Energy power carbon emission monitoring analysis modeling method and device

Abstract

This invention discloses a method and apparatus for monitoring, analyzing, and modeling carbon emissions in the energy and power sector, specifically relating to the field of carbon emissions in the power industry. It addresses the problem that existing carbon emission analyses typically focus on specific regions, resulting in lengthy analyses and an inability to directly predict overall carbon emission trends. The method involves dividing the carbon emission regulatory area into several smaller regulatory regions, calculating the carbon emission intensity of each region, determining whether the intensity meets standards, and marking and issuing warnings for regions that do not meet the standards. This invention calculates the carbon emission intensity of each region, filters out regions that do not meet the standards, performs cluster analysis on different regions to filter out regions outside the standard range and issue alarms, and finally combines the status of all regions to predict and evaluate the overall region, facilitating the formulation of relevant optimization policies.

Description

Technical Field

[0001] This invention relates to the field of carbon emission technology in the power industry, and more specifically, to a method and apparatus for monitoring, analyzing and modeling carbon emissions from energy and power. Background Technology

[0002] Carbon emissions are one of the major greenhouse gases that accelerate climate change and lead to global climate instability, including more frequent extreme weather events such as torrential rains, floods, droughts, and forest fires, severely impacting human life, agricultural production, and water resources. Air pollution is also a serious problem; controlling carbon emissions can reduce air pollution and related health problems. Therefore, controlling carbon emissions is one of the necessary means to protect the planet and human health.

[0003] To meet carbon emission targets, it is necessary to build a database of carbon emissions for each region and analyze the carbon emission situation of each region based on the data in the database. However, due to the different conditions in each region, the existing carbon emission analysis is usually a targeted analysis of a specific region, which takes a long time and cannot directly judge the overall carbon emission trend. Summary of the Invention

[0004] To overcome the aforementioned deficiencies in the prior art, embodiments of the present invention provide an energy and power carbon emission monitoring, analysis, and modeling method and apparatus. First, by calculating the carbon emission intensity of each region, regions that do not meet the standards are screened out and given an early warning. Then, different regions are clustered according to their respective attribute states to screen out regions that are not within the standard range and issue an alarm. Finally, by combining the states of all regions, the overall region is predicted and evaluated, which facilitates the formulation of relevant optimization policies to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for monitoring, analyzing, and modeling carbon emissions from energy and electricity includes the following steps:

[0007] Step S1: Divide the carbon emission regulatory area into several carbon emission regulatory sub-areas, calculate the carbon emission intensity of each carbon emission regulatory sub-area, determine whether the carbon emission intensity of each carbon emission regulatory sub-area meets the standard, and mark and warn the carbon emission regulatory sub-areas that do not meet the standard.

[0008] Step S2: Calculate the carbon emission evaluation coefficient for each carbon emission regulatory area that meets the standard based on the area size information, population size information and industrial structure information, and cluster each carbon emission regulatory area based on the carbon emission evaluation coefficient to determine the carbon emission standard for each carbon emission regulatory area.

[0009] Step S3: Analyze and process the actual carbon emissions of each category of carbon emission monitoring areas after clustering, screen out carbon emission monitoring areas that do not meet the carbon emission standards, and mark and warn them.

[0010] Step S4: Obtain early warning information within the carbon emission regulatory area, combine it with population flow information within the carbon emission regulatory area, determine future carbon emission trends, and complete carbon emission database modeling and analysis.

[0011] In a preferred embodiment, in step S2, the present invention uses Logistic regression analysis to calculate the carbon emission evaluation coefficients for each carbon emission monitoring sub-region. The specific process is as follows:

[0012] Before determining the carbon emission assessment coefficients, all the main factors affecting carbon emissions are first set as the set x, and each main factor is represented as {x1, x2, ..., x...}. n}, where n is the number of major influencing factors, and n is a positive integer. The exponential expression for the Logistic regression analysis method is:

[0013]

[0014] In the formula, C is the carbon emission evaluation coefficient, Q is a constant term, representing the adjustment required when all representative major influencing factors are absent, i.e., Q represents the coefficients of all minor influencing factors {x1, x2, ..., x...}. n} represents the number of main influencing factors, {g1, g2, ..., g n} represents the regression coefficients of each major influencing factor.

