Method and device for predicting provincial carbon emission, and medium

Abstract

The invention relates to the field of carbon emission prediction, in particular to a provincial carbon emission prediction method and device and a medium, and the method comprises the steps: analyzing carbon emission influence factors through a GDIM model, screening out a plurality of carbon emission driving factors which have large influence on carbon emission, and then bringing the carbon emission driving factors into an SD model, according to the method, the carbon emission driving factor is adjusted by combining historical data, different carbon emission factors are combined and set into different scene models, and the different scene models are used for carrying out scene analysis on the carbon emission to obtain the corresponding carbon emission peak time and the carbon emission, so that the prediction result is more accurate and more targeted.

Description

Technical Field

[0001] The present application relates to the field of carbon emission prediction, and in particular to a provincial carbon emission prediction method, device and medium. Background Art

[0002] When predicting future carbon emissions, the LMDI and STIRPAT models are usually used. The STIRPAT model quantitatively studies the relationship between carbon emissions and various influencing factors and predicts regional carbon emissions. It can also be predicted by constructing an energy consumption LEAP model. The LEAP model uses the obtained carbon emission factors of various types of energy consumption to calculate the total carbon emissions in the energy target year and the energy consumption data of the target year under different development intensity scenarios, and determines the target year for the peak carbon emissions of each energy source based on the total carbon emissions of the corresponding energy. In recent years, by embedding carbon emissions or carbon absorption as the main control factor into the System Dynamics (SD) model, carbon emissions can be simulated in scenarios to obtain more accurate carbon emissions prediction results.

[0003] However, most of the existing technologies directly predict regional carbon emissions without properly screening the factors affecting carbon emissions. Even if some technologies mention the driving factors of carbon emissions, they are not included in the prediction of carbon emissions, and the relationship between the two is not close.

[0004] Therefore, how to accurately screen the influencing factors of carbon emissions and add the influencing factors to the prediction process of carbon emissions to obtain a more accurate prediction of carbon emissions in a certain area is an urgent problem to be solved. Summary of the invention

[0005] The present application provides a provincial carbon emissions prediction method, which can accurately screen the influencing factors of carbon emissions, add the influencing factors to the carbon emissions prediction process, and accurately obtain the predicted carbon emissions in a certain area.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme:

[0007] In a first aspect, the present invention provides a method for predicting provincial carbon emissions, the method comprising:

[0008] Collecting historical data of the area to be predicted, wherein the historical data includes economic growth data and energy consumption data of the area to be predicted over the years;

[0009] Calculate the total carbon emissions of the area to be predicted by combining the energy consumption data with the IPCC method;

[0010] The GDIM model is used to factorize the total carbon emissions, and the R software is used to simulate the contribution of each influencing factor to the carbon emissions, and the contribution of the influencing factors is ranked to obtain multiple carbon emission driving factors;

[0011] Combining the multiple carbon emission driving factors, setting the combined results into multiple different scenarios in combination with the historical data, and constructing SD models based on the multiple different scenarios;

[0012] The scenario and the SD model are combined to predict the carbon peak time and carbon emissions of the area to be predicted.

[0013] In a preferred example of the present application, it can be further configured that the total carbon emissions of the area to be predicted are calculated by combining the IPCC method with the energy consumption data, including:

[0014] The calculation formula of the IPCC method is:

[0015]

[0016] Among them, I represents carbon emissions, E i represents the consumption of the i-th energy source, n is the number of energy types, NCV i 、CC i 、COF i They represent the lower calorific value, carbon content per unit calorific value and carbon oxidation rate of the i-th energy source, respectively. The coefficient that represents the conversion of carbon into carbon dioxide.

[0017] In a preferred example of the present application, it can be further configured that the energy consumption data includes the consumption of energy types, and the energy types include coal, coke, crude oil, fuel oil, gasoline, kerosene, diesel, liquefied petroleum gas or electricity.

