Carbon emission prediction method, device and system

Abstract

The invention discloses a carbon emission prediction method, device and system. The carbon emission prediction method comprises the following steps: calculating a grey correlation degree between electric energy consumption and various types of non-electric energy consumption; aiming at the non-electric energy of which the grey correlation degree is greater than a set threshold value, converting the consumption of each type of non-electric energy into standard coal, calculating energy by using electricity by adopting an ARDL model, and further calculating a first carbon emission amount through an energy carbon emission factor; for the non-electric energy sources with the grey correlation degree smaller than a set threshold value, a GM (1, 1) model is adopted to predict the consumption of each non-electric energy source, and then second carbon emission is calculated through the energy carbon emission factor; and adding the first carbon emission, the second carbon emission and the electric power carbon emission to obtain total carbon emission, and completing carbon emission prediction. According to the method, the association relationship between the electric energy and the non-electric energy is fully considered, different prediction methods are adopted for energy types with different association intensities, and the carbon emission is accurately predicted.

Description

Technical Field

[0001] The present invention belongs to the technical field of carbon emission prediction, and specifically relates to a carbon emission prediction method, device and system. Background Art

[0002] In the international carbon market, there are two main types of carbon emission accounting methods: online monitoring method and carbon emission factor method. The online monitoring method uses a continuous emission monitoring system to monitor the CO2 concentration and flue gas flow in the exhaust gas in real time to obtain continuous and real-time CO2 emissions. In the future, the online monitoring method will face difficulties and challenges such as high cost pressure and limited industry scope in its implementation and promotion. Therefore, in practice, my country's carbon market currently mainly uses the emission factor method to calculate the carbon emissions of enterprises. However, due to the lack of real-time data of non-electric energy, this method has a certain lag, so a reliable carbon emission prediction method is needed to improve the current carbon emission accounting system. Summary of the invention

[0003] In response to the above problems, the present invention proposes a carbon emission prediction method, device and system, which fully consider the correlation between electric energy and non-electric energy, adopt different prediction methods for energy types with different correlation strengths, and accurately predict carbon emissions.

[0004] In order to achieve the above technical objectives and the above technical effects, the present invention is implemented through the following technical solutions:

[0005] In a first aspect, the present invention provides a carbon emission prediction method, comprising:

[0006] Calculate the grey correlation between electricity consumption and various types of non-electric energy consumption;

[0007] For non-electric energy with grey correlation greater than the set threshold, the consumption of various types of non-electric energy is converted into standard coal, and the ARDL model is used to calculate energy with electricity, and then the first carbon emission is calculated through the energy carbon emission factor;

[0008] For non-electric energy with grey correlation less than the set threshold, the GM (1,1) model is used to predict the consumption of each non-electric energy, and then the second carbon emission is calculated through the energy carbon emission factor;

[0009] The first carbon emissions, the second carbon emissions and the electricity carbon emissions are added together to obtain the total carbon emissions, thereby completing the carbon emissions forecast.

[0010] In combination with the first aspect, optionally, the method for calculating the grey relational degree includes:

[0011] The grey correlation analysis method is used to calculate the grey correlation between electricity consumption and various types of non-electric energy consumption.

[0012] In combination with the first aspect, optionally, the method for calculating the grey relational degree includes:

[0013] Take the energy consumption as the reference series:

[0014] Y = {y(k)|k = 1, 2, ..., n};

[0015] Use non-electrical energy consumption as a comparison series:

[0016] X i ={x i (k)|k=1,2,…,n},i=1,2,…,m;

[0017] In the formula, n represents the total number of years, m represents the total number of non-electric energy types, y(k) is the electricity consumption in the kth year, and x i (k) is the consumption of non-electric energy i in year k;

[0018] The reference sequence and the comparison sequence are dimensionally processed to obtain dimensionally processed data. The processing formula of the dimensionally processed data is:

[0019]

[0020] Based on the data obtained after dimensionless processing, the grey correlation coefficient is calculated. The calculation formula of the grey correlation coefficient is:

[0021]

[0022] Among them, ξ i (k) is the grey correlation coefficient between the electric energy consumption in the kth year and the consumption of non-electric energy i, ρ is the resolution coefficient,

[0023] Based on the grey relational coefficient, the grey relational degree is calculated, and the calculation formula of the grey relational degree is:

[0024]

[0025] In the formula, r i It is the grey correlation degree between the electric energy consumption and the non-electric energy i consumption.