[0015] In a preferred embodiment, in step S2, after calculating and obtaining the carbon emission evaluation coefficients of each carbon emission regulatory sub-region, the k-means clustering algorithm is used to perform cluster analysis on the carbon emission evaluation coefficients of each carbon emission regulatory sub-region, and the carbon emission regulatory sub-regions are clustered at the cluster centers through cluster analysis to obtain K carbon emission standard clusters.

[0016] In a preferred embodiment, the specific steps for performing cluster analysis on the carbon emission assessment coefficients of each carbon emission monitoring sub-region using the k-means clustering algorithm in step S2 are as follows:

[0017] Step S21: Determine the number K of cluster centers for the K-means algorithm using the silhouette coefficient method;

[0018] Step S22: Use the KMEANS algorithm to cluster the carbon emission evaluation coefficients of each carbon emission regulatory area to obtain K carbon emission standard clusters.

[0019] In a preferred embodiment, in step S2, after determining the cluster centers of each carbon emission regulatory sub-region, the carbon emission standards of each carbon emission regulatory sub-region are determined according to the carbon emission standards corresponding to the cluster centers.

[0020] In a preferred embodiment, in step S3, after obtaining K carbon emission standard clusters through clustering, the actual carbon emissions of each carbon emission monitoring sub-region within the K carbon emission standard clusters are compared with the carbon emission standard corresponding to the cluster center:

[0021] If the actual carbon emissions of a carbon emission monitoring area exceed the corresponding carbon emission standard, the carbon emission monitoring area will be marked as a high-carbon emission monitoring area and an alarm will be triggered.

[0022] In a preferred embodiment, in step S4, the ratio of high-carbon emission regulatory areas to the total carbon emission regulatory areas is calculated and denoted as RR. The population flow value within the carbon emission regulatory area is obtained and denoted as PM. The future risk coefficient RC is calculated using a formula based on the population flow value PM and the ratio of high-carbon emission regulatory areas to the total carbon emission regulatory areas RR. The specific calculation expression is as follows.

[0023] RC = ln(αRR + βPM + 1)

[0024] In the formula, α and β are the preset proportional coefficients of the ratio RR of high carbon emission regulatory areas to the total carbon emission regulatory areas and the population mobility value PM, respectively, and α>β>0.

[0025] In a preferred embodiment, in step S4, the future risk coefficient RC is compared with a standard risk threshold:

[0026] If the future risk coefficient RC is greater than or equal to the standard risk threshold, the carbon emission regulatory area will be marked as a high-risk area and an early warning will be issued.

[0027] If the future risk coefficient RC is less than the standard risk threshold, the carbon emission regulatory area will be marked as a low-risk area.

[0028] An energy and power carbon emission monitoring, analysis and modeling device includes: a data acquisition and analysis module, a clustering evaluation module, an early warning module and a carbon emission trend prediction module;

[0029] The data acquisition and analysis module divides the carbon emission regulatory area into several carbon emission regulatory sub-areas, calculates the carbon emission intensity of each carbon emission regulatory sub-area, and determines whether the carbon emission intensity of each carbon emission regulatory sub-area meets the standards.

[0030] The clustering evaluation module calculates the carbon emission evaluation coefficient for the carbon emission regulatory micro-regions that meet the standards, and clusters each carbon emission regulatory micro-region according to the carbon emission evaluation coefficient to determine the carbon emission standards for each carbon emission regulatory micro-region.

[0031] The early warning module is used to analyze and process the actual carbon emissions of each clustered category of carbon emission monitoring area and to mark and issue early warnings.

[0032] The carbon emission trend prediction module acquires early warning information within the carbon emission regulatory area, combines it with population flow information within the carbon emission regulatory area to determine future carbon emission trends, and completes carbon emission database modeling and analysis.

[0033] In a preferred embodiment, the clustering evaluation module calculates the carbon emission evaluation coefficient for carbon emission regulatory micro-regions that meet the standards. The specific process is as follows:

[0034] Before determining the carbon emission assessment coefficients, all the main factors affecting carbon emissions are first set as the set x, and each main factor is represented as {x1, x2, ..., x...}. n}, where n is the number of major influencing factors, and n is a positive integer. The exponential expression for the Logistic regression analysis method is:

[0035]

[0036] In the formula, C is the carbon emission evaluation coefficient, Q is a constant term, representing the adjustment required when all representative major influencing factors are absent, i.e., Q represents the coefficients of all minor influencing factors {x1, x2, ..., x...}. n} represents the number of main influencing factors, {g1, g2, ..., g n} represents the regression coefficients of each major influencing factor.

