A regional carbon peak prediction method and system, and a storage medium

Abstract

The present application relates to a kind of regional carbon peak prediction method and system, storage medium, as follows: the energy historical consumption of collecting regional years is collected;The historical carbon emissions are calculated by the method of IPCC coefficient conversion;The main influencing factors of regional carbon emissions are filtered by dynamic time warping algorithm;According to the main influencing factors of regional historical carbon emissions and carbon emissions, the principal component analysis method and STIRPAT model are comprehensively used, and the regression prediction model of regional carbon emissions is constructed;Select the main influence of carbon emissions as the core element to be quantified and generate multiple scenario modes;The corresponding influence factor under scenario mode is input into carbon emission regression prediction model, and the future carbon emissions of the region to be measured, regional carbon peak peak value and occurrence time are calculated.The present application effectively solves the problem that the identification result has great deviation caused by the inconsistency of element time series and the obvious fluctuation of element in the process of carbon peak prediction, provides theoretical basis and technical support for government carbon reduction policy making.

Description

Technical Field

[0001] This invention relates to the field of carbon emission prediction technology, specifically to a regional carbon peak prediction method and system, and a storage medium. Background Technology

[0002] Global warming is one of the most significant challenges facing the world and humanity, profoundly impacting the environment upon which we depend for survival. As a major energy consumer and carbon emitter, my country needs to demonstrate its responsibility as a major power in global climate governance within the context of the world's active response to climate change. Its ability to make sufficient contributions to carbon emission reduction is increasingly becoming an important criterion for measuring whether it is a responsible major power. This demonstrates the Chinese government's determination to address greenhouse gas emissions and resolutely pursue a path of energy conservation, emission reduction, and low-carbon sustainable development. my country's economic development has entered a "new normal" phase, leading to increased pressure on social development from resources, the environment, and climate change. As a developing country, how China fulfills its commitments and targets offers important insights for other developing countries.

[0003] Currently, the top-level design of predictions and implementation paths for carbon peaking and carbon neutrality in various provinces and cities across China has attracted widespread attention from scholars both domestically and internationally. A scientific and reasonable assessment of the peak carbon emission levels and timing in each province and city, and accurate identification of key influencing factors, can provide reference and guidance for regions to formulate energy structure adjustment strategies, build low-carbon industrial systems, and promote low-carbon economic and social development. This can ensure that each province and city effectively achieves its own peak emission targets while also contributing to the realization of the national "dual carbon" goals. However, existing regional carbon peaking prediction studies generally suffer from inaccurate identification of influencing factors, low precision in carbon emission prediction models, and excessive reliance on subjective human judgment in scenario design. These issues lead to significant deviations in the estimated peak emission levels and timing, making it impossible to assess and support the successful achievement of my country's 2030 carbon peaking target from the perspective of provincial and regional policy implementation and operation. Summary of the Invention

[0004] This invention focuses on regional carbon peak prediction, providing a method and system for such prediction. Based on a summary and analysis of the region's current socio-economic development, energy consumption, industrial development, and carbon emission status, it innovatively introduces dynamic time-adjustment algorithms and scenario analysis methods, using commonly used IPCC coefficient conversion methods, principal component analysis, and the STIRPAT model as a basic framework. This effectively addresses issues such as inconsistencies in the time series of carbon emission influencing factors and significant deviations in identification results due to fluctuations in these factors, as well as the over-reliance on subjective human judgment in scenario design, which makes it difficult to accurately determine peak values ​​and their timing. The invention provides a comprehensive quantitative analysis and calculation of regional carbon emission influencing factors, peak values, and peak occurrence times, exploring the general patterns of peak values ​​and their timing under different scenarios. This provides a theoretical basis and technical support for government carbon reduction pathway planning and policy formulation.

[0005] The present invention provides the following solution to the above-mentioned technical problems: a regional carbon peak prediction method, comprising the following steps:

[0006] Step A: Collect historical energy consumption data for the area to be tested over the years;

[0007] Step B: Calculate the historical carbon emissions of the area under test based on the historical energy consumption of the area under test using the IPCC coefficient conversion method.

[0008] Step C: Preliminary selection of factors influencing regional carbon emissions. Based on the historical carbon emissions of the region to be measured, the main factors influencing regional carbon emissions are screened using a dynamic time-rounding algorithm.

[0009] Step D: Based on the historical carbon emissions and main influencing factors of carbon emissions in the area to be measured, a regional carbon emission regression prediction model is constructed by comprehensively applying principal component analysis and the STIRPAT model.

