Power carbon checking method and device based on big data analysis

Abstract

The invention provides an electric power carbon checking method and device based on big data analysis, and relates to the technical field of electric power grids. According to the method, big data analysis and carbon emission calculation are carried out through the monitoring data of the target regional power grid in the set period, the carbon emission factor and the calculated value of the carbon emission of each user are determined, checking is carried out in combination with the reported carbon emission data of each user, manual participation is not needed, automatic checking of the carbon emission in the target regional power grid is realized, and the checking efficiency is improved. And the checking efficiency of power carbon checking is improved. In addition, in the checking process, through first-level carbon checking, second-level carbon checking and a second-level checking mechanism, reported abnormal users are determined firstly, then refined checking is conducted on the reported abnormal users, automatic and accurate checking of the carbon emission is achieved, and the checking efficiency and accuracy of power carbon checking are improved.

Description

Technical Field

[0001] This invention relates to the field of power grid technology, and in particular to a method and apparatus for power carbon verification based on big data analysis. Background Technology

[0002] In the carbon emission management system of the power industry, accurate carbon verification is not only the cornerstone for measuring emission reduction effectiveness and ensuring the smooth achievement of policy objectives, but also a key link in promoting global environmental sustainability. Given that climate change has become a major challenge under global consensus, the accurate verification and reporting of carbon emissions by the power industry, as one of the major greenhouse gas emitters, is particularly urgent and important. This is not only related to the industry's green transformation process, but also a core issue in international climate negotiations and cooperation.

[0003] However, for a long time, carbon verification in the power sector has relied primarily on traditional manual methods. This approach has revealed numerous limitations when dealing with the ever-increasing volume of carbon emission data. Manual data collection and analysis not only require significant human and time resources, leading to low efficiency, but also exposes every step of the verification process to human error, potentially affecting the objectivity and accuracy of the results. This reliance on manual methods is particularly vulnerable to complex and ever-changing carbon emission data, making it difficult to guarantee the comprehensiveness and accuracy of the verification results, thus impacting the formulation and implementation of emission reduction strategies.

[0004] Currently, traditional manual methods for verifying carbon emissions of electricity suffer from technical problems such as low efficiency and inaccuracy. Summary of the Invention

[0005] This invention provides a method and apparatus for electricity carbon verification based on big data analysis, which can improve the verification efficiency and accuracy of electricity carbon verification.

[0006] In a first aspect, the present invention provides a method for electricity carbon verification based on big data analysis. The method includes: acquiring monitoring data of the power grid in a target area during a set period, and carbon emission data reported by each user; the monitoring data includes the power generation, electricity consumption, and fuel consumption of each node; calculating carbon emissions based on the monitoring data during the set period to determine the calculated carbon emission data for each user, the calculated carbon emission data including the calculated values ​​of carbon emission factors and carbon emission amounts; conducting a primary carbon verification based on the calculated carbon emission data and reported carbon emission data of each user to identify reporting abnormal users; extracting electricity carbon verification characteristics of reporting abnormal users based on the monitoring data during the set period; and conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of reporting abnormal users, as well as an electricity carbon verification model, to determine the electricity carbon verification result.

[0007] In one possible implementation, carbon emissions are calculated based on monitoring data for a set period to determine the calculated carbon emissions data for each user. This includes: dividing the data into nodes based on the monitoring data for the set period; determining the conventional energy generation, renewable energy generation, electricity consumption, and fuel consumption of each node; determining the total emissions of each node based on its fuel consumption and fuel type; determining the calculated carbon emission factor for each node based on its total carbon emissions, conventional energy generation, renewable energy generation, and electricity consumption; the carbon emission factor is used to characterize the carbon emissions per unit of electricity consumed; and determining the calculated carbon emissions for each user based on the electricity consumption of each user in the region where each node is located and the calculated carbon emission factor for each node.

[0008] In one possible implementation, a first-level carbon verification is performed based on each user's calculated and reported carbon emission data to identify users with abnormal reporting. This includes: calculating a first error between the calculated and reported values ​​of each user's carbon emission factor, and a second error between the calculated and reported values ​​of carbon emissions, based on each user's calculated and reported carbon emission data; for any user, if the user's first error is greater than a first set threshold, then the user is identified as a user with abnormal reporting; if the user's first error is less than or equal to the first set threshold and the second error is greater than a second set threshold, then the user is identified as a user with abnormal reporting; if the user's first error is less than or equal to the first set threshold and the second error is less than or equal to the second set threshold, then the user is identified as a user with normal reporting.

[0009] In one possible implementation, based on monitoring data for a set period, the electricity carbon verification characteristics of reported abnormal users are extracted, including: dividing the electricity consumption based on the power generation and consumption of each node in the set period, determining the metered electricity consumption for each time period, the metered electricity consumption during peak hours, and the metered electricity consumption during off-peak hours; determining the fuel consumption for each time period and the proportion of renewable energy consumption based on the power generation and fuel consumption of each node; and generating the electricity carbon verification characteristics of reported abnormal users based on the metered electricity consumption for each time period, the metered electricity consumption during peak hours, the metered electricity consumption during off-peak hours, the fuel consumption for each time period, the proportion of renewable energy consumption, and pre-stored user type, user geographical location, historical carbon emissions, first error, and second error.

[0010] In one possible implementation, a secondary verification is performed based on the electricity carbon verification characteristics and reported carbon emission data of reported abnormal users, as well as the electricity carbon verification model, to determine the electricity carbon verification results. This includes: generating an input feature vector based on the electricity carbon verification characteristics and reported carbon emission data of reported abnormal users; performing a secondary verification based on the input feature vector and the electricity carbon verification model to determine the secondary verification results, which include the electricity consumption verification results, carbon emission verification results, and carbon emission factor verification results for each time period; and determining the electricity carbon verification results based on the secondary verification results, which include verified carbon emission data and the reasons for data anomalies. The verified carbon emission data includes the verified values ​​of carbon emission factors and carbon emission amounts, and the reasons for data anomalies include data reporting errors, metering equipment malfunctions, or changes in the production process.

[0011] In one possible implementation, before determining the electricity carbon verification result by conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of reported abnormal users, and an electricity carbon verification model, the following steps are included: acquiring historical monitoring data of the target area's power grid and reported carbon emission data of each user in each reporting period; dividing the historical monitoring data into time periods to generate electricity carbon verification characteristics for each user in each reporting period; and generating electricity carbon verification characteristics for each user in each reporting period based on the electricity carbon verification characteristics and reported carbon emission data of each user in each reporting period. The system generates the following data: input feature vectors for each user in each reporting period; electricity carbon verification characteristics and reported carbon emission data for each user in each reporting period; electricity verification results, carbon emission verification results, and carbon emission factor verification results for each time period within each reporting period; multiple training samples are generated using the input feature vectors for each user in each reporting period as input and the electricity verification results, carbon emission verification results, and carbon emission factor verification results for each time period within each reporting period as output; and a neural network is trained based on these multiple training samples to obtain the electricity carbon verification model.

