Accounting method, system and equipment for regional carbon emission statistics and medium

Abstract

The invention relates to the technical field of regional carbon emission quantitative management, in particular to an accounting method, system, equipment and medium for regional carbon emission statistics, and the method comprises the steps: collecting carbon emission accounting basic data, and building a dynamically updated historical database; performing prediction and trend analysis on the carbon emission through a composite model fusing regression analysis and time sequence analysis on the basis of a historical database; monitoring the change of an energy structure, and dynamically adjusting a carbon emission factor and a weight parameter of the energy structure; and updating the composite model based on the dynamically adjusted weight parameters, and generating an optimized regional carbon emission statistics and prediction result. The method has the beneficial effects that the accuracy and reliability of the input data are ensured by collecting the carbon emission accounting basic data and performing strict data preprocessing. Regional electricity utilization carbon emission is analyzed by utilizing ridge regression and a time sequence algorithm, the prediction accuracy is improved, and a scientific basis is provided for a local government to optimize an energy structure and promote green and low-carbon development.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of regional carbon emission quantification management, in particular to a regional carbon emission statistical accounting method, system, device and medium. BACKGROUND

[0002] Currently, carbon emission statistical accounting mainly relies on traditional statistical methods and models. These methods are usually based on historical data and static emission factors for calculation, which can provide a certain degree of carbon emission estimation. In addition, with the development of information technology, some regions have begun to try to use online monitoring equipment and automated data collection systems to improve the real-time and accuracy of data. Although the existing technology has made some progress in carbon emission statistical accounting, there are still several major problems:

[0003] Data accuracy is insufficient: traditional carbon emission accounting methods rely on static emission factors and historical data, which are difficult to reflect the dynamic changes of energy structure in time, resulting in deviations between accounting results and actual situations; poor timeliness: due to the cumbersome data collection and processing process, the data statistical period of existing methods is long, which cannot meet the needs of governments and enterprises for real-time monitoring and rapid response; insufficient operability: the existing accounting method is complex to operate, lacks user-friendly interface and tools, making it difficult for ordinary users to effectively conduct carbon emission statistics and analysis; insufficient regional and industry refinement: the existing technology lacks the statistical precision of regional carbon emissions, making it difficult to support analysis of regions below the provincial level, and failing to provide detailed carbon emission statistics and display for different industries; limited prediction capability: the existing technology lacks prediction capability based on scientific algorithms, and cannot accurately estimate future carbon emission trends, with limited comprehensive analysis capability for multi-dimensional data such as energy consumption, carbon factor and historical data; limited data display effect: the existing technology has a single carbon emission result display method, usually providing only numbers or tables, lacking intuitive chart analysis, and unable to clearly convey the trends and key influencing factors behind the data.

[0004] These problems limit the application effect of existing technology in carbon emission statistical accounting, and there is an urgent need to develop more accurate, real-time, easy-to-use, refined and predictive new technologies to solve these problems. SUMMARY

[0005] Therefore, the technical problem to be solved by the present application is to solve the problems of insufficient data accuracy, poor timeliness, weak operability, insufficient regional and industry refinement analysis, limited prediction capability and poor data display effect of existing carbon emission statistical accounting technology.

[0006] The above technical problems are solved by the following technical solutions: the present application proposes a regional carbon emission statistical accounting method, which comprises collecting carbon emission accounting basic data, establishing a dynamically updated historical database;

[0007] Based on historical databases, a composite model integrating regression analysis and time series analysis is used to predict and analyze carbon emissions trends.

[0008] Monitor changes in the energy structure and dynamically adjust the carbon emission factor and the weighting parameters of the energy structure.

[0009] The composite model is updated based on dynamically adjusted weight parameters to generate optimized regional carbon emission statistics and prediction results.

[0010] In a preferred embodiment of the regional carbon emission statistics calculation method of the present invention: the prediction and trend analysis of carbon emissions by using a composite model that integrates regression analysis and time series analysis includes:

[0011] Regression analysis is used to combine energy consumption data and carbon emission factors to build carbon emission prediction models;

[0012] Time series analysis is used to capture the time dependence and dynamic trends of carbon emission data.