[0010] Step E: Rank the main influencing factors of carbon emissions based on importance and uncertainty. Select the main influencing factors of various carbon emissions as core elements according to the ranking to construct a scenario matrix. Use scenario analysis methods to quantify the key influencing factors of carbon emissions into influencing factors and bring them into the scenario matrix to generate multiple scenario models.

[0011] Step F: Input the corresponding influencing factors under the scenario model into the regional carbon emission regression prediction model to calculate the future carbon emissions, regional carbon peak value, and occurrence time of the region to be tested.

[0012] Preferably, the historical consumption of crude oil, raw coal, coke, gasoline, kerosene, diesel, fuel oil and natural gas in the region under test is collected by consulting the "China Statistical Yearbook" to reflect the region's energy consumption.

[0013] Preferably, in step B, the historical carbon emissions of the area to be measured are obtained using the IPCC coefficient conversion method, and the specific calculation formula is as follows:

[0014]

[0015] Where: C p Historical carbon emissions; P i E represents the consumption of the i-th energy source; i Q represents the net calorific value of the i-th energy source; i Let be the carbon emission coefficient of the i-th energy source; I is the total number of energy types.

[0016] Preferably, step C specifically includes:

[0017] Step C1: Using literature search methods, the total population, GDP per capita, urbanization rate, energy intensity, industrial structure, carbon emission intensity, green area, energy structure and number of motor vehicles were initially selected as the influencing factors of regional carbon emissions.

[0018] Step C2: Consult the "China Statistical Yearbook" to determine the historical values ​​of the factors influencing regional carbon emissions;

[0019] Step C3: Based on the historical values ​​of regional carbon emission influencing factors, the total population, GDP per capita, urbanization rate, energy intensity, carbon emission intensity, and energy structure are selected as the main influencing factors of regional carbon emissions by using a dynamic time-rounding algorithm.

[0020] Preferably, the specific calculation process in step C3 is as follows:

[0021] The numerical normalization of regional carbon emission influencing factors is shown in the specific calculation formula (2a):

[0022]

[0023] In the formula: x i * The normalized result for influencing factor i; x i x represents the original values ​​of influencing factor i over the years; i,max x represents the historical maximum value of influencing factor i; i,min This represents the historical minimum value of influencing factor i.

[0024] Considering the significant differences in the numerical values ​​and dimensions of the influencing factors, a normalization method was used to process the original historical values ​​of the influencing factors in order to avoid the impact of these differences on the screening results.

[0025] Constructing a distance matrix: Given the time series of carbon emissions in a known region as M = {m1, m2, ..., m}t The time series of a certain influencing factor is N = {n1, n2, ..., n}. r}, where t and r are the number of elements in the two time series, and all the curved paths form the distance matrix E of the path space;

[0026]

[0027] Where: d(m) i ,n j The Euclidean distance represents the correspondence between elements in two sequences, as shown below:

[0028] E ij =d(m i ,n j )=(m i -n j ) 2 (2c)

[0029] Calculate the curved path: According to the calculation rules, the selected path must start from the bottom left corner and end at the top right corner; the curved path must be continuous, cannot cross intermediate points, and can only be aligned with adjacent elements; and all points must be matched monotonically according to the time sequence.

[0030] P = {p1, p2, ..., p} s ,...,p l} (2d)

[0031] p s =(i,j)=E ij (2e)

[0032] Where: P is the curved path; s is the coordinate of the s-th point on the dynamic curved path; l is the number of elements in the path;

[0033] Determining the optimal path: From numerous curved paths, the path that minimizes the sum of distances between all elements on the path is selected as the optimal path, i.e., the Dynamic Time Warp Distance (DTW). The calculation formula is as follows:

[0034]

[0035] Identify key influencing factors: Based on the calculation of the optimal path for all influencing factors and regional carbon emissions, sort them by distance from nearest to farthest, and screen and identify key influencing factors, namely, total regional population, GDP per capita, urbanization rate, energy intensity, carbon emission intensity, and energy structure.

[0036] Preferably, step D specifically includes:

[0037] Step D1: Based on the STIRPAT model, after calculating the logarithmic values ​​of the influencing factors and regional carbon emissions, the logarithmic values ​​x of the influencing factors are... ij Perform standardization to generate a standardized matrix Z. ij The conversion process is shown in (3a) and (3b):

[0038]

[0039]

[0040] Among them: Z ij A standardized matrix; and s j denoted as the sample mean and sample standard deviation of the j-th indicator, respectively; i represents the statistical period; n represents the total number of statistical periods; j represents the type of carbon emission influencing factors; and p represents the total number of carbon emission influencing factors.

