Industrial enterprise carbon emission allocation method based on regional energy carbon platform supervision data

Abstract

The invention relates to the field of carbon emission management, energy distribution and optimization regulation and control, in particular to an industrial enterprise carbon emission allocation method based on regional energy and carbon platform supervision data. The method comprises the following steps: step 1, data acquisition and preprocessing, including data acquisition, data preprocessing and data analysis; 2, initial carbon quota distribution, wherein a multi-level decision-making model is established, and the initial carbon quota of an enterprise is calculated; 3, a dynamic adjustment mechanism is provided, wherein the dynamic adjustment mechanism comprises the steps of obtaining power data feedback, calculating a quota adjustment coefficient and dynamically adjusting a quota; step 4, accumulation of double-control index data, including accumulation of the double-control index data and accumulation of carbon emission intensity data; and 5, continuously optimizing the model. According to the method, the flexibility of carbon quota distribution is improved, normal production of enterprises is ensured, meanwhile, the total carbon emission control target is not exceeded, and the overall efficiency of carbon emission management is improved by introducing a multi-level decision model and a feedback mechanism.

Description

Technical Field

[0001] The present invention relates to the fields of carbon emission management, energy allocation and optimization regulation, and in particular to a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data. Background Art

[0002] With the rapid industrialization of society and the rapid development of various industrial enterprises, the issue of carbon emissions has received increasing attention. As the main energy consumers, industrial enterprises account for a large part of the carbon emissions of the whole society. Especially in high-energy-consuming and high-emission industries, carbon emissions are more concentrated. It is necessary to put forward more stringent requirements for the carbon emission management and control of industrial enterprises, and the reasonable allocation of carbon quotas is one of the key measures to achieve total carbon emission control.

[0003] At present, the allocation of carbon quotas to industrial enterprises mainly relies on the historical carbon emission data of each enterprise, and the carbon emissions of each enterprise are limited by setting a fixed carbon quota. However, the traditional carbon quota allocation method has certain limitations. First, the historical carbon emission data cannot reflect the current production status and energy demand of each enterprise in real time, resulting in the lack of flexibility and accuracy in the allocation of carbon quotas. Secondly, the production activities and energy consumption of each enterprise have cyclical fluctuations, and fixed carbon quotas are difficult to meet the needs of each enterprise during the peak production period, which may lead to production restrictions or excessive carbon emissions in each enterprise. In addition, due to the large differences in energy structure and electricity consumption in various regions, it is difficult for the carbon quota allocation standard to take into account the specific conditions of each region, thus affecting the fairness and rationality of carbon quota allocation. Therefore, it is necessary to design a new and more reasonable carbon emission allocation method to meet the actual needs of society. Summary of the invention

[0004] In response to this problem, the present invention proposes a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data. This method integrates the historical carbon emission data and real-time electricity demand data of each enterprise to dynamically adjust the carbon quota allocation plan, thereby achieving more accurate carbon emission management. Specifically, the government first allocates initial carbon quotas based on the historical carbon emission data and energy demand of each enterprise; during the actual production process of each enterprise, the system dynamically adjusts its carbon quota according to the changes in the real-time electricity demand of each enterprise. This method not only improves the flexibility of carbon quota allocation, ensuring that each enterprise does not exceed the total carbon emission control target while in normal production, but also further optimizes the carbon quota allocation plan by introducing a multi-level decision-making model and feedback mechanism, thereby improving the overall efficiency of carbon emission management.

[0005] The present invention provides a method for allocating carbon emission quotas to industrial enterprises based on the regulatory data of the regional energy carbon platform, aiming to optimize the allocation of carbon quotas and accumulate dual control indicator data of total carbon emissions and carbon emission intensity. By establishing a multi-level decision-making model, the initial carbon quota is first allocated based on the historical carbon emissions and power demand data of each enterprise in the regulatory platform, and then the quota is dynamically adjusted according to the power data feedback, the system requirements are optimized, and the effective control of carbon emissions and the rational allocation of resources are achieved.

[0006] The present invention provides a method for allocating carbon emission quotas to various industrial enterprises based on regional energy and carbon platform supervision data as follows:

[0007] Step 1: Data collection and preprocessing, including: data collection, data preprocessing and data analysis;

[0008] Step 2: Allocation of initial carbon quotas, including: establishing a multi-level decision-making model and calculating the initial carbon quotas of enterprises;

[0009] Step 3: Dynamic adjustment mechanism, including: obtaining power data feedback, calculating quota adjustment coefficients and dynamically adjusting quotas;

[0010] Step 4: Accumulation of dual control indicator data, including: accumulation of dual control indicator data and accumulation of carbon emission intensity data;

[0011] Step 5: Continuous optimization of the model, including: parameter adjustment and model optimization, data feedback and decision support.

