Regional carbon emission monitoring method and device, terminal and medium
By establishing a regional dynamic power consumption-energy consumption model and dynamic carbon emission factor, combined with the electric carbon coupling model, the problems of low statistical efficiency, high cost and low accuracy in traditional carbon metering methods are solved, and efficient and accurate carbon emission monitoring is achieved.
Patent Information
- Application Number
- CN202411697435.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-26
- Publication Date
- 2025-02-28
AI Technical Summary
Traditional carbon metering methods ignore the diversity and complexity of user energy consumption in the carbon metering monitoring area, resulting in low statistical efficiency, high cost of collection system construction, narrow applicability and insufficient accuracy.
Multivariate linear regression is used to establish a regional dynamic power consumption-energy consumption model, combine the power grid end data to construct regional dynamic carbon emission factors, and build an electrical carbon coupling model to achieve accurate calculation of carbon emissions through real-time power consumption monitoring.
It improves the efficiency and accuracy of carbon metering, reduces the computational complexity and cost, has better adaptability, and avoids the complexity of traditional methods.
Smart Images
Figure CN119539284A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of carbon emission monitoring, and in particular to a method, device, terminal and medium for monitoring regional carbon emissions. Background Art
[0002] In order to achieve the "dual carbon" goal together, all provinces, cities and industries have been involved in the research or practice of "energy measurement" and "carbon measurement". Statistics of users' daily electricity consumption data and energy consumption are the basis for carbon measurement. At present, there are three main monitoring methods for carbon measurement: carbon emission factor method, material balance method and actual measurement method. Among them, the carbon emission factor method is the most widely used carbon measurement method in my country, and the compilation of domestic and foreign inventories is also statistically based on this method; however, this method requires accurate measurement of various energy consumption, which makes statistics difficult and the construction cost of the statistical system high. In addition, the current carbon emission calculation usually ignores the impact of users' peak electricity consumption in different time periods, resulting in inaccurate measurement results. The material balance method is also called the mass balance method. It measures carbon emissions based on the conservation of input and output mass. The method is simple and practical, reducing the uncertainty of the data; however, this method is mostly used for carbon measurement for physical products. Carbon measurement involving non-physical perspectives requires a more abstract measurement mechanism, which has a narrower applicability and is not suitable for counting the total carbon emissions in the carbon emission detection area. The actual measurement method refers to a statistical method of measuring the velocity, flow rate and concentration of wastewater or waste gas emissions through monitoring means or standard metering facilities recognized by relevant national departments. It is generally used for supervisory testing to regularly measure whether various wastewater and waste gas emissions meet the standards. However, this method requires on-site data collection, and there are problems such as high cost of data collection system construction and difficulty in data collection.
[0003] In summary, the traditional carbon metering method ignores the diversity and complexity of energy consumption of users in the carbon metering monitoring area, and needs to count the types of energy consumption in the area and the consumption of each energy, resulting in low statistical efficiency, high cost of collection system construction, narrow applicability and insufficient accuracy. Carbon metering is the basis for reducing carbon emissions. Therefore, it is of great significance to study a simple, efficient and accurate monitoring method for carbon emissions. Summary of the invention
[0004] In order to solve the deficiencies in the prior art, the present invention provides a regional carbon emissions monitoring method, device, terminal and medium, which overcomes the problems of traditional methods relying on long-term statistical tracking of multi-department and multi-energy data, the difficulty in obtaining data, and the high statistical cost, thereby ensuring the reliability of carbon emissions monitoring results, while reducing the complexity of calculation and improving efficiency.
[0005] The present invention adopts the following technical solution.
[0006] In a first aspect, the present invention provides a method for monitoring regional carbon emissions, the method comprising: Collect historical consumption data and grid data of various energy sources in the target industries in the monitored area; Based on the historical consumption data of each energy source, a regional dynamic electricity consumption-energy consumption model is established using multiple linear regression; Perform power flow calculations on the collected grid data to construct regional dynamic carbon emission factors; Combining the regional dynamic electricity consumption-energy consumption model and the regional dynamic carbon emission factor, an electricity-carbon coupling model integrating the carbon emission measurement of various energy sources is constructed; The real-time power consumption of the target industry in the region is obtained, and the real-time power consumption is input into the electricity-carbon coupling model for measurement, and the monitoring results of its carbon emissions are output.