[0018] In a preferred example of the present application, it can be further configured that when the GDIM model is used to factorize the total carbon emissions, the Kaya identity is used to decompose the total carbon emissions.

[0019] In a preferred example of the present application, it can be further configured that the total carbon emissions are decomposed using the Kaya identity, and the decomposition formula includes:

[0020]

[0021] Among them, GDP is gross domestic product, POP is population, CO2 is carbon emissions, and Energy is energy consumption.

[0022] In a preferred example of the present application, it can be further configured that when the total carbon emissions are factored out using the GDIM model, the Jacobian matrix is ​​calculated according to the Kaya identity, and the carbon emissions change is calculated by combining the Jacobian matrix and the GDIM method.

[0023] In a preferred example of the present application, it can be further set that the Jacobian matrix is ​​calculated according to the Kaya identity, and the carbon emission change is calculated by combining the Jacobian matrix and the GDIM method. The calculation process is:

[0024] Assuming carbon emissions Z, gross domestic product X1, energy consumption X3, and population X5 as total indicators, combined with the Kaya identity for decomposing the total carbon emissions, we have:

[0025] Z=CO2, X1=GDP, X3=Energy, X5=POP

[0026] Assuming that the carbon emissions per unit of GDP are X2, the carbon emissions per unit of energy are X4, and the per capita carbon emissions are X6 as the corresponding carbon intensity, we have:

[0027]

[0028] Assume that GDP per capita is X7 and the energy generated by producing a unit of GDP is X8:

[0029]

[0030] From the above formula, we can get the following set of equations:

[0031] Z = X1X2-X3X4 = 0;

[0032]

[0033] According to the set of equations, the Jacobian matrix is ​​obtained:

[0034]

[0035] The carbon emission change is calculated based on the Jacobian matrix and the GDIM method.

[0036] In a preferred example of the present application, it can be further configured that the calculation of the carbon emission change according to the Jacobian matrix and the GDIM method includes:

[0037] Based on the GDIM method, the change in carbon emissions is decomposed into the sum of the contributions of various influencing factors, and the expression of the change in carbon emissions is obtained.

[0038] In a preferred example of the present application, it can be further set that the expression of the carbon emission change includes:

[0039]

[0040] Among them, ΔC is the change in carbon emissions, and L represents the time span ΔC T =(X2X1 0 0 0 0 0 0 0 0)T, I represents the identity matrix, “+” represents the generalized inverse matrix, if the Jacobian matrix Φ X If the column vectors are linearly independent, then Φ X : =(Φ X T Φ X ) ；1 Φ X T .

[0041] In a second aspect, the present application provides a provincial carbon emissions prediction device, the device comprising:

[0042] A data collection module is used to collect historical data of the area to be predicted, wherein the historical data includes economic growth data and energy consumption data of the area to be predicted over the years;

[0043] A factor decomposition module is used to calculate the total carbon emissions of the area to be predicted by combining the IPCC method with the energy consumption data; the GDIM model is used to factorize the total carbon emissions, and the R software is used to simulate the contribution of each influencing factor to the carbon emissions, and the contribution of the influencing factors is ranked to obtain multiple carbon emission driving factors;

[0044] A prediction module is used to combine the multiple carbon emission driving factors, set the combination results into a variety of scenarios in combination with the historical data, and build an SD model based on the multiple scenarios; combine the scenarios and the SD model to predict the carbon peak time and carbon emissions of the area to be predicted.

[0045] In a third aspect, the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the provincial carbon emissions prediction method as described in any one of the above items are implemented.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, a provincial carbon emissions prediction method as described in any one of the above items is implemented.

[0047] In a fifth aspect, the present application provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the provincial carbon emissions prediction method as described in any one of the above items.