[0041] Step D2: Based on the normalized matrix Z obtained in step D1 ij Generate the correlation coefficient matrix R, and calculate it as shown in (3c):

[0042]

[0043] Step D3: Based on the correlation coefficient matrix R obtained above, first use the matrix characteristic polynomial solution method to solve equation (3d) to obtain p eigenvalues ​​λ. j (j = 1, 2, ..., p); Next, according to the principle that the information utilization rate exceeds 85% as specified by inequality (3e), m eigenvalues ​​λ are selected from the p eigenvalues. j (j=1,2,...,m); Finally, solve equation (3f) to obtain the unit eigenvector u corresponding to the eigenvalue λ.

[0044] |R-λE|=0 (3d)

[0045]

[0046] Ru=λ j u (3f)

[0047] Where: λ j is the j-th eigenvalue of matrix R; E is the identity matrix; u is the unit eigenvector.

[0048] Step D4: Convert the standardized influencing factors into principal components, as shown in (3g):

[0049]

[0050] Where: Y1 is the first principal component, Y2 is the second principal component, ..., Y m It is the m-th principal component, u i It is the i-th eigenvector;

[0051] Step D5: Based on the eigenvalues ​​λ obtained in step D3 j A comprehensive evaluation of the m principal components is performed, and the principal component Y is calculated. j The information contribution rate and cumulative contribution rate of (j=1,2,...,m) are calculated as shown in (3h) and (3i):

[0052]

[0053]

[0054] Where: b j For a single principal component Y j Information contribution rate; α is the information contribution rate of all principal components Y j The cumulative contribution rate.

[0055] Step D6: Based on the cumulative contribution rate of over 99% obtained in Step D5, determine the number of principal component factors that can explain the original data. Combined with the transformation results of Step D4, generate principal component factor expressions based on the original carbon emission influencing factors, as shown in (3j):

[0056] FA i =a i ln P+b i ln A+c i ln SP+d i ln T+e i ln F+f i ln E (3j)

[0057] Among them: FA i Let be the principal component factor of group i; P be the total population; A be the GDP per capita; SP be the urbanization rate; T be the energy intensity; F be the carbon emission intensity; E be the energy structure; a i b i c i d i e i f i These are the coefficients of each influencing factor.

[0058] Step D7: Based on the logarithmic values ​​of regional historical carbon emissions obtained in Step D1 and the principal component factor expressions selected in Step D6, establish a polynomial regression equation for regional carbon emissions and principal component factors, as shown in (3k):

[0059] ln C=a ln FA1+b ln FA2+...+n ln FA n +d (3k)

[0060] Where: lnC is the logarithm of the region's annual carbon emissions; FA1, FA2, ..., FA n , respectively, are the expressions for the selected principal component factors; a, b, ..., n are the regression coefficients of the principal component factors; d is the constant term.

[0061] Step D8: Based on the principal component factor expression generated in step D6, establish a regional carbon emission prediction model based on the STIRPAT model, as shown in (3l):

[0062] ln C=β1ln P+β2ln A+β3ln SP+β4ln T+β5ln F+β6ln E+d (3l)

[0063] Where: β1, β2, β3, β4, β5, and β6 are the regression coefficients of each influencing factor; d is a constant term; the above elasticity index is obtained by solving the two equations (3h) and (3i).

[0064] Preferably, step E specifically includes:

[0065] Step E1: Rank the main influencing factors of regional carbon emissions based on the importance and uncertainty determined in Step C using two-dimensional coordinate axes;

[0066] Step E2: Based on the ranking, select two or more major influencing factors of regional carbon emissions as the core uncertainty elements for constructing scenarios, and generate a scenario matrix;

[0067] Taking two core elements as examples, suppose that the population size (U1) and GDP per capita (U2) are designed as two (or more) development trends of U1 and U2 respectively, thus forming an n*m matrix S, forming n*m different scenarios, as shown in (4a):

[0068] S=f(U1,U2)=f({U 1,1 ,...U 1,i ...,U 1,n},{U 2,1 ,...U 2,j ...,U 2,m})={S 1,1 ,...S i,j ...,S n,m} (4a)

[0069] Where: f represents the composition function of U1 and U2; U1，i and U 2，j These represent the different development trends of U1 and U2, respectively; S i，j The final designed scenario is represented using a scenario matrix or a scenario tree method.