[0012] Specifically, step 1: data collection and preprocessing

[0013] 1.1 Data Collection

[0014] Historical carbon emission data acquisition:

[0015] Obtain the carbon emission data E of each industrial enterprise i in the past T cycles from the regional energy carbon platform i,t , including direct carbon emissions and indirect carbon emissions. Where t=1,2,…,T.

[0016] Historical power demand data acquisition:

[0017] Obtain the power demand data D of each enterprise i in the past T cycles i,t , including electricity consumption, peak and valley electricity consumption, etc.

[0018] Production activity level data acquisition:

[0019] Obtain the production activity level data P of each enterprise i in the past T cycles i,t , such as key indicators such as output, output value, and operating income.

[0020] Other relevant data:

[0021] Obtain data on other factors that affect carbon emissions, such as energy structure, technology level, equipment updates, energy-saving and emission reduction measures, etc.

[0022] 1.2 Data Preprocessing

[0023] Data cleaning:

[0024] The collected data was quality checked to remove missing values, outliers and duplicate values. Statistical methods were used, which were visual methods, to identify and process abnormal data.

[0025] Visualization method refers to the use of visual and intuitive forms to display complex resource content after the original data is converted into visual elements, thereby deepening the user's understanding. Common ones include scatter plots, histograms, timelines, and tree maps.

[0026] Data correction:

[0027] For missing values, appropriate interpolation methods are used to fill them, including linear interpolation or Lagrange interpolation. For outliers, corrections are made based on industry standards and the actual conditions of each enterprise.

[0028] Linear interpolation is a simple and effective interpolation method, which is suitable for the case where the changes between data points are relatively stable. This method assumes that there is a linear relationship between the value of the point where the missing value is located and the known data points before and after it. Suppose there is a missing value at time point t, and the data at time points t-1 and t+1 are X t-1 and X t+1 . Then the missing value X t The linear interpolation formula is:

[0029]

[0030] Lagrange interpolation is a polynomial interpolation method that is suitable for situations where there are few data points and the data changes are more complex. This method estimates the value of the point where the missing value is located by constructing a polynomial that passes through all known data points. Compared with linear interpolation, Lagrange interpolation performs better in situations where the data changes rapidly or is nonlinear, but the computational complexity is higher. Suppose there is a missing value at time point t, and there are n+1 known data points (t0, X0), (t1, X1), …, (t n , X n ). Then the missing value X t The Lagrange interpolation formula is:

[0031]

[0032] Data Standardization:

[0033] In order to eliminate the dimensional differences between different indicators, the minimum-maximum standardization method is adopted:

[0034]

[0035] Among them, X i,t is the original data, and are the minimum and maximum values ​​of the index of each enterprise i, respectively.

[0036] Data Integration:

[0037] The processed data is integrated according to each enterprise and time dimension to form a complete data set, providing a basis for subsequent analysis.

[0038] 1.3 Data Analysis

[0039] Correlation analysis:

[0040] The Pearson correlation coefficient method was used to analyze the correlation between carbon emissions, electricity demand and production activity levels and to identify key influencing factors.

[0041] The Pearson correlation coefficient is a statistical indicator that measures the strength and direction of the linear relationship between two continuous variables, with a value range of -1 to +1:

[0042] +1 indicates a perfect positive correlation, meaning that if one variable increases, the other variable also increases proportionally.

[0043] -1 indicates a perfect negative correlation, meaning that when one variable increases, the other decreases proportionally.

[0044] 0 means no linear correlation.

[0045] The calculation formula is:

[0046]

[0047] Among them, X i and Y i are the observed values ​​of variables X and Y, respectively. and is its mean value.

[0048] Trend Analysis:

[0049] Conduct time series analysis on historical data to identify changing trends in carbon emissions and electricity demand, providing a basis for forecasting and decision-making.

[0050] Specifically, step 2: allocation of initial carbon quotas

[0051] 2.1 Establishing a multi-level decision-making model

[0052] First-level decision: Regional carbon emission total control

[0053] According to the regional development plan for carbon emission reduction, determine the regional carbon emission total control target E total , meet the total carbon emission requirements within a certain period of time.

[0054] Secondary decision: Industry carbon quota allocation

[0055] The total regional carbon emissions

[0056] E total The carbon quotas of various industries are decomposed according to their economic contribution, energy consumption and emission reduction potential. Where h represents the hth industry.

[0057] The calculation of industry carbon quota can be done using the following formula:

[0058]

[0059] in and are the weights of industry economic contribution and energy consumption, GDP h For industry output value, Energy h is the total energy consumption of the industry, and H is the total number of industries.

