Carbon neutralization optimization method and system based on SDs dynamic prediction

Abstract

The invention discloses a carbon neutralization optimization method and system based on SDs dynamic prediction. The method comprises the following steps: acquiring multi-dimensional influence factor data; predicting the carbon emission of the power consumer through the power consumption dynamic prediction model, and outputting power consumption and carbon emission prediction results; inputting the power consumption and carbon emission prediction result into a carbon emission optimization model, and optimizing the carbon emission of the power consumer to obtain an optimized carbon emission scheme; and performing economic evaluation on the optimized carbon emission scheme by calculating the carbon tax cost and the power technology subsidy to obtain a carbon neutralization evaluation report. According to the invention, the inclusiveness of various renewable energy technologies is effectively improved, and the method is suitable for the requirements of reducing carbon emission of various renewable energy technologies.

Description

Technical Field

[0001] The present invention relates to the field of carbon neutrality optimization technology, and in particular to a carbon neutrality optimization method and system based on SDs dynamic prediction. Background Art

[0002] Carbon emissions from energy consumption are a global issue, and to address this, there's growing interest in achieving carbon neutrality. Various carbon neutrality technologies have emerged to address this issue. However, with the continuous advancement of renewable energy technologies, traditional carbon neutrality approaches haven't yet tied these approaches to renewable energy consumption and production. In recent years, the effective use of renewable energy in both consumption and production has become a key focus in the carbon neutrality field. Summary of the Invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a carbon neutrality optimization method and system based on SDs dynamic prediction to solve the problem of the single method of traditional carbon neutrality solutions.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a carbon neutrality optimization method based on SDs dynamic prediction, comprising:

[0007] Obtain multi-dimensional influencing factor data;

[0008] Through the dynamic prediction model of electricity consumption, the carbon emissions of electricity users are predicted, and the prediction results of electricity consumption and carbon emissions are output;

[0009] The electricity consumption and carbon emission forecast results are input into the carbon emission optimization model to optimize the carbon emissions of electricity users and obtain the optimized carbon emission plan;

[0010] By calculating the carbon tax cost and electricity technology subsidies, the economic feasibility of the optimized carbon emission plan is evaluated to obtain a carbon neutrality assessment report.

[0011] As a preferred embodiment of the carbon neutrality optimization method based on SDs dynamic prediction described in the present invention,

[0012] The method of predicting carbon emissions of electricity users and outputting carbon emissions prediction results includes the following steps:

[0013] By analyzing the characteristics of the carbon neutrality scenario, new factors affecting electricity consumption are extracted;

[0014] Based on the theory of system dynamics, all influencing factors are selected to build a dynamic prediction model for electricity consumption

[0015] Partial least squares regression is used to fit historical data and establish a quantitative relationship model of various influencing factors;

[0016] Introduce feedback mechanisms into various stock modules, including population module, GDP module, energy consumption module, and energy consumption structure module, and establish a quantitative relationship model of stock feedback structure;

[0017] By improving the IPAT equation of the environmental impact factor model, the power consumption equation is established to quantitatively analyze the energy flow relationship;

[0018] Using the standard coal coefficient and carbon emission coefficient, a quantitative relationship between primary energy consumption and carbon emissions is constructed;

[0019] Derive a quantitative relationship model between electricity consumption and carbon emissions;

[0020] Output the predicted results of electricity consumption and carbon emissions.

[0021] As a preferred embodiment of the carbon neutrality optimization method based on SDs dynamic prediction described in the present invention,

[0022] The feedback equation of the energy consumption structure module is expressed as:

[0023]

[0024] Where N S,t is the net growth of energy consumption structure in year t.