[0012] In one possible implementation, after conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of reported abnormal users, as well as the electricity carbon verification model, and determining the electricity carbon verification results, the following steps are also included: obtaining carbon emission data for each user after the electricity carbon verification; filtering out high-carbon emission users based on the carbon emission data of each user after the electricity carbon verification; obtaining electricity consumption records of high-carbon emission users during a set period; determining the metered electricity consumption, carbon emission, and carbon emission factor of each device of high-carbon emission users in each time period based on the electricity consumption records of high-carbon emission users during the set period, as well as the metered electricity consumption, carbon emission, and carbon emission factor of high-carbon emission users in each time period; traversing the metered electricity consumption, carbon emission, and carbon emission factor of each device of high-carbon emission users in each time period to determine the energy-saving and emission-reduction schemes for high-carbon emission users in each time period; the energy-saving and emission-reduction schemes include time-switching sub-schemes and direct optimization sub-schemes; the time-switching sub-schemes include transferable devices, the time period before the transfer of transferable devices, and the time period before the transfer; the direct optimization sub-schemes include directly optimized devices and the time period in which the directly optimized devices are located.

[0013] In one possible implementation, after conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal user, as well as the electricity carbon verification model, and determining the electricity carbon verification result, the process further includes: obtaining a review application from the reported abnormal user, which instructs the reported abnormal user to request a review of the electricity carbon verification result; in response to the review application, generating a tertiary verification instruction based on the monitoring data of the reported abnormal user, the primary verification result, the secondary verification result, and the electricity carbon verification result; determining the verification personnel based on the geographical location of the reported abnormal user; and sending the tertiary verification instruction to the verification personnel, instructing them to conduct an on-site verification.

[0014] In one possible implementation, after conducting a secondary verification based on the reported abnormal user's electricity carbon verification characteristics and reported carbon emission data, as well as the electricity carbon verification model, and determining the electricity carbon verification results, the following steps are also included: obtaining the verification values ​​of carbon emission factors for each node in the target area's power grid after the electricity carbon verification; filtering each node based on the verification values ​​of its carbon emission factors to identify high-carbon emission nodes; obtaining the conventional power generation capacity, renewable energy power generation capacity, and user load of the high-carbon emission node area; calculating the new renewable energy power generation capacity based on the conventional power generation capacity, renewable energy power generation capacity, and user load of the high-carbon emission node area, as well as a preset renewable energy installation ratio threshold; determining the installation location of the new renewable energy based on the power grid architecture of the high-carbon emission node area; and generating energy-saving and emission-reduction schemes for the high-carbon emission nodes based on the new renewable energy power generation capacity and the installation location of the new renewable energy.

[0015] Secondly, embodiments of the present invention provide a power carbon verification device based on big data analysis. The device includes a communication module and a processing module. The communication module is used to acquire monitoring data of the power grid in a target area during a set period, as well as carbon emission data reported by each user. The monitoring data includes the power generation, power consumption, and fuel consumption of each node. The processing module is used to calculate carbon emissions based on the monitoring data during the set period, determine the calculated carbon emission data for each user, and the calculated carbon emission data includes the calculated values ​​of carbon emission factors and carbon emission amounts. Based on the calculated carbon emission data and reported carbon emission data of each user, a first-level carbon verification is performed to identify users reporting abnormal emissions. Based on the monitoring data during the set period, power carbon verification characteristics of users reporting abnormal emissions are extracted. Based on the power carbon verification characteristics of users reporting abnormal emissions, the reported carbon emission data, and the power carbon verification model, a second-level verification is performed to determine the power carbon verification result.

[0016] Thirdly, embodiments of the present invention provide an electronic device including a memory and a processor. The memory stores a computer program, and the processor is configured to call and run the computer program stored in the memory to perform the steps of the method as described in the first aspect and any possible implementation thereof.

[0017] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method as described in the first aspect and any possible implementation thereof.

[0018] This invention provides a method and apparatus for electricity carbon verification based on big data analysis. The invention performs big data analysis and carbon emission calculations on monitoring data of the power grid in a target area during a set period to determine the carbon emission factors and calculated carbon emission values ​​for each user. This is then combined with the carbon emission data reported by each user for verification. This automatic verification of carbon emissions within the target area's power grid is achieved without manual intervention, improving the efficiency of electricity carbon verification. Furthermore, the invention employs a primary and secondary carbon verification mechanism. The secondary verification mechanism first identifies users who report abnormal emissions and then conducts a refined verification of these users, achieving automatic and accurate verification of carbon emissions and improving the accuracy of electricity carbon verification. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a method for verifying electricity carbon based on big data analysis, provided in an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of the structure of a power carbon verification device based on big data analysis provided in an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0023] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0024] In the description of this invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" and "more than one" refer to two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0025] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0026] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0027] To make the objectives, technical solutions, and advantages of the present invention clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0028] As described in the background section, current traditional manual methods for verifying carbon emissions from electricity suffer from technical problems such as low efficiency and inaccuracy.

[0029] To solve the above technical problems, such as Figure 1 As shown, this embodiment of the invention provides a method for verifying carbon emissions in the power sector based on big data analysis. The method includes steps S101-S106.

[0030] S101. Obtain monitoring data of the power grid in the target area during the set period, as well as carbon emission data reported by each user.

[0031] In this embodiment of the application, the monitoring data includes the power generation, power consumption, and fuel consumption of each node.

[0032] In some embodiments, the carbon emission data reported by each user includes reported values ​​for carbon emission factors and carbon emission amounts.

[0033] S102. Based on monitoring data for a set period, perform big data analysis and carbon emission calculation to determine the calculated carbon emission data for each user.

[0034] In this embodiment of the application, the calculation of carbon emission data includes the calculated values ​​of carbon emission factor and carbon emission amount.

[0035] As one possible implementation, step S102 can be specifically implemented as steps S1021-S1024.

[0036] S1021. Based on the monitoring data of the set period, divide the nodes and determine the conventional energy power generation, new energy power generation, electricity consumption and fuel consumption of each node.

