Carbon emission monitoring method and system based on electric power big data

Abstract

The invention belongs to the technical field of electric power big data, and particularly relates to a carbon emission monitoring method and system based on electric power big data. According to the method, the power related data of the target area is obtained from the data center, the time sequence data set is constructed and input into the electric carbon calculation model trained based on the ARDL-ECM model, the energy consumption amount is rapidly predicted, and then direct carbon emission is determined. Meanwhile, indirect implicit carbon emission is calculated in combination with the called-in power data and the power emission factor, and the final carbon emission is comprehensively obtained. According to the scheme, high efficiency, low cost and wide applicability of carbon emission monitoring are realized by utilizing the real-time and high-frequency characteristics of electric power big data and combining the prediction capability of a machine learning model.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power big data, and specifically relates to a carbon emission monitoring method and system based on electric power big data. Background Art

[0002] At present, the main carbon emission accounting methods are calculation method and measurement method. Among them: (1) Calculation method: Calculate carbon dioxide emissions based on emission activity data or material balance relationships, mainly including emission factor method and material balance method. Emission factor method: According to the carbon emission inventory, for each carbon emission source, construct its activity data and emission factor, and use the product of activity data and emission factor as the estimated value of carbon emissions for the emission project; Application scope: Carbon emission accounting for different dimensions such as countries, regions, and industries; Advantages: Wide application range and low cost; Disadvantages: Relying on a large amount of statistical data, affected by data quality, frequency, cycle, etc. Material balance method: Based on the law of conservation and transformation of matter, a method of material balance calculation for its chemical reaction process. For carbon dioxide, carbon emissions are obtained by subtracting the non-carbon dioxide carbon output from the input carbon content; Application scope: Used for carbon emission accounting in industrial production processes; Advantages: More accurate calculation for single equipment; Disadvantages: Limited application scope; Limited by the accuracy of mass, density and other measuring equipment.

[0003] (2) Actual measurement method: It is to directly monitor and measure the concentration and flow of carbon dioxide in real time through measuring instruments, including satellite monitoring method at the macro level and continuous monitoring of flue gas emissions at the micro level. The satellite monitoring method is to measure the infrared radiation on the earth's surface through satellites to determine the temperature distribution on the earth's surface, thereby inferring the amount of carbon emissions; Application scope: Monitoring of carbon dioxide concentration in the atmosphere of macro-regions; Advantages: wide monitoring range; Disadvantages: can only monitor the carbon concentration state, not directly monitor carbon emissions. The flue gas monitoring method is to directly calculate the CO2 emissions in a certain period of time based on the flue gas flow and flue gas components measured at the emission end of a fixed pollution source (thermal power plant); Application scope: emission source facilities (exhaust outlets) of enterprises; Advantages: high measurement accuracy and strong real-time measurement; Disadvantages: the cost of a single device is about 100,000 yuan, and the investment and operation and maintenance costs are high.

[0004] The basic data required for the calculation method mainly include various fossil fuel consumption data, industrial product output data, electricity purchase (transfer) volume, etc. The data sources are mainly government statistical data, industry statistical data, enterprise ledgers and statistical report data, etc. The data frequency is annual and monthly.

[0005]

[0006] From the perspective of scope of application, accounting costs, data status, etc., the material balance method and the actual measurement method can provide a reference for the statistics of carbon emissions in some industries by monitoring the carbon emissions of specific enterprises, but it is difficult to calculate monthly carbon emissions by region and industry. The most appropriate accounting method for carbon emissions by region and industry is the emission factor method, and the "Guidelines for the Preparation of Provincial Greenhouse Gas Inventories (Trial)" issued by the National Development and Reform Commission is also mainly based on the emission factor method.

[0007]

[0008] The low accuracy and frequency of data from the emission factor method are both related to the current source of activity data. Currently, regional and industry carbon emission accounting is mainly based on yearbooks, departmental statistics and other data. The data statistical calibers are inconsistent, the collection time is long, and the statistical workload is large.

[0009] In summary, the existing calculation method for calculating carbon emissions has problems such as low timeliness, while the actual measurement method has problems such as high cost and limited application scope. Summary of the invention

[0010] The purpose of the present invention is to provide a carbon emissions monitoring method and system based on power big data, which can effectively solve the problems in the prior art, such as poor timeliness of the calculation method, limited scope of application and high cost of the actual measurement method.