[0025] As a preferred embodiment of the carbon neutrality optimization method based on SDs dynamic prediction described in the present invention,

[0026] By improving the IPAT equation of the environmental impact factor model, the power consumption equation is established as follows:

[0027] I t =P t ×A t ×W t ×S t

[0028] A t =G t / P t

[0029] W t =(E coal,t +E oil,t +E gas,t +E other,t ) / G t

[0030] St =I t / (E coal,t +E oil,t +E gas,t +E other,t )

[0031] Among them, E oil,t 、E gas,t 、E other,t They are t Annual oil consumption, natural gas consumption and other energy consumption.

[0032] As a preferred embodiment of the carbon neutrality optimization method based on SDs dynamic prediction described in the present invention,

[0033] The carbon emission optimization model includes the following steps:

[0034] Define the regression function and constraints;

[0035] Define input parameters for the optimization cycle;

[0036] Determine the actual current consumption of renewable energy;

[0037] Using optimization algorithms, calculate the optimal renewable energy production under existing conditions;

[0038] Calculate the required consumption subsidies based on the optimal renewable energy production;

[0039] Through the iterative optimization process, the final optimal power generation and subsidy plan are obtained.

[0040] As a preferred embodiment of the carbon neutrality optimization method based on SDs dynamic prediction described in the present invention,

[0041] The evaluation of the optimized carbon emission scheme by calculating the carbon tax cost and the power technology subsidy includes the following steps:

[0042] Define the formula for calculating carbon tax costs;

[0043] A constant substitution elasticity function is used to describe the production process of power technology and the corresponding subsidies are calculated;

[0044] Combining carbon taxes and subsidies results in a carbon neutrality assessment report.

[0045] As a preferred embodiment of the carbon neutrality optimization method based on SDs dynamic prediction described in the present invention,

[0046] The constant substitution elasticity function is used to describe the production process of electric power technology as follows:

[0047]

[0048] Among them, Gentech tech and PGentech tech are the total output and output price of the technology, INT1 tech and INT2 tech They are the two top-level investments in technology, PINT1 tech and PINT2 tech are the corresponding input prices, A tech and α tech are the technology transfer parameter and share parameter, σ tech INT1 tech and INT2 tech Substitution parameters between tech The subsidy rate for technical technology.

[0049] In a second aspect, the present invention provides a carbon neutrality optimization system based on SDs dynamic prediction, comprising:

[0050] The prediction module is used to predict the carbon emissions of power users based on the acquired data through the power consumption dynamic prediction model, and output the power consumption and carbon emission prediction results;

[0051] The optimization module is used to input the power consumption and carbon emission prediction results into the carbon emission optimization model, optimize the carbon emissions of power users, and obtain the optimized carbon emission plan;

[0052] The economic assessment module is used to conduct an economic assessment of the optimized carbon emission plan by calculating the carbon tax cost and power technology subsidies to obtain a carbon neutrality assessment report.

[0053] In a third aspect, the present invention provides a computing device, comprising:

[0054] Memory, used to store programs;

[0055] A processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the carbon neutrality optimization method based on SDs dynamic prediction.

[0056] In a fourth aspect, the present invention provides a computer-readable storage medium, comprising: when the program is executed by a processor, the steps of implementing the carbon neutrality optimization method based on SDs dynamic prediction are implemented.

[0057] The beneficial effects of the present invention are as follows: the present invention realizes scale prediction by establishing a dynamic prediction model of electricity consumption based on SDs, electricity consumption identities, etc.; realizes carbon emission optimization processing through a carbon emission optimization model; finally, the scheme is evaluated through an economic evaluation module, which can effectively predict the carbon neutrality scale of electricity users, and can optimize carbon emissions according to the characteristics of users, thereby effectively reducing their carbon emissions; it can also conduct economic evaluation of users' carbon emission plans to ensure the economic benefits of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort. Among them:

[0059] Figure 1 A basic flow chart of a carbon neutrality optimization method based on SDs dynamic prediction provided by one embodiment of the present invention;

[0060] Figure 2 A dynamic prediction flow chart of a carbon neutrality optimization method based on SDs dynamic prediction provided by one embodiment of the present invention;