[0007] Optionally, the historical consumption data of each energy source includes the consumption of electricity, coal, coke, crude oil, gasoline, kerosene, diesel, fuel oil and / or natural gas by the target industry within a set historical time period; The grid-side data includes voltage, current, active power and reactive power at the power generation side and the user side.
[0008] Optionally, the step of establishing a regional dynamic power consumption-energy consumption model by using multiple linear regression includes: Step a: Divide the collected historical consumption data of each energy source into a training set and a test set; Step b, respectively performing multiple linear regression modeling on the electricity consumption and the other energy consumption to obtain the initial regression model of each energy; Step c, selecting multiple groups of data from the training set, and training the initial regression model of each energy source respectively; Step d: Based on the test set, the fitting errors of each regression model after training are calculated respectively; if the fitting error is less than the set threshold, the corresponding regression model is output; otherwise, the process returns to step c until the fitting errors of all regression models meet the requirements; Step e: Combining the regression models corresponding to the energy sources output in step d to form a regional dynamic power consumption-energy consumption model.
[0009] Optionally, after step e, the method further includes: Step f, updating the regional dynamic power consumption-energy consumption model according to the set cycle, that is, adding the fitting results of the model using the power consumption to other energy consumption in the previous cycle into the training set to retrain the model, and updating the regional dynamic power consumption-energy consumption model in the current cycle.
[0010] Optionally, the expression of the regional dynamic power consumption-energy consumption model is as follows: , In the formula, Indicates the amount of electrical energy consumed. Represents the dimension of the data, Indicates The amount of energy consumed, Indicates the number of types of energy other than electrical energy, Respectively represent The first and second fitting coefficients of the regression model of the energy source.
[0011] Optionally, the calculation formula of the fitting error in step d is as follows: , In the formula, Y MSE(n) Indicates The fitting error of the regression model for the energy source, =1,2……; L represents the data dimension of the test set, Indicates The regression model of energy i The fitting results of the input samples are Indicates i The actual value of energy consumption corresponding to the fitting result.
[0012] Optionally, the method also includes: using a data interpolation algorithm based on a GAN generative adversarial network to replace outliers and supplement missing values in the collected historical consumption data of each energy source and grid-end data.
[0013] Optionally, the expression of the regional dynamic carbon emission factor is as follows: , In the formula, Indicated in t Regional dynamic carbon emission factors for different time periods; is the load power of node i in period t, is the carbon emission factor of node i, and U is the set of nodes within the coverage of the regional power grid; Indicated in t Dynamic correction factor for the time period.
[0014] Optionally, the dynamic correction factor The calculation formula is as follows: , In the formula, Indicates the total number of users in the target industry within the monitoring area; Indicated in tThe number of high energy-consuming users in a time period, wherein the high energy-consuming users are business units whose electricity consumption exceeds a set power consumption threshold.
[0015] Optionally, the expression of the electric-carbon coupling model is as follows: , In the formula, It represents the total carbon emissions of the target industry in the monitoring area during period t; Represents enterprise users m exist t Power consumption during the time period; Indicates the monitoring time interval, Represents the carbon emission factor matrix of each energy source except electricity; Represents the consumption matrix of various energy sources except electric energy; where: , … .
[0016] In a second aspect, the present invention provides a regional carbon emissions monitoring device, which runs the steps of any method described in the first aspect of the present invention, and the device comprises: The data collection module is used to collect the historical consumption data of various energy sources and grid-end data in the target industry in the monitored area; Establish a dynamic power consumption-energy consumption model module, which is used to establish a regional dynamic power consumption-energy consumption model based on the historical consumption data of each energy source using multiple linear regression; Build a dynamic carbon emission factor module to calculate the power flow of the collected grid data to build a regional dynamic carbon emission factor; Constructing an electricity-carbon coupling model, which is used to combine the regional dynamic electricity consumption-energy consumption model and the regional dynamic carbon emission factor to construct an electricity-carbon coupling model that integrates the carbon emission measurement of various energy sources; The carbon emission monitoring module is used to obtain the real-time power consumption of the target industry in the region, input the real-time power consumption into the electricity-carbon coupling model for measurement, and output the monitoring results of its carbon emissions.
[0017] Optionally, the expression of the regional dynamic power consumption-energy consumption model is as follows: , In the formula, Indicates the amount of electrical energy consumed. Represents the dimension of the data, Indicates The amount of energy consumed, Indicates the number of types of energy other than electrical energy, Respectively represent The first and second fitting coefficients of the regression model of the energy source.