[0011] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a carbon emissions monitoring method based on power big data, comprising the following steps: Obtain the current regional data for calculating carbon emissions in the target area from the data center; The current regional related data is constructed as a data set based on a time series, and the data set based on a time series is input into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area; wherein the electric carbon calculation model is obtained by training based on the ARDL-ECM model; Determine direct carbon emissions based on the energy consumption of the target area; determine the imported power data and power emission factors; calculate indirect implicit carbon emissions based on the imported power data and power emission factors; determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

[0012] Further, in the step of obtaining the current regional relevant data for calculating carbon emissions in the target area from the data center: The current regional relevant data include: current energy consumption, current electricity consumption, current regional GDP, current regional clean energy share, current regional output of major industrial products, current regional electricity consumption of major industrial products, and supply index of major industrial products.

[0013] Furthermore, the electric carbon calculation model is obtained based on the ARDL-ECM model training, including: Obtaining regional data for calculating carbon emissions, and cleaning and processing the regional data to obtain a data set for model training; wherein the regional data includes historical energy consumption, historical electricity consumption, regional GDP, regional clean energy share, regional major industrial product output, regional major industrial product electricity consumption, and major industrial product supply index; The ARDL-ECM model is determined as the basic model, and the ARDL-ECM model is trained based on the data set to obtain a trained electric carbon calculation model.

[0014] Furthermore, the ARDL-ECM model is trained based on the data set to obtain a trained electric carbon calculation model, including: ARDL model training: Determine the objective function of the ARDL model, and determine each coefficient item to be fitted and each lag order to be fitted of the ARDL model based on the objective function of the ARDL model; The coefficients to be fitted of the ARDL model are estimated by the least square method to obtain the estimated values ​​of the coefficients of the ARDL model; The lag orders to be fitted in the ARDL model are determined by the AIC information criterion, and the estimated values ​​of the lag orders to be fitted in the ARDL model are obtained; Substituting the estimated values ​​of each coefficient term and each estimated value of the lag order to be fitted of the ARDL model into the objective function of the ARDL model to obtain a trained ARDL model; ECM model training: Constructing the objective function of the ECM model, substituting the estimated values ​​of each coefficient term and each lag order estimated value to be fitted of the ARDL model into the objective function of the ECM model to obtain a trained ECM model; The trained ECM model and the trained ARDL model are combined to obtain a trained electric-carbon calculation model.

[0015] Further, in the step of determining each coefficient term to be fitted and each lag order to be fitted of the ARDL model based on the objective function of the ARDL model: The coefficients to be fitted in the ARDL model include: basic influencing factors a 0、 Fitting coefficient of the lagged dependent variable in year i φ i 、 Fitting coefficient of the lagged independent variable in year i β i 、 Fitting coefficient of the lagged independent variable in year i γ i and the random deviation part μ t,i ; The lag orders to be fitted in the ARDL model include: the maximum lag order of the dependent variable p、 Maximum lag order of the independent variable q and the maximum lag order of the auxiliary variables s .

[0016] Furthermore, the coefficient items to be fitted of the ARDL model are estimated by the least square method to obtain the estimated values ​​of the coefficient items of the ARDL model; the lag orders to be fitted of the ARDL model are determined by the AIC information criterion to obtain the estimated values ​​of the lag orders to be fitted of the ARDL model, including: The objective function of the ARDL model is used to calculate the estimated value of the objective function, and the residual is calculated based on the estimated value of the objective function and the actual value of the objective function; the parameter value that minimizes the sum of squares of the residual is found as the estimated value of each coefficient term of the ARDL model; Based on the determination formula of the AIC information criterion, the parameter group corresponding to the minimum AIC value is found as the estimated value of each lag order to be fitted.

[0017] In a second aspect, the present invention provides a carbon emission monitoring device based on power big data, comprising: A data acquisition module, used to obtain the current regional relevant data in the target area for calculating carbon emissions from the data center; A numerical correction module is used to construct the current regional related data into a data set based on a time series, input the data set based on a time series into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area; wherein the electric carbon calculation model is obtained by training based on the ARDL-ECM model; The carbon emission calculation module is used to determine direct carbon emissions based on the energy consumption of the target area; determine the input power data and power emission factors; calculate indirect implicit carbon emissions based on the input power data and power emission factors; and determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

[0018] Furthermore, in the data acquisition module: The current regional relevant data include: current energy consumption, current electricity consumption, current regional GDP, current regional clean energy share, current regional output of major industrial products, current regional electricity consumption of major industrial products, and supply index of major industrial products.