[0037] In some embodiments, the present invention can divide a target area power grid into multiple nodes based on the power grid topology and actual operating conditions. Each node should include a clearly defined geographical area, power plants, substations, and user groups. Node division is performed using data provided by a Geographic Information System (GIS) and a power grid dispatching system, combined with the power grid's physical structure and operational data. This ensures that the boundaries of each node are clear and the data is complete.

[0038] In some embodiments, the present invention can statistically analyze the conventional energy generation, renewable energy generation, electricity consumption, and fuel consumption of each node within a set period based on monitoring data. The generation, electricity consumption, and fuel consumption of each node are extracted using data provided by the power grid dispatch system. Simultaneously, renewable energy generation is statistically analyzed by combining operational data from renewable energy power generation projects. This ensures the accuracy and completeness of the data.

[0039] S1022. Based on the fuel consumption and fuel type of each node, determine the total emissions of each node.

[0040] In some embodiments, the present invention can calculate the total emissions of each node using the emission factor method based on the fuel consumption and fuel type of each node. First, the emission factor (i.e., the greenhouse gas emissions per unit of fuel consumption) is determined for each fuel. Then, the fuel consumption of each node is multiplied by the corresponding emission factor to obtain the total emissions of each node. The accuracy and applicability of the emission factors are ensured.

[0041] S1023. Based on the total carbon emissions, conventional energy power generation, new energy power generation and electricity consumption of each node, determine the calculated value of the carbon emission factor for each node.

[0042] In some embodiments, the carbon emission factor is used to characterize the amount of carbon emitted per unit of electrical energy consumed.

[0043] In some embodiments, the present invention can calculate the carbon emission factor of each node using the total carbon emissions, conventional energy generation, renewable energy generation, and electricity consumption of each node. First, the net power generation of each node is calculated (conventional energy generation + renewable energy generation - electricity consumption). Then, the total carbon emissions of each node are divided by the net power generation to obtain the calculated value of the carbon emission factor for each node. This ensures the accuracy and rationality of the calculation process.

[0044] S1024. Based on the electricity consumption of each user in the area where each node is located, and the calculated value of the carbon emission factor of each node, determine the calculated value of the carbon emission of each user.

[0045] In some embodiments, the present invention can calculate the carbon emissions of each user based on the calculated carbon emission factor of the node where each user is located and the electricity consumption of each user. First, the calculated carbon emission factor of the node where each user is located is determined. Then, the electricity consumption of each user is multiplied by the calculated carbon emission factor of the corresponding node to obtain the calculated carbon emissions of each user. This ensures the accuracy and reliability of the calculation results.

[0046] S103. Based on the calculated carbon emission data and reported carbon emission data of each user, conduct a first-level carbon verification to identify users with abnormal reports.

[0047] As one possible implementation, step S103 can be specifically implemented as steps S1031-S1034.

[0048] S1031. Based on the calculated carbon emission data and reported carbon emission data of each user, calculate the first error between the calculated value and the reported value of the carbon emission factor of each user, and the second error between the calculated value and the reported value of carbon emission amount.

[0049] In some embodiments, the first error refers to the difference or ratio between the carbon emission factor reported by the user and the carbon emission factor calculated through big data analysis, used to measure the accuracy of the user-reported carbon emission factor. The second error refers to the difference or ratio between the carbon emissions reported by the user and the carbon emissions calculated through big data analysis, used to measure the accuracy of the user-reported carbon emissions. A first set threshold is a critical value used to determine whether the user-reported carbon emission factor is abnormal, typically set based on historical data, industry standards, or policy requirements. A second set threshold is a critical value used to determine whether the user-reported carbon emissions are abnormal, also set based on historical data, industry standards, or policy requirements.

[0050] For example, embodiments of the present invention can compare the carbon emission factors reported by users with those calculated through big data analysis, calculate the difference or ratio between the two, and obtain a first error. The carbon emission factor data reported by users is extracted. According to the carbon emission factor calculation method, the calculated value of the carbon emission factor for each user is calculated. The difference or ratio between the reported value and the calculated value is calculated to obtain the first error.

[0051] For example, embodiments of the present invention can compare the carbon emissions reported by users with the carbon emissions calculated through big data analysis, calculate the difference or ratio between the two, and obtain a second error. The carbon emission data reported by users is extracted. According to the carbon emission calculation method, the calculated value of carbon emissions for each user is calculated. The difference or ratio between the reported value and the calculated value is calculated to obtain the second error.

[0052] S1032. For any user, if the user's first error is greater than the first set threshold, then the user is determined to be a user reporting an abnormality.

[0053] S1033. If the user's first error is less than or equal to the first set threshold and the second error is greater than the second set threshold, then the user is determined to be a user reporting an abnormality.

[0054] S1034. If the user's first error is less than or equal to the first set threshold and the second error is less than or equal to the second set threshold, then the user is a normal reporting user.

[0055] S104. Based on monitoring data for a set period, extract the electricity carbon verification characteristics of reported abnormal users.

[0056] As one possible implementation, step S104 can be specifically implemented as steps S1041-S1043.

[0057] S1041. Based on the power generation and power consumption of each node in a set period, divide the power into categories and determine the metered power for each time period, the metered power during peak hours, and the metered power during off-peak hours.

[0058] In some embodiments, the power consumption division divides the total power consumption within a set period into different time periods or categories according to time or specific conditions, such as peak period power consumption, off-peak period power consumption, etc.

[0059] In some embodiments, peak-hour electricity metering refers to the electricity consumed by a user or node during periods of high grid load.

[0060] In some embodiments, off-peak electricity metering refers to the electricity consumed by a user or node during periods of low grid load.

[0061] In some embodiments, the renewable energy consumption ratio is the proportion of renewable energy power generation in the total power generation, reflecting the degree of utilization of renewable energy.

[0062] In some embodiments, the electricity carbon verification feature is used to describe and distinguish the specific attributes or characteristics of reported abnormal users in terms of electricity carbon emissions, and is an important basis for subsequent secondary carbon verification.

[0063] In some embodiments, the present invention can divide the electricity consumption within a set period into different time periods, such as peak periods and off-peak periods, based on the load conditions and time distribution of the power grid, and calculate the metered electricity consumption for each time period. It collects power generation and consumption data for each node within the set period. Based on the power grid load curve or historical data, it determines the specific time ranges for peak and off-peak periods. It calculates the metered electricity consumption for each node within each time period, including total electricity consumption, peak period electricity consumption, and off-peak period electricity consumption.

[0064] S1042. Based on the power generation and fuel consumption of each node, determine the fuel consumption for each time period and the proportion of new energy consumption.