[0060] Three-level decision-making: initial carbon quota allocation for each enterprise

[0061] Carbon quotas in the industry Under this scenario, each enterprise is allocated an initial carbon quota based on its historical carbon emissions and electricity demand data.

[0062] 2.2 Calculation of initial carbon quota for each enterprise

[0063] Determination of comprehensive distribution coefficient

[0064] Determine the comprehensive allocation coefficient θ of each enterprise i i , considering the weights w of historical carbon emissions, historical electricity demand and production activity levels E 、w D and w P , satisfying w E +w D +w P =1:

[0065]

[0066] in, and are the historical average carbon emissions, historical average electricity demand and historical average production activity level of each enterprise i, Nh is the total number of enterprises in the industry.

[0067] Calculation of initial carbon quota

[0068] The initial carbon quota allocated to each enterprise i

[0069]

[0070] Specifically, step 3: dynamic adjustment mechanism

[0071] 3.1 Obtaining power data feedback

[0072] Real-time electricity demand data

[0073] Through the regional energy carbon platform, real-time data on the electricity demand of each enterprise in the current cycle is obtained Electricity demand data includes electricity consumption and load profiles.

[0074] 3.2 Calculation of quota adjustment coefficient

[0075] Calculation of the rate of change of power demand

[0076] Calculate the power demand change rate δ of each enterprise i i :

[0077]

[0078] When δ i >0, indicating an increase in electricity demand; when δ i When <0, it indicates that the power demand is decreasing.

[0079] Determination of adjustment factor

[0080] According to the power demand change rate δ i and the energy conservation and emission reduction measures of each enterprise to determine the quota adjustment coefficient α i Considering that the impact of changes in electricity demand on carbon emissions is not linear, nonlinear functions can be used for adjustment, such as:

[0081]

[0082] Among them, k is the adjustment coefficient sensitivity parameter, which reflects the impact of changes in electricity demand on carbon quotas.

[0083] 3.3 Dynamically Adjust Quotas

[0084] Adjusted carbon quota

[0085] Calculate the adjusted carbon quota for each enterprise i

[0086]

[0087] Total quota constraints

[0088] To ensure that the total amount of quota after adjustment does not exceed the industry carbon quota Need to To scale:

[0089]

[0090] Specifically, step 4: accumulation of dual control indicator data

[0091] 4.1 Accumulating total carbon emissions data

[0092] Monitoring of total carbon emissions of each enterprise

[0093] Real-time monitoring of the total carbon emissions of each enterprise i A combination of online monitoring equipment (such as flue gas online monitoring system) and regular verification is used to ensure the accuracy of the data.

[0094] Regional carbon emissions summary

[0095] Summarize the carbon emission data of each enterprise to form the total regional carbon emission data E region , used to meet the regional carbon emission control target E total Make comparisons and evaluations.

[0096] 4.2 Accumulating carbon emission intensity data

[0097] Calculation of carbon emission intensity

[0098] Calculate the carbon emission intensity I of each enterprise i i :

[0099]

[0100] Among them, P i current is the level of production activity of each enterprise in the current cycle.

[0101] Carbon emission intensity by industry and region and regional average carbon emission intensity Analyze the changing trend of carbon emission intensity and provide a basis for policy formulation and improvements of various enterprises.

[0102]

[0103]

[0104] Specifically, step 5: continuous optimization of the model

[0105] 5.1 Parameter adjustment and model optimization

[0106] Sensitivity analysis

[0107] Conduct sensitivity analysis on key parameters in the model, including weight coefficients and adjustment coefficient sensitivity parameters, to assess their impact on the quota allocation results.

[0108] Model calibration

[0109] The prediction accuracy of the model is verified through historical data, and the parameters are adjusted to improve the adaptability and accuracy of the model.

[0110] Uncertainty Analysis

[0111] Considering the impact of changes in the external environment on the model, including energy prices, market demand and policy adjustments, the Monte Carlo simulation method is used to evaluate the robustness of the model.

[0112] 5.2 Data Feedback and Decision Support

[0113] Data Feedback Mechanism

[0114] Establish a regular data feedback mechanism to collect each company's operating data, carbon emission performance and feedback, and provide first-hand information for model optimization.

[0115] Decision Support System

[0116] Develop a decision support system based on big data and artificial intelligence, use machine learning algorithms (such as random forests and neural networks) to deeply mine data, and provide carbon quota management and decision-making support for governments and enterprises.

[0117] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that the memory stores the computer program, and when the processor executes the computer program, it implements the method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data.

[0118] A computer-readable storage medium having a computer program stored thereon, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data.