[0048] In summary, compared with the prior art, the technical solution provided in the embodiment of the present application has at least the following beneficial effects:

[0049] The present application provides a provincial carbon emissions prediction method, which analyzes the factors affecting carbon emissions through the GDIM model, screens out several carbon emission driving factors that have a greater impact on carbon emissions, and then introduces the carbon emission driving factors into the SD model. The carbon emission driving factors are adjusted in combination with historical data, and different carbon emission factors are combined to form different scenario models. Different scenario models are used to perform scenario analysis on carbon emissions to obtain the corresponding carbon emissions peak time and carbon emissions, so that the prediction results are more accurate and more targeted. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a provincial carbon emissions prediction method provided for one embodiment of the present application.

[0051] Figure 2 A structural diagram of a provincial carbon emissions prediction device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] In one embodiment of the present application, a provincial carbon emissions prediction method is provided. Figure 1 As shown, the method includes:

[0054] S100: Collect historical data of the area to be predicted, where the historical data includes economic growth data and energy consumption data of the area to be predicted over the years.

[0055] Specifically, the area to be predicted in this embodiment is a province, and the historical energy consumption and economic growth data come from the statistical yearbooks of various provinces over the years.

[0056] In a preferred embodiment, the energy consumption data includes the consumption of energy types, and the energy types include coal, coke, crude oil, fuel oil, gasoline, kerosene, diesel, liquefied petroleum gas or electricity. In this embodiment, by collecting the consumption of multiple energy types, the energy consumption data is more comprehensive and the prediction result of carbon emissions is more accurate.

[0057] S200: Calculate the total carbon emissions of the area to be predicted by combining the IPCC method with the energy consumption data.

[0058] Specifically, in this embodiment, the IPCC method (carbon emission factor method) is used to calculate carbon emissions, wherein the carbon content per unit calorific value and the carbon oxidation rate of each energy type are taken with reference to the energy-related parameters in the "Guidelines for the Preparation of Provincial Greenhouse Gas Inventories (Trial)".

[0059] In a preferred embodiment, the calculation of the total carbon emissions of the region to be predicted by combining the IPCC method with the energy consumption data includes:

[0060] The calculation formula of the IPCC method is:

[0061]

[0062] Among them, I represents carbon emissions, E i represents the consumption of the i-th energy source, n is the number of energy types, NCV i 、CC i 、COF i They represent the lower calorific value, carbon content per unit calorific value and carbon oxidation rate of the i-th energy source, respectively. Indicates the coefficient of carbon conversion into carbon dioxide. n can be 9. When n is 9, the 9 energy types include coal, coke, crude oil, fuel oil, gasoline, kerosene, diesel, liquefied petroleum gas and electricity.

[0063] S300: The GDIM model is used to factorize the total carbon emissions, and R software is used to simulate the contribution of each influencing factor to the carbon emissions, and the contribution of the influencing factors is ranked to obtain multiple carbon emission driving factors.

[0064] The total carbon emissions are decomposed using the Kaya identity, and the decomposition formula includes:

[0065]

[0066] Among them, GDP is gross domestic product, POP is population, CO2 is carbon emissions, and Energy is energy consumption.

[0067] The decomposition formula can be rewritten as:

[0068]

[0069] Assuming carbon emissions Z, gross domestic product X1, energy consumption X3, and population X5 as total indicators, combined with the Kaya identity for decomposing the total carbon emissions, we have:

[0070] Z=CO2, X1=GDP, X3=Energy, X5=POP

[0071] Assuming that the carbon emissions per unit of GDP are X2, the carbon emissions per unit of energy are X4, and the per capita carbon emissions are X6 as the corresponding carbon intensity, we have:

[0072]

[0073] Assume that GDP per capita is X7 and the energy generated by producing a unit of GDP is X8:

[0074]

[0075] From the above formula, we can get the following set of equations:

[0076] Z = X1X2-X3X4 = 0;

[0077] X1X2-X5X6=0;

[0078] X1-X5X7=0;

[0079] X3-X1X8=0;

[0080] According to the set of equations, the Jacobian matrix is ​​obtained:

[0081]

[0082] Then, based on the GDIM method, the change in carbon emissions is decomposed into the sum of the contributions of each influencing factor, and the expression for the change in carbon emissions is obtained:

[0083]

[0084] Among them, ΔC is the change in carbon emissions, and L represents the time span ΔC T =(X2X1 0 0 0 0 0 0 0 0)T, I represents the identity matrix, “+” represents the generalized inverse matrix, if the Jacobian matrix Φ X If the column vectors are linearly independent, then Φ X : =(Φ X T Φ X ) ；1 Φ X T .