[0018] Optionally, the expression of the regional dynamic carbon emission factor is as follows: , In the formula, Indicated in t Regional dynamic carbon emission factors for different time periods; is the load power of node i in period t, is the carbon emission factor of node i, and U is the set of nodes within the coverage of the regional power grid; Indicated in t Dynamic correction factor for the time period.
[0019] Optionally, the dynamic correction factor The calculation formula is as follows: , In the formula, Indicates the total number of users in the target industry within the monitoring area; Indicated in t The number of high energy-consuming users in a time period, wherein the high energy-consuming users are business units whose electricity consumption exceeds a set power consumption threshold.
[0020] In a third aspect, the present invention provides a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of any one of the methods described in the first aspect of the present invention.
[0021] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect of the present invention.
[0022] The beneficial effects of the present invention are as follows: 1. In view of the problems that traditional carbon metering methods require statistical analysis of regional energy consumption types and the consumption of various energy sources, and have high statistical costs and low computational efficiency, the present invention uses multivariate linear autoregression to establish the relationship between electric energy consumption and the consumption of other energy sources. The model is dynamically updated while calculating the consumption of other energy sources by calculating the power consumption. The constructed regional dynamic power consumption-energy consumption model can reflect the changing trends of other energy consumption by power consumption alone, thereby improving the efficiency of carbon metering and reducing the cost and complexity of carbon metering.
[0023] 2. The regional dynamic carbon emission factor constructed by the present invention not only takes into account the fairness of spatial differences and the impact of the energy structure on the power generation side, but also fully considers the impact of users' peak electricity consumption in different time periods. By introducing a dynamic correction factor to correct the carbon emission factor, the problem of low calculation accuracy of the traditional carbon emission factor is solved, and the accuracy of carbon measurement is further improved.
[0024] 3. The electricity-carbon coupling model constructed by the present invention is based on the electricity consumption-energy consumption model and is combined with the regional dynamic carbon emission factor. The present invention can monitor the total amount of regional carbon emissions only by monitoring the regional electricity consumption at the power grid end, thereby greatly improving the efficiency of regional carbon emission measurement.
[0025] 4. Experimental results show that compared with traditional calculation methods, the present invention is more efficient, more reliable, and more adaptable. It avoids the complexity of traditional methods that rely on long-term statistical tracking of various energy consumptions and has important practical significance. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a schematic diagram of the process of the regional carbon emission monitoring method in the present invention; Figure 2 It is a schematic diagram of the principle of the power consumption-energy consumption model in the present invention; Figure 3 A schematic diagram of the process of establishing a regional dynamic power consumption-energy consumption model in the present invention; Figure 4 A schematic diagram of the process of establishing an electric-carbon coupling model in the present invention; Figure 5 This is a graph showing changes in energy consumption of non-ferrous metal smelting and rolling industries from 2012 to 2020 in the present invention; Figure 6 To calculate the carbon emissions of non-ferrous metal smelting and rolling industries from 1988 to 2023 using the electric-carbon coupling model of the present invention; Figure 7 This is a comparison chart of the carbon emission calculation results of the electric-carbon coupling model of the present invention and the traditional model; Figure 8 A comparison chart of carbon emission calculation results combining the traditional dynamic carbon emission factor model with the traditional model; Fig. 9 This is a structural principle block diagram of the regional carbon emission monitoring device in the present invention. DETAILED DESCRIPTION
[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in the present invention are only part of the embodiments of the present invention, not all of the embodiments. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.
[0028] Embodiment 1: Reference Figure 1 The embodiment of the present invention provides a method for monitoring regional carbon emissions, which specifically includes the following steps: S1. Collect historical consumption data and grid data of various energy sources in the target industry in the monitored area; In this embodiment, various energy consumption data within a period of time in the carbon metering monitoring area are collected, such as the consumption of electricity, coal, coke, crude oil, gasoline, kerosene, diesel, fuel oil and / or natural gas, and the data of the first 2 / 3 of the time length are taken as the training set, and the remaining data are used as the test set.
[0029] The collected grid data include voltage, current, active power and reactive power at the power generation side and the user side.
[0030] Furthermore, a data interpolation algorithm based on the GAN generative adversarial network is used to replace outliers and supplement missing values in the collected historical consumption data of various energy sources and power grid data.