[0070] Step E3: Analyze the current development status of the region under test through literature review, quantify the main influencing factors of regional carbon emissions, and input the influencing factors into the scenario matrix to generate multiple scenario models.

[0071] Preferably, the scenario modes include an energy-saving scenario mode, a strong energy-saving scenario mode, and a low-carbon scenario mode.

[0072] A regional carbon peak prediction system, the system comprising:

[0073] The historical energy consumption module is used to collect historical energy consumption data for the area under test over the years.

[0074] The historical carbon emissions module is used to calculate the historical carbon emissions of the area under test based on the historical energy consumption of the area over the years using the IPCC factor conversion method.

[0075] The module for obtaining the main influencing factors of carbon emissions is used to initially select the influencing factors of regional carbon emissions. Based on the historical carbon emissions of the region to be measured, the main influencing factors of regional carbon emissions are screened through a dynamic time-rounding algorithm.

[0076] The carbon emission regression prediction model construction module is used to construct a regional carbon emission regression prediction model based on the historical carbon emissions and main influencing factors of the region under test, by comprehensively applying principal component analysis and the STIRPAT model.

[0077] The scenario model generation module is used to rank the main influencing factors of carbon emissions based on their importance and uncertainty. According to the ranking, it selects the main influencing factors of various carbon emissions as core elements to construct a scenario matrix. The scenario analysis method is used to quantify the key influencing factors of carbon emissions into influencing factors and bring them into the scenario matrix to generate various scenario models.

[0078] The carbon peak prediction module is used to input the corresponding influencing factors under the scenario model into the regional carbon emission regression prediction model to calculate the future carbon emissions, regional carbon peak value and occurrence time of the region to be predicted.

[0079] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the regional carbon peak prediction method described above.

[0080] The beneficial effects of this invention are as follows: Based on a summary and analysis of the current status of regional socio-economic development, industrial development, and carbon emissions, factors influencing carbon emissions are screened. Combined with the current energy consumption situation, and using commonly used IPCC coefficient conversion methods, principal component analysis, and the STIRPAT model as a basic framework, a dynamic time-correction algorithm is introduced to effectively solve the problems of inconsistent time series of factors and significant fluctuations in factor changes leading to large deviations in identification results during the identification of carbon emission influencing factors. Through scenario analysis, the invention addresses the problem of over-reliance on subjective human judgment in scenario design, which makes it difficult to accurately determine peak values ​​and their occurrence times. A comprehensive quantitative analysis and calculation of regional carbon emission influencing factors, peak values, and peak occurrence times are conducted, exploring the general patterns of peak values ​​and peak times under different scenarios, providing a theoretical basis and technical support for government carbon reduction pathway planning and policy formulation.

[0081] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0082] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0083] Figure 1 This is a technical roadmap for a regional carbon peak prediction method proposed in an embodiment of the present invention;

[0084] Figure 2 This is a flowchart illustrating the construction of a regional carbon emission prediction model in an embodiment of the present invention;

[0085] Figure 3 This is a schematic diagram showing the ranking of the main influencing factors of carbon emissions using two-dimensional coordinate axes according to an embodiment of the present invention;

[0086] Figure 4 This is a graph showing the prediction results of the carbon emission prediction model applied in this embodiment of the invention, based on the peak carbon emission value and the time of peak occurrence under certain scenario modes. Detailed Implementation

[0087] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0088] A method for predicting regional carbon peaks, the steps of which are as follows: Figure 1 As shown:

[0089] Step A: By consulting the "China Statistical Yearbook", collect the consumption of common energy sources such as crude oil, raw coal, coke, gasoline, kerosene, diesel, fuel oil and natural gas in the region under test over the years to reflect the region's energy consumption situation, as shown in Table 1.

[0090] Table 1. Historical Consumption of Major Energy Forms in the Region

[0091]

[0092] Step B: Using the IPCC factor conversion method, calculate the historical carbon emissions of the area under test based on the historical energy consumption of the area. The specific calculation formula is as follows:

[0093]

[0094] Where: C p Historical carbon emissions; P i E represents the consumption of the i-th energy source; i Q represents the net calorific value of the i-th energy source; i Let be the carbon emission coefficient of the i-th energy source; I is the total number of energy types.

