon consumption parameters, and the target variable group containing the target input variable value.

[0112] Optionally, the second determining unit is specifically configured to:

[0113] randomly generate a first random input variable group based on a preset constraint range of the target input variable value;

[0114] determine, by using the black-box model, the second carbon consumption parameter corresponding to the first random input variable group;

[0115] If the difference between the second carbon consumption parameter and the actual carbon consumption parameter is not less than a preset difference, then a second random input variable group is selected based on the preset constraint range using a preset optimization algorithm.

[0116] Using the black-box model, the second carbon consumption parameter corresponding to the second random input variable group is determined until the difference between the second carbon consumption parameter and the actual carbon consumption parameter is less than a preset difference.

[0117] In one embodiment, in Figure 2 Based on the illustrated embodiment, the device further includes:

[0118] The acquisition module is used to acquire sensor data from electrical equipment;

[0119] The analysis module is used to perform data analysis on the sensor data based on a preset carbon efficiency analysis strategy to determine the type of carbon efficiency problem of the electrical equipment.

[0120] The carbon efficiency analysis device for electrical equipment described above can implement the carbon efficiency analysis method for electrical equipment described in the above method embodiments. The options in the above method embodiments are also applicable to this embodiment, and will not be detailed here. The remaining content of this application embodiment can be referred to the content of the above method embodiments, and will not be repeated in this embodiment.

[0121] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 3 As shown, the computer device 3 of this embodiment includes: at least one processor 30 ( Figure 3 (Only one is shown in the diagram) a processor, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, wherein the processor 30 executes the computer program 32 to implement the steps in any of the above method embodiments.

[0122] The computer device 3 can be a smartphone, tablet, desktop computer, cloud server, or other computing device. This computer device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 The computer device 3 is merely an example and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0123] The processor 30 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0124] The memory 31 can be an internal storage unit of the computer device 3 in some embodiments, for example, a hard disk or a memory of the computer device 3. The memory 31 can also be an external storage device of the computer device 3 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 31 can include both an internal storage unit and an external storage device of the computer device 3. The memory 31 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0125] In addition, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in any of the above method embodiments.

[0126] The embodiments of the present application provide a computer program product. When the computer program product is run on a computer device, the computer device executes the steps in each of the above method embodiments.

[0127] In several embodiments provided by the present application, it can be understood that each block in the flowchart or block diagram can represent a module, a segment or a portion of code which includes one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figure. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the reverse order, depending on the functionality involved.

[0128] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device to perform all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0129] The specific embodiments described above further illustrate the purposes, technical solutions and beneficial effects of the present application. It should be understood that the above description is only for specific embodiments of the present application and is not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for carbon efficiency analysis of electrical equipment, characterized in that, include: Using a pre-defined white-box model, the first carbon consumption parameter corresponding to multiple sets of input variables is simulated; The input variable set and the first carbon consumption parameter are combined to form a training set, and the data fitting model is trained to obtain a black box model. Using the black-box model, the target input variable value of the electrical equipment is predicted based on the actual carbon consumption parameters of the electrical equipment. If the target input variable value is within the preset reference value range, then it is determined that the electrical equipment has a carbon efficiency problem; The process of training the data fitting model to obtain the black-box model includes: Using the data fitting model, based on the first carbon consumption parameter in the training set, the input variable group of the electrical equipment is predicted. This input variable group is compared with the input variable group corresponding to the first carbon consumption parameter in the training set, and the loss function value of the data fitting model is calculated. If the loss function value is not less than a preset loss value, the model parameters of the data fitting model are updated, and the above training process is repeated based on the data fitting model with updated model parameters until the number of repetitions reaches a preset number, or the loss function value is less than the preset loss value. The data fitting model obtained from the last training is then used as a black box model.

2. The carbon efficiency analysis method for electrical equipment as described in claim 1, characterized in that, The process of simulating the first carbon consumption parameter corresponding to multiple input variable groups using a pre-defined white-box model includes: Data processing is performed on multiple input parameters of the electrical equipment to obtain multiple sets of input variables; Based on the white-box model, the first carbon consumption parameter corresponding to each input variable group is determined.

3. The carbon efficiency analysis method for electrical equipment as described in claim 2, characterized in that, The data processing of multiple input parameters of the electrical equipment to obtain multiple sets of input variables includes: If there are missing parameters among the multiple input parameters, the missing values ​​of the missing parameters are filled in to obtain multiple complete input parameters; For each complete input parameter, a data transformation is performed to obtain multiple extended parameters corresponding to each complete input parameter; Multiple sets of input variables are obtained by randomly combining multiple complete input parameters and multiple extended parameters.

4. The carbon efficiency analysis method for electrical equipment as described in claim 2, characterized in that, The step of determining the first carbon consumption parameter corresponding to each input variable group based on the white-box model includes: The multiple sets of input variables are input into the white box model, and the energy consumption parameter corresponding to each set of input variables is output. Based on the energy consumption parameters and the preset carbon emission factor, a first carbon consumption parameter is generated for each of the input variable groups.

5. The carbon efficiency analysis method for electrical equipment as described in claim 1, characterized in that, The step of using the black-box model to predict the target input variable value of the electrical equipment based on the actual carbon consumption parameters of the electrical equipment includes: Using the black-box model, the second carbon consumption parameter corresponding to multiple sets of random input variables is determined; If the difference between the target carbon consumption parameter and the actual carbon consumption parameter is less than a preset difference, then the random input variable group corresponding to the target carbon consumption parameter is taken as the target input variable group, the target carbon consumption parameter is one of the second carbon consumption parameters, and the target input variable group contains the target input variable value.

6. The carbon efficiency analysis method for electrical equipment as described in claim 5, characterized in that, The process of using the black-box model to determine the second carbon consumption parameter corresponding to multiple sets of random input variables includes: Based on the preset constraint range of the target input variable values, a first random input variable group is randomly generated; Using the black-box model, the second carbon consumption parameter corresponding to the first set of random input variables is determined; If the difference between the second carbon consumption parameter and the actual carbon consumption parameter is not less than a preset difference, then a second random input variable group is selected based on the preset constraint range using a preset optimization algorithm. Using the black-box model, the second carbon consumption parameter corresponding to the second random input variable group is determined until the difference between the second carbon consumption parameter and the actual carbon consumption parameter is less than a preset difference.

7. The carbon efficiency analysis method for electrical equipment as described in claim 1, characterized in that, After determining that the electrical equipment has a carbon efficiency problem if the target input variable value is within a preset reference range, the method further includes: Acquire sensor data from electrical equipment; Based on a preset carbon efficiency analysis strategy, the sensor data is analyzed to determine the type of carbon efficiency problem of the electrical equipment.

8. A carbon efficiency analysis device for electrical equipment, characterized in that, A method for performing carbon efficiency analysis of electrical equipment as described in any one of claims 1 to 7, comprising: The simulation module is used to simulate the first carbon consumption parameter corresponding to multiple input variable groups using a preset white box model; The training module is used to form a training set with the input variable group and the first carbon consumption parameter, train the data fitting model, and obtain a black box model. The prediction module is used to predict the target input variable value of the electrical equipment based on the actual carbon consumption parameters of the electrical equipment using the black box model. The determination module is used to determine that the electrical equipment has a carbon efficiency problem if the target input variable value is within a preset reference value range.

9. A computer device, characterized in that, It includes a processor and a memory, the memory being used to store a computer program, which, when executed by the processor, implements the carbon efficiency analysis method for electrical equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the carbon efficiency analysis method for electrical equipment as described in any one of claims 1 to 7.

Images