Enterprise-level carbon emission measuring and calculating method based on electric power big data mining
By acquiring electricity consumption and energy consumption data from enterprises, conducting data quality verification and validation, and constructing a big data carbon emission calculation model for the power industry, the problems of data falsification and subjective auditing in enterprise carbon emission verification have been solved, improving verification efficiency and accuracy, and reducing costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-20
- Publication Date
- 2026-04-07
AI Technical Summary
Existing technologies for enterprise carbon emission verification processes suffer from problems such as falsification of basic data acquisition, lack of objective methods for data verification, and falsification of carbon emission accounting data, resulting in low verification efficiency and high costs.
By acquiring historical electricity consumption and energy consumption data of enterprises, conducting data quality verification and validation, constructing an enterprise-level carbon emission calculation model based on big data of electricity, and using the direct carbon calculation method and the electricity consumption factor method to calculate carbon emissions, considering the carbon emission structure and stability, and designing differentiated calculation methods.
It has improved the efficiency and accuracy of carbon emission verification, saved on-site verification labor costs, solved the problem of non-objectivity in data acquisition and review, and enabled timely and accurate calculation of carbon emissions.
Smart Images
Figure CN121809805A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of carbon emission measurement technology, and in particular to an enterprise-level carbon emission measurement method based on big data mining of electricity. Background Technology
[0002] In recent years, the Ministry of Ecology and Environment has focused on comprehensively improving data quality and has adopted a "zero-tolerance" policy towards data falsification.
[0003] The MRV (Monitoring, Reporting, and Verification) system is the cornerstone of carbon market construction, mainly comprising three parts: Monitoring, Reporting, and Verification. The monitoring and verification stages are prone to falsification risks, primarily including falsification of basic data acquisition, a lack of objective methods for data verification, and falsification of carbon emission accounting data. Falsification of basic data acquisition manifests in the reliance on offline reporting. Taking externally purchased electricity as an example, current data acquisition mainly depends on companies providing their own data, leading to incomplete electricity statistics and inconsistent statistical periods. The lack of effective means for data verification is evident in the reliance on manual reports, invoices, and on-site inspections, lacking relatively objective and quantitative verification methods, resulting in low efficiency and high subjectivity. The problem of falsified carbon emission accounting data manifests in the falsification of carbon emission data by relevant entities, with companies or third-party institutions potentially altering corporate carbon emission data.
[0004] Electricity data is characterized by its real-time nature, high accuracy, high resolution, and wide data collection range. It is closely linked to enterprise production processes and can accurately reflect the production situation of enterprises, with the proportional relationships between various energy sources being roughly determined. Therefore, electricity big data can be used to analyze the carbon emissions generated by the energy consumption of key enterprises. Summary of the Invention
[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and propose an enterprise-level carbon emission calculation method based on big data mining of electricity. This method can solve problems such as falsification of basic data acquisition, lack of objective methods for data verification, and falsification of carbon emission accounting data in the traditional enterprise carbon verification process. By calculating the carbon emissions of enterprise energy activities, the efficiency and accuracy of carbon emission verification can be improved, and costs can be saved.
[0006] The technical problem solved by this invention is achieved through the following technical solution: A method for calculating enterprise-level carbon emissions based on big data mining in the power sector includes the following steps: Step 1: Obtain the company's historical electricity consumption, energy consumption data for each energy category, and carbon emission factor data for each energy type for each period. Step 2: Based on the data obtained in Step 1, perform data quality verification, and improve the quality of the accessed data by filling in missing values and checking outliers; Step 3: Construct an enterprise-level carbon emission calculation model based on big data of electricity, and predict carbon emissions based on the data obtained in Step 2.
[0007] Furthermore, the specific implementation method of step 1 is as follows: obtain the enterprise's historical energy consumption data, which is divided into energy type carbon dioxide emission factor data and enterprise carbon emission data calculated by the enterprise carbon verification. At the same time, based on the emission factor method, calculate the enterprise's carbon emissions by energy type and the enterprise's overall carbon emissions at different periods.
[0008] in CO2 emissions from the combustion of fossil fuels by businesses For the consumption of the i-th type of fossil fuel energy, Let be the carbon dioxide emission factor for the i-th fossil fuel.