[0031] S2. Based on the historical consumption data of each energy source, a regional dynamic electricity consumption-energy consumption model is established using multiple linear regression; Research has found that in the same region, the same type of high-energy-consuming enterprises have stability in their production processes and product types over a certain time dimension, so there is a relatively stable correlation between the amounts of energy consumed in the entire production process; analyzing the relationship between the consumption of various energy sources is helpful to predict and analyze the consumption of other energy sources through the consumption trend of one energy, and to simplify the analysis of complex regional energy consumption types.
[0032] In this embodiment, according to the energy consumption structure of the target industry being studied, the consumption of various energy sources such as electricity, natural gas, coal, steam and fuel oil is further counted; the relationship between the company's electricity consumption in previous years and other energy consumption is analyzed, and combined with the characteristics of the company's industrial process, a multivariate linear regression model is used to establish a functional relationship between electricity consumption and other energy consumption, and further establish an electricity consumption-energy model; after constructing the electricity consumption-energy model, all energy consumption can be obtained through the company's electricity consumption, achieving the purpose of reflecting energy consumption from electricity consumption. The principle of constructing the electricity consumption-energy model is as follows: Figure 2As shown. The multiple linear regression model has the advantage of fully considering the effect of each independent variable on the dependent variable, and can more comprehensively explain the changes in the dependent variable. According to the principle of multiple linear regression, the model is constructed using formula (1): (1) In the formula, is the constant term in the equation, b p For the p Independent variables x p The partial regression coefficient of .
[0033] In order to quickly obtain the energy consumption other than electricity required for carbon measurement, the initial regression model system of electricity consumption and various energy consumption is established as shown in formula (2). In the model, electricity consumption is used as the independent variable and various energy consumption is used as the dependent variable: (2) In the formula, Indicates the amount of electrical energy consumed. Represents the dimension of the data, Indicates The amount of energy consumed, Indicates the number of types of energy other than electrical energy, Respectively represent The first and second fitting coefficients of the regression model of the energy source.
[0034] Reference Figure 3 As shown, in order to solve the first and second fitting coefficients in formula (2), the steps of establishing the final regional dynamic power consumption-energy consumption model include: Step a: Divide the collected historical consumption data of each energy source into a training set and a test set; The first 2 / 3 of the time length of the data is taken as the training set, and the rest of the data is taken as the test set.
[0035] Step b: Perform multiple linear regression modeling on the electricity consumption and other energy consumption respectively to obtain the initial regression model of each energy, such as formula (2); Step c, selecting multiple groups of data from the training set, and training the initial regression model of each energy source respectively; Step d: Based on the test set, the fitting errors of each regression model after training are calculated respectively; if the fitting error is less than the set threshold, the corresponding regression model is output (according to the fitting coefficient obtained by training); otherwise, the process returns to step c until the fitting errors of all regression models meet the requirements; In this embodiment, the mean square error between the fitted value and the true value is used as an indicator to determine whether the model is accurate. Y MSE(n)<W When , the model meets the fitting requirements; the calculation formula of the fitting error is as follows: (3) In the formula, Y MSE(n) Indicates The fitting error of the regression model for the energy source, =1,2……; L represents the data dimension of the test set, Indicates The regression model of energy i The fitting results of the input samples are Indicates i The actual value of energy consumption corresponding to the fitting result is W To set the threshold.
[0036] Step e: Combining the regression models corresponding to the energy sources output in step d to form a regional dynamic power consumption-energy consumption model.
[0037] It is particularly noted that in order to further improve the fitting accuracy of the power consumption-energy consumption model, the present invention needs to dynamically update the model every set period (one month in this embodiment), add the calculation results of the model in the previous period to the training set to retrain and update the model, and enhance the model. Therefore, in a preferred but non-limiting embodiment, the step of establishing a regional dynamic power consumption-energy consumption model also includes: Step f, updating the regional dynamic power consumption-energy consumption model according to the set cycle, that is, adding the fitting results of the model using the power consumption to other energy consumption in the previous cycle into the training set to retrain the model, and updating the regional dynamic power consumption-energy consumption model in the current cycle.
[0038] S3. Calculate the power flow of the collected grid data to construct a regional dynamic carbon emission factor. The specific steps include: Step 3.1: Calculate the carbon flow rate of each branch of the regional power grid per unit time along with the branch flow rate using formula (4): : (4) In the formula, is the branch flow, Monitoring period.