[0013] In a preferred embodiment of the method for calculating regional carbon emission statistics of the present invention: dynamically adjusting the carbon emission factor includes:

[0014] Real-time calculation of carbon emission intensity for different energy types;

[0015] Based on the current energy structure ratio, a dynamic total carbon emission factor is generated using weighted averages.

[0016] In a preferred embodiment of the regional carbon emission statistics calculation method of the present invention: the dynamic adjustment of the energy structure weight parameters is achieved through the following means:

[0017] The consumption percentage of each energy type is calculated based on a sliding time window.

[0018] The weight parameters are updated in real time based on changes in the proportion to adapt to dynamic fluctuations in the energy structure.

[0019] In a preferred embodiment of the method for calculating regional carbon emissions statistics of the present invention: updating the composite model includes:

[0020] Based on the adjusted carbon emission factor and energy structure weight parameters, the model parameters were retrained.

[0021] The model's predictive performance is evaluated through cross-validation, and its generalization ability is optimized.

[0022] In a preferred embodiment of the carbon emission accounting method of the present invention: the basic data for carbon emission accounting includes:

[0023] Regional electricity consumption, dynamic carbon factor, various energy consumption data, and historical carbon emission data;

[0024] The various energy consumption data include electricity consumption and the consumption of various energy types.

[0025] In a preferred embodiment of the method for calculating regional carbon emissions statistics in this invention: the optimized prediction results include:

[0026] The system uses visual charts to display total carbon emissions, intensity, and trends. It also dynamically sets threshold ranges based on historical carbon emission data and policy standards to generate different warning levels and provide real-time alerts for abnormal carbon emission risks.

[0027] To solve the above-mentioned technical problems, the present invention also provides the following technical solution: a regional carbon emission statistics accounting system, which includes a data collection module for collecting basic data related to regional carbon emissions, including energy consumption data and environmental monitoring data;

[0028] The data processing and storage module is used to store, clean, preprocess, and organize the collected data, and to manage the security and privacy protection of the data.

[0029] The carbon emission accounting model module is used to establish and maintain carbon emission accounting models, providing a basis for carbon emission management for governments and enterprises.

[0030] The communication and integration module is used for communication between modules within the system, as well as for integration with external systems.

[0031] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the content of a method for calculating regional carbon emissions statistics.

[0032] A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the content of a method for calculating regional carbon emissions statistics.

[0033] The beneficial effects of this invention are as follows: By collecting basic data for carbon emission accounting and performing rigorous data preprocessing, this invention ensures the accuracy and reliability of the input data. Utilizing ridge regression and time-series algorithms to analyze regional electricity consumption carbon emissions not only improves prediction accuracy but also captures the time dependence and trends in time-series data, making carbon emission predictions more precise and providing a scientific basis for local governments to optimize energy structures and promote green and low-carbon development. Real-time updates of dynamic electricity carbon factors and energy structure data ensure that the carbon emission accounting model can reflect changes in the energy structure in a timely manner, improving the model's adaptability and accuracy, and making the carbon emission accounting results closer to reality. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to specific embodiments.

[0035] The terminology used in this invention is that which is currently widely used in the art in consideration of the function of the invention; however, these terms may vary according to the intent of those skilled in the art, precedent, or new technology in the art. Furthermore, specific terms may be chosen by the applicant, and in such cases, their detailed meanings will be described in the detailed description of the invention. Therefore, the terms used in this specification should not be construed as simple names, but rather based on their meanings and the overall description of the invention.

[0036] Example 1

[0037] This embodiment is one example of the present invention, providing a method for calculating regional carbon emission statistics, including:

[0038] S100: Collect basic data for carbon emission accounting and establish a dynamically updated historical database;

[0039] S200: Based on historical databases, it uses a composite model that integrates regression analysis and time series analysis to predict and analyze carbon emissions trends.

[0040] S300: Monitors changes in the energy structure and dynamically adjusts the carbon emission factor and the weighting parameters of the energy structure;

[0041] S400: Based on dynamically adjusted weight parameters, update the composite model to generate optimized regional carbon emission statistics and prediction results.