[0065] In some embodiments, the present invention can calculate the fuel consumption for each time period based on the power generation data and fuel consumption data of each node. The power generation data and fuel consumption data of each node are collected. The fuel consumption for each time period is calculated based on the correspondence between the power generation data and fuel consumption.

[0066] In some embodiments, the present invention can calculate the proportion of renewable energy generation in the total power generation, i.e., the renewable energy consumption ratio, based on the power generation data of each node. This involves collecting renewable energy generation data and total power generation data from each node. The renewable energy consumption ratio for each time period is then calculated, i.e., renewable energy generation divided by total power generation.

[0067] S1043. Based on the metered electricity consumption for each time period, the metered electricity consumption during peak hours, the metered electricity consumption during off-peak hours, the fuel consumption for each time period, the proportion of new energy consumption, and the pre-stored user type, user geographical location, historical carbon emissions, first error and second error, generate the electricity carbon verification characteristics of reported abnormal users.

[0068] In some embodiments, the present invention can synthesize the data obtained from the above steps and combine it with pre-stored information such as user type, user geographical location, historical carbon emissions, first error, and second error to generate electricity carbon verification features for reported abnormal users. Basic user information such as user type, user geographical location, and historical carbon emissions is collected and organized. The first error and second error are used as evaluation indicators for the accuracy of user carbon emission data. Combining all the above information, an electricity carbon verification feature vector for reported abnormal users is constructed. This vector contains information from multiple dimensions, including the user's electricity usage, fuel consumption, renewable energy utilization, and the accuracy of carbon emission data. This feature vector will serve as an important input for subsequent secondary carbon verification, used to further analyze and judge the user's carbon emission situation.

[0069] S105. Based on the electricity carbon verification characteristics of reported abnormal users and the reported carbon emission data, as well as the electricity carbon verification model, conduct secondary carbon verification to determine the electricity carbon verification results.

[0070] As one possible implementation, step S105 can be specifically implemented as steps S1051-S1055.

[0071] S1051. Based on the electricity carbon verification characteristics of reported abnormal users and the reported carbon emission data, generate an input feature vector.

[0072] In some embodiments, the input feature vector is a data vector that integrates multiple information such as the electricity carbon verification features of reported abnormal users and the reported carbon emission data, and is used to input the electricity carbon verification model for secondary verification.

[0073] In some embodiments, the electricity carbon verification model is a model built based on technologies such as machine learning or deep learning, which can receive input feature vectors and output secondary verification results through algorithm analysis.

[0074] In some embodiments, the secondary verification results are the results obtained by the electricity carbon verification model after analyzing the input feature vector, including the electricity verification results, carbon emission verification results, and carbon emission factor verification results for each time period.

[0075] In some embodiments, carbon emission data is verified: the verified values ​​of carbon emission factors and carbon emission amounts obtained after secondary verification are used to compare with the reported values ​​to assess the accuracy of the reported data.

[0076] In some embodiments, the cause of data anomalies is: based on the results of the secondary verification, the specific reasons for the data anomalies are analyzed, such as data reporting errors, metering equipment failures, or changes in the production process.

[0077] In some embodiments, the present invention can integrate the electricity carbon verification characteristics and reported carbon emission data of reported abnormal users into an input feature vector for input into the electricity carbon verification model for secondary verification. The electricity carbon verification characteristics of reported abnormal users are collected, including metered electricity consumption for each time period, peak-hour metered electricity consumption, off-peak-hour metered electricity consumption, fuel consumption for each time period, and the proportion of renewable energy consumption. The reported carbon emission data of reported abnormal users are also collected, including reported values ​​of carbon emission factors and carbon emissions. The above data are integrated into an input feature vector, ensuring that the data format and data type conform to the input requirements of the electricity carbon verification model.

[0078] S1052. Based on the input feature vector and the power carbon verification model, conduct secondary verification and determine the secondary verification results.

[0079] In some embodiments, the secondary verification results include the electricity consumption verification results, carbon emission verification results, and carbon emission factor verification results for each time period.

[0080] In some embodiments, the present invention can input the input feature vector into an electricity carbon verification model for secondary verification to obtain secondary verification results. A suitable electricity carbon verification model is selected, ensuring that the model has been trained and possesses high accuracy. The input feature vector is input into the model, and the model outputs the secondary verification results. The secondary verification results may include electricity consumption verification results for each time period, carbon emission verification results, and carbon emission factor verification results, depending on the model's output design.

[0081] S1053. Based on the results of the secondary verification, determine the results of the electricity carbon verification.

[0082] In some embodiments, the results of a power carbon verification include verified carbon emission data and reasons for data anomalies. Verified carbon emission data includes verified values ​​for carbon emission factors and carbon emission amounts, and reasons for data anomalies include data reporting errors, metering equipment malfunctions, or changes in production processes.

[0083] In some embodiments, this invention can determine the electricity carbon verification results based on the secondary verification results, including verified carbon emission data and the reasons for data anomalies. The accuracy of the reported data is assessed by comparing the secondary verification results with the reported values. Verified carbon emission data, including verified values ​​for carbon emission factors and carbon emissions, is calculated based on the electricity consumption verification results, carbon emission quantity verification results, and carbon emission factor verification results from the secondary verification results. Abnormal data in the secondary verification results is analyzed, and the reasons for data anomalies are determined by combining information such as user type, user geographical location, and historical carbon emissions. Reasons for data anomalies may include data reporting errors, metering equipment malfunctions, or changes in production processes, requiring judgment and handling based on specific circumstances.

[0084] This invention provides a power carbon verification method based on big data analysis. It performs big data analysis and carbon emission calculations on monitoring data of the target area's power grid during a set period to determine the carbon emission factors and calculated carbon emission values ​​for each user. This is then combined with the carbon emission data reported by each user for verification. This method requires no manual intervention, achieving automatic verification of carbon emissions within the target area's power grid and improving the efficiency of power carbon verification. Furthermore, this invention employs a primary and secondary carbon verification mechanism. The secondary verification mechanism first identifies users who report abnormal emissions and then conducts a refined verification of these users, achieving automatic and accurate verification of carbon emissions and improving the accuracy of power carbon verification.

[0085] Optionally, the electricity carbon verification method based on big data analysis provided in this embodiment of the invention further includes steps S201-S206 before step S105.

[0086] S201. Obtain historical monitoring data of the power grid in the target area and carbon emission data reported by each user in each reporting period.