[0039] Step 3.2: Based on the branch carbon flow rate , calculate the carbon flow rate and active power of each branch The ratio is the carbon flow density of the branch : (5) Step 3.2: Based on the definition of the node carbon emission factor, i Carbon emission factor The calculation formula is as follows: (6) Where: There is a flow into the node i The branch set of For branch s exist t Active power in the time period, For the s The carbon flow density of the branch, For the v The power generation capacity of each generator set, For the v Generator sets in t Carbon emission factor for the period.
[0040] Step 3.3: According to formula (6), the nodes in the regional power grid topology are obtained. t Matrix of carbon emission factors for each period The expression is as follows: (7) in, express t Regional node carbon emission factor for the period, Indicates the total number of user nodes.
[0041] Step 3.4: According to the above formula, the carbon emission factor of each node in the system is obtained. In order to balance the spatial differences of the node carbon emission factors, the node carbon emission factor obtained by formula (7) is multiplied by the spatial average node carbon potential to obtain the regional initial carbon emission factor: for: (8) In the formula, For Node i exist t The load power of the time period, For Node i The carbon emission factor, U is the node set within the coverage of the regional power grid; In order to consider the impact of the dynamic carbon emission factor on the power consumption of power grid users in different time periods, the initial carbon emission factor is adjusted by combining the dynamic correction factor. After correction, the final expression of regional dynamic carbon emission factor is as follows: (9) In the formula, Indicated in t Regional dynamic carbon emission factors for different time periods; Indicated in t The dynamic correction factor of the time period is calculated as follows: (10) In the formula, Indicates the total number of users in the target industry within the monitoring area; Indicated in t The number of high energy consumption users in the time period, wherein the high energy consumption users are those whose power consumption exceeds a set power consumption threshold; In this embodiment, an enterprise unit with a monthly electricity consumption of more than 1000 kWh is defined as a high energy consumption user. The dynamic correction factor is dynamically updated every month. When the number of high energy consumption users is 0, the dynamic correction factor is is 1, when a high energy consumption user appears in a certain period of time, The regional carbon emission factors under normal circumstances will be corrected.
[0042] S4. Combining the regional dynamic electricity consumption-energy consumption model and the regional dynamic carbon emission factor, constructing an electricity-carbon coupling model integrating carbon emission measurement of various energy sources; It is further explained that regional carbon emissions are generally divided into two parts: one is the carbon emissions generated by the power grid, and the other is the carbon emissions generated by energy consumption other than electricity. The construction process of the regional dynamic electricity-carbon coupling model is as follows: Figure 4 As shown in the figure; Carbon emissions from consuming coal, coke, crude oil, gasoline, kerosene, diesel, fuel oil and natural gas in addition to electricity It can be expressed by formula (11): (11) (12) (13) In the formula, It represents the sum of carbon emissions generated by all energy consumption except electricity; Represents the carbon emission factor matrix of each energy source except electricity, Indicates n The carbon emission factor of each energy source is determined by an authoritative organization; Represents the consumption matrix of each energy source, Indicates n The amount of energy consumed.
[0043] Regional carbon emissions As shown in formula (14), it is composed of carbon emissions generated by the grid and carbon emissions generated by other energy consumption except electricity: (14) In the formula, It represents the total carbon emissions of the target industry in the monitoring area during period t; Represents enterprise users m exist t Power consumption during the time period; Indicates the monitoring time interval.
[0044] According to the power consumption-energy consumption model, the other energy consumption in the region can be obtained as follows: , , , (15) in, is the energy consumption matrix in formula (13), is the energy consumption calculated in the power consumption-energy consumption model of formula (2).
[0045] Combining equations (2), (13) and (14), the final expression of the electricity-carbon coupling model integrating the carbon emission measurements of various energy sources is as follows: (16) S5. Obtain the real-time power consumption of the target industry in the region, input the real-time power consumption into the electricity-carbon coupling model (16) for measurement, and output the monitoring results of its carbon emissions.
[0046] It should be noted that the method provided in the embodiment of the present invention is applicable to carbon emission monitoring of various industries within the required research area. In order to verify the applicability of the model, the following experimental analysis is carried out using the non-ferrous metal smelting and rolling industry as an example to further verify the effectiveness of the regional carbon emission monitoring provided by the present invention.