[0061] Figure 3 A flowchart of the operation of an optimization processing model for a carbon neutrality optimization method based on dynamic prediction of SDs provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0062] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0063] Example 1

[0064] Reference Figure 1-3 , as an embodiment of the present invention, provides a carbon neutrality optimization method based on SDs dynamic prediction, comprising:

[0065] S1: Obtain multidimensional influencing factor data;

[0066] In an embodiment of the present application, obtaining multidimensional influencing factor data includes collecting basic data such as population, GDP, energy consumption intensity, energy consumption structure, obtaining consumption and power generation data of various types of energy (such as hydropower, photovoltaics, wind power, etc.), and collecting information such as policies, subsidies, technical parameters, etc. related to electricity consumption.

[0067] In the embodiments of the present application, energy consumption intensity refers to energy consumption per unit of GDP, and its main influencing factors are efficiency factors and structural factors; energy consumption structure refers to the proportion of social electricity consumption in the total social energy consumption, and its main influencing factors are efficiency factors and environmental factors, among which environmental factors mainly include renewable energy penetration rate, new energy vehicle penetration rate, carbon emission intensity, etc.

[0068] S2: Use the power consumption dynamic prediction model to predict the carbon emissions of power users and output the power consumption and carbon emissions prediction results;

[0069] In the embodiment of the present application, the carbon emissions of the electricity users are predicted and the carbon emissions prediction results are output, such as Figure 2 As shown, the following steps are included:

[0070] By analyzing the characteristics of the carbon neutrality scenario, new factors affecting electricity consumption are extracted;

[0071] Based on the theory of system dynamics, all influencing factors are selected to build a dynamic prediction model for electricity consumption

[0072] Partial least squares regression is used to fit historical data and establish a quantitative relationship model of various influencing factors;

[0073] Introduce feedback mechanisms into various stock modules, including population module, GDP module, energy consumption module, and energy consumption structure module, and establish a quantitative relationship model of stock feedback structure;

[0074] By improving the IPAT equation of the environmental impact factor model, the power consumption equation is established to quantitatively analyze the energy flow relationship;

[0075] Using the standard coal coefficient and carbon emission coefficient, a quantitative relationship between primary energy consumption and carbon emissions is constructed;

[0076] Derive a quantitative relationship model between electricity consumption and carbon emissions;

[0077] Output the predicted results of electricity consumption and carbon emissions.

[0078] In this embodiment, the quantitative relationship model of influencing factors includes identifying the main factors affecting electricity consumption and classifying them into different subsystems. The subsystems include population subsystem, per capita GDP subsystem, energy consumption structure subsystem, and energy consumption intensity subsystem. Based on the selected influencing factors, the quantitative relationship model of each subsystem is established using the partial least squares regression method.

[0079] It should be noted that the factors affecting electricity consumption often have strong correlation. In order to eliminate the multiple correlations between factors and obtain an equation with strong explanatory power for reality, the partial least squares regression method is used to establish a quantitative relationship model of each factor.

[0080] The quantitative relationship model of each influencing factor is as follows:

[0081] a. Energy consumption intensity subsystem

[0082] Taking coal consumption intensity as an example, its quantitative relationship can be expressed as:

[0083] F(E coal,t )=k0f(x s,t )+k1f(p coal,t )+k2f(q coal,t )+k3f(x r,t )+k4f(x h,t )+k5f(x e,t )+k6f(x g,t )+k7f(x u,t )+ε

[0084]

[0085] Among them, E coal,t is the coal consumption in year t, p coal,t is the proportion of coal consumption in primary energy consumption in year t, q coal,t for t Coal consumption intensity in a year, x i,t To refer to x s,t ~x u,t The variable x s,t is the proportion of secondary industry, x r,t is the research and experimental development input intensity in year t, x h,t is the number of high-value invention patents per 10,000 people in year t, x e,t is the energy infrastructure investment in year t, x g,t is the GDP per capita in year t, x u,t is the urbanization rate in year t, ε is the energy intensity constant, and k0~k7 are the coefficients of the regression equation of the energy intensity subsystem.