[0087] In some embodiments, the present invention can extract monitoring data of the target area's power grid over a historical period and carbon emission data reported by each user in each reporting period from a database. The time range of the historical period is determined, such as the past year or two. Monitoring data within this time range is extracted from the database, including power generation, electricity consumption, fuel consumption, etc., of each node. Carbon emission data reported by each user in each reporting period is extracted from the database, including reported values ​​of carbon emission factors and carbon emission amounts.

[0088] S202. Divide the monitoring data within the historical period into time periods and generate the electricity carbon verification characteristics of each user in each reporting cycle.

[0089] In some embodiments, the present invention can divide historical monitoring data into time periods and generate electricity carbon verification characteristics for each user in each reporting period based on the divided data. The rules for dividing the time periods are determined, such as by hour, day, or week. The monitoring data is divided into time periods, and the power generation, power consumption, fuel consumption, etc., are calculated for each time period. Based on the divided data, the electricity carbon verification characteristics for each user in each reporting period are calculated, such as metered power consumption in each time period, metered power consumption during peak hours, metered power consumption during off-peak hours, fuel consumption in each time period, and the proportion of renewable energy consumption, etc.

[0090] S203. Based on the electricity carbon verification characteristics of each user in each reporting period and the carbon emission data reported by each user in each reporting period, generate the input feature vector of each user in each reporting period.

[0091] In some embodiments, the present invention can integrate the electricity carbon verification characteristics and reported carbon emission data of each user in each reporting period into an input feature vector. The format and structure of the input feature vector are determined. The electricity carbon verification characteristics and reported carbon emission data of each user in each reporting period are integrated according to the format of the input feature vector. The data quality of the input feature vector is ensured, such as by removing missing values ​​and outliers.

[0092] S204. Based on the electricity carbon verification characteristics of each user in each reporting period and the carbon emission data reported by each user in each reporting period, generate the electricity verification results, carbon emission verification results and carbon emission factor verification results for each time period in each reporting period.

[0093] S205. Using the input feature vector of each user in each reporting period as input, and the electricity verification results, carbon emission verification results and carbon emission factor verification results of each time period in each reporting period as output, generate multiple training samples.

[0094] In some embodiments, this invention can generate electricity verification results, carbon emission verification results, and carbon emission factor verification results for each time period within each reporting period based on the electricity carbon verification characteristics and reported carbon emission data of each user in each reporting period. Multiple training samples are generated using an input feature vector as input and the verification results as output. The calculation method or standard for the electricity verification results, carbon emission verification results, and carbon emission factor verification results is determined. Verification results for each time period within each reporting period are calculated based on the electricity carbon verification characteristics and reported carbon emission data of each user in each reporting period. Multiple training samples are generated using an input feature vector as input and the verification results as output.

[0095] S206. Based on multiple training samples, perform neural network training to obtain the electricity carbon verification model.

[0096] In some embodiments, the present invention can use generated training samples to train a neural network to obtain an electricity carbon verification model capable of predicting or classifying verification results corresponding to input feature vectors. A suitable neural network architecture is selected, such as a multilayer perceptron (MLP), convolutional neural network (CNN), or recurrent neural network (RNN). The parameters of the neural network are configured, such as the number of layers, the number of neurons, and the activation function. The neural network is trained using the generated training samples, and the model's performance is optimized by continuously adjusting the parameters. The model's performance is evaluated, such as using cross-validation to assess its accuracy and generalization ability. The model is then fine-tuned based on the evaluation results until the requirements are met.

[0097] In this way, the present invention can train an electricity carbon verification model before conducting electricity carbon verification, which facilitates big data analysis and electricity carbon verification.

[0098] Optionally, the electricity carbon verification method based on big data analysis provided in this embodiment of the invention further includes steps S301-S305 after step S105.

[0099] S301. Obtain carbon emission data for each user after the electricity carbon verification.

[0100] In some embodiments, the carbon emission data of each user after the electricity carbon verification refers to the final confirmed carbon emission data of each user obtained after processing by the electricity carbon verification method.

[0101] In some embodiments, high carbon emission users refer to users whose carbon emissions exceed a set threshold, and these users are the focus of energy conservation and emission reduction efforts.

[0102] In some embodiments, electricity consumption behavior records refer to user behavior data related to electricity consumption over a certain period of time, such as the time of switching on and off equipment, the power consumption of equipment, etc.

[0103] In some embodiments, metered electricity consumption refers to the actual electricity consumption of each user's devices within a certain period of time.

[0104] In some embodiments, energy conservation and emission reduction schemes are measures or plans proposed for high-carbon-emission users to reduce carbon emissions.

[0105] In some embodiments, a time-shifting sub-scheme refers to a scheme that reduces carbon emissions by adjusting the time of electricity use, and is applicable to equipment with transferable electrical loads.

[0106] In some embodiments, direct optimization sub-schemes refer to schemes that directly reduce carbon emissions by improving equipment efficiency or replacing low-carbon equipment.

[0107] In some embodiments, the present invention can extract verified carbon emission data of each user from the database of an electricity carbon verification system. This ensures the accuracy and completeness of the data. Data preprocessing is performed, such as removing outliers and filling in missing values.

[0108] S302. Based on the carbon emission data of each user after the electricity carbon verification, high carbon emission users are screened out.

[0109] In some embodiments, this invention can filter users whose carbon emissions exceed a set carbon emission threshold as high-carbon-emission users from all users. A reasonable carbon emission threshold is determined. High-carbon-emission users are filtered out using SQL queries or data analysis software.

[0110] S303. Obtain records of electricity consumption behavior of high-carbon emission users during a set period.

[0111] In some embodiments, the present invention can obtain electricity consumption records of high-carbon-emission users over a set period (such as the past month or quarter) from smart meters or electricity management systems. The time range of the set period is determined. The accuracy and completeness of the electricity consumption records are ensured.

[0112] S304. Based on the electricity consumption records of high-carbon emission users during a set period, as well as the metered electricity consumption, carbon emissions, and carbon emission factors of high-carbon emission users in each time period during the set period, determine the metered electricity consumption, carbon emissions, and carbon emission factors of each device of high-carbon emission users in each time period.

[0113] In some embodiments, this invention can analyze the electricity consumption and carbon emissions of each device in different time periods based on the electricity consumption behavior records of high-carbon-emission users, combined with metered electricity consumption, carbon emissions, and carbon emission factors for each time period. The electricity consumption behavior records are divided into time periods and aligned with the data on metered electricity consumption, carbon emissions, and carbon emission factors. Based on device type and electricity consumption pattern, the electricity consumption and carbon emissions of each device are identified and allocated.

[0114] S305. Iterate through the metered electricity consumption, carbon emissions, and carbon emission factors of each device of high-carbon emission users in each time period to determine the energy-saving and emission reduction plans for high-carbon emission users in each time period.