[0037] In a preferred embodiment, the clustering evaluation module calculates and obtains the carbon emission evaluation coefficients of each carbon emission regulatory sub-region, and then uses the k-means clustering algorithm to perform cluster analysis on the carbon emission evaluation coefficients of each carbon emission regulatory sub-region. Through cluster analysis, each carbon emission regulatory sub-region is clustered at a cluster center to obtain K carbon emission standard clusters.

[0038] In a preferred embodiment, the specific steps of the cluster evaluation module in performing cluster analysis on the carbon emission evaluation coefficients of each carbon emission monitoring sub-region using the k-means clustering algorithm are as follows:

[0039] The number of cluster centers K in the K-means algorithm is determined using the silhouette coefficient method.

[0040] The KMEANS algorithm was used to cluster the carbon emission evaluation coefficients of each carbon emission regulatory area to obtain K carbon emission standard clusters.

[0041] In a preferred embodiment, the cluster evaluation module determines the cluster centers of each carbon emission regulatory sub-region after identifying them, and then determines the carbon emission standards for each carbon emission regulatory sub-region based on the carbon emission standards corresponding to the cluster centers.

[0042] In a preferred embodiment, after obtaining K carbon emission standard clusters based on clustering, the early warning module compares the actual carbon emissions of each carbon emission monitoring area within the K carbon emission standard clusters with the carbon emission standard corresponding to the cluster center:

[0043] If the actual carbon emissions of a carbon emission monitoring area exceed the corresponding carbon emission standard, the carbon emission monitoring area will be marked as a high-carbon emission monitoring area and an alarm will be triggered.

[0044] In a preferred embodiment, the early warning module calculates the ratio of high-carbon emission monitoring areas to the total carbon emission monitoring areas and labels it as RR; obtains the population flow value within the carbon emission monitoring area and labels it as PM; and calculates the future risk coefficient RC based on the population flow value PM and the ratio of high-carbon emission monitoring areas to the total carbon emission monitoring areas RR using a formula. The specific calculation expression is as follows.

[0045] RC = ln(αRR + βPM + 1)

[0046] In the formula, α and β are the preset proportional coefficients of the ratio RR of high carbon emission regulatory areas to the total carbon emission regulatory areas and the population mobility value PM, respectively, and α>β>0.

[0047] In a preferred embodiment, the early warning module compares the future risk coefficient RC with a standard risk threshold:

[0048] If the future risk coefficient RC is greater than or equal to the standard risk threshold, the carbon emission regulatory area will be marked as a high-risk area and an early warning will be issued.

[0049] If the future risk coefficient RC is less than the standard risk threshold, the carbon emission regulatory area will be marked as a low-risk area.

[0050] The technical effects and advantages of the energy and power carbon emission monitoring, analysis and modeling method and device of the present invention are as follows:

[0051] This invention calculates the carbon emission intensity of each region, screens out and issues warnings for regions that do not meet the standards, then performs cluster analysis on different regions according to their respective attribute states, screens out regions that are not within the standard range and issues alarms, and finally combines the status of all regions to predict and evaluate the overall region, which is convenient for formulating relevant optimization policies.

[0052] This invention comprehensively calculates the carbon emission evaluation coefficients of each carbon emission monitoring area, and then clusters them according to the carbon emission evaluation coefficients and compares them with the corresponding carbon emission standards. This allows for a more accurate analysis of the carbon emission status of each carbon emission monitoring area and enables the marking and alarming. This avoids the drawback of existing carbon emission monitoring methods that require separate analysis of each monitoring area. It is faster and more convenient, and also allows for understanding the similarity of each carbon emission monitoring area, which facilitates subsequent adjustments to the overall structure within the carbon emission monitoring area.

[0053] This invention combines high-carbon emission monitoring areas with future population flow patterns to comprehensively analyze the carbon emission compliance risks of the monitored areas over a future period. Based on the actual carbon emission situation, it can make a more comprehensive prediction of the future and help relevant personnel to make overall optimizations and adjustments in advance when there are significant risks. Attached Figure Description

[0054] Figure 1 This is a flowchart of a carbon emission monitoring, analysis and modeling method for energy and electricity according to the present invention;

[0055] Figure 2 This is a schematic diagram of an energy and electricity carbon emission monitoring, analysis and modeling device according to the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0057] This invention provides a method for monitoring, analyzing, and modeling carbon emissions from energy and electricity. First, by calculating the carbon emission intensity of each region, regions that do not meet the standards are screened out and given an early warning. Then, different regions are clustered according to their respective attribute states to screen out regions that are not within the standard range and issue an alarm. Finally, by combining the states of all regions, the overall region is predicted and evaluated, which facilitates the formulation of relevant optimization policies, such as optimizing the energy structure and strengthening environmental protection measures.