[0095] Table 2 shows the main parameters involved in the IPCC coefficient conversion method. Table 3 shows the calculated carbon emissions for the region over the years.

[0096] Table 2 Carbon emission coefficients and net calorific value of various energy types

[0097]

[0098] Table 3 shows the historical carbon emissions calculation results for the region.

[0099]

[0100] Step C: Using literature search methods, the total population, GDP per capita, urbanization rate, energy intensity, industrial structure, carbon emission intensity, green area, energy structure, and number of motor vehicles were initially selected as influencing factors of regional carbon emissions. The historical values ​​of the influencing factors of regional carbon emissions were determined by consulting the "China Statistical Yearbook", as shown in Table 4. Based on the historical values ​​of the influencing factors of regional carbon emissions, the total population, GDP per capita, urbanization rate, energy intensity, carbon emission intensity, and energy structure were selected as the main influencing factors of regional carbon emissions by using the dynamic time integration algorithm, as shown in Table 5.

[0101] Table 4 Factors affecting regional carbon emissions

[0102]

[0103]

[0104] Table 5. Results of screening for influencing factors of the dynamic time-normalization algorithm.

[0105] Influencing factors DTW value Total population 0.59 GDP per capita 0.66 urbanization rate 0.68 Energy intensity 13.18 carbon emission intensity 2.61 Energy Structure 5.87 Industrial structure 14.38 Green area 17.74 Number of motor vehicles 15.19

[0106] Step D: Based on the historical carbon emissions and main influencing factors of the area to be measured, a regional carbon emission regression prediction model is constructed by comprehensively applying principal component analysis and the STIRPAT model, such as... Figure 2 As shown, the specific steps are as follows:

[0107] Step D1: Based on the extended STIRPAT model, and after calculating the logarithmic values ​​of the influencing factors and regional carbon emissions, adjust the logarithmic values ​​x of the influencing factors. ij Perform standardization to generate a standardized matrix Z. ij The conversion process is shown in (3a) and (3b):

[0108]

[0109]

[0110] Among them: Z ij A standardized matrix; and s j denoted as the sample mean and sample standard deviation of the j-th indicator, respectively; i represents the statistical period; n represents the total number of statistical periods; j represents the type of carbon emission influencing factors; and p represents the total number of carbon emission influencing factors.

[0111] Step D2: Based on the normalized matrix Z obtained in step D1 ij Generate the correlation coefficient matrix R, and calculate it as shown in (3c):

[0112]

[0113] Step D3: Based on the correlation coefficient matrix R obtained above, first use the matrix characteristic polynomial solution method to solve equation (3d) to obtain p eigenvalues ​​λ. j (j = 1, 2, ..., p); Next, according to the principle that the information utilization rate exceeds 85% as specified by inequality (3e), m eigenvalues ​​λ are selected from the p eigenvalues. j (j=1,2,...,m); Finally, solve equation (3f) to obtain the unit eigenvector u corresponding to the eigenvalue λ.

[0114] |R-λE|=0 (3d)

[0115]

[0116] Ru=λj u (3f)

[0117] Where: λ j is the j-th eigenvalue of matrix R; E is the identity matrix; u is the unit eigenvector.

[0118] Step D4: Convert the standardized influencing factors into principal components, as shown in (3g):

[0119]

[0120] Where: Y1 is the first principal component, Y2 is the second principal component, ..., Y m It is the m-th principal component

[0121] Step D5: Based on the eigenvalues ​​λ obtained in step D3 j A comprehensive evaluation of the m principal components is performed, and the principal component Y is calculated. j The information contribution rate and cumulative contribution rate of (j=1,2,...,m) are calculated as shown in (3h) and (3i):

[0122]

[0123]

[0124] Where: b j For a single principal component Y j Information contribution rate; α is the information contribution rate of all principal components Y j The cumulative contribution rate.

[0125] Table 6 shows the information contribution rate and cumulative contribution rate of the principal components.

[0126] Table 6 shows the calculation results of the information contribution rate and cumulative contribution rate of the principal components.

[0127]

[0128] Step D6: Based on the cumulative contribution rate obtained above (which should theoretically exceed 99%), select the top 3 principal component factors to interpret the original data. Table 7 lists the coefficients of each influencing factor corresponding to the 3 principal component factors.