[0119] Beneficial Effects

[0120] The present invention effectively improves the scientificity and flexibility of carbon quota allocation by establishing a multi-level decision-making model. First, based on the historical carbon emission data and power demand data of each enterprise accumulated in the supervision platform, an initial carbon quota is allocated to each enterprise to ensure that the allocation process is accurate and reasonable. On this basis, the system combines the real-time power usage data of each enterprise, dynamically adjusts the carbon quota, and promptly responds to changes in the production activities of each enterprise, thereby optimizing system requirements and avoiding waste or insufficient quotas caused by production fluctuations. In addition, through this decision-making model, the carbon emissions of each enterprise can be effectively managed and supervised to achieve the dual control goals of total carbon emissions and intensity. The present invention also improves the flexibility of quota allocation through a dynamic adjustment mechanism, and uses early warning and corrective measures to prevent each enterprise from exceeding the emission standard, ensuring that the production efficiency of each enterprise is improved under the premise of compliance. At the same time, the introduction of the carbon trading market further optimizes resource allocation, and each enterprise can flexibly handle excess or insufficient carbon quotas, both achieving production goals and meeting environmental protection requirements. This carbon quota management method based on multi-level decision-making and dynamic adjustment provides a highly efficient carbon emission control and optimization tool for governments and enterprises.

[0121] 1. Initial carbon quota allocation: The government uses the historical carbon emission data and electricity demand data of each enterprise in the regional energy carbon platform to allocate initial carbon emission quotas to each industry and enterprise according to predetermined rules or algorithms. This method improves the scientificity and fairness of carbon quota allocation.

[0122] 2. Establishment and application of multi-level decision-making model: A multi-level decision-making model including initial allocation and dynamic adjustment was constructed. After the initial quota allocation is completed, the model dynamically adjusts the carbon quota of each enterprise based on real-time power data feedback to optimize system requirements and meet the balance between actual production and carbon reduction targets.

[0123] 3. Accumulate carbon emission dual control indicator data: In the process of carbon quota allocation and dynamic adjustment, continuously collect and accumulate the total carbon emission and carbon emission intensity data of industrial enterprises. These dual control indicator data provide important data support for the government to formulate and adjust carbon emission reduction policies and regulatory measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0124] Figure 1 This is a flow chart of the method for allocating carbon quotas to industrial enterprises in the present invention;

[0125] Figure 2 It is the operating mechanism of the carbon emission rights trading system in the present invention. DETAILED DESCRIPTION

[0126] The following is in conjunction with the instruction manual Figure 1-2 The present invention is further described in detail:

[0127] The specific method of the present invention is a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data as follows:

[0128] Step 1: Data collection and preprocessing

[0129] 1.1 Data Collection

[0130] Historical carbon emission data acquisition:

[0131] Obtain the carbon emission data E of each industrial enterprise i in the past T cycles from the regional energy carbon platform i,t , including direct carbon emissions and indirect carbon emissions. Where t=1,2,…,T.

[0132] Historical power demand data acquisition:

[0133] Obtain the power demand data D of each enterprise i in the past T cycles i,t , including electricity consumption, peak and valley electricity consumption, etc.

[0134] Production activity level data acquisition:

[0135] Obtain the production activity level data P of each enterprise i in the past T cycles i,t , such as key indicators such as output, output value, and operating income.

[0136] Other relevant data:

[0137] Obtain data on other factors that affect carbon emissions, such as energy structure, technology level, equipment updates, energy-saving and emission reduction measures, etc.

[0138] 1.2 Data Preprocessing

[0139] Data cleaning:

[0140] The collected data was quality checked to remove missing values, outliers and duplicate values. Statistical methods were used, which were visual methods, to identify and process abnormal data.

[0141] Visualization method refers to the use of visual and intuitive forms to display complex resource content after the original data is converted into visual elements, thereby deepening the user's understanding. Common ones include scatter plots, histograms, timelines, and tree maps.

[0142] Data correction:

[0143] For missing values, appropriate interpolation methods are used to fill them, including linear interpolation or Lagrange interpolation. For outliers, corrections are made based on industry standards and the actual conditions of each enterprise.

[0144] Linear interpolation is a simple and effective interpolation method, which is suitable for the case where the changes between data points are relatively stable. This method assumes that there is a linear relationship between the value of the point where the missing value is located and the known data points before and after it. Suppose there is a missing value at time point t, and the data at time points t-1 and t+1 are X t-1 and X t+1 . Then the missing value X t The linear interpolation formula is:

[0145]

[0146] Lagrange interpolation is a polynomial interpolation method that is suitable for situations where there are few data points and the data changes are more complex. This method estimates the value of the point where the missing value is located by constructing a polynomial that passes through all known data points. Compared with linear interpolation, Lagrange interpolation performs better in situations where the data changes rapidly or is nonlinear, but the computational complexity is higher. Suppose there is a missing value at time point t, and there are n+1 known data points (t0, X0), (t1, X1), …, (t n , X n ). Then the missing value X t The Lagrange interpolation formula is:

[0147]

[0148] 1.3 Data Analysis

[0149] Correlation analysis:

[0150] The Pearson correlation coefficient method was used to analyze the correlation between carbon emissions, electricity demand and production activity levels and to identify key influencing factors.