[0115] In some embodiments, the energy conservation and emission reduction scheme includes a time-shifting sub-scheme and a direct optimization sub-scheme; the time-shifting sub-scheme includes the transferable equipment, the time period before the transfer of the transferable equipment, and the time period before the transfer; the direct optimization sub-scheme includes the directly optimized equipment and the time period in which the directly optimized equipment is located.

[0116] In some embodiments, the present invention can examine the electricity consumption and carbon emissions of each device belonging to high-carbon-emission users in different time periods, providing a basis for formulating energy-saving and emission-reduction plans. Data analysis tools or programming scripts are used for this process. The electricity consumption and carbon emission characteristics of each device are recorded and analyzed.

[0117] In some embodiments, the present invention can formulate energy-saving and emission-reduction plans for high-carbon emission users based on the above analysis, including time-shifting sub-plans and direct optimization sub-plans.

[0118] Time-of-use (TOU) sub-scheme: Identify devices with transferable electrical loads, such as washing machines and water heaters. Analyze the electricity usage periods of these devices to determine the periods before and after TOU transfer. Develop a TOU transfer strategy, such as shifting electricity usage from peak hours to off-peak hours.

[0119] Direct optimization sub-schemes: Identify equipment to be directly optimized, such as old or inefficient equipment. Analyze the electricity consumption and carbon emissions of these devices during different time periods. Develop direct optimization strategies, such as replacing them with more efficient equipment or adjusting equipment parameters.

[0120] In this way, the embodiments of the present invention can formulate energy-saving and emission-reduction plans for users with high carbon emissions, realize high carbon transfer or direct optimization, and facilitate users to implement energy-saving and emission-reduction plans.

[0121] Optionally, the electricity carbon verification method based on big data analysis provided in this embodiment of the invention further includes steps S401-S404 after step S105.

[0122] S401. Obtain the appeal application from the user who reported the abnormality.

[0123] In some embodiments, a reconsideration request is used to instruct the reporting user to request a reconsideration of the electricity carbon verification results.

[0124] In some embodiments, a reconsideration application refers to an application submitted by a reporting user who objects to the results of an electricity carbon verification and requests a re-verification.

[0125] In some embodiments, a Level 3 verification instruction refers to an instruction to conduct an on-site verification based on the monitoring data, Level 1 verification results, Level 2 verification results, and electricity carbon verification results of a user who has reported an anomaly and has requested a review.

[0126] In some embodiments, "verifiers" refers to professionals responsible for conducting on-site verifications who typically possess the relevant knowledge and skills in electricity carbon verification.

[0127] In some embodiments, this invention can receive reconsideration requests submitted by users reporting abnormalities. These requests typically include the user's objection to the electricity carbon verification results and the reasons for requesting a re-verification. A user-friendly reconsideration request interface or process is designed and developed to facilitate user submission. The completeness and accuracy of the reconsideration request information are ensured, including the user's identity information, objection explanation, and reasons for requesting a re-verification. The received reconsideration requests undergo a preliminary review to confirm they meet the reconsideration criteria.

[0128] S402. In response to the reconsideration application, a third-level verification instruction is generated based on the monitoring data of the reported abnormal users, the results of the first-level verification, the results of the second-level verification, and the results of the electricity carbon verification.

[0129] In some embodiments, this invention can comprehensively analyze and generate a third-level verification instruction based on monitoring data of reported abnormal users, first-level verification results, second-level verification results, and electricity carbon verification results. It calls relevant databases or systems to obtain the monitoring data, first-level verification results, second-level verification results, and electricity carbon verification results of reported abnormal users. This data is then comprehensively analyzed to identify potential problems or doubts. Based on the analysis results, detailed third-level verification instructions are formulated, specifying the content, scope, methods, and requirements of the verification.

[0130] S403. Based on the geographical location of the reported abnormal user, determine the personnel to conduct the verification.

[0131] In some embodiments, the present invention can select appropriate verification personnel for on-site verification based on the geographical location information of reported abnormal users. The geographical location information of the reported abnormal users, such as their region, street, and floor, is obtained. Verification personnel meeting the criteria are selected from the verification personnel database based on the geographical location information. The final list of verification personnel is determined by considering factors such as the professional skills, work experience, and availability of the verification personnel.

[0132] S404. Send a Level 3 verification instruction to the verification personnel, instructing them to conduct on-site verification.

[0133] In some embodiments, the present invention can send the generated Level 3 verification instructions to designated verification personnel, instructing them to conduct on-site verification. An efficient instruction sending mechanism is designed and developed to ensure that the Level 3 verification instructions are accurately and promptly sent to the verification personnel. The instructions clearly specify the purpose, requirements, time, location, and other information of the verification so that the verification personnel can prepare accordingly. Necessary verification tools or equipment, such as portable monitoring instruments and data recording forms, are provided to support on-site verification work.

[0134] In this way, the embodiments of the present invention can achieve three-level verification through on-site inspection, further improving the accuracy of power carbon verification.

[0135] Optionally, the electricity carbon verification method based on big data analysis provided in this embodiment of the invention further includes steps S501-S504 after step S105.

[0136] S501. Obtain the verification values ​​of carbon emission factors for each node in the target area's power grid after the power carbon verification.

[0137] In some embodiments, the carbon emission factor verification value refers to the actual carbon emission factor value of each node in the target area power grid within a specific time period, obtained through the power carbon verification method.

[0138] In some embodiments, high carbon emission nodes refer to grid nodes whose carbon emission factor verification values ​​exceed a preset threshold. These nodes are the focus of energy conservation and emission reduction efforts.

[0139] In some embodiments, conventional power generation capacity refers to the installed capacity of power plants that rely on fossil fuels (such as coal, oil, natural gas, etc.) to generate electricity.

[0140] In some embodiments, new energy power generation capacity refers to the installed capacity of power plants that generate electricity using renewable energy sources (such as solar, wind, and hydropower).

[0141] In some embodiments, user load refers to the total electricity demand of all users in the power grid during a specific time period.

[0142] In some embodiments, the new energy installation ratio threshold refers to the minimum limit of the proportion of new energy power generation capacity in the total power generation capacity, which is preset in order to achieve energy conservation and emission reduction goals.

[0143] In some embodiments, the present invention can obtain the carbon emission factor verification values ​​of each node in the power grid of a target area within a specific time period through a power carbon verification system or database. It ensures that the data originates from a reliable power carbon verification process. The data should include the carbon emission factor verification value of each node and its corresponding timestamp.