[0086] b. Energy consumption structure subsystem

[0087]

[0088] Where S t is the energy consumption structure in year t, x p,t is the renewable energy penetration rate in year t, x v,t is the sales proportion of new energy vehicles in year t, x c,t is the carbon emissions per unit GDP in year t, is the energy consumption constant, and l0~l7 are the coefficients of the regression equation of the energy consumption structure subsystem.

[0089] In the present embodiment, the quantitative relationship model of the inventory feedback structure is established, in which the state of the system at any time is captured by a set of state variables, which are called inventory. To reflect the interaction between system variables in the carbon neutral scenario, IFM is added to each inventory module to construct a feedback structure, including population, GDP, various energy consumption, energy consumption structure, etc. The inventory feedback equation of each inventory module is as follows:

[0090] a. Population and Economic Subsystem

[0091] The stock feedback equations of the population module and the economic module are expressed as follows:

[0092]

[0093] Among them, P t and G t are the total population and GDP in year t, N P,t and N GDP,t are the net population growth and net GDP growth in year t, respectively, P,t and f GDP,t are the net population growth percentage and GDP net growth percentage in year t respectively.

[0094] b. Energy consumption intensity subsystem

[0095] The energy consumption intensity subsystem includes four stock modules: coal consumption, oil consumption, natural gas consumption, and other energy consumption (including nuclear energy and renewable energy). Therefore, taking the coal consumption module as an example, the stock feedback equation of the energy consumption module can be expressed as:

[0096]

[0097] Where N coal,t is the net increase in coal consumption in year t.

[0098] c. Energy consumption structure subsystem

[0099] In the energy consumption structure subsystem, the energy consumption structure stock feedback equation is:

[0100]

[0101] Where N S,t is the net growth of energy consumption structure in year t.

[0102] In the embodiment of the present application, the power consumption identity includes setting I as power consumption, P as population, A as GDP per capita, W as energy consumption intensity, and S as energy consumption structure. The identity factors are as follows:

[0103] I t =P t ×A t ×W t ×S t

[0104] The equations of each subsystem are as follows:

[0105] A t =G t / P t

[0106] W t =(E coal,t +E oil,t +E gas,t +E other,t ) / G t

[0107] S t =I t / (E coal,t +E oil,t +E gas,t +E other,t )

[0108] Among them, E oil,t 、E gas,t 、E other,t are respectively the oil consumption, natural gas consumption and other energy consumption in year t.

[0109] S3: Input the electricity consumption and carbon emission prediction results into the carbon emission optimization model, optimize the carbon emissions of electricity users, and obtain an optimized carbon emission plan;

[0110] In the embodiment of the present application, the carbon emission optimization model, such as Figure 3 As shown, the following steps are included:

[0111] Define the regression function and constraints;

[0112] Define input parameters for the optimization cycle;

[0113] Determine the actual current consumption of renewable energy;

[0114] Using optimization algorithms, calculate the optimal renewable energy production under existing conditions;

[0115] Calculate the required consumption subsidies based on the optimal renewable energy production;

[0116] Through the iterative optimization process, the final optimal power generation and subsidy plan are obtained.

[0117] In the embodiment of the present application, the decision equation of the regression function and the function constraint is as follows:

[0118] y=α0+α1c he +α2c se +α3c we +α4g he +α5g se +α6g we +α7k he sc he +α8k se sc se +α9k we sc we +α 10 z he sg he +α 11 z se sg se +α 12 z we sg we +e i

[0119] Where c he 、c se 、c we are the consumption of hydropower, photovoltaic power and wind power, g he 、g se 、g we are the power generation of hydropower, photovoltaic power and wind power respectively, s che 、s cse 、s cwe are consumption subsidies for hydropower, photovoltaic power and wind power, respectively. ghe 、s gse 、s gwe are the power generation subsidies for hydropower, photovoltaic power and wind power respectively, y is the carbon dioxide emissions, k he 、k se 、k we 、z he 、z se 、z we is a decision variable with a value of [0, 1], α0~α 12 is the proportional coefficient, e iis the carbon emission constant.