[0151] The Pearson correlation coefficient is a statistical indicator that measures the strength and direction of the linear relationship between two continuous variables, with a value range of -1 to +1:

[0152] +1 indicates a perfect positive correlation, meaning that if one variable increases, the other variable also increases proportionally.

[0153] -1 indicates a perfect negative correlation, meaning that when one variable increases, the other decreases proportionally.

[0154] 0 means no linear correlation.

[0155] The calculation formula is:

[0156]

[0157] Among them, X i and Y i are the observed values ​​of variables X and Y, respectively. and is its mean value.

[0158] Trend Analysis:

[0159] Conduct time series analysis on historical data to identify changing trends in carbon emissions and electricity demand, providing a basis for forecasting and decision-making.

[0160] Step 2: Allocation of initial carbon allowances

[0161] 2.1 Establishing a multi-level decision-making model

[0162] First-level decision: Regional carbon emission total control

[0163] According to the regional development plan for carbon emission reduction, determine the regional carbon emission total control target E total , meet the total carbon emission requirements within a certain period of time.

[0164] Secondary decision: Industry carbon quota allocation

[0165] The total regional carbon emissions

[0166] E total The carbon quotas of various industries are decomposed according to their economic contribution, energy consumption and emission reduction potential. Where h represents the hth industry.

[0167] The calculation of industry carbon quota can be done using the following formula:

[0168]

[0169] in and are the weights of industry economic contribution and energy consumption, GDP h For industry output value, Energy h is the total energy consumption of the industry, and H is the total number of industries.

[0170] Three-level decision-making: initial carbon quota allocation for each enterprise

[0171] Carbon quotas in the industry Under this scenario, each enterprise is allocated an initial carbon quota based on its historical carbon emissions and electricity demand data.

[0172] 2.2 Calculation of initial carbon quota for each enterprise

[0173] Determination of comprehensive distribution coefficient

[0174] Determine the comprehensive allocation coefficient θ of each enterprise i i , considering the weights w of historical carbon emissions, historical electricity demand and production activity levels E 、w D and wP , satisfying w E +w D +w P =1:

[0175]

[0176] in, and are the historical average carbon emissions, historical average electricity demand and historical average production activity level of each enterprise i, N h is the total number of enterprises in the industry.

[0177] Calculation of initial carbon quota

[0178] The initial carbon quota allocated to each enterprise i

[0179]

[0180] Step 3: Dynamic Adjustment Mechanism

[0181] 3.1 Obtaining power data feedback

[0182] Real-time electricity demand data

[0183] Through the regional energy carbon platform, real-time data on the electricity demand of each enterprise in the current cycle is obtained Electricity demand data includes electricity consumption and load profiles.

[0184] 3.2 Calculation of quota adjustment coefficient

[0185] Calculation of the rate of change of power demand

[0186] Calculate the power demand change rate δ of each enterprise i i :

[0187]

[0188] When δ i >0, indicating an increase in electricity demand; when δ i When <0, it indicates that the power demand is decreasing.

[0189] Determination of adjustment factor

[0190] According to the power demand change rate δ i and the energy conservation and emission reduction measures of each enterprise to determine the quota adjustment coefficient α i Considering that the impact of changes in electricity demand on carbon emissions is not linear, nonlinear functions can be used for adjustment, such as:

[0191]

[0192] Among them, k is the adjustment coefficient sensitivity parameter, which reflects the impact of changes in electricity demand on carbon quotas.

[0193] 3.3 Dynamically Adjust Quotas

[0194] Adjusted carbon quota

[0195] Calculate the adjusted carbon quota for each enterprise i

[0196]

[0197] Total quota constraints

[0198] To ensure that the total amount of quota after adjustment does not exceed the industry carbon quota Need to To scale:

[0199]

[0200] Step 4: Accumulation of dual control indicator data

[0201] 4.1 Accumulating total carbon emissions data

[0202] Monitoring of total carbon emissions of each enterprise

[0203] Real-time monitoring of the total carbon emissions of each enterprise A combination of online monitoring equipment (such as flue gas online monitoring system) and regular verification is used to ensure the accuracy of the data.