[0042] In this embodiment of the application, step S100 involves collecting basic carbon emission accounting data and establishing a dynamically updated historical database. The basic carbon emission accounting data includes:

[0043] Regional electricity consumption, dynamic carbon factor, various energy consumption data, and historical carbon emission data;

[0044] Multiple energy consumption data include electricity consumption and consumption of various energy types.

[0045] Specifically, the data sources include real-time collection of electricity consumption data in various regions (such as provincial and municipal levels) through smart meters, in units of 10,000 kilowatt-hours, and stored as time-series data;

[0046] The dynamic carbon factor, calculated based on the power generation energy structure (thermal power, hydropower, wind power, etc.), is given by the following formula:

[0047]

[0048] Where k represents the energy type, and the data is updated hourly;

[0049] Data on various energy consumption, including coal, oil, and natural gas consumption, are collected through energy monitoring equipment.

[0050] Historical carbon emission data, including monthly carbon emissions over the past five years, with breakdowns for industry, agriculture, and services.

[0051] The database is built and updated based on the collected basic data for carbon emission accounting, including:

[0052] Data is stored using a time-series database, and monitoring data is synchronized once per hour;

[0053] Missing values ​​were filled using linear interpolation, and outliers were removed using the 3σ principle and replaced with the mean of adjacent time periods.

[0054] In this embodiment of the application, step S200 predicts and analyzes carbon emissions based on a historical database using a composite model that integrates regression analysis and time series analysis, including the following steps A1-A2:

[0055] A1: Regression analysis is used to combine energy consumption data and carbon emission factors to build carbon emission prediction models.

[0056] Specifically, the regression analysis uses the ridge regression algorithm, and the objective function formula is:

[0057]

[0058] Among them, y i This represents actual carbon emissions. The predicted value λ is optimized through cross-validation (range: 0.01–100).

[0059] It should be noted that the input features of the ridge regression algorithm include electricity consumption, coal consumption, and dynamic carbon factor, which are then standardized and input into the model.

[0060] The training process for the ridge regression algorithm model is as follows:

[0061] First, the dataset is divided into a training set and a test set in a 7:3 ratio;

[0062] Secondly, the optimal regression coefficient β is solved using the L-BFGS algorithm (Broyden-Fletcher-Goldfarb-Shanno algorithm with limited memory). The specific steps include:

[0063] First, initialize the parameters:

[0064] The regression coefficient β is initialized as a zero vector: β(0)=[0,0,…,0]T, and the maximum number of iterations and the convergence threshold are set.

[0065] Next, the gradient of the objective function is calculated, and the formula is as follows:

[0066]

[0067] Where X is the feature matrix and y is the target vector.

[0068] Finally, iterative optimization is performed, with the following specific steps:

[0069] (1) Calculate the current gradient

[0070] (2) Update the parameters using the quasi-Newton method of L-BFGS, the formula of which is as follows:

[0071]

[0072] Where, β k+1 It is the parameter vector after the (k+1)th iteration update; β k It is the parameter vector for the k-th iteration; Is the objective function J in β k gradient at; This is the inverse of the Hessian matrix, approximated by historical gradient information.

[0073] (3) Check the convergence condition. If it is met, terminate the iteration; otherwise, return to step 1.

[0074] Finally, the regularization parameter λ is determined through a grid search, selecting the value with the smallest MSE on the test set.

[0075] Specifically, the training set is divided into 5 subsets. The model is trained using 4 subsets and validated using 1 subset. Five-fold cross-validation is performed on the training set, and the mean squared error (MSE) of the validation set is calculated using the following formula:

[0076]

[0077] Where, n val y is the number of samples in the validation set; i,val It is the actual value of the i-th sample in the validation set;

[0078] It is the predicted value of the i-th sample in the validation set.

[0079] Finally, after iterating through all λ values, the parameter with the smallest average MSE after cross-validation is selected as the optimal solution for the regularization parameter λ.

[0080] A2: Time series analysis is used to capture the time dependence and dynamic trends of carbon emission data.

[0081] Time series analysis includes:

[0082] Historical carbon emission data is differentially processed to stabilize it;

[0083] The model order is determined based on the autocorrelation plot and the partial autocorrelation plot.

[0084] The model parameters are optimized using the maximum likelihood estimation method to predict future carbon emission trends.