[0009] Furthermore, the data quality check in step 2 includes routine verification and noise reduction: The specific processing method for routine verification is as follows: data verification is carried out from two aspects: data integrity and consistency, missing values are supplemented, and names are standardized; The specific methods for noise processing are as follows: for outlier cases, data completion is achieved through filtering, data cleaning, smoothing, and other methods.
[0010] Furthermore, step 3 includes the following steps: Step 3.1: Calculate the proportion of carbon emissions of various energy types in the overall energy carbon emissions of the enterprise. If the proportion of carbon emissions of a certain energy type is greater than α1, then that energy type is the main energy type. Step 3.2: Determine the stability of the carbon emission structure by the coefficient of variation of the carbon emission ratio. If the coefficient of variation is less than or equal to β1, the carbon emission structure is considered stable; otherwise, it is unstable. Step 3.3: Calculate the proportion of the enterprise's electricity carbon emissions to the overall energy carbon emissions. If the proportion is greater than γ1, the enterprise's carbon emissions are determined to be mainly composed of electricity. For enterprises with unstable carbon emissions, the electricity consumption factor method is used for calculation. For enterprises whose carbon emissions are mainly composed of electricity, the direct carbon calculation method is used for calculation. For enterprises whose carbon emissions are not mainly composed of electricity, the method of calculating carbon based on electricity and carbon based on energy is used for calculation.
[0011] Moreover, the specific implementation method of the direct carbon calculation method in step 3.3 is as follows: by constructing the correlation between the enterprise's electricity carbon emissions and the overall carbon emissions, the overall carbon emissions data of the enterprise are directly calculated based on the enterprise's electricity carbon emissions.
[0012] Furthermore, the specific implementation method of the electricity consumption factor method in step 3.3 is as follows: the electricity consumption factor method needs to calculate the ratio of carbon emissions from electricity to carbon emissions from different energy sources after the change in energy structure, and use this as the electricity consumption factor to calculate the carbon emissions from other energy sources and the overall energy mix.
[0013] As the power consumption factor, For carbon emissions from electricity, For carbon emissions from other energy sources, i refers to the energy source, such as natural gas, gasoline, diesel, etc.
[0014]
[0015] C represents the total carbon emissions. As the power consumption factor, This is a carbon emission factor for the power grid.
[0016] The advantages and positive effects of this invention are: 1. This invention acquires historical electricity consumption data, energy consumption data for various energy categories, and carbon emission factor data for each energy type from enterprises at different periods. Based on the acquired data, it performs data quality verification and improves the quality of the accessed data by filling in missing values and checking outliers. It constructs an enterprise-level carbon emission calculation model based on big data in the power sector and predicts carbon emissions based on the obtained data. This invention fully considers the composition and stability of enterprise carbon emission structures, designs differentiated calculation methods to calculate enterprise carbon emissions, supports the verification of enterprise carbon verification data, improves data verification efficiency, saves on-site verification labor costs, and provides data support for government enterprises' annual quota allocation.
[0017] 2. This invention addresses the problem of outdated carbon emission verification data in traditional enterprises by using a big data mining method for enterprise-level carbon emission calculation. It constructs a correlation between historical electricity consumption and carbon emissions from various energy sources. Leveraging the timeliness, accuracy, and high correlation between electricity consumption and enterprise production, it calculates carbon emission data based on current electricity consumption data. This effectively avoids issues such as falsification of basic carbon verification data, lack of objective methods for data review, and falsification of carbon emission accounting data, thereby improving the timeliness of enterprise carbon emission calculation. Attached Figure Description
[0018] Figure 1 This is a flowchart of the present invention; Figure 2 This is a structural diagram of the carbon emission calculation model of the present invention. Detailed Implementation
[0019] The present invention will be further described in detail below with reference to the accompanying drawings.
[0020] A method for enterprise-level carbon emission measurement based on big data mining of electricity data, such as Figure 1 As shown, it includes the following steps: Step 1: Obtain the company's historical electricity consumption data for various periods, energy consumption data for each energy category, and carbon emission factor data for each energy type.