[0129] Table 7 Summary of coefficients of various influencing factors of principal component factors

[0130]

[0131] Based on Table 7 and the transformation results of step D4, the principal component factor expressions based on the original carbon emission influencing factors are determined, as shown in (5a) to (5c):

[0132] FA1=0.483 ln P+0.292 ln A+0.484 ln SP-0.014 ln T-0.264 ln F-0.199 lnE (5a)

[0133] FA2=-0.122 ln P-0.118 ln A+0.049 ln SP+0.232 ln T+0.253 ln F+0.983ln E (5b)

[0134] FA3=-0.921ln P+0.024 ln A-1.392 ln SP-1.683 ln T+1.598 ln F-1.074 lnE (5c)

[0135] Where: P is the total population; A is the GDP per capita; SP is the urbanization rate; T is the energy intensity; F is the carbon emission intensity; and E is the energy structure.

[0136] Step D7: Based on the logarithmic value of the region's historical carbon emissions and the screening results of the principal component factors, a polynomial regression equation for the region's carbon emissions and the principal component factors is established, as shown in (5d). Table 8 reflects the fit of the regression equation.

[0137] ln C=0.702 ln FA1+0.362 ln FA2+0.12 ln FA3+9.488 (5d)

[0138] Where: lnC is the logarithm of the region's annual carbon emissions.

[0139] Table 8 Summary of Regression Equation Fit

[0140]

[0141] Step D8: Based on the principal component factor expressions obtained above, establish a regional carbon emission prediction model based on the STIRPAT model. The model is shown in (5e):

[0142] ln C=0.573 ln P+0.513 ln A+0.591 ln SP-0.397 ln T+0.304 ln F+0.281ln E+5.925 (5e)

[0143] Step E: Use a two-dimensional coordinate axis to rank the importance and uncertainty of the main influencing factors of carbon emissions identified above, such as... Figure 3As shown, the overall ranking is: total population > GDP per capita > urbanization rate > carbon emission intensity > energy intensity > energy structure. Based on this ranking, ignoring urbanization rate (limited numerical variation) and energy structure (too low in the overall ranking), total population, GDP per capita, carbon emission intensity, and energy intensity were selected for scenario design. Combining field surveys, literature reviews, policy analysis, and expert consultations, the selected influencing factors were quantified, generating multiple scenarios reflecting different socio-economic development levels, technological levels, and policy implementation effects in the region, including energy-saving, strong energy-saving, and low-carbon scenarios. Table 9 shows the future values ​​of the influencing factors under the low-carbon scenario.

[0144] Table 9 Future Values ​​of Influencing Factors under Regional Low-Carbon Scenario Model

[0145]

[0146]

[0147] Step F: Using the constructed regional carbon emission regression prediction model, combined with the carbon emission impact parameters under various scenario modes, calculate the future carbon emissions of the region, and determine the peak value and occurrence time of regional carbon emissions under different scenario modes, such as... Figure 4 As shown, this provides a useful reference for the formulation and implementation of subsequent regional carbon peak control strategies and countermeasures.

[0148] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Those skilled in the art can readily implement the present invention based on the accompanying drawings and the above description. However, any modifications, alterations, or variations made by those skilled in the art without departing from the scope of the present invention, utilizing the disclosed technical content, are equivalent embodiments of the present invention. Furthermore, any modifications, alterations, or variations made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the present invention.

Claims

1. A method for predicting regional carbon peak, characterized in that, Includes the following steps: Step A: Collect historical energy consumption data for the area to be tested over the years; Step B: Calculate the historical carbon emissions of the area under test based on the historical energy consumption of the area under test using the IPCC coefficient conversion method. Step C: Preliminary selection of factors influencing regional carbon emissions. Based on the historical carbon emissions of the region to be measured, the main factors influencing regional carbon emissions are screened using a dynamic time-rounding algorithm. Step D: Based on the historical carbon emissions and main influencing factors of carbon emissions in the area to be measured, a regional carbon emission regression prediction model is constructed by comprehensively applying principal component analysis and the STIRPAT model. Step E: Rank the main influencing factors of carbon emissions based on importance and uncertainty. Select the main influencing factors of various carbon emissions as core elements according to the ranking to construct a scenario matrix. Use scenario analysis methods to quantify the key influencing factors of carbon emissions into influencing factors and bring them into the scenario matrix to generate multiple scenario models. Step F: Input the corresponding influencing factors under the scenario model into the regional carbon emission regression prediction model to calculate the future carbon emissions, regional carbon peak value, and occurrence time of the region to be tested.