[0085] Finally, carbon emissions are decomposed into 8 carbon emission driving factors.

[0086] S400: combining the multiple carbon emission driving factors, setting the combined results into multiple different scenarios in combination with the historical data, and constructing SD models based on the multiple different scenarios;

[0087] S500: Predicting the carbon peak time and carbon emissions of the area to be predicted by combining the scenario and the SD model.

[0088] In this embodiment, the GDIM model is used to factorize the total carbon emissions, which not only takes into account the decomposition of multiple absolute and relative factors at the same time, but also analyzes the factors affecting carbon emissions based on the source, and accurately provides the basic influencing factors for carbon emission prediction. By combining the SD model for scenario analysis, the accuracy of the carbon emission prediction results is improved.

[0089] This application also provides a provincial carbon emissions prediction device, see Figure 2 As shown, the device comprises:

[0090] The data collection module 100 is used to collect historical data of the area to be predicted, wherein the historical data includes economic growth data and energy consumption data of the area to be predicted over the years;

[0091] The factor decomposition module 200 is used to calculate the total carbon emissions of the area to be predicted by combining the energy consumption data with the IPCC method; to decompose the total carbon emissions by factors using the GDIM model, to simulate the contribution of each influencing factor to the carbon emissions using R software, and to rank the contribution of the influencing factors to obtain multiple carbon emission driving factors;

[0092] The prediction module 300 is used to combine the multiple carbon emission driving factors, set the combination results into a variety of scenarios in combination with the historical data, and build an SD model based on the multiple scenarios; combine the scenarios and the SD model to predict the carbon peak time and carbon emissions of the area to be predicted.

[0093] The functional implementation of each module in the above-mentioned provincial carbon emission prediction device corresponds to the steps in the above-mentioned provincial carbon emission prediction method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0094] The present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the provincial carbon emissions prediction method as described in any of the above embodiments are implemented.

[0095] The present application also provides a computer-readable storage medium, on which a program is stored, wherein the computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The working process, working details and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment of a provincial carbon emissions prediction method, which will not be repeated here.

[0096] The application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the provincial carbon emissions prediction method as described in any of the above embodiments.

[0097] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0098] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above-mentioned embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several deformations and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of this application shall be based on the attached claims.

Claims

1. A provincial carbon emissions prediction method, characterized in that: include: Collecting historical data of the area to be predicted, wherein the historical data includes economic growth data and energy consumption data of the area to be predicted over the years; Calculate the total carbon emissions of the area to be predicted by combining the energy consumption data with the IPCC method; The GDIM model is used to factorize the total carbon emissions, and the R software is used to simulate the contribution of each influencing factor to the carbon emissions, and the contribution of the influencing factors is ranked to obtain multiple carbon emission driving factors; Combining the multiple carbon emission driving factors, setting the combined results into multiple different scenarios in combination with the historical data, and constructing SD models based on the multiple different scenarios; The scenario and the SD model are combined to predict the carbon peak time and carbon emissions of the area to be predicted.

2. The provincial carbon emissions prediction method according to claim 1, characterized in that: The method of using the IPCC method in combination with the energy consumption data to calculate the total carbon emissions of the area to be predicted includes: The calculation formula of the IPCC method is: Among them, I represents carbon emissions, E i represents the consumption of the i-th energy source, n is the number of energy types, NCV i 、CC i 、COF i They represent the lower calorific value, carbon content per unit calorific value and carbon oxidation rate of the i-th energy source, respectively. The coefficient that represents the conversion of carbon into carbon dioxide.