[0019] According to a third aspect of the present invention, there is provided an electronic device comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the carbon emission monitoring method based on electric power big data as described above.

[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the carbon emission monitoring method based on electric power big data as described above is implemented.

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows: Existing carbon emission calculation methods mainly rely on government statistics, industry statistics, etc. These data often have problems such as long statistical cycles and slow updates, resulting in low timeliness of carbon emission accounting. The carbon emission monitoring method based on power big data of the present invention utilizes power big data, constructs a data set based on time series, and inputs it into a pre-trained power-carbon calculation model, which can quickly calculate the energy consumption and carbon emissions of the target area with strong timeliness.

[0022] Although the actual measurement method has high accuracy, it is not suitable for large-scale promotion due to high equipment cost and complex operation and maintenance. The present invention uses power big data and machine learning model (ARDL-ECM model) to avoid expensive monitoring equipment investment and reduce the overall cost of carbon emission monitoring.

[0023] The application scope of material balance method and actual measurement method is relatively limited, mainly concentrated in specific industries or enterprises. Through the wide applicability and accessibility of power big data, the present invention can cover a wider range of regions and industries and realize cross-regional and cross-industry monitoring of carbon emissions.

[0024] The data sources of existing methods are diverse and inconsistent, and the data quality is uneven, which affects the accuracy of the accounting results. The present invention can improve the timeliness and accuracy of the data to a certain extent by constructing a data set based on time series and using a machine learning model for data processing and prediction, thereby improving the accuracy of carbon emission accounting.

[0025] In summary, the present invention proposes a new carbon emissions monitoring method through power big data and machine learning, which shows significant advantages in improving timeliness, reducing costs, expanding the scope of application and improving data quality, and can effectively solve the problems existing in existing carbon emissions accounting methods. The carbon emissions monitoring device, electronic device and computer-readable storage medium based on power big data provided by the present invention also solve the problems raised in the background technology section. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a flow chart of a carbon emissions monitoring method based on power big data according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a carbon emission monitoring device based on power big data according to an embodiment of the present invention; Figure 3 The present invention is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0028] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.

[0029] Glossary: GDP, Gross Domestic Product (GDP for short).

[0030] IQR (Interquartile Range) abnormal data analysis method is used to detect outliers.

[0031] ARDL-ECM model, full spelling Autoregressive Distributed Lag-Error CorrectionModel.

[0032] ARDL model, Auto-regressive Distributed Lag Model‌.

[0033] ‌ECM model, Error Correction Model (ECM for short).

[0034] Example 1 like Figure 1 As shown, a carbon emission monitoring method based on power big data includes the following steps: S1. Obtain the current regional data for calculating carbon emissions in the target area from the data center.

[0035] Specifically, in step S1: the current regional relevant data include: current energy consumption, current electricity consumption, current regional GDP, current regional clean energy proportion, current regional main industrial product output, current regional main industrial product electricity consumption, and main industrial product supply index.

[0036] Optionally, the data center can be used to collect data related to the region where carbon emissions need to be calculated. The data related to the region is then cleaned and processed, including missing data processing, abnormal data processing, etc.

[0037] Specifically, missing data processing: the missing data is filled with the previous and next average method. If the missing data is the last data, the previous value is used to fill it. If the missing data is the first data, the latter value is used to fill it.

[0038] Specifically, abnormal data processing: use the IQR abnormal data analysis method to analyze the abnormal data, and use the front and back average method to replace the abnormal data. If the abnormal data is the last value, use the previous value to fill it. If the abnormal data is the first data, use the latter value to fill it.

[0039] S2. Construct the current regional related data into a time series-based data set, input the time series-based data set into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area.

[0040] Specifically, the electric carbon calculation model is obtained based on ARDL-ECM model training, including: S21. Acquire regional relevant data for calculating carbon emissions, and clean and process the regional relevant data to obtain a data set for model training; wherein the regional relevant data includes historical energy consumption, historical electricity consumption, regional GDP, regional clean energy share, regional major industrial product output, regional major industrial product electricity consumption, and major industrial product supply index; S22, determining the ARDL-ECM model as the basic model, and training the ARDL-ECM model based on the data set to obtain a trained electric-carbon calculation model.