[0204] Regional carbon emissions summary

[0205] Summarize the carbon emission data of each enterprise to form the total regional carbon emission data E region , used to meet the regional carbon emission control target E total Make comparisons and evaluations.

[0206] 4.2 Accumulating carbon emission intensity data

[0207] Calculation of carbon emission intensity

[0208] Calculate the carbon emission intensity I of each enterprise i i :

[0209]

[0210] Among them, P i current is the level of production activity of each enterprise in the current cycle.

[0211] Carbon emission intensity by industry and region and regional average carbon emission intensity Analyze the changing trend of carbon emission intensity and provide a basis for policy formulation and improvements of various enterprises.

[0212]

[0213]

[0214] Step 5: Continuous optimization of the model

[0215] 5.1 Parameter adjustment and model optimization

[0216] Sensitivity analysis

[0217] Conduct sensitivity analysis on key parameters in the model, including weight coefficients and adjustment coefficient sensitivity parameters, to assess their impact on the quota allocation results.

[0218] Model calibration

[0219] The prediction accuracy of the model is verified through historical data, and the parameters are adjusted to improve the adaptability and accuracy of the model.

[0220] Uncertainty Analysis

[0221] Considering the impact of changes in the external environment on the model, including energy prices, market demand and policy adjustments, the Monte Carlo simulation method is used to evaluate the robustness of the model.

[0222] 5.2 Data Feedback and Decision Support

[0223] Data Feedback Mechanism

[0224] Establish a regular data feedback mechanism to collect each company's operating data, carbon emission performance and feedback, and provide first-hand information for model optimization.

[0225] Develop a decision support system based on big data and artificial intelligence, use machine learning algorithms (such as random forests and neural networks) to conduct in-depth data mining, and provide carbon quota management and decision-making support for governments and enterprises.

[0226] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that the memory stores the computer program, and when the processor executes the computer program, it implements the method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data.

[0227] A computer-readable storage medium having a computer program stored thereon, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data.

[0228] Example:

[0229] There are two industrial enterprises in the region: Enterprise A and Enterprise B.

[0230] Regional carbon emission total control target: E total =1 million tons.

[0231] Step 1: Data collection and preprocessing

[0232] 1.1 Obtain historical data of each enterprise

[0233] Company A:

[0234] Historical average carbon emissions

[0235] Historical average electricity demand

[0236] Historical average production activity level

[0237] Company B:

[0238] Historical average carbon emissions

[0239] Historical average electricity demand

[0240] Historical average production activity level

[0241] Step 2: Allocation of initial carbon allowances

[0242] 2.1 Determine the weight coefficient

[0243] Carbon emission weight w E =0.4

[0244] Power demand weight w D =0.3

[0245] Production level weight w P =0.3

[0246] 2.2 Calculation of comprehensive allocation coefficient

[0247] Company A: θ A =0.6

[0248] Company B: θ B =0.4

[0249] 2.3 Allocation of initial carbon quotas

[0250] Company A:

[0251] Company B:

[0252] Step 3: Dynamic Adjustment Mechanism

[0253] 3.1 Obtain current power demand

[0254] Current electricity demand of Enterprise A:

[0255] Current electricity demand of enterprise B:

[0256] 3.2 Calculation of power demand change rate

[0257] Company A: δ A =0.0333

[0258] Company B: δ B =0.05

[0259] 3.3 Calculation of adjustment coefficient

[0260] Assume the adjustment coefficient sensitivity parameter k = 0.5

[0261] Company A: α A =1.0168

[0262] Company B: α B =0.9753

[0263] 3.4 Calculation of adjusted carbon quota

[0264] Company A:

[0265] Company B:

[0266] 3.5 Check the total quota

[0267] Total quota: Q total =1,000,200 tons

[0268] Adjustment ratio: r≈0.9998

[0269] 3.6 Calculation of final carbon quota

[0270] Company A:

[0271] Company B:

[0272] Step 4: Carbon emission intensity analysis

[0273] 4.1 Calculation of carbon emission intensity of each enterprise

[0274] Assume that the actual carbon emissions of each enterprise are:

[0275] Company A:

[0276] Company B:

[0277] Assuming current production activity levels:

[0278] Company A:

[0279] Company B:

[0280] Company A: I A ≈0.4918 tons of carbon dioxide / ton of product

[0281] Company B: I B ≈0.4937 tons of carbon dioxide / ton of product

[0282] 4.2 Calculation of regional carbon emission intensity

[0283] Total regional carbon emissions: E region =990,000 tons

[0284] Regional total production activity level: P region = 2.01 million tons of products

[0285] Regional carbon emission intensity: I region ≈0.4925 tonnes of CO2 / tonne of product.