[0026] In combination with the first aspect, optionally, the resolution coefficient ρ has a value range of 0-1.

[0027] In combination with the first aspect, optionally, the value of the resolution coefficient ρ is 0.5.

[0028] In combination with the first aspect, optionally, the first carbon emission calculation method includes:

[0029] Multiply the consumption of various types of non-electric energy by the corresponding discount coefficient to convert it into standard coal, and then add them together to obtain the total non-electric energy consumption discount;

[0030] The electric energy consumption is taken as the explanatory variable, and the total non-electric energy consumption is taken as the explained variable. The ARDL model is used to calculate the energy with electricity. The expression of the ARDL model is:

[0031]

[0032] In the formula, X is the explanatory variable, Y is the explained variable, δ0+δ1k+…+δ h k h represents the trend term, δ h represents the hth fitting coefficient, represents the autoregressive term, represents the distribution lag term, q represents the lag order of the explanatory variable, Q represents the total number of lag orders of the explanatory variable, ∈ k represents the noise term of the kth year, P represents the total number of lag orders of the explained variable, p represents the lag order of the explained variable, and k represents the kth year;

[0033] Substituting the electricity consumption of the year to be predicted into the ARDL electric energy model, the total non-electric energy consumption of that year can be predicted, and then the factor method is used to calculate the first carbon emissions.

[0034] In combination with the first aspect, optionally, the second carbon emission calculation method includes:

[0035] The GM (1,1) model is used to predict the consumption of each non-electric energy source. The prediction steps of the GM (1,1) model are as follows:

[0036] Suppose the original sequence is: x (0) ={x (0) (k)|k=1,2,...,n}, where n is the year, x (0) (k) is the value of non-electric energy consumption in year k;

[0037] Accumulate the original sequence to get a cumulative generated sequence: x (1) ={x (1 )(k)|k=1,2,...,n}, where x (1) The sequence satisfies the first-order linear differential equation model:

[0038] The least squares method is used to solve the unknown parameters a and u, including:

[0039] definition: Yn =[x (0) (2)x (0) (3)…x (0) (n)] T , then the estimated values ​​of a and u are:

[0040] The parameters Substitute it into the differential equation and solve it,

[0041] The predicted values ​​of the original series are as follows:

[0042]

[0043] The non-electric energy consumption predicted by the GM(1,1) model By multiplying by the corresponding carbon emission factor, we can get the second carbon emission corresponding to non-electric energy that is not strongly related to electric energy.

[0044] In combination with the first aspect, optionally, the method for calculating the total carbon emissions includes:

[0045] Multiply the electricity consumption by the electricity carbon emission factor to obtain the electricity carbon emissions, and add them to the calculated first carbon emissions and second carbon emissions to obtain the total carbon emissions.

[0046] In a second aspect, the present invention provides a carbon emission prediction device, comprising:

[0047] Grey correlation calculation module, used to calculate the grey correlation between electric energy consumption and various non-electric energy consumption;

[0048] The first carbon emission calculation module is used to convert the consumption of various types of non-electric energy into standard coal for non-electric energy with a grey correlation greater than a set threshold, and use the ARDL model to calculate energy with electricity, and then calculate the first carbon emission through the energy carbon emission factor;

[0049] The second carbon emission calculation module is used to use the GM (1,1) model to predict the consumption of each non-electric energy source with a grey correlation degree less than a set threshold, and then calculate the second carbon emission through the energy carbon emission factor;

[0050] The total carbon emissions calculation module is used to add the first carbon emissions, the second carbon emissions and the electricity carbon emissions to obtain the total carbon emissions and complete the carbon emissions forecast.