[0041] Among them, the ARDL-ECM model uses electricity data to fit energy consumption.

[0042] More specifically, the ARDL-ECM model is trained based on the data set to obtain a trained electric carbon calculation model, including the following specific steps: S221, ARDL model training: determining the objective function of the ARDL model, and determining each coefficient item to be fitted and each lag order to be fitted of the ARDL model based on the objective function of the ARDL model; estimating each coefficient item to be fitted of the ARDL model by the least squares method to obtain an estimated value of each coefficient item of the ARDL model; determining each lag order to be fitted of the ARDL model by the AIC information criterion to obtain an estimated value of each lag order to be fitted of the ARDL model; substituting the estimated value of each coefficient item and the estimated value of each lag order to be fitted of the ARDL model into the objective function of the ARDL model to obtain a trained ARDL model; S222, ECM model training: constructing the objective function of the ECM model, substituting the estimated values ​​of each coefficient term of the ARDL model and the estimated values ​​of each lag order to be fitted into the objective function of the ECM model, and obtaining a trained ECM model; S223, combining the trained ECM model and the trained ARDL model to obtain a trained electric-carbon calculation model.

[0043] In step S221, the objective function of the ARDL model is determined, and each coefficient term to be fitted and each lag order to be fitted of the ARDL model are determined based on the objective function of the ARDL model, including: The objective function of the ARDL model is determined as:

[0044] in, y t,r is the energy consumption and industrial output of region r in year t; a 0 is the basic influencing factor; y t-i,r is the energy consumption and industrial output of region r in year ti; φ i is the fitted coefficient of the lagged dependent variable in year i; p is the maximum lag order of the dependent variable; x t-i,r The electricity data for region r in ti year; βi is the fitting coefficient of the lagged independent variable in year i; q is the maximum lag order of the independent variable; z t-i,r Economic data or clean power data of region r for ti years, etc.; γ i is the fitting coefficient of the lagged independent variable in year i; s is the maximum lag order of the auxiliary variable; μ t,r is the random deviation part; The coefficients to be fitted in the ARDL model include: basic influencing factors a 0 、 Fitting coefficient of the lagged dependent variable in year i φ i 、 Fitting coefficient of the lagged independent variable in year i β i 、 Fitting coefficient of the lagged independent variable in year i γ i and the random deviation part μ t,r ; The lag orders to be fitted in the ARDL model include: the maximum lag order of the dependent variable p、 Maximum lag order of the independent variable q and the maximum lag order of the auxiliary variables s .

[0045] In this scheme, each coefficient item to be fitted of the ARDL model is estimated by the least squares method to obtain the estimated value of each coefficient item of the ARDL model, including: calculating the estimated value of the objective function through the objective function of the ARDL model, calculating the residual based on the estimated value of the objective function and the actual value of the objective function; and finding the parameter value that minimizes the sum of squares of the residual as the estimated value of each coefficient item of the ARDL model.

[0046] More specifically, the coefficients to be fitted in the ARDL model are estimated by the least squares method, including: Determine the objective function of the ARDL model; after initializing the parameters, calculate the estimated value through the objective function ; Calculate the residual: ; Minimize the sum of squares of the residuals, that is, find the parameter value that minimizes the sum of squares of the residuals. In this solution, the loss function used is the average value of the sum of squares of the residuals, that is, minimize the following formula:

[0047] Where n is the total number of samples, and j is the current jth sample. The coefficient that minimizes the residual sum of squares is solved by analytical methods to determine a0 ,φ i 、β i , γ i and μ t,r The numerical value of .

[0048] In this scheme, the lag orders to be fitted of the ARDL model are determined by the AIC information criterion, and the estimated values ​​of the lag orders to be fitted of the ARDL model are obtained, including: based on the determination formula of the AIC information criterion, finding the parameter group corresponding to the minimum AIC value as the estimated values ​​of the lag orders to be fitted.

[0049] The lag orders of the objective function to be fitted p,q,s Determined by the AIC information criterion, the formula is as follows:

[0050] in, L is the maximum likelihood value of the objective function, and k is the number of contrast models. p,q, s The values ​​are combined into estimated parameter groups, using p,q,s The model is trained with the value, the AIC value is calculated, and the value with the smallest AIC value is selected. p,q,s The value is the final value of each lag order to be fitted.