[0047] like Figure 5 As shown in the figure, the energy consumption of non-ferrous metal smelting and rolling industry from 2012 to 2020 is calculated by the National Bureau of Statistics. From the changes in the consumption of various energy sources, it can be seen that coal, natural gas and electricity consumption are increasing year by year, while the consumption of coke, crude oil, gasoline, kerosene, diesel and fuel oil is decreasing. By the method provided by the present invention, the historical data of various energy sources of non-ferrous metal smelting and rolling industry from 1988 to 2012 are used to train the electric-carbon coupling model, and the electricity consumption data of non-ferrous metal smelting and rolling industry from 2012 to 2020 are input into the model to obtain the trend of carbon emissions in the industry from 2012 to 2020. The results are as follows: Figure 6 shown.
[0048] In order to verify the accuracy of the model of the present invention, the traditional carbon emission factor method (traditional model) is used to calculate the trend of carbon emissions from 2012 to 2020, and the results are compared with the results of the electric-carbon coupling model of the present invention which only calculates the total carbon emissions of the region by electricity consumption. Figure 7 As shown, from Figure 7 It can be seen that the results of the electric-carbon coupling model of the present invention are roughly consistent with the traditional carbon emission factor method, and the changing trends of the two are also roughly the same. This result verifies the effectiveness of the model.
[0049] Referring to Figure 8, the carbon measurement comparison results of the traditional dynamic carbon emission factor model that does not consider the impact of user peak electricity consumption in different time periods and the traditional carbon emission factor method (traditional model) are shown in this embodiment. Figure 7 The electric-carbon coupling model of the present invention is Figure 8 The measurement errors of the traditional dynamic carbon emission factor model are summarized in Table 1. From the data results in Table 1, it can be seen that the electric-carbon coupling model after the dynamic correction factor is introduced to correct the carbon emission factor in the present invention has higher accuracy and smaller calculation error.
[0050] Table 1 Error comparison between the electricity-carbon coupling model and the traditional dynamic carbon emission factor model Error Year 2012 2013 2014 2015 2016 2017 2018 2019 2020 Error of the electric-carbon coupling model 0．052% 0．091% 0．053% 0．079% 0．014% 0．171% 0．050% 0．121% 0．116% Error of traditional dynamic carbon emission factor model 7．992% 5．624% 7．146% 9．579% 1．795% 0．171% 0．050% 9．781% 7．949% The beneficial effects of the present invention are as follows: 1. In view of the problems that traditional carbon metering methods require statistical analysis of regional energy consumption types and the consumption of various energy sources, and have high statistical costs and low computational efficiency, the present invention uses multivariate linear autoregression to establish the relationship between electric energy consumption and the consumption of other energy sources. The model is dynamically updated while calculating the consumption of other energy sources by calculating the power consumption. The constructed regional dynamic power consumption-energy consumption model can reflect the changing trends of other energy consumption by power consumption alone, thereby improving the efficiency of carbon metering and reducing the cost and complexity of carbon metering.
[0051] 2. The regional dynamic carbon emission factor constructed by the present invention not only takes into account the fairness of spatial differences and the impact of the energy structure on the power generation side, but also fully considers the impact of users' peak electricity consumption in different time periods. By introducing a dynamic correction factor to correct the carbon emission factor, the problem of low calculation accuracy of the traditional carbon emission factor is solved, and the accuracy of carbon measurement is further improved.
[0052] 3. The electricity-carbon coupling model constructed by the present invention is based on the electricity consumption-energy consumption model and is combined with the regional dynamic carbon emission factor. The present invention can monitor the total amount of regional carbon emissions only by monitoring the regional electricity consumption at the power grid end, thereby greatly improving the efficiency of regional carbon emission measurement.
[0053] 4. Experimental results show that compared with traditional calculation methods, the present invention is more efficient, more reliable, and more adaptable. It avoids the complexity of traditional methods that rely on long-term statistical tracking of various energy consumptions and has important practical significance.