[0144] S502. Based on the verification values ​​of carbon emission factors of each node, each node is screened to identify high carbon emission nodes.

[0145] In some embodiments, this invention can identify high-carbon-emission nodes based on their carbon emission factor verification values, using threshold settings or comparative analysis methods. Reasonable carbon emission factor thresholds are set and adjusted according to regional and industry characteristics. Data analysis tools or programming scripts are used to filter and sort the verification values.

[0146] S503: Obtain the conventional power generation capacity, renewable energy power generation capacity, and user load of high-carbon emission node areas.

[0147] In some embodiments, the present invention can obtain conventional power generation capacity, renewable energy power generation capacity, and user load data for areas where high-carbon emission nodes are located from a power grid management system or related databases. The accuracy and timeliness of the data are ensured by preprocessing the data, such as removing outliers and filling in missing values.

[0148] S504. Calculate the new renewable energy generation capacity based on the conventional power generation capacity, renewable energy generation capacity, and user load of high-carbon emission node areas, as well as the preset renewable energy installation ratio threshold.

[0149] In some embodiments, the present invention can calculate the required new renewable energy generation capacity based on the conventional power generation capacity, renewable energy generation capacity, and user load in the region where the high-carbon emission node is located, as well as a preset renewable energy installation ratio threshold. A reasonable renewable energy installation ratio threshold is set according to energy conservation and emission reduction targets and renewable energy development policies. A mathematical model or algorithm is used to calculate the specific value of the new renewable energy generation capacity.

[0150] S505. Based on the power grid architecture of high-carbon emission node areas, determine the installation locations of new renewable energy sources.

[0151] In some embodiments, the present invention can determine the optimal installation location for new renewable energy sources based on the power grid architecture of the region where high-carbon emission nodes are located through optimization analysis. Power grid architecture analysis is performed considering the stability, security, and economy of the power grid. Optimization calculations for the installation locations of renewable energy sources are then conducted using power grid planning software or tools.

[0152] S506. Based on the newly added renewable energy power generation capacity and the installation location of the new renewable energy, generate energy-saving and emission-reduction schemes for high-carbon emission nodes.

[0153] In some embodiments, the present invention can formulate energy conservation and emission reduction plans for high-carbon emission nodes based on the new renewable energy power generation capacity and the installation location of the new renewable energy sources. The energy conservation and emission reduction plan should include detailed information such as the type, scale, investment budget, and implementation timetable of the renewable energy power generation project. The plan should consider factors such as technical feasibility, economic feasibility, and environmental friendliness. The energy conservation and emission reduction plan will be submitted to relevant departments or decision-making bodies for approval and implementation.

[0154] In this way, embodiments of the present invention can improve the existing power grid architecture based on the results of power carbon verification, increase the proportion of new energy sources, and achieve energy conservation and emission reduction in regional power grids.

[0155] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0156] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0157] Figure 2 This illustration shows a schematic diagram of an electricity carbon verification device based on big data analysis, according to an embodiment of the present invention. The device 600 includes a communication module 601 and a processing module 602.

[0158] The communication module 601 is used to acquire monitoring data of the power grid in the target area during a set period, as well as carbon emission data reported by each user; the monitoring data includes the power generation, power consumption and fuel consumption of each node.

[0159] The processing module 602 is used to calculate carbon emissions based on monitoring data for a set period, determine the calculated carbon emission data for each user, including the calculated values ​​of carbon emission factors and carbon emission amounts; perform a first-level carbon verification based on the calculated carbon emission data and reported carbon emission data for each user to identify users reporting abnormal emissions; extract the power carbon verification characteristics of users reporting abnormal emissions based on the monitoring data for the set period; and perform a second-level verification based on the power carbon verification characteristics of users reporting abnormal emissions, the reported carbon emission data, and the power carbon verification model to determine the power carbon verification result.

[0160] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 700 includes: a processor 701, a memory 702, and a computer program 703 stored in the memory 702 and executable on the processor 701. When the processor 701 executes the computer program 703, it implements the steps in the above-described method embodiments, for example... Figure 1 The steps S101-S105 are shown. Alternatively, when the processor 701 executes the computer program 703, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of the communication module 601 and the processing module 602 shown are illustrated.

[0161] For example, the computer program 703 can be divided into one or more modules / units, which are stored in the memory 702 and executed by the processor 701 to complete the present invention. The one or more modules / units can be capable of performing specific tasks... Figure 3 A series of computer program instruction segments with defined functions, which describe the execution process of the computer program 703 in the electronic device 700. For example, the computer program 703 can be divided into... Figure 2 The communication module 601 and the processing module 602 are shown.

[0162] The processor 701 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0163] The memory 702 can be an internal storage unit of the electronic device 700, such as a hard disk or memory of the electronic device 700. The memory 702 can also be an external storage device of the electronic device 700, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the electronic device 700. Furthermore, the memory 702 can include both internal and external storage units of the electronic device 700. The memory 702 is used to store the computer program and other programs and data required by the terminal. The memory 702 can also be used to temporarily store data that has been output or will be output.

[0164] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for verifying electricity carbon emissions based on big data analysis, characterized in that, include: Acquire monitoring data of the power grid in the target area during a set period, as well as carbon emission data reported by each user; the monitoring data includes the power generation, electricity consumption, and fuel consumption of each node; Based on monitoring data for a set period, big data analysis and carbon emission calculation are performed to determine the calculated carbon emission data for each user. The calculated carbon emission data includes the calculated values ​​of carbon emission factors and carbon emission amounts. Based on each user's calculated and reported carbon emission data, a first-level carbon verification is conducted to identify users with abnormal reports. Based on the monitoring data for the specified period, extract the electricity carbon verification characteristics of the reported abnormal users; Based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, as well as the electricity carbon verification model, a secondary carbon verification is conducted to determine the electricity carbon verification results.

2. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, The calculation of carbon emissions based on the monitoring data for the set period, and the determination of calculated carbon emission data for each user, include: Based on the monitoring data of the set period, nodes are divided, and the conventional energy power generation, new energy power generation, electricity consumption and fuel consumption of each node are determined. The total emissions of each node are determined based on its fuel consumption and fuel type. Based on the total carbon emissions, conventional energy power generation, new energy power generation, and electricity consumption of each node, the calculated value of the carbon emission factor for each node is determined; the carbon emission factor is used to characterize the carbon emissions per unit of electricity consumed. Based on the electricity consumption of each user in the region where each node is located, and the calculated value of the carbon emission factor of each node, the calculated value of the carbon emission of each user is determined.

3. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, The calculation and reported carbon emission data of each user are used to conduct a first-level carbon verification to identify users who report abnormal emissions, including: Based on the calculated carbon emission data and reported carbon emission data of each user, calculate the first error between the calculated value and the reported value of the carbon emission factor of each user, and the second error between the calculated value and the reported value of carbon emission amount. For any user, if the user's first error is greater than the first set threshold, then the user is determined to be a user reporting an abnormality. If the user's first error is less than or equal to the first set threshold and the second error is greater than the second set threshold, then the user is determined to be a user reporting an abnormality. If a user's first error is less than or equal to the first set threshold and the second error is less than or equal to the second set threshold, then the user is considered a normal reporting user.

4. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, The extraction of electricity carbon verification characteristics from the monitoring data based on the set period includes: Based on the power generation and consumption of each node in a set period, the power is divided to determine the metered power for each time period, including the metered power during peak hours and the metered power during off-peak hours. Based on the power generation and fuel consumption of each node, determine the fuel consumption for each time period and the proportion of new energy consumption; Based on the metered electricity consumption for each time period, the metered electricity consumption during peak hours, the metered electricity consumption during off-peak hours, the fuel consumption for each time period, the proportion of new energy consumption, and the pre-stored user type, user geographical location, historical carbon emissions, first error and second error, the electricity carbon verification characteristics of the reported abnormal users are generated.

5. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, The process of conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, as well as the electricity carbon verification model, to determine the electricity carbon verification results includes: Based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, an input feature vector is generated; Based on the input feature vector and the electricity carbon verification model, a secondary verification is performed to determine the secondary verification results. The secondary verification results include the electricity verification results, carbon emission verification results, and carbon emission factor verification results for each time period. Based on the results of the secondary verification, the results of the power carbon verification are determined. The results of the power carbon verification include verified carbon emission data and the reasons for data anomalies. The verified carbon emission data includes verified values ​​of carbon emission factors and carbon emission amounts. The reasons for data anomalies include data reporting errors, metering equipment failures, or changes in the production process.

6. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, Before determining the electricity carbon verification result by conducting secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, and the electricity carbon verification model, the process also includes: Acquire historical monitoring data of the power grid in the target area and carbon emission data reported by each user in each reporting period; The monitoring data from the historical period is divided into time periods to generate the electricity carbon verification characteristics of each user in each reporting cycle; Based on the electricity carbon verification characteristics of each user in each reporting period, and the carbon emission data reported by each user in each reporting period, an input feature vector for each user in each reporting period is generated. Based on the electricity carbon verification characteristics of each user in each reporting period, and the carbon emission data reported by each user in each reporting period, the electricity verification results, carbon emission verification results and carbon emission factor verification results for each time period in each reporting period are generated. The input feature vector of each user in each reporting period is used as input, and the results of electricity verification, carbon emission verification and carbon emission factor verification in each time period within each reporting period are used as output to generate multiple training samples. Based on the multiple training samples, a neural network is trained to obtain the electricity carbon verification model.

7. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, After determining the electricity carbon verification result by conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, and the electricity carbon verification model, the process further includes: Obtain carbon emission data for each user after the electricity carbon verification; Based on the carbon emission data of each user after the electricity carbon verification, high carbon emission users were identified. Obtain records of electricity consumption behavior of high-carbon-emission users during a set period; Based on the electricity consumption records of high-carbon emission users during a set period, as well as the metered electricity consumption, carbon emissions, and carbon emission factors of high-carbon emission users in each time period during the set period, the metered electricity consumption, carbon emissions, and carbon emission factors of each device of high-carbon emission users in each time period are determined. The metered electricity consumption, carbon emissions, and carbon emission factors of each device of high-carbon emission users in each time period are traversed to determine the energy-saving and emission-reduction schemes for high-carbon emission users in each time period. The energy-saving and emission-reduction schemes include time period transfer sub-schemes and direct optimization sub-schemes. The time period transfer sub-schemes include transferable devices, the time period before the transfer of transferable devices, and the time period before the transfer. The direct optimization sub-schemes include directly optimized devices and the time period in which the directly optimized devices are located.

8. The electricity carbon verification method based on big data analysis according to claim 1, characterized in that, After determining the electricity carbon verification result by conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, and the electricity carbon verification model, the process further includes: Obtain the reconsideration request from the user who reported the abnormality, the reconsideration request being used to instruct the user who reported the abnormality to request a reconsideration of the electricity carbon verification results; In response to the aforementioned reconsideration application, a third-level verification instruction is generated based on the monitoring data of the reported abnormal user, the results of the first-level verification, the results of the second-level verification, and the results of the electricity carbon verification. Based on the geographical location of the reported abnormal users, the personnel responsible for verification were determined; The Level 3 verification instruction is sent to the verification personnel, instructing them to conduct an on-site verification.

9. The electricity carbon verification method based on big data analysis according to any one of claims 1 to 8, characterized in that, After determining the electricity carbon verification result by conducting a secondary verification based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, and the electricity carbon verification model, the process further includes: Obtain the verification values ​​of carbon emission factors for each node in the target area's power grid after the power carbon verification; Based on the verification values ​​of carbon emission factors at each node, each node is screened to identify high-carbon emission nodes. Obtain the conventional power generation capacity, renewable energy power generation capacity, and user load of the region described by the high carbon emission node; Based on the conventional power generation capacity, renewable energy power generation capacity, and user load of the region described by the high carbon emission node, as well as the preset renewable energy installation ratio threshold, the new renewable energy power generation capacity is calculated. Based on the power grid architecture of the high-carbon emission nodes, determine the installation locations for new renewable energy sources; Based on the newly added renewable energy power generation capacity and the installation location of the new renewable energy sources, energy conservation and emission reduction schemes are generated for high-carbon emission nodes.

10. A power carbon verification device based on big data analysis, characterized in that, include: The communication module is used to acquire monitoring data of the power grid in the target area during a set period, as well as carbon emission data reported by each user; the monitoring data includes the power generation, power consumption and fuel consumption of each node; The processing module is used to calculate carbon emissions based on monitoring data for the set period, determine the calculated carbon emission data for each user, the calculated carbon emission data including the calculated values ​​of carbon emission factors and carbon emission amounts; perform a first-level carbon verification based on the calculated carbon emission data and reported carbon emission data of each user, and identify users who have reported abnormal emissions; and extract the power carbon verification characteristics of the users who have reported abnormal emissions based on the monitoring data for the set period. Based on the electricity carbon verification characteristics and reported carbon emission data of the reported abnormal users, as well as the electricity carbon verification model, a secondary verification is conducted to determine the electricity carbon verification results.

Images