[0051] In step S222, the objective function of the ECM model is constructed, and the estimated values ​​of the coefficient terms and the estimated values ​​of the lag orders to be fitted of the ARDL model are substituted into the objective function of the ECM model to obtain a trained ECM model, including: The ECM model is used to capture the relationship between short-term dynamic adjustment and long-term equilibrium, and its objective function formula is as follows.

[0052]

[0053] Among them, ∆ y t,r ,∆ y t-i,r ,∆ x t-i,r， ∆ z t-i,r For each variable y t,r , y t-i,r , x t-i,r , z t-i,r The difference of EC t−1,ris the error correction term, calculated as follows:

[0054] All variables and coefficients in the formula come from the model coefficients and values ​​obtained in the ARDL model training. The values ​​of each coefficient in the ECM model are determined using the same least squares method and AIC information criterion method as the ARDL model, which will not be repeated here.

[0055] In step S223, the trained ECM model and the trained ARDL model are combined, including: The ARDL model and the ECM model are added together to get the final ARDL-ECM model, which can be used to calculate the regional energy consumption data and product output data. The ARDL-ECM model calculation formula is as follows:

[0056] in, AC t,r It is the final value after correction of energy consumption and industrial output in region r in year t.

[0057] S3. Determine direct carbon emissions based on energy consumption in the target area; determine the imported power data and power emission factors; calculate indirect implicit carbon emissions based on the imported power data and power emission factors; determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

[0058] Specifically, the final carbon emissions are calculated according to the following formula:

[0059] in, E For final carbon emissions; AC i Calculated by ARDL-ECM model AC t,r The consumption or product output of the i-th fossil fuel; EF i is the emission factor of the i-th fossil fuel or product; AC 电 To import power data; EF 电 is the electricity emission factor; n is the type of fossil fuel consumption or product output.

[0060] Preferably, carbon emission data can reflect the energy consumption structure. In this scheme, the optimization of energy structure can be guided by carbon emission data. If it is shown that coal consumption accounts for a high proportion, it can promote the substitution of clean energy (such as solar energy and wind energy) to reduce carbon emissions.

[0061] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiment, the present invention also provides a carbon emission monitoring device based on power big data, comprising: A data acquisition module, used to obtain the current regional relevant data in the target area for calculating carbon emissions from the data center; A numerical correction module is used to construct the current regional related data into a data set based on a time series, input the data set based on a time series into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area; wherein the electric carbon calculation model is trained based on the ARDL-ECM model; The carbon emission calculation module is used to determine direct carbon emissions based on the energy consumption of the target area; determine the input power data and power emission factors; calculate indirect implicit carbon emissions based on the input power data and power emission factors; and determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

[0062] In the data acquisition module: The current regional relevant data include: current energy consumption, current electricity consumption, current regional GDP, current regional clean energy share, current regional output of major industrial products, current regional electricity consumption of major industrial products, and supply index of major industrial products.

[0063] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a carbon emission monitoring method based on power big data in Example 1; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .

[0064] The memory 101 can be used to store a computer program 103. The processor 102 implements the steps of a carbon emissions monitoring method based on power big data in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0065] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0066] At least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0067] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a carbon emission monitoring method based on power big data, and the processor 102 can execute the plurality of instructions to implement: Obtain the current regional data for calculating carbon emissions in the target area from the data center; The current regional related data is constructed as a data set based on a time series, and the data set based on the time series is input into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area; wherein the electric carbon calculation model is trained based on the ARDL-ECM model; Determine direct carbon emissions based on the energy consumption of the target area; determine the imported power data and power emission factors; calculate indirect implicit carbon emissions based on the imported power data and power emission factors; determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

[0068] Example 4 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0069] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A carbon emissions monitoring method based on power big data, characterized in that: The steps include: Obtain the current regional data for calculating carbon emissions in the target area from the data center; The current regional related data is constructed as a data set based on a time series, and the data set based on a time series is input into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area; wherein the electric carbon calculation model is obtained by training based on the ARDL-ECM model; Determine direct carbon emissions based on the energy consumption of the target area; determine the imported power data and power emission factors; calculate indirect implicit carbon emissions based on the imported power data and power emission factors; determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

2. The carbon emission monitoring method based on power big data according to claim 1 is characterized in that: In the step of obtaining the current regional data for calculating carbon emissions in the target area from the data center: The current regional relevant data include: current energy consumption, current electricity consumption, current regional GDP, current regional clean energy share, current regional output of major industrial products, current regional electricity consumption of major industrial products, and supply index of major industrial products.