[0021] We acquire historical energy consumption data for enterprises, categorized into energy type carbon dioxide emission factor data and enterprise carbon emission data calculated from enterprise carbon verification. Simultaneously, relying on the emission factor method, we calculate the enterprise's carbon emissions by energy type and overall carbon emissions for different periods.
[0022] in CO2 emissions from the combustion of fossil fuels by businesses For the consumption of the i-th type of fossil fuel energy, Let be the carbon dioxide emission factor for the i-th fossil fuel.
[0023] Step 2: Based on the data obtained in Step 1, perform data quality verification, and improve the quality of the accessed data by filling in missing values and checking outliers.
[0024] Data quality checks include routine verification and noise reduction: The specific processing method for routine verification is as follows: data verification is carried out from two aspects: data integrity and consistency, missing values are supplemented, and names are standardized; The specific methods for noise processing are as follows: for outlier cases, data completion is achieved through filtering, data cleaning, smoothing, and other methods.
[0025] Step 3: Construct an enterprise-level carbon emission calculation model based on big data of electricity, and predict carbon emissions based on the data obtained in Step 2. Based on the historical carbon emission data and energy consumption data of enterprises, enterprises are grouped according to the composition and stability of their carbon emission structure, and an enterprise-level "electricity-carbon calculation model" is constructed to realize the calculation of enterprise carbon emissions based on electricity data.
[0026] like Figure 2 As shown, step 3 includes the following steps: Step 3.1: Calculate the proportion of carbon emissions of various energy types in the overall energy carbon emissions of the enterprise. If the proportion of carbon emissions of a certain energy type is greater than α1, then that energy type is the main energy type. Step 3.2: Determine the stability of the carbon emission structure by the coefficient of variation of the carbon emission ratio. If the coefficient of variation is less than or equal to β1, the carbon emission structure is considered stable; otherwise, it is unstable. Step 3.3: Calculate the proportion of the enterprise's electricity carbon emissions to the overall energy carbon emissions. If the proportion is greater than γ1, the enterprise's carbon emissions are determined to be mainly composed of electricity. For enterprises with unstable carbon emissions, the electricity consumption factor method is used for calculation. For enterprises whose carbon emissions are mainly composed of electricity, the direct carbon calculation method is used for calculation. For enterprises whose carbon emissions are not mainly composed of electricity, the method of calculating carbon based on electricity and carbon based on energy is used for calculation.
[0027] For enterprises with stable carbon emission structures, where electricity emissions are the primary component, this study establishes a correlation between enterprise electricity carbon emissions and overall carbon emissions. Based on these electricity carbon emissions, the overall energy carbon emissions of the enterprise can be directly extrapolated. Conduct correlation analysis between carbon emissions of different energy types and carbon emissions of electricity, and calculate the company’s overall energy carbon emissions based on the regression relationship between the company’s historical carbon emissions of electricity and overall carbon emissions, and calculate the company’s overall energy carbon emissions based on the company’s latest carbon emissions of electricity. The specific implementation method of direct carbon emission calculation is as follows: by constructing the correlation between enterprise electricity carbon emissions and overall carbon emissions, the overall carbon emission data of the enterprise can be directly estimated based on the enterprise's electricity carbon emissions.
[0028] For enterprises whose carbon emission structure of their main energy sources has changed, the latest carbon emission of energy sources is calculated based on the ratio of carbon emissions from electricity to carbon emissions from non-electric energy sources in the latest carbon emission structure. Based on the company's historical electricity carbon emissions and carbon emissions by energy type, the electricity consumption factor ki is calculated. Based on the current electricity carbon emission data and combined with the electricity consumption factor, the carbon emissions by energy type are calculated, and the overall energy carbon emissions of the company are obtained by summing them up.
[0029] The specific implementation method of the electricity consumption factor method is as follows: The electricity consumption factor method needs to calculate the ratio of carbon emissions from electricity to carbon emissions from different energy sources after changes in the energy structure, and use this as the electricity consumption factor to calculate carbon emissions from other energy sources and the overall energy mix.
[0030] As the power consumption factor, For carbon emissions from electricity, For carbon emissions from other energy sources, i refers to the energy source, such as natural gas, gasoline, diesel, etc.
[0031]
[0032] C represents the total carbon emissions. As the power consumption factor, This is a carbon emission factor for the power grid.