[0120] In the embodiment of the present application, the constraints include:

[0121] CO2 emissions:

[0122] y≥0

[0123] Subsidies based on renewable energy consumption:

[0124] k he ,k we ,k se ≥0

[0125] Subsidies for renewable energy production:

[0126] z he ,z we ,z se ≥0

[0127] In the embodiment of the present application, the optimization cycle includes:

[0128] The optimization module is organized according to the input parameters of the simulation model during setup. Experimental methods are implemented to determine the model's results EC(sc he ,sc we ,sc se ). This EC(sc he ,sc we ,sc se ) as input variables and obtain the optimal EG(sg he ,sg we ,sg se ). Best EG(sg he ,sg we ,sg se ) serves as input variable and obtains the optimal EC(sc he ,sc we ,sc se In this system, multiple DEOs are performed by making the best decision. If the expected result is not achieved, the experiment is repeated. The decision variables are set at the beginning of the optimization process. Iterations continue until all decisions remain unchanged. he , sc we , sc se represents hydropower consumption, wind power consumption and solar power consumption; sg he 、sg we 、sg se They represent hydropower production, wind power production, and solar power production, respectively.

[0129] S4: Conduct an economic evaluation of the optimized carbon emission plan by calculating the carbon tax cost and electricity technology subsidies to obtain a carbon neutrality assessment report.

[0130] In the embodiment of the present application, the optimized carbon emission scheme is evaluated by calculating the carbon tax cost and the power technology subsidy, including the following steps:

[0131] Define the formula for calculating carbon tax costs;

[0132] A constant substitution elasticity function is used to describe the production process of power technology and the corresponding subsidies are calculated;

[0133] Combining carbon taxes and subsidies results in a carbon neutrality assessment report.

[0134] In the embodiment of this application, the carbon tax cost formula is:

[0135] In the model, the carbon tax formula is as follows:

[0136] CT fe,ih =CTAX*PFfactor fe,ih

[0137] Where CTAX is the specific tax rate for each ton of CO2, in RMB per ton of CO2; PFfactor fe,ih For the f e Comprehensive CO2 emission factors of various fossil energy sources.

[0138] Formula for increasing the cost of using fossil energy:

[0139] PQ′ fe,ih =PQ fe,ih +CT fe,ih *CPI

[0140] Among them, PQ′ fe,ih It is the f e The composite price of fossil fuels, CPI is the consumer price index.

[0141] In the embodiment of the present application, a constant elasticity of substitution function is used to describe the production process of CCS and non-fossil energy power generation technologies (including nuclear energy, hydropower, wind power, solar power and other power generation technologies). The top-level nesting is:

[0142]

[0143]

[0144] Among them, Gentech tech and PGentech tech are the total output and output price of the technology, INT1 tech and INT2 tech They are the two top-level investments in technology, PINT1 techand PINT2 tech are the corresponding input prices, A tech and α tech are the technology transfer parameter and share parameter, σ tech INT1 tech and INT2 tech Substitution parameters between tech The subsidy rate for technical technology.

[0145] For CCS technology, INT1 tech and TNT2 tech are the sum of fixed factors and other inputs respectively. For nuclear and hydro technologies, INT1 tecg and INT2 tech are natural resources and total labor capital. For wind, solar and other energy technologies, INT1 tech and INT2 tech are the sum of land and other inputs respectively.

[0146] It should be noted that the present invention detects the scale of carbon neutrality by establishing a dynamic prediction module for electricity consumption; then minimizes carbon dioxide emissions through a carbon emission optimization processing module, and considers the most efficient use of renewable energy in consumption and production; finally, conducts an overall economic evaluation of the plan through a carbon neutrality economic evaluation module.