[0286] The present invention provides a method for allocating carbon quotas to industrial enterprises based on regional energy and carbon platform supervision data. By comprehensively considering the historical carbon emissions and real-time electricity demand data of the enterprise, the carbon quota allocation plan is dynamically adjusted to achieve the dual control goals of total carbon emissions and carbon emission intensity. This method can improve the efficiency of carbon management, ensure the fair and reasonable allocation of carbon emissions, and provide enterprises with flexible energy use strategies to avoid production being affected by insufficient quotas.

Claims

1. A method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data. Its features are as follows: Step 1: Data collection and preprocessing, including: Data collection, data preprocessing and data analysis; Step 2: Allocation of initial carbon quotas, including: establishing a multi-level decision-making model and calculating the initial carbon quotas of enterprises; Step 3: Dynamic adjustment mechanism, including: obtaining power data feedback, calculating quota adjustment coefficients and dynamically adjusting quotas; Step 4: Accumulation of dual control indicator data, including: accumulation of dual control indicator data and accumulation of carbon emission intensity data; Step 5: Continuous optimization of the model, including: parameter adjustment and model optimization, data feedback and decision support.

2. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data, Its features are as follows: 1.1 Data Collection Historical carbon emission data acquisition: Obtain the carbon emission data E of each industrial enterprise i in the past T cycles from the regional energy and carbon platform i,t , including direct carbon emissions and indirect carbon emissions, among which, t=1,2,…,T。 Historical power demand data acquisition: Obtain the power demand data D of each enterprise i in the past T cycles i,t , including electricity consumption and peak and valley electricity consumption; Production activity level data acquisition: Obtain the production activity level data P of each enterprise i in the past T cycles i,t , including key indicators of output, output value and operating income; Other relevant data: Obtain data on other factors that affect carbon emissions, including energy structure, technology level, equipment updates, and energy-saving and emission-reduction measures.

3. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data, Its features are as follows: 1.2 Data Preprocessing Data cleaning: Conduct quality checks on the collected data, remove missing values, outliers, and duplicates, and use statistical methods, which are visualization methods, to identify and process abnormal data; Visualization method refers to the use of visual and intuitive forms of expression to display complex resource content after the original data is converted into visual elements, so as to deepen the user's understanding. Common ones include scatter plots, histograms, timelines and tree maps; For missing values, appropriate interpolation methods are used to fill them, including linear interpolation or Lagrange interpolation; For outliers, corrections are made based on industry standards and the actual conditions of each enterprise; Linear interpolation is a simple and effective interpolation method, which is suitable for the case where the changes between data points are relatively stable. This method assumes that there is a linear relationship between the value of the point where the missing value is located and the known data points before and after it. Suppose there is a missing value at time point t, and the data at time points t-1 and t+1 are X t-1 and X t+1 ; then the missing value X t The linear interpolation formula is: Lagrange interpolation is a polynomial interpolation method that is suitable for situations where there are few data points and the data changes are more complex. This method estimates the value of the point where the missing value is located by constructing a polynomial that passes through all known data points. Compared with linear interpolation, Lagrange interpolation performs better in situations where the data changes rapidly or is nonlinear, but the computational complexity is higher. Suppose there is a missing value at time point t, and there are n+1 known data points (t0, X0), (t1, X1), …, (t n , X n ), then the missing value X t The Lagrange interpolation formula is: Data Standardization: In order to eliminate the dimensional differences between different indicators, the minimum-maximum standardization method is adopted: Among them, X i,t is the original data, and are the minimum and maximum values ​​of the index of each enterprise i, respectively; Data Integration: The processed data is integrated according to each enterprise and time dimension to form a complete data set, providing a basis for subsequent analysis.

4. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data, Its features are as follows: 1.3 Data Analysis Correlation analysis: The Pearson correlation coefficient method was used to analyze the correlation between carbon emissions, electricity demand and production activity levels and identify key influencing factors; The Pearson correlation coefficient is a statistical indicator that measures the strength and direction of the linear relationship between two continuous variables, with a value range of -1 to +1: +1 indicates a perfect positive correlation, that is, if one variable increases, the other variable also increases proportionally; -1 indicates a perfect negative correlation, that is, when one variable increases, the other variable decreases proportionally; 0 means no linear correlation; The calculation formula is: in, X i and Y i are the observed values ​​of variables X and Y, respectively. and is its mean value; Trend Analysis: Conduct time series analysis on historical data to identify changing trends in carbon emissions and electricity demand, providing a basis for forecasting and decision-making.

5. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data is characterized by the following: 2.1 Establishing a multi-level decision-making model First-level decision: Regional carbon emission control According to the regional development plan for carbon emission reduction, determine the regional carbon emission total control target E total , meet the total carbon emission requirements within a certain period; Secondary decision: Industry carbon quota allocation The total regional carbon emissions E total The carbon quotas for each industry are broken down according to their economic contribution, energy consumption and emission reduction potential. Where h represents the hth industry. The calculation of industry carbon quota can be done using the following formula: in and are the weights of industry economic contribution and energy consumption, GDP h For industry output value, Energy h is the total energy consumption of the industry, H is the total number of industries; Three-level decision-making: initial carbon quota allocation for each enterprise Carbon quotas in the industry Under this scenario, each enterprise is allocated an initial carbon quota based on its historical carbon emissions and electricity demand data.

6. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data is characterized by the following: 2.2 Calculation of initial carbon quota for each enterprise Determination of comprehensive distribution coefficient Determine the comprehensive allocation coefficient θ of each enterprise i i , considering the weights w of historical carbon emissions, historical electricity demand and production activity levels E 、w D and w P , satisfying w E +w D +w P =1: in, and are the historical average carbon emissions, historical average electricity demand and historical average production activity level of each enterprise i, N h is the total number of enterprises in the industry; Calculation of initial carbon quota The initial carbon quota allocated to each enterprise i 7. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data is characterized by the following: Step 3: Dynamic adjustment mechanism; 3.1 Obtaining power data feedback Real-time electricity demand data Through the regional energy carbon platform, real-time data on the electricity demand of each enterprise in the current cycle is obtained Electricity demand data includes electricity consumption and load profiles; 3.2 Calculation of quota adjustment coefficient Calculation of the rate of change of power demand Calculate the power demand change rate δ of each enterprise i i : When δ i >0, indicating an increase in electricity demand; when δ i When <0, it means that the power demand is reduced; Determination of adjustment factor According to the power demand change rate δ i and the energy conservation and emission reduction measures of each enterprise to determine the quota adjustment coefficient α i ; Considering that the impact of changes in electricity demand on carbon emissions is not linear, a nonlinear function is used for adjustment, such as: in, k is the adjustment coefficient sensitivity parameter, which reflects the impact of changes in electricity demand on carbon quotas; 3.3 Dynamically Adjust Quotas Adjusted carbon quota Calculate the adjusted carbon quota for each enterprise i Total quota constraints To ensure that the total amount of quota after adjustment does not exceed the industry carbon quota Need to To scale:

8. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data, Its features are as follows: Step 4: Accumulation of dual control indicator data 4.1 Accumulating total carbon emissions data Monitoring of total carbon emissions of each enterprise Real-time monitoring of the total carbon emissions of each enterprise i Use a combination of online monitoring equipment and regular verification to ensure data accuracy; Regional carbon emissions summary Summarize the carbon emission data of each enterprise to form the total regional carbon emission data E region , used to meet the regional carbon emission control target E total to make comparisons and assessments; 4.2 Accumulating carbon emission intensity data Calculation of carbon emission intensity Calculate the carbon emission intensity I of each enterprise i i : Among them, P i current is the level of production activity of each enterprise in the current cycle; Carbon emission intensity by industry and region and regional average carbon emission intensity Analyze the changing trend of carbon emission intensity and provide a basis for policy formulation and improvement of various enterprises; 9. According to claim 1, a method for allocating carbon emission quotas to industrial enterprises based on regional energy and carbon platform supervision data, Its features are as follows: Specifically, step 5: continuous optimization of the model 5.1 Parameter adjustment and model optimization Sensitivity analysis Conduct sensitivity analysis on key parameters in the model, including weight coefficients and adjustment coefficient sensitivity parameters, to assess their impact on quota allocation results; Model calibration Verify the prediction accuracy of the model through historical data and adjust parameters to improve the adaptability and accuracy of the model; Uncertainty analysis Consider the impact of external environmental changes on the model, including energy prices, market demand and policy adjustments, and use the Monte Carlo simulation method to evaluate the robustness of the model; 5.2 Data Feedback and Decision Support Data Feedback Mechanism Establish a regular data feedback mechanism to collect the operating data, carbon emission performance and feedback of each enterprise to provide first-hand information for model optimization; Decision Support System Develop a decision support system based on big data and artificial intelligence, and use machine learning algorithms to deeply mine data. Machine learning algorithms include random forest algorithms and neural network algorithms to provide carbon quota management and decision-making support for governments and enterprises.

10. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and is characterized in that the memory stores a computer program, and when the processor executes the computer program, it implements a method for allocating carbon emission quotas to industrial enterprises based on regional energy carbon platform supervision data as described in any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute a method for allocating carbon emission quotas to industrial enterprises based on regional energy carbon platform supervision data as described in any one of claims 1 to 9.

Images