[0033] For enterprises with stable carbon emission structures and whose carbon emission composition is mainly non-electricity carbon emissions, carbon emissions of each energy type are predicted based on electricity consumption, thereby obtaining the overall energy carbon emissions.
[0034] It should be emphasized that the embodiments described in this invention are illustrative rather than limiting. Therefore, this invention includes, but is not limited to, the embodiments described in the specific implementation. Any other implementations derived by those skilled in the art based on the technical solutions of this invention are also within the scope of protection of this invention.
Claims
1. A method for calculating enterprise-level carbon emissions based on big data mining of the power industry, characterized in that: Includes the following steps: Step 1: Obtain the company's historical electricity consumption, energy consumption data for each energy category, and carbon emission factor data for each energy type for each period. Step 2: Based on the data obtained in Step 1, perform data quality verification, and improve the quality of the accessed data by filling in missing values and checking outliers; Step 3: Construct an enterprise-level carbon emission calculation model based on big data of electricity, and predict carbon emissions based on the data obtained in Step 2.
2. The enterprise-level carbon emission calculation method based on power big data mining according to claim 1, characterized in that: The specific implementation method of step 1 is as follows: Obtain the enterprise's historical energy consumption data, which is divided into energy type carbon dioxide emission factor data and enterprise carbon emission data calculated by the enterprise carbon verification. At the same time, based on the emission factor method, calculate the enterprise's carbon emissions by energy type and the enterprise's overall carbon emissions at different periods. ； in CO2 emissions from the combustion of fossil fuels by businesses For the consumption of the i-th type of fossil fuel energy, Let be the carbon dioxide emission factor for the i-th fossil fuel.
3. The enterprise-level carbon emission calculation method based on power big data mining according to claim 1, characterized in that: The data quality check in step 2 includes routine verification and noise reduction: The specific processing method for routine verification is as follows: data verification is carried out from two aspects: data integrity and consistency, missing values are supplemented, and names are standardized; The specific methods for noise processing are as follows: for outlier cases, data completion is achieved through filtering, data cleaning, smoothing, and other methods.
4. The enterprise-level carbon emission calculation method based on power big data mining according to claim 1, characterized in that: Step 3 includes the following steps: Step 3.1: Calculate the proportion of carbon emissions of various energy types in the overall energy carbon emissions of the enterprise. If the proportion of carbon emissions of a certain energy type is greater than α1, then that energy type is the main energy type. Step 3.2: Determine the stability of the carbon emission structure by the coefficient of variation of the carbon emission ratio. If the coefficient of variation is less than or equal to β1, the carbon emission structure is considered stable; otherwise, it is unstable. Step 3.3: Calculate the proportion of the enterprise's electricity carbon emissions to the overall energy carbon emissions. If the proportion is greater than γ1, the enterprise's carbon emissions are determined to be mainly composed of electricity. For enterprises with unstable carbon emissions, the electricity consumption factor method is used for calculation. For enterprises whose carbon emissions are mainly composed of electricity, the direct carbon calculation method is used for calculation. For enterprises whose carbon emissions are not mainly composed of electricity, the method of calculating carbon based on electricity and carbon based on energy is used for calculation.
5. The enterprise-level carbon emission calculation method based on power big data mining according to claim 4, characterized in that: The specific implementation method of the direct carbon calculation method in step 3.3 is as follows: by constructing the correlation between the enterprise's electricity carbon emissions and the overall carbon emissions, the overall carbon emissions of the enterprise are directly calculated based on the enterprise's electricity carbon emissions.
6. The enterprise-level carbon emission calculation method based on power big data mining according to claim 4, characterized in that: The specific implementation method of the electricity consumption factor method in step 3.3 is as follows: The electricity consumption factor method needs to calculate the ratio of carbon emissions from electricity to carbon emissions from different energy sources after the change in energy structure, and use this as the electricity consumption factor to calculate the carbon emissions from other energy sources and the overall energy mix. ； As the power consumption factor, For carbon emissions from electricity, For carbon emissions from other energy sources, i refers to the energy source, such as natural gas, gasoline, diesel, etc. ； C represents the total carbon emissions. As the power consumption factor, This is a carbon emission factor for the power grid.