[0147] This embodiment also provides a carbon neutrality optimization system based on SDs dynamic prediction, including:

[0148] The prediction module is used to predict the carbon emissions of power users based on the acquired data through the power consumption dynamic prediction model, and output the power consumption and carbon emission prediction results;

[0149] The optimization module is used to input the power consumption and carbon emission prediction results into the carbon emission optimization model, optimize the carbon emissions of power users, and obtain the optimized carbon emission plan;

[0150] The economic assessment module is used to conduct an economic assessment of the optimized carbon emission plan by calculating the carbon tax cost and power technology subsidies to obtain a carbon neutrality assessment report.

[0151] Furthermore, it also includes:

[0152] Memory, used to store programs;

[0153] A processor is used to load the program to execute the carbon neutrality optimization method based on SDs dynamic prediction.

[0154] This embodiment also provides a computer-readable storage medium storing a program. When the program is executed by a processor, it implements the carbon neutrality optimization method based on SDs dynamic prediction.

[0155] The storage medium proposed in this embodiment and the carbon neutrality optimization method based on SDs dynamic prediction proposed in the above embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0156] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer's floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0157] Example 2

[0158] This is an embodiment of the present invention, which provides a carbon neutrality optimization system based on SDs dynamic prediction, including an acquisition module, a prediction module, an optimization module and an economic evaluation module;

[0159] In an embodiment of the present application, the acquisition module includes acquiring multidimensional influencing factor data; collecting and organizing multidimensional influencing factor data related to electricity consumption and carbon emissions. The acquisition module provides basic data support for all subsequent steps to ensure the reliability and accuracy of the model input.

[0160] In the embodiment of the present application, the prediction module includes predicting the carbon emissions of power users through a dynamic power consumption prediction model and outputting power consumption and carbon emission prediction results; and using a system dynamics (SDs) model and partial least squares regression (PLSR) method to predict power users' power consumption and carbon emissions. Based on the data from the "Multi-dimensional Influencing Factor Data Acquisition Module", the prediction module generates prediction results for power consumption and carbon emissions through a dynamic prediction model, providing a basis for subsequent optimization and evaluation.

[0161] In an embodiment of the present application, the optimization module includes inputting the electricity consumption and carbon emission prediction results into the carbon emission optimization model, optimizing the carbon emissions of electricity users, and obtaining an optimized carbon emission plan; the optimization module is based on the prediction results of the "electricity consumption dynamic prediction module" and generates the optimal carbon emission plan through an optimization algorithm to provide a basis for further economic evaluation.

[0162] In this embodiment of the present application, the economic evaluation module includes an economic evaluation of the optimized carbon emission solution by calculating carbon tax costs and power technology subsidies to obtain a carbon neutrality evaluation report. Based on the optimization results of the "Carbon Emission Optimization Processing Module", the economic evaluation module performs a comprehensive economic evaluation by calculating carbon tax costs and subsidies, and ultimately generates a carbon neutrality evaluation report.

[0163] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A carbon neutrality optimization method based on SDs dynamic prediction, characterized in that: include: Obtain multi-dimensional influencing factor data; Based on the acquired data, the carbon emissions of electricity users are predicted through the dynamic prediction model of electricity consumption, and the prediction results of electricity consumption and carbon emissions are output; The electricity consumption and carbon emission forecast results are input into the carbon emission optimization model to optimize the carbon emissions of electricity users and obtain the optimized carbon emission plan; By calculating the carbon tax cost and electricity technology subsidies, the economic feasibility of the optimized carbon emission plan is evaluated to obtain a carbon neutrality assessment report.