[0051] In a third aspect, the present invention provides a carbon emission prediction system, including a storage medium and a processor;

[0052] The storage medium is used to store instructions;

[0053] The processor is configured to operate according to the instructions to execute the method according to any one of the first aspects.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention proposes a carbon emission prediction method, device and system, which fully consider the correlation between electric energy and non-electric energy, adopt different prediction methods for energy types with different correlation strengths, and accurately predict carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor, among which:

[0057] Figure 1 A schematic diagram of a process flow of a carbon emission prediction method according to an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of the grey correlation between non-electric energy consumption and electric energy consumption according to an embodiment of the present invention;

[0059] Figure 3 A schematic diagram of carbon emissions and errors predicted by the GRA-GM(1,1)-ARDL model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0062] Example 1

[0063] The present invention provides a carbon emission prediction method. Figure 1 As shown, including:

[0064] (1) Calculate the grey correlation between electricity consumption and various types of non-electric energy consumption;

[0065] (2) For non-electric energy sources with grey correlation greater than the set threshold, the consumption of various types of non-electric energy is converted into standard coal, and the ARDL model is used to calculate energy with electricity, and then the first carbon emission is calculated through the energy carbon emission factor;

[0066] (3) For non-electric energy sources whose grey correlation is less than the set threshold, the GM (1,1) model is used to predict the consumption of each non-electric energy source, and then the second carbon emission is calculated through the energy carbon emission factor;

[0067] (4) Add the first carbon emissions, the second carbon emissions and the electricity carbon emissions to obtain the total carbon emissions, thereby completing the carbon emissions forecast.

[0068] In a specific implementation of the embodiment of the present invention, the method for calculating the grey relational degree includes:

[0069] The grey correlation analysis method is used to calculate the grey correlation between electricity consumption and various types of non-electric energy consumption.

[0070] In a specific implementation of the embodiment of the present invention, the method for calculating the grey relational degree includes:

[0071] Take the energy consumption as the reference series:

[0072] Y = {y(k)|k = 1, 2, ..., n};

[0073] Use non-electrical energy consumption as a comparison series:

[0074] X i ={x i (k)|k=1,2,…,n},i=1,2,…,m;

[0075] In the formula, n represents the total number of years, m represents the total number of non-electric energy types, y(k) is the electricity consumption in the kth year, and x i (k) is the consumption of non-electric energy i in year k;

[0076] The reference sequence and the comparison sequence are dimensionally processed to obtain dimensionally processed data. The processing formula of the dimensionally processed data is:

[0077]

[0078] Based on the data obtained after dimensionless processing, the grey correlation coefficient is calculated. The calculation formula of the grey correlation coefficient is:

[0079]

[0080] Among them, ξ i (k) is the grey correlation coefficient between the electric energy consumption in the kth year and non-electric energy i, ρ is the resolution coefficient, The value range of the resolution coefficient ρ is 0-1. Preferably, the value of the resolution coefficient ρ is 0.5.

[0081] Based on the grey relational coefficient, the grey relational degree is calculated, and the calculation formula of the grey relational degree is:

[0082]

[0083] In the formula, r i It is the grey correlation degree between the electric energy consumption and the non-electric energy i consumption.

[0084] In a specific implementation of the embodiment of the present invention, the first carbon emission calculation method includes:

[0085] Multiply the consumption of various types of non-electric energy by the corresponding discount coefficient to convert it into standard coal, and then add them together to obtain the total non-electric energy consumption discount;

[0086] The electric energy consumption is taken as the explanatory variable, and the total non-electric energy consumption is taken as the explained variable. The ARDL model is used to calculate the energy with electricity. The expression of the ARDL model is:

[0087]

[0088] In the formula, X is the explanatory variable, Y is the explained variable, δ0+δ1k+…+δ h k h represents the trend term, δ h represents the hth fitting coefficient, represents the autoregressive term, represents the distribution lag term, q represents the lag order of the explanatory variable, Q represents the total number of lag orders of the explanatory variable, ∈ k represents the noise term of the kth year, P represents the total number of lag orders of the explained variable, p represents the lag order of the explained variable, and k represents the kth year;

[0089] Substituting the electricity consumption of the year to be predicted (this parameter can be obtained through collection) into the ARDL electric energy model, the total non-electric energy consumption of that year can be predicted, and then the factor method is used to calculate the first carbon emissions.