[0085] Specifically, the time series analysis employs the ARIMA (Autoregressive Integrated Moving Average Model), where differencing is performed on the non-stationary carbon emission data Y. t Performing first-order differencing yields a stationary sequence.

[0086] Further model order determination includes: ADF test (Augmented Dickey-Fuller, original sequence stationarity test, hypothesis test: the null hypothesis is that the sequence has a unit root (non-stationarity), if the p-value > 0.05, the null hypothesis is rejected and differencing is required to obtain the differencing order d; the moving average order q (cutoff position) is determined through the autocorrelation plot; the autoregression order p (cutoff position) is determined through the partial autocorrelation plot; the final output model is ARIMA(p, q, d).

[0087] The maximum likelihood estimation method is used to optimize the autoregressive AR and moving average (MA) coefficients. The likelihood function is:

[0088]

[0089] Where L(θ) is the likelihood function, used to evaluate the probability of observed data given parameter θ; T is the sample size, i.e., the total number of observation points in the time series data; Y t It is the actual value of the t-th observation point; σ is the predicted value for the t-th observation point, generated by the AR and MA models; 2 θ is the variance of the error term, representing the average of the squared differences between the model's predicted and actual values; θ is the set of model parameters, including the AR and MA coefficients.

[0090] Carbon emissions for the next 12 months are predicted based on a fitted model and then weighted and fused with the results of regression analysis.

[0091] In this embodiment of the application, step S300, which involves monitoring changes in the energy structure and dynamically adjusting the carbon emission factor and the weighting parameters of the energy structure, includes the following steps B1-B3:

[0092] B1: Dynamic adjustment of carbon emission factors includes:

[0093] Real-time calculation of carbon emission intensity for different energy types;

[0094] Based on the current energy structure ratio, a dynamic total carbon emission factor is generated using weighted averages.

[0095] Specifically, carbon emission intensity is calculated in real time, with the carbon emission intensity of each energy type updated hourly. The formula is as follows:

[0096]

[0097] A weighted dynamic total carbon emission factor is generated, and the proportion of each energy consumption is calculated based on a sliding time window (window size: 24 hours). k The total factor formula is:

[0098]

[0099] Where m is the total number of energy types; w k It represents the consumption percentage of the k-th energy source, indicating the proportion of that energy source in total energy consumption.

[0100] B2: The dynamic adjustment of the energy structure weight parameters is achieved through the following methods:

[0101] The consumption percentage of each energy type is calculated based on a sliding time window.

[0102] The weight parameters are updated in real time based on changes in the proportion to adapt to dynamic fluctuations in the energy structure.

[0103] Specifically, dynamic weight updates include:

[0104] Calculate the percentage of each energy source within the hourly window, for example, the percentage of thermal power = thermal power consumption / total energy consumption;

[0105] If the proportion of a certain energy source changes by more than 5%, the weighting parameters will be updated.

[0106] B3: Updates to the composite model include:

[0107] Based on the adjusted carbon emission factor and energy structure weight parameters, the model parameters were retrained.

[0108] The model's predictive performance is evaluated through cross-validation, and its generalization ability is optimized.

[0109] Specifically, firstly, the model parameters are retrained. When changes in the energy structure trigger updates, the standardized data is re-inputted to train the ridge regression model.

[0110] Incremental learning is used to update the ARIMA model coefficients, and to ensure data accuracy, only the latest 30 days of data are used to fine-tune the parameters.

[0111] Furthermore, cross-validation and performance evaluation were conducted, with validation methods including 5-fold cross-validation, calculation of average MSE and R0. 2 If the validation set MSE increases by more than 10%, expand the range of the regularization parameter λ and search again.

[0112] Finally, the system outputs the predicted carbon emissions and confidence intervals for the next 12 months, and generates carbon emission intensity heat maps by region, marking areas that exceed the standards.

[0113] In this embodiment of the application, step S400, which monitors changes in the energy structure and dynamically adjusts the carbon emission factor and the weighting parameters of the energy structure, includes the following steps C1-C2:

[0114] C1: Displays total carbon emissions, intensity, and trends through visual charts, and dynamically sets threshold ranges based on historical carbon emission data and policy standards to generate different early warning levels and provide real-time alerts for abnormal carbon emission risks.