2. The regional carbon peak prediction method according to claim 1, characterized in that, Step A involves collecting historical consumption data for crude oil, raw coal, coke, gasoline, kerosene, diesel, fuel oil, and natural gas in the region under test by consulting the "China Statistical Yearbook".

3. The regional carbon peak prediction method according to claim 1, characterized in that, In step B, the historical carbon emissions of the area to be measured are obtained using the IPCC coefficient conversion method. The specific calculation formula is as follows: Where: C p Historical carbon emissions; P i E represents the consumption of the i-th energy source; i Q represents the net calorific value of the i-th energy source; i Let be the carbon emission coefficient of the i-th energy source; I is the total number of energy types.

4. The regional carbon peak prediction method according to claim 1, characterized in that, Step C specifically includes: Step C1: Using literature search methods, the total population, GDP per capita, urbanization rate, energy intensity, industrial structure, carbon emission intensity, green area, energy structure and number of motor vehicles were initially selected as the influencing factors of regional carbon emissions. Step C2: Consult the "China Statistical Yearbook" to determine the historical values ​​of the factors influencing regional carbon emissions; Step C3: Based on the historical values ​​of regional carbon emission influencing factors, the total population, GDP per capita, urbanization rate, energy intensity, carbon emission intensity, and energy structure are selected as the main influencing factors of regional carbon emissions by using a dynamic time-rounding algorithm.

5. The regional carbon peak prediction method according to claim 4, characterized in that, In step C3, the specific calculation process is as follows: The numerical normalization of regional carbon emission influencing factors is shown in the specific calculation formula (2a): In the formula: x i * The normalized result for influencing factor i; x i x represents the original values ​​of influencing factor i over the years; i,max x represents the historical maximum value of influencing factor i; i,min The historical minimum value of influencing factor i; Constructing a distance matrix: Given the time series of carbon emissions for a given region as M = {m1, m2, ..., m} t The time series of a certain influencing factor is N = {n1, n2, ..., n}. r }, where t and r are the number of elements in the two time series, and all the curved paths form the distance matrix E of the path space; Where: d(m) i ,n j The Euclidean distance represents the correspondence between elements in two sequences, as shown below: E ij =d(m i ,n j )=(m i -n j ) 2 (2c) Calculate the curved path: According to the calculation rules, the selected path must start from the bottom left corner and end at the top right corner; the curved path must be continuous, cannot cross intermediate points, and can only be aligned with adjacent elements; and all points must be matched monotonically according to the time sequence. P={p1,p2,…,p s ,…,p l } (2d) p s =(i,j)=E ij (2e) Where: P is the curved path; s is the coordinate of the s-th point on the dynamic curved path; l is the number of elements in the path; Determining the optimal path: From numerous curved paths, the path that minimizes the sum of distances between all elements on the path is selected as the optimal path, i.e., the Dynamic Time Warp Distance (DTW). The calculation formula is as follows: Identify key influencing factors: Based on the calculation of the optimal path for all influencing factors and regional carbon emissions, sort them by distance from nearest to farthest, and screen and identify key influencing factors, namely, total regional population, GDP per capita, urbanization rate, energy intensity, carbon emission intensity, and energy structure.