[0090] In a specific implementation of the embodiment of the present invention, the second carbon emission calculation method includes:

[0091] The GM (1,1) model is used to predict the consumption of each non-electric energy source. The prediction steps of the GM (1,1) model are as follows:

[0092] Suppose the original sequence is: x (0) ={x (0) (k)|k=1,2,...,n}, where n is the year, x (0) (k) is the value of non-electric energy consumption in year k;

[0093] Accumulate the original sequence to get a cumulative generated sequence: x (1) ={x (1) (k)|k=1,2,...,n}, where x (1) The sequence satisfies the first-order linear differential equation model:

[0094] Use the least squares method to solve the unknown parameters a and u, including

[0095] definition: Y n =[x (0) (2)x (0) (3)…x (0) (n)] T , then the estimated values ​​of a and u are:

[0096] The parameters Substitute it into the differential equation and solve it,

[0097] The predicted values ​​of the original series are as follows:

[0098]

[0099] The non-electric energy consumption predicted by the GM(1,1) model By multiplying by the corresponding carbon emission factor, we can get the second carbon emission corresponding to non-electric energy that is not strongly related to electric energy.

[0100] In a specific implementation of the embodiment of the present invention, the method for calculating the total carbon emissions includes:

[0101] Multiply the electricity consumption by the electricity carbon emission factor to obtain the electricity carbon emissions, and add them to the calculated first carbon emissions and second carbon emissions to obtain the total carbon emissions.

[0102] The carbon emission prediction method in the embodiment of the present invention is described in detail below in conjunction with a specific implementation method. The energy and GDP data of a province from 2005 to 2021 are used to predict carbon emissions, wherein the data from 2005 to 2018 are used for model training, and the data from 2019 to 2021 are used for model verification.

[0103] (1) Grey correlation analysis of electricity and non-electric energy consumption

[0104] The grey correlation between various non-electric energy consumption and electric energy consumption obtained by GRA analysis is as follows: Figure 2 As shown. Figure 2 It can be seen that the grey correlation between other coal gas, coal gangue, other energy, raw coal, crude oil, liquefied petroleum gas, washed coal, fuel oil, other petroleum products and electricity is less than 0.6, which shows that the correlation strength between these 9 types of energy and electricity is not high enough. Further analysis of the energy consumption data over the years found that the consumption of washed coal, coal gangue, and other coal gas was 0 in recent years, so no prediction is made. The GM (1,1) model is used to predict the consumption of other energy, raw coal, crude oil, liquefied petroleum gas, fuel oil, and other petroleum products in 2019-2021, and the remaining 21 types of energy with high correlation intensity with electricity are converted into standard coal and predicted using the ARDL model.

[0105] (2) ARDL model predicts energy consumption with strong grey correlation

[0106] 21 types of energy with high correlation intensity with electricity are converted into standard coal, and the ARDL model is used to calculate energy with electricity in combination with GDP data and electricity data. Since the data does not meet the requirements of stability, the data is first preprocessed by taking the logarithm method. After preprocessing, the energy data is still not stable, and the energy data is further first-order differentiated. Comparing the AIC values ​​of different models, it is found that the ARDL model works best when energy consumption lags for 3 periods, the economy does not lag, and the electricity does not lag. The model results are shown in Table 1. The model predicts that the energy consumption in 2019-2021 will be 13460.84367, 13530.62997 and 13771.0836 million tons of standard coal, respectively, and the corresponding carbon emissions will be 37330.96, 37524.50 and 38191.35 million tons, respectively.