2. The carbon neutrality optimization method based on SDs dynamic prediction according to claim 1, characterized in that: The method of predicting carbon emissions of electricity users and outputting carbon emissions prediction results includes the following steps: By analyzing the characteristics of the carbon neutrality scenario, new factors affecting electricity consumption are extracted; Based on the theory of system dynamics, all influencing factors are selected to build a dynamic prediction model for electricity consumption; Partial least squares regression is used to fit historical data and establish a quantitative relationship model of various influencing factors; Introduce feedback mechanisms into various stock modules, including population module, GDP module, energy consumption module, and energy consumption structure module, and establish a quantitative relationship model of stock feedback structure; By improving the IPAT equation, the power consumption equation is established to quantitatively analyze the energy flow relationship; Using the standard coal coefficient and carbon emission coefficient, a quantitative relationship between primary energy consumption and carbon emissions is constructed; Derive a quantitative relationship model between electricity consumption and carbon emissions; Output the predicted results of electricity consumption and carbon emissions.

3. The carbon neutrality optimization method based on SDs dynamic prediction according to claim 1 or 2, characterized in that: The feedback equation of the energy consumption structure module is expressed as: Where N S,t is the net growth of energy consumption structure in year t.

4. The carbon neutrality optimization method based on SDs dynamic prediction according to claim 3 is characterized by: By improving the IPAT equation, the power consumption equation is established as follows: I t =P t ×A t ×W t ×S t A t =G t / P t W t =(E coal,t +E oil,t +E gas,t +E other,t ) / G t S t =I t / (E coal,t +E oil,t +E gas,t +E other,t ) Among them, E oil,t 、E gas,t 、E other,t are respectively the oil consumption, natural gas consumption and other energy consumption in year t.

5. The carbon neutrality optimization method based on SDs dynamic prediction according to claim 4, characterized in that: The carbon emission optimization model includes the following steps: Define the regression function and constraints; Define input parameters for the optimization cycle; Determine the actual current consumption of renewable energy; Using optimization algorithms, calculate the optimal renewable energy production under existing conditions; Calculate the required consumption subsidies based on the optimal renewable energy production; Through the iterative optimization process, the final optimal power generation and subsidy plan are obtained.

6. The carbon neutrality optimization method based on SDs dynamic prediction according to claim 5, characterized in that: The evaluation of the optimized carbon emission scheme by calculating the carbon tax cost and the power technology subsidy includes the following steps: Define the formula for calculating carbon tax costs; A constant substitution elasticity function is used to describe the production process of power technology and the corresponding subsidies are calculated; Combining carbon taxes and subsidies results in a carbon neutrality assessment report.

7. The carbon neutrality optimization method based on SDs dynamic prediction according to claim 6, characterized in that: The constant substitution elasticity function is used to describe the production process of electric power technology as follows: Among them, Gentech tech and PGentech tech are the total output and output price of the technology, INT1 tech and INT2 tech They are the two top-level investments in technology, PINT1 tech and PINT2 tech are the corresponding input prices, A tech and α tech are the technology transfer parameter and share parameter, σ tech INT1 tech and INT2 tech Substitution parameters between tech The subsidy rate for technical technology.

8. A system based on the carbon neutrality optimization method based on SDs dynamic prediction according to claim 1, characterized in that: An acquisition module is used to obtain multi-dimensional influencing factor data; The prediction module is used to predict the carbon emissions of power users based on the acquired data through the power consumption dynamic prediction model, and output the power consumption and carbon emission prediction results; The optimization module is used to input the power consumption and carbon emission prediction results into the carbon emission optimization model, optimize the carbon emissions of power users, and obtain the optimized carbon emission plan; The economic assessment module is used to conduct an economic assessment of the optimized carbon emission plan by calculating the carbon tax cost and power technology subsidies to obtain a carbon neutrality assessment report.

9. A computing device, characterized in that include: Memory, used to store programs; A processor for loading the program to execute the steps of the carbon neutrality optimization method based on SDs dynamic prediction as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by the processor, the steps of the carbon neutrality optimization method based on SDs dynamic prediction as described in any one of claims 1 to 7 are implemented.

Images