3. The carbon emission monitoring method based on power big data according to claim 1 is characterized in that: The electric carbon calculation model is obtained based on the ARDL-ECM model training, and includes: Obtaining regional data for calculating carbon emissions, and cleaning and processing the regional data to obtain a data set for model training; wherein the regional data includes historical energy consumption, historical electricity consumption, regional GDP, regional clean energy share, regional major industrial product output, regional major industrial product electricity consumption, and major industrial product supply index; The ARDL-ECM model is determined as the basic model, and the ARDL-ECM model is trained based on the data set to obtain a trained electric-carbon calculation model.

4. The carbon emission monitoring method based on power big data according to claim 3 is characterized in that: The ARDL-ECM model is trained based on the data set to obtain a trained electric carbon calculation model, including: ARDL model training: Determine the objective function of the ARDL model, and determine each coefficient item to be fitted and each lag order to be fitted of the ARDL model based on the objective function of the ARDL model; The coefficients to be fitted of the ARDL model are estimated by the least square method to obtain the estimated values ​​of the coefficients of the ARDL model; The lag orders to be fitted in the ARDL model are determined by the AIC information criterion, and the estimated values ​​of the lag orders to be fitted in the ARDL model are obtained; Substituting the estimated values ​​of each coefficient term and each estimated value of the lag order to be fitted of the ARDL model into the objective function of the ARDL model to obtain a trained ARDL model; ECM model training: Constructing the objective function of the ECM model, substituting the estimated values ​​of each coefficient term and each lag order estimated value to be fitted of the ARDL model into the objective function of the ECM model to obtain a trained ECM model; The trained ECM model and the trained ARDL model are combined to obtain a trained electric-carbon calculation model.

5. The carbon emission monitoring method based on power big data according to claim 4 is characterized in that: In the step of determining each coefficient item to be fitted and each lag order to be fitted of the ARDL model based on the objective function of the ARDL model: The coefficients to be fitted in the ARDL model include: basic influencing factors a 0 、 Fitting coefficient of the lagged dependent variable in year i φ i 、 Fitting coefficient of the lagged independent variable in year i β i 、 Fitting coefficient of the lagged independent variable in year i γ i and the random deviation part μ t,i ; The lag orders to be fitted in the ARDL model include: the maximum lag order of the dependent variable p、 Maximum lag order of the independent variable q and the maximum lag order of the auxiliary variables s .

6. The carbon emission monitoring method based on power big data according to claim 5 is characterized in that: The coefficients to be fitted of the ARDL model are estimated by the least square method to obtain the estimated values ​​of the coefficients of the ARDL model; The lag orders to be fitted in the ARDL model are determined by the AIC information criterion, and the estimated values ​​of the lag orders to be fitted in the ARDL model are obtained, including: The objective function of the ARDL model is used to calculate the estimated value of the objective function, and the residual is calculated based on the estimated value of the objective function and the actual value of the objective function; the parameter value that minimizes the sum of squares of the residual is found as the estimated value of each coefficient term of the ARDL model; Based on the determination formula of the AIC information criterion, the parameter group corresponding to the minimum AIC value is found as the estimated value of each lag order to be fitted.

7. A carbon emission monitoring device based on power big data, characterized in that: include: A data acquisition module, used to obtain the current regional relevant data in the target area for calculating carbon emissions from the data center; A numerical correction module is used to construct the current regional related data into a data set based on a time series, input the data set based on a time series into a pre-trained electric carbon calculation model, and the electric carbon calculation model outputs the energy consumption of the target area; wherein the electric carbon calculation model is obtained by training based on the ARDL-ECM model; The carbon emission calculation module is used to determine direct carbon emissions based on the energy consumption of the target area; determine the input power data and power emission factors; calculate indirect implicit carbon emissions based on the input power data and power emission factors; and determine the final carbon emissions of the target area based on direct carbon emissions and indirect implicit carbon emissions.

8. The carbon emission monitoring device based on electric power big data according to claim 7 is characterized in that: In the data acquisition module: The current regional relevant data include: current energy consumption, current electricity consumption, current regional GDP, current regional clean energy share, current regional output of major industrial products, current regional electricity consumption of major industrial products, and supply index of major industrial products.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the carbon emission monitoring method based on power big data as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, it implements the carbon emission monitoring method based on power big data as described in any one of claims 1 to 6.

Images