[0115] Specifically, visual chart design includes,

[0116] Trend chart: The line chart shows historical and projected carbon emissions, overlaid with policy limits, such as the "carbon peaking" target;

[0117] Heat map: Colored by administrative division, with shades indicating carbon emission intensity, e.g., dark red > 20 tCO2 / 10,000 yuan, green < 5 tCO2 / 10,000 yuan;

[0118] Warning panel: Displays the current warning level (Level 1 / Level 2 / Safe) and recommended measures in real time.

[0119] The dynamic threshold setting and early warning logic includes,

[0120] The threshold range is set as follows:

[0121] Level 1 Warning: Carbon emission intensity > 90% of historical peak or exceeds policy limits;

[0122] Level 2 warning: Carbon emission intensity > 80% of historical peak and trend forecast indicates that it will exceed the limit in the next 3 months.

[0123] Once an early warning is triggered, if it is a Level 1 warning, a report will be automatically generated and sent to the management department, recommending production restrictions or adjustments to the energy structure; if it is a Level 2 warning, the company will be prompted to optimize energy efficiency and a list of emission reduction technology solutions will be provided.

[0124] In summary, this invention ensures the accuracy and reliability of input data by collecting fundamental data for carbon emission accounting and performing rigorous data preprocessing. Analyzing regional electricity consumption carbon emissions using ridge regression and time-series algorithms not only improves prediction accuracy but also captures the time dependence and trends in time-series data, making carbon emission predictions more precise and providing a scientific basis for local governments to optimize energy structures and promote green and low-carbon development. Real-time updates of dynamic electricity carbon factors and energy structure data ensure that the carbon emission accounting model can reflect changes in the energy structure in a timely manner, improving the model's adaptability and accuracy, and making the carbon emission accounting results closer to reality.

[0125] Example 2

[0126] This embodiment is one example of the present invention. Based on the above embodiment, a method for calculating regional carbon emission statistics is provided. This embodiment is a specific application example of the method.

[0127] First, relevant data for the past three years (36 months) were collected for a certain province and its subordinate cities X, Y, and Z. Regional codes were set as follows: province "001", city X "001X", city Y "001Y", and city Z "001Z". Electricity consumption data (unit: 10,000 kWh) was generated based on the economic scale and industrial structure of different regions. For example, the province's overall electricity consumption was relatively large and growing steadily; city X had a high proportion of industry and its electricity consumption fluctuated significantly; city Y had a developed service industry and its electricity consumption showed some seasonality; and city Z was an emerging development area with rapidly growing electricity consumption. Dynamic carbon dioxide factor (unit: kg CO2 / kWh) was generated based on changes in the power generation energy structure. It was assumed that initially, thermal power was dominant, resulting in a higher carbon dioxide factor, which gradually decreased as the proportion of renewable energy increased. Some of the generated data is shown in Table 1.

[0128] Table 1. Partial Data on Electricity Consumption and Carbon Factor Variation

[0129] Region Code Month Power Consumption Carbon Factor 001 2021-01 120000 0.85 001 2021-02 115000 0.84 001X 2021-01 45000 0.86 001X 2021-02 42000 0.85 001Y 2021-01 30000 0.83 001Y 2021-02 28000 0.82 001Z 2021-01 20000 0.87 001Z 2021-02 22000 0.86

[0130] Secondly, the collected data was cleaned to check for missing and outlier values. Assuming that the electricity consumption data for City X in May 2022 was abnormally high, exceeding the normal range for that region, mean interpolation was used to replace it with the average of the electricity consumption of the two adjacent months. Simultaneously, electricity consumption and carbon dioxide factors were standardized to eliminate the influence of different units on the model. The standardization formula is x... norm =σx-μ, where x is the original data, μ is the mean, and σ is the standard deviation.

[0131] Next, a ridge regression model is trained, using electricity consumption data for each region as the independent variable X, and the corresponding carbon emissions (obtained by multiplying electricity consumption by the carbon factor, used here as the target variable in the regression model) as the dependent variable Y. The formula for calculating carbon emissions is...