[0107] Table 1 ARDL model results

[0108] coef std err z P>|z| [0.025 0.975] const -2.979 2.089 -1.426 0.192 -7.796 1.838 EnergyConsumption_diff.L1 0.0157 0.228 0.069 0.947 -0.509 0.541 EnergyConsumption_diff.L2 -0.3643 0.274 -1.329 0.221 -0.997 0.268 EnergyConsumption_diff.L3 -0.6309 0.279 -2.265 0.053 -1.273 0.011 Log_Electricity.L0 2.5844 1.161 2.225 0.057 -0.094 5.263 Log_GDP.L0 -1.7020 0.708 -2.405 0.043 -3.334 -0.070

[0109] (3) GM (1,1) model predicts energy consumption with weak grey correlation

[0110] The consumption of six types of energy in 2019-2021 predicted by the GM (1,1) model and the carbon emissions multiplied by the corresponding energy carbon emission factors are shown in Table 2. The negative signs of the raw coal and other energy consumption values ​​in the table are related to the statistical method of the energy balance sheet.

[0111] Table 2 Energy consumption predicted by GM(1,1) model from 2019 to 2021

[0112]

[0113] (4) Carbon emission prediction results and errors

[0114] The carbon emissions from 2019 to 2021 predicted by the GRA-GM (1,1)-ARDL model in the embodiment of the present invention and the carbon emissions calculated by the factor method are as follows: Figure 3 The forecast errors for 2019, 2020 and 2021 are 3.08%, 4.57% and 1.76% respectively, indicating that the GRA-GM(1,1)-ARDL model proposed in the embodiment of the present invention has high accuracy.

[0115] Example 2

[0116] An embodiment of the present invention provides a carbon emission prediction device, comprising:

[0117] Grey correlation calculation module, used to calculate the grey correlation between electric energy consumption and various non-electric energy consumption;

[0118] The first carbon emission calculation module is used to convert the consumption of various types of non-electric energy into standard coal for non-electric energy with a grey correlation greater than a set threshold, and use the ARDL model to calculate energy with electricity, and then calculate the first carbon emission through the energy carbon emission factor;

[0119] The second carbon emission calculation module is used to use the GM (1,1) model to predict the consumption of each non-electric energy source with a grey correlation degree less than a set threshold, and then calculate the second carbon emission through the energy carbon emission factor;

[0120] The total carbon emissions calculation module is used to add the first carbon emissions, the second carbon emissions and the electricity carbon emissions to obtain the total carbon emissions and complete the carbon emissions forecast.

[0121] The rest are the same as in Example 1.

[0122] Example 3

[0123] An embodiment of the present invention provides a carbon emission prediction system, including a storage medium and a processor;

[0124] The storage medium is used to store instructions;

[0125] The processor is configured to operate according to the instructions to execute the method according to any one of the embodiments 1.

[0126] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

[0131] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A carbon emission prediction method, characterized in that: include: Calculate the grey correlation between electricity consumption and various types of non-electric energy consumption; For non-electric energy with grey correlation greater than the set threshold, the consumption of various types of non-electric energy is converted into standard coal, and the ARDL model is used to calculate energy with electricity, and then the first carbon emission is calculated through the energy carbon emission factor; For non-electric energy with grey correlation less than the set threshold, the GM (1,1) model is used to predict the consumption of each non-electric energy, and then the second carbon emission is calculated through the energy carbon emission factor; The first carbon emissions, the second carbon emissions and the electricity carbon emissions are added together to obtain the total carbon emissions, thereby completing the carbon emissions forecast.

2. A carbon emission prediction method according to claim 1, characterized in that: The calculation method of the grey relational degree includes: The grey correlation analysis method is used to calculate the grey correlation between electricity consumption and various types of non-electric energy consumption.

3. A carbon emission prediction method according to claim 2, characterized in that: The calculation method of the grey relational degree includes: Take the energy consumption as the reference series: Y = {y(k)|k = 1, 2, ..., n}; Use non-electrical energy consumption as a comparison series: X i ={x i (k)|k=1,2,…,n},i=1,2,…,m; In the formula, n represents the total number of years, m represents the total number of non-electric energy types, y(k) is the electricity consumption in the kth year, and x i (k) is the consumption of non-electric energy i in year k; The reference sequence and the comparison sequence are dimensionally processed to obtain dimensionally processed data. The processing formula of the dimensionally processed data is: Based on the data obtained after dimensionless processing, the grey correlation coefficient is calculated. The calculation formula of the grey correlation coefficient is: Among them, ξ i (k) is the grey correlation coefficient between the electric energy consumption in the kth year and the consumption of non-electric energy i, ρ is the resolution coefficient, Based on the grey relational coefficient, the grey relational degree is calculated, and the calculation formula of the grey relational degree is: In the formula, r i It is the grey correlation degree between the electric energy consumption and the non-electric energy i consumption.