[0054] Embodiment 2: like Fig. 9 As shown, the present invention provides a regional carbon emissions monitoring device, which is used to implement the steps of the method in the above embodiment 1, and the device specifically includes: The data collection module is used to collect the historical consumption data of various energy sources and grid-end data in the target industry in the monitored area; Establish a dynamic power consumption-energy consumption model module, which is used to establish a regional dynamic power consumption-energy consumption model based on the historical consumption data of each energy source using multiple linear regression; Build a dynamic carbon emission factor module to calculate the power flow of the collected grid data to build a regional dynamic carbon emission factor; Constructing an electricity-carbon coupling model, which is used to combine the regional dynamic electricity consumption-energy consumption model and the regional dynamic carbon emission factor to construct an electricity-carbon coupling model that integrates the carbon emission measurement of various energy sources; The carbon emission monitoring module is used to obtain the real-time power consumption of the target industry in the region, input the real-time power consumption into the electricity-carbon coupling model for measurement, and output the monitoring results of its carbon emissions.
[0055] In this embodiment, the expression of the regional dynamic power consumption-energy consumption model is as follows: , In the formula, Indicates the amount of electrical energy consumed. Represents the dimension of the data, Indicates The amount of energy consumed, Indicates the number of types of energy other than electrical energy, Respectively represent The first and second fitting coefficients of the regression model of the energy source.
[0056] As an embodiment of the present invention, the expression of the regional dynamic carbon emission factor is as follows: , In the formula, Indicated in t Regional dynamic carbon emission factors for different time periods; is the load power of node i in period t, is the carbon emission factor of node i, and U is the set of nodes within the coverage of the regional power grid; Indicated in t Dynamic correction factor for the time period.
[0057] Furthermore, the dynamic correction factor The calculation formula is as follows: .
[0058] In the formula, Indicates the total number of users in the target industry within the monitoring area; Indicated in t The number of high energy-consuming users in a time period, wherein the high energy-consuming users are business units whose electricity consumption exceeds a set power consumption threshold.
[0059] The regional carbon emission monitoring device provided in the embodiment of the present invention and the regional carbon emission monitoring method provided in Example 1 are based on the same technical concept, and can produce the beneficial effects as described in Example 1. For the contents not described in detail in this embodiment, please refer to Example 1.
[0060] Embodiment three: A terminal provided by an embodiment of the present invention includes a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instruction to execute the steps of the method according to any one of the first embodiments.
[0061] Embodiment 4: An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of any method described in Embodiment 1 are implemented.
[0062] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.
[0063] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0064] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0065] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.
[0066] 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, and any modifications or equivalent replacements that do 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 method for monitoring regional carbon emissions, characterized in that the method include: Collect historical consumption data and grid data of various energy sources in the target industries in the monitored area; Based on the historical consumption data of each energy source, a regional dynamic electricity consumption-energy consumption model is established using multiple linear regression; Perform power flow calculations on the collected grid data to construct regional dynamic carbon emission factors; Combining the regional dynamic electricity consumption-energy consumption model and the regional dynamic carbon emission factor, an electricity-carbon coupling model integrating the carbon emission measurement of various energy sources is constructed; The real-time power consumption of the target industry in the region is obtained, and the real-time power consumption is input into the electricity-carbon coupling model for measurement, and the monitoring results of its carbon emissions are output.
2. The method for monitoring regional carbon emissions according to claim 1, characterized in that: The historical consumption data of each energy source includes the consumption of electricity, coal, coke, crude oil, gasoline, kerosene, diesel, fuel oil and / or natural gas by the target industry within a set historical time period; The grid-side data includes voltage, current, active power and reactive power at the power generation side and the user side.
3. The method for monitoring regional carbon emissions according to claim 1, characterized in that: The step of establishing a regional dynamic power consumption-energy consumption model by using multiple linear regression includes: Step a: Divide the collected historical consumption data of each energy source into a training set and a test set; Step b, respectively performing multiple linear regression modeling on the electricity consumption and the other energy consumption to obtain the initial regression model of each energy; Step c, selecting multiple groups of data from the training set, and training the initial regression model of each energy source respectively; Step d: Based on the test set, the fitting errors of each regression model after training are calculated respectively; if the fitting error is less than the set threshold, the corresponding regression model is output; otherwise, the process returns to step c until the fitting errors of all regression models meet the requirements; Step e: Combining the regression models corresponding to the energy sources output in step d to form a regional dynamic power consumption-energy consumption model.
4. The method for monitoring regional carbon emissions according to claim 3, characterized in that: After step e, the method further comprises: Step f, updating the regional dynamic power consumption-energy consumption model according to the set cycle, that is, adding the fitting results of the model using the power consumption to other energy consumption in the previous cycle to the training set to retrain the model, and updating the regional dynamic power consumption-energy consumption model in the current cycle.