3. The provincial carbon emissions prediction method according to claim 2, characterized in that: The energy consumption data includes the consumption of energy types, and the energy types include coal, coke, crude oil, fuel oil, gasoline, kerosene, diesel, liquefied petroleum gas or electricity.

4. The provincial carbon emissions prediction method according to claim 1, characterized in that: When the GDIM model is used to factorize the total carbon emissions, the Kaya identity is used to decompose the total carbon emissions.

5. The provincial carbon emissions prediction method according to claim 4, characterized in that: The Kaya identity is used to decompose the total carbon emissions, and the decomposition formula includes: Among them, GDP is gross domestic product, POP is population, CO2 is carbon emissions, and Energy is energy consumption.

6. The provincial carbon emissions prediction method according to claim 5, characterized in that: When the GDIM model is used to factorize the total carbon emissions, it includes calculating the Jacobian matrix according to the Kaya identity, and calculating the carbon emission change in combination with the Jacobian matrix and the GDIM method.

7. The provincial carbon emissions prediction method according to claim 6, characterized in that: The Jacobian matrix is ​​calculated according to the Kaya identity, and the carbon emission change is calculated by combining the Jacobian matrix and the GDIM method. The calculation process is: Assuming carbon emissions Z, gross domestic product X1, energy consumption X3, and population X5 as total indicators, combined with the Kaya identity for decomposing the total carbon emissions, we have: Z=CO2, X1=GDP, X3=Energy, X5=POP Assuming that the carbon emissions per unit of GDP are X2, the carbon emissions per unit of energy are X4, and the per capita carbon emissions are X6 as the corresponding carbon intensity, we have: Assume that GDP per capita is X7 and the energy generated by producing a unit of GDP is X8: From the above formula, we can get the following set of equations: Z = X1X2-X3X4 = 0; X1X2-X5X6=0; X1-X5X7=0; X3-X1X8=0; According to the set of equations, the Jacobian matrix is ​​obtained: The carbon emission change is calculated based on the Jacobian matrix and the GDIM method.

8. The provincial carbon emissions prediction method according to claim 7, characterized in that: The calculating of the carbon emission change according to the Jacobian matrix and the GDIM method includes: Based on the GDIM method, the change in carbon emissions is decomposed into the sum of the contributions of various influencing factors, and the expression of the change in carbon emissions is obtained.

9. The provincial carbon emissions prediction method according to claim 8, characterized in that: The expression of the carbon emission change includes: Among them, ΔC is the change in carbon emissions, and L represents the time span ΔC T =(X2X1 0 0 0 0 0 0 0 0)T, I represents the identity matrix, "+" represents the generalized inverse matrix, if the Jacobian matrix Φ X If the column vectors are linearly independent, then Φ X : =(Φ X T Φ X ) ；1 Φ X T .

10. A provincial carbon emissions prediction device, characterized in that: include: A data collection module is used to collect historical data of the area to be predicted, wherein the historical data includes economic growth data and energy consumption data of the area to be predicted over the years; A factor decomposition module is used to calculate the total carbon emissions of the area to be predicted by combining the IPCC method with the energy consumption data; the GDIM model is used to factorize the total carbon emissions, and the R software is used to simulate the contribution of each influencing factor to the carbon emissions, and the contribution of the influencing factors is ranked to obtain multiple carbon emission driving factors; A prediction module is used to combine the multiple carbon emission driving factors, set the combination results into a variety of scenarios in combination with the historical data, and build an SD model based on the multiple scenarios; combine the scenarios and the SD model to predict the carbon peak time and carbon emissions of the area to be predicted.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the provincial carbon emissions prediction method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, wherein when the program is executed by a processor, the provincial carbon emissions prediction method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising computer instructions, characterized in that: The computer instructions, when executed by a processor, implement the steps of the provincial carbon emissions prediction method described in claims 1 to 9.

Images