4. A carbon emission prediction method according to claim 3, characterized in that: The resolution coefficient ρ ranges from 0 to 1.

5. A carbon emission prediction method according to claim 4, characterized in that: The resolution coefficient ρ is set to 0.

5.

6. A carbon emission prediction method according to claim 1, characterized in that: The first carbon emission calculation method includes: Multiply the consumption of various types of non-electric energy by the corresponding discount coefficient to convert it into standard coal, and then add them together to obtain the total non-electric energy consumption discount; The electric energy consumption is taken as the explanatory variable, and the total non-electric energy consumption is taken as the explained variable. The ARDL model is used to calculate the energy with electricity. The expression of the ARDL model is: In the formula, X is the explanatory variable, Y is the explained variable, δ0+δ1k+...+δ h k h represents the trend term, δ h represents the hth fitting coefficient, represents the autoregressive term, represents the distribution lag term, q represents the lag order of the explanatory variable, Q represents the total number of lag orders of the explanatory variable, ∈ k represents the noise term of the kth year, P represents the total number of lag orders of the explained variable, p represents the lag order of the explained variable, and k represents the kth year; Substituting the electricity consumption of the year to be predicted into the ARDL electric energy model, the total non-electric energy consumption of that year can be predicted, and then the factor method is used to calculate the first carbon emissions.

7. A carbon emission prediction method according to claim 1, characterized in that: The second carbon emission calculation method includes: The GM (1,1) model is used to predict the consumption of each non-electric energy source. The prediction steps of the GM (1,1) model are as follows: Assume that the original sequence is: x (0) ={x (0) (k)|k=1,2,...,n}, where n is the year, x (0) (k) is the value of non-electric energy consumption in year k; Accumulate the original sequence to get a cumulative generated sequence: x (1) ={x (1) (k)|k=1,2,...,n}, where x (1) The sequence satisfies the first-order linear differential equation model: The least squares method is used to solve the unknown parameters a and u, including: definition: Y n =[x (0) (2) x (0) (3) … x (0) (n)] T , then the estimated values ​​of a and u are: The parameters Substitute it into the differential equation and solve it, The predicted values ​​of the original series are as follows: The non-electric energy consumption predicted by the GM(1,1) model By multiplying by the corresponding carbon emission factor, we can get the second carbon emission corresponding to non-electric energy that is not strongly related to electric energy.

8. A carbon emission prediction method according to claim 1, characterized in that: The calculation method of the total carbon emissions includes: Multiply the electricity consumption by the electricity carbon emission factor to obtain the electricity carbon emissions, and add them to the calculated first carbon emissions and second carbon emissions to obtain the total carbon emissions.

9. A carbon emission prediction device, characterized in that: include: Grey correlation calculation module, used to calculate the grey correlation between electric energy consumption and various non-electric energy consumption; The first carbon emission calculation module is used to convert the consumption of various types of non-electric energy into standard coal for non-electric energy with a grey correlation greater than a set threshold, and use the ARDL model to calculate energy with electricity, and then calculate the first carbon emission through the energy carbon emission factor; The second carbon emission calculation module is used to use the GM (1,1) model to predict the consumption of each non-electric energy source with a grey correlation degree less than a set threshold, and then calculate the second carbon emission through the energy carbon emission factor; The total carbon emissions calculation module is used to add the first carbon emissions, the second carbon emissions and the electricity carbon emissions to obtain the total carbon emissions and complete the carbon emissions forecast.

10. A carbon emission prediction system, characterized in that: including storage media and processors; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the method according to any one of claims 1-8.

Images