[0132] cE=eC×eF

[0133] Where cE represents the calculated carbon emissions, which is the target variable Y of the model; eC represents the electricity consumption data of each region, which is the independent variable X of the model; and eF represents the electricity carbon factor, which is the carbon emission coefficient obtained by multiplying the electricity consumption by the electricity carbon factor.

[0134] The model is trained using the ridge regression algorithm, and the objective function of ridge regression is:

[0135]

[0136] Where n is the number of samples; y i This refers to the actual carbon emissions; This is the carbon emissions predicted by the model; β j λ is the regression coefficient; λ is the regularization parameter, used to balance the complexity and fit of the model; P is the number of features.

[0137] To determine a suitable regularization parameter λ, cross-validation is employed. The dataset is divided into k subsets, with each subset serving as the validation set and the remaining k-1 subsets as the training set. Ridge regression models are trained for different λ values, and the mean squared error (MSE) on the validation set is calculated. The MSE calculation formula is as follows:

[0138]

[0139] Where, n val y is the number of samples in the validation set; i,val It is the actual value of the i-th sample in the validation set; It is the predicted value of the i-th sample in the validation set.

[0140] By iterating through different λ values ​​(e.g., from 0.001 to 100, at certain intervals), the λ value that minimizes the MSE is selected. Assume that after cross-validation, the λ value is determined to be 0.1 for the provincial model, 0.05 for the X city model, 0.08 for the Y city model, and 0.12 for the Z city model.

[0141] Finally, using the trained ridge regression model, the electricity consumption data for each region for the next month is input (e.g., the province's electricity consumption in January 2024 is 150 million kWh, City X's is 500 million kWh, City Y's is 350 million kWh, and City Z's is 280 million kWh). Combined with the known dynamic carbon emission factor (assuming the province's carbon emission factor in January 2024 is 0.78, City X's is 0.79, City Y's is 0.77, and City Z's is 0.80), the carbon emissions for each region are predicted. For example, the predicted carbon emissions for the province in January 2024...

[0142]

[0143] in, β0 is the predicted carbon emissions, representing the carbon emissions in January 2024; β1 is the intercept term, representing the carbon emissions when all independent variables are 0; β2 is the regression coefficient of the independent variable "electricity consumption", representing the increase in carbon emissions for each unit increase in electricity consumption; β3 is the regression coefficient of the independent variable "electricity carbon factor", representing the increase in carbon emissions for each unit increase in the electricity carbon factor; 150000 is the value of electricity consumption, which may be in kilowatt-hours (kWh) or other appropriate units; 0.78 is the value of the electricity carbon factor, representing the carbon emissions corresponding to each unit of electricity consumption.

[0144] Example 3

[0145] The above is an illustrative scheme for a regional carbon emission statistics calculation method. It should be noted that the technical solution of this regional carbon emission statistics calculation system belongs to the same concept as the technical solution of the aforementioned regional carbon emission statistics calculation method. Details not described in detail in the technical solution of the regional carbon emission statistics calculation system in this embodiment can be found in the description of the technical solution of the aforementioned regional carbon emission statistics calculation method.

[0146] This embodiment also provides an accounting system for regional carbon emission statistics, including:

[0147] The data collection module is used to collect basic data related to regional carbon emissions, including energy consumption data and environmental monitoring data;

[0148] It should be noted that the data collection module includes,

[0149] Energy consumption monitoring equipment, such as smart meters, is used to monitor and record electricity consumption data in real time;

[0150] Environmental monitoring sensors: such as CO2 sensors, used to monitor and record carbon emissions in the environment;

[0151] Data acquisition terminal: Used to collect data from monitoring equipment and sensors and transmit it to the data processing module.

[0152] The data processing and storage module is used to store, clean, preprocess, and organize the collected data, and to manage the security and privacy protection of the data.

[0153] It should be noted that the data processing and storage module includes,

[0154] Data server: Provides the necessary computing resources and storage space for processing and storing large amounts of data;

[0155] Database management system: used to organize, manage, and retrieve data stored on a data server;

[0156] Data cleaning and preprocessing tools: used to remove noise, missing values, and outliers from data to ensure data quality.

[0157] The carbon emission accounting model module is used to establish and maintain carbon emission accounting models, providing a basis for carbon emission management for governments and enterprises.