5. The method for monitoring regional carbon emissions according to claim 1 or 4, characterized in that: The expression of the regional dynamic power consumption-energy consumption model is as follows: , In the formula, Indicates the amount of electrical energy consumed. Represents the dimension of the data, Indicates The amount of energy consumed, Indicates the number of types of energy other than electrical energy, Respectively represent The first and second fitting coefficients of the regression model of the energy source.
6. The method for monitoring regional carbon emissions according to claim 3, characterized in that: The calculation formula of the fitting error in step d is as follows: , In the formula, Y MSE(n) Indicates The fitting error of the regression model for the energy source, =1,2……; L represents the data dimension of the test set, Indicates The regression model of energy i The fitting results of the input samples are Indicates i The actual value of energy consumption corresponding to the fitting result.
7. The method for monitoring regional carbon emissions according to claim 1, characterized in that: The method also includes: using a data interpolation algorithm based on the GAN generative adversarial network to replace abnormal values and supplement missing values in the collected historical consumption data of various energy sources and power grid-end data.
8. The method for monitoring regional carbon emissions according to claim 5, characterized in that: The expression of the regional dynamic carbon emission factor is as follows: , In the formula, Indicated in t Regional dynamic carbon emission factors for different time periods; is the load power of node i in period t, is the carbon emission factor of node i, and U is the set of nodes within the coverage of the regional power grid; Indicated in t Dynamic correction factor for the time period.
9. The method for monitoring regional carbon emissions according to claim 8, characterized in that: The dynamic correction factor The calculation formula is as follows: , In the formula, Indicates the total number of users in the target industry within the monitoring area; Indicated in t The number of high energy-consuming users in a time period, wherein the high energy-consuming users are business units whose electricity consumption exceeds a set power consumption threshold.
10. The method for monitoring regional carbon emissions according to claim 9, characterized in that: The expression of the electric-carbon coupling model is as follows: , In the formula, It represents the total carbon emissions of the target industry in the monitoring area during period t; Represents enterprise users m exist t Power consumption during the time period; Indicates the monitoring time interval, Represents the carbon emission factor matrix of each energy source except electricity; Represents the consumption matrix of various energy sources except electric energy; where: , … .
11. A regional carbon emission monitoring device, running the regional carbon emission monitoring method according to any one of claims 1 to 10, characterized in that: The device includes: The data collection module is used to collect the historical consumption data of various energy sources and grid data in the target industry in the monitored area; Establish a dynamic power consumption-energy consumption model module, which is used to establish a regional dynamic power consumption-energy consumption model based on the historical consumption data of each energy source using multiple linear regression; Build a dynamic carbon emission factor module to calculate the power flow of the collected grid data to build a regional dynamic carbon emission factor; Constructing an electricity-carbon coupling model, which is used to combine the regional dynamic electricity consumption-energy consumption model and the regional dynamic carbon emission factor to construct an electricity-carbon coupling model that integrates the carbon emission measurement of various energy sources; The carbon emission monitoring module is used to obtain the real-time power consumption of the target industry in the region, input the real-time power consumption into the electricity-carbon coupling model for measurement, and output the monitoring results of its carbon emissions.
12. The regional carbon emission monitoring device according to claim 11, characterized in that: The expression of the regional dynamic power consumption-energy consumption model is as follows: , In the formula, Indicates the amount of electrical energy consumed. Represents the dimension of the data, Indicates The amount of energy consumed, Indicates the number of types of energy other than electrical energy, Respectively represent The first and second fitting coefficients of the regression model of the energy source.
13. The regional carbon emission monitoring device according to claim 11, characterized in that: The expression of the regional dynamic carbon emission factor is as follows: , In the formula, Indicated in t Regional dynamic carbon emission factors for different time periods; is the load power of node i in period t, is the carbon emission factor of node i, and U is the set of nodes within the coverage of the regional power grid; Indicated in t Dynamic correction factor for the time period.
14. The regional carbon emission monitoring device according to claim 13, characterized in that: The dynamic correction factor The calculation formula is as follows: 。 15. In the formula, Indicates the total number of users in the target industry within the monitoring area; Indicated in t The number of high energy-consuming users in a time period, wherein the high energy-consuming users are business units whose electricity consumption exceeds a set power consumption threshold.
16. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-10.
17. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.