6. The regional carbon peak prediction method according to claim 1, characterized in that, Step D specifically includes: Step D1: Based on the STIRPAT model, after calculating the logarithmic values ​​of the main influencing factors of carbon emissions and the regional carbon emissions, calculate the logarithmic values ​​x of the main influencing factors of carbon emissions. ij Perform standardization to generate a standardized matrix Z. ij The conversion process is shown in (3a) and (3b): Where: Z ij A standardized matrix; and s j , i and n are the sample mean and sample standard deviation of the j-th indicator, respectively; i is the statistical period; n is the total number of statistical periods; j is the type of carbon emission influencing factors; p is the total number of carbon emission influencing factors. Step D2: Based on the normalized matrix Z obtained in step D1 ij Generate the correlation coefficient matrix R, and calculate it as shown in (3c): Step D3: Based on the correlation coefficient matrix R obtained above, firstly, use the matrix characteristic polynomial solution method to solve equation (3d) to obtain p eigenvalues ​​λ. j (j = 1, 2, ..., p); Next, according to the principle that the information utilization rate exceeds 85% as specified by inequality (3e), m eigenvalues ​​λ are selected from the p eigenvalues. j (j=1,2,…,m); Finally, solve equation (3f) to obtain the unit eigenvector u corresponding to the eigenvalue λ; |R-λE|=0 (3d) Ru=λ j u (3f) Where: λ j It is the j-th eigenvalue of matrix R; E is the identity matrix; u is the unit eigenvector; Step D4: Convert the standardized influencing factors into principal components, as shown in (3g): Where: Y1 is the first principal component, Y2 is the second principal component, ..., Y m It is the m-th principal component, u i It is the i-th eigenvector; Step D5: Based on the eigenvalues ​​λ obtained in step D3 j A comprehensive evaluation of the m principal components is performed, and the principal component Y is calculated. j The information contribution rate and cumulative contribution rate of (j=1,2,…,m) are calculated as shown in (3h) and (3i): Where: b j For a single principal component Y j Information contribution rate; α is the information contribution rate of all principal components Y j The cumulative contribution rate; Step D6: Based on the cumulative contribution rate of over 99% obtained in Step D5, determine the number of principal component factors in the original data. Combined with the transformation results of Step D4, generate principal component factor expressions based on the original carbon emission influencing factors, as shown in (3j): AGO i =a i lnP+b i lnA+c i lnSP+d i lnT+e i lnF+f i lnE (3j) Among them: FA i Let be the principal component factor of group i; P be the total population; A be the GDP per capita; SP be the urbanization rate; T be the energy intensity; F be the carbon emission intensity; E be the energy structure; a i b i c i d i e i f i These are the coefficients of each influencing factor; Step D7: Based on the logarithmic values ​​of regional historical carbon emissions obtained in Step D1 and the principal component factor expressions selected in Step D6, establish a polynomial regression equation for regional carbon emissions and principal component factors, as shown in (3k): lnC of lnFA1+blnFA2+...+nlnFA n +d (3k) Where: lnC is the logarithm of the region's annual carbon emissions; FA1, FA2, ..., FA n These are the expressions for the selected principal component factors; a, b, ..., n are the regression coefficients of the principal component factors; d is the constant term. Step D8: Based on the principal component factor expression generated in step D6, establish a regional carbon emission prediction model based on the STIRPAT model, as shown in (3l): lnC=β1lnP+β2lnA+β3lnSP+β4lnT+β5lnF+β6lnE+d (3l) Where: β1, β2, β3, β4, β5, and β6 are the regression coefficients of each influencing factor; d is the constant term.

7. The regional carbon peak prediction method according to claim 1, characterized in that, Step E specifically includes: Step E1: Rank the main influencing factors of regional carbon emissions based on the importance and uncertainty determined in Step C using two-dimensional coordinate axes; Step E2: Based on the ranking, select two or more major influencing factors of regional carbon emissions as the core uncertainty elements for constructing scenarios, and generate a scenario matrix; Step E3: Analyze the current development status of the region under test through literature review, quantify the main influencing factors of regional carbon emissions, and input the influencing factors into the scenario matrix to generate multiple scenario models.

8. The regional carbon peak prediction method according to claim 1, characterized in that, The scenario modes include energy-saving scenario mode, strong energy-saving scenario mode, and low-carbon scenario mode.

9. A regional carbon peak prediction system, characterized in that, The system includes: The historical energy consumption module is used to collect historical energy consumption data for the area under test over the years. The historical carbon emissions module is used to calculate the historical carbon emissions of the area under test based on the historical energy consumption of the area over the years using the IPCC factor conversion method. The module for obtaining the main influencing factors of carbon emissions is used to initially select the influencing factors of regional carbon emissions. Based on the historical carbon emissions of the region to be measured, the main influencing factors of regional carbon emissions are screened through a dynamic time-rounding algorithm. The carbon emission regression prediction model construction module is used to construct a regional carbon emission regression prediction model based on the historical carbon emissions and main influencing factors of the region under test, by comprehensively applying principal component analysis and the STIRPAT model. The scenario model generation module is used to rank the main influencing factors of carbon emissions based on their importance and uncertainty. According to the ranking, it selects the main influencing factors of various carbon emissions as core elements to construct a scenario matrix. The scenario analysis method is used to quantify the key influencing factors of carbon emissions into influencing factors and bring them into the scenario matrix to generate various scenario models. The carbon peak prediction module is used to input the corresponding influencing factors under the scenario model into the regional carbon emission regression prediction model to calculate the future carbon emissions, the regional carbon peak value, and the occurrence time of the predicted area.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the regional carbon peak prediction method as described in any one of claims 1 to 8.

Images