[0158] It should be noted that the carbon emission accounting model module includes,

[0159] High-performance computing servers: provide powerful computing capabilities for running complex carbon emission accounting models;

[0160] Algorithm development and testing environment: such as statistical analysis software like Python and R, used to develop, test, and optimize carbon emission accounting models;

[0161] Model training and validation tools: used to evaluate the performance and accuracy of the model and ensure its reliability.

[0162] The communication and integration module is used for communication between modules within the system, as well as for integration with external systems.

[0163] It should be noted that the communication and integration module includes,

[0164] Communication interface: Used for communication between different systems to achieve data and function integration;

[0165] Integration platform: Used to integrate data and systems from different sources, providing a unified access point;

[0166] Security devices, such as firewalls and intrusion detection systems, are used to protect data security and prevent unauthorized access.

[0167] This embodiment also provides an electronic device suitable for calculating regional carbon emission statistics, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the regional carbon emission statistics calculation method proposed in the above embodiment.

[0168] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the accounting method for regional carbon emission statistics as proposed in the above embodiments.

[0169] The storage medium proposed in this embodiment and the accounting method for regional carbon emission statistics proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0170] Based on the above description of the implementation methods, those skilled in the art will clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0171] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for calculating regional carbon emissions statistics, characterized in that: include, Collect basic data for carbon emission accounting and establish a dynamically updated historical database; Based on historical databases, a composite model integrating regression analysis and time series analysis is used to predict and analyze carbon emissions trends. Monitor changes in the energy structure and dynamically adjust the carbon emission factor and the weighting parameters of the energy structure. The composite model is updated based on dynamically adjusted weight parameters to generate optimized regional carbon emission statistics and prediction results.

2. The method for calculating regional carbon emissions statistics as described in claim 1, characterized in that: The method for predicting and analyzing carbon emissions using a composite model that integrates regression analysis and time series analysis includes: The regression analysis is used to construct a carbon emission prediction model by combining energy consumption data and carbon emission factors. The time series analysis is used to capture the time dependence and dynamic trends of carbon emission data.

3. The method for calculating regional carbon emissions statistics as described in claim 2, characterized in that: The dynamically adjusted carbon emission factor includes: Real-time calculation of carbon emission intensity for different energy types; Based on the current energy structure ratio, a dynamic total carbon emission factor is generated using weighted averages.

4. The method for calculating regional carbon emissions statistics as described in claim 3, characterized in that: The dynamic adjustment of the energy structure weight parameters is achieved through the following methods: The consumption percentage of each energy type is calculated based on a sliding time window. The weight parameters are updated in real time based on changes in the proportion to adapt to dynamic fluctuations in the energy structure.

5. The method for calculating regional carbon emissions statistics as described in claim 4, characterized in that: The update of the composite model includes: Based on the adjusted carbon emission factor and energy structure weight parameters, the model parameters were retrained. The model's predictive performance is evaluated through cross-validation, and its generalization ability is optimized.

6. The method for calculating regional carbon emissions statistics as described in claim 5, characterized in that: The basic data for carbon emission accounting includes: Regional electricity consumption, dynamic carbon factor, various energy consumption data, and historical carbon emission data; The various energy consumption data include electricity consumption and the consumption of various energy types.

7. The method for calculating regional carbon emissions statistics as described in any one of claims 3 to 6, characterized in that: The optimized prediction results include: The system uses visual charts to display total carbon emissions, intensity, and trends. It also dynamically sets threshold ranges based on historical carbon emission data and policy standards to generate different warning levels and provide real-time alerts for abnormal carbon emission risks.

8. A system employing the accounting method for regional carbon emission statistics as described in any one of claims 1 to 7, characterized in that: include, The data collection module is used to collect basic data related to regional carbon emissions, including energy consumption data and environmental monitoring data; The data processing and storage module is used to store, clean, preprocess, and organize the collected data, and to manage the security and privacy protection of the data. The carbon emission accounting model module is used to establish and maintain carbon emission accounting models, providing a basis for carbon emission management for governments and enterprises. The communication and integration module is used for communication between modules within the system, as well as for integration with external systems.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the accounting method for regional carbon emission statistics according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the accounting method for regional carbon emission statistics as described in any one of claims 1 to 7.

Images