[0058] It should be noted that the carbon emission regulatory area or carbon emission regulatory sub-area mentioned in this specification may represent multiple meanings. For example, the carbon emission regulatory area may be various cities, while the carbon emission regulatory sub-area may be the jurisdiction under each city. Or, for example, the carbon emission regulatory area may be the jurisdiction under each city, in which case the carbon emission regulatory sub-area may be the industrial parks under the jurisdiction, etc. There is no limitation here, and appropriate scenarios can be selected according to actual needs.

[0059] Example 1

[0060] Figure 1 A flowchart of a carbon emission monitoring, analysis, and modeling method for energy and electricity according to the present invention is provided, including the following steps:

[0061] Step S1: Divide the carbon emission regulatory area into several carbon emission regulatory sub-areas, calculate the carbon emission intensity of each carbon emission regulatory sub-area, determine whether the carbon emission intensity of each carbon emission regulatory sub-area meets the standard, and mark and warn the carbon emission regulatory sub-areas that do not meet the standard.

[0062] Step S2: Calculate the carbon emission evaluation coefficient for each carbon emission regulatory sub-region that meets the standard based on the sub-region size information, population size information, and industrial structure information. Then, cluster each carbon emission regulatory sub-region based on the carbon emission evaluation coefficient to determine the carbon emission standard for each carbon emission regulatory sub-region.

[0063] Step S3: Analyze and process the actual carbon emissions of each clustered carbon emission monitoring area, screen out carbon emission monitoring areas that do not meet the carbon emission standards, and mark and warn them.

[0064] Step S4: Obtain early warning information within the carbon emission regulatory area, combine it with population flow information within the carbon emission regulatory area, determine future carbon emission trends, and complete carbon emission database modeling and analysis.

[0065] Specifically, since the actual carbon emission regulatory area is large and the industrial and energy structures of its various regions are not similar, dividing it into several smaller regions for targeted analysis is more conducive to accurately grasping the carbon emission regulatory area. Therefore, in step S1, the carbon emission regulatory area is first divided into several smaller carbon emission regulatory regions.

[0066] Carbon emission intensity refers to the amount of carbon dioxide (CO2) emitted per unit of GDP (Gross Domestic Product), usually measured in tons of CO2 equivalent per 10,000 yuan of GDP. It reflects the relationship between economic development and carbon emissions, specifically the amount of energy consumed and carbon emissions emitted per unit of GDP. A decrease in carbon emission intensity means that economic development can be achieved at the cost of less carbon emissions, and also implies that the economic development of a region or country is more sustainable. Therefore, carbon emission intensity has certain indicative significance. The carbon emission intensity of each carbon emission monitoring area is calculated and compared with the critical carbon emission intensity. If the carbon emission intensity of a monitoring area is greater than the critical carbon emission intensity, it indicates that the amount of CO2 emitted per unit of GDP in that monitoring area exceeds the standard and does not meet low-carbon requirements. In this case, the monitoring area is marked as a high-carbon emission monitoring area, and an alarm is triggered, prompting relevant personnel to make subsequent optimizations and adjustments.

[0067] It should be noted that carbon emission intensity is calculated as a weighted average of the contribution of each industry to GDP and the corresponding carbon emissions in the carbon emission regulatory area. The specific calculation can be performed according to the following steps:

[0068] Step 11: Calculate the proportion of each industry's output value to GDP in the carbon emission regulatory area. For example, assuming that the output value of a city's primary industry is 10 million yuan, the output value of its secondary industry is 50 million yuan, the output value of its tertiary industry is 90 million yuan, and the total GDP is 150 million yuan, then the output value of the primary industry accounts for 6.67% (1000 / 15000), the output value of the secondary industry accounts for 33.33% (5000 / 15000), and the output value of the tertiary industry accounts for 60% (9000 / 15000).

[0069] Step S12: Calculate the carbon emissions for each industry. For example, assuming the carbon emissions of the primary industry in this region are 100 tons, the carbon emissions of the secondary industry are 500 tons, and the carbon emissions of the tertiary industry are 1000 tons, then the carbon emissions of the primary industry are 6.67 tons (1006.67%), the carbon emissions of the secondary industry are 166.67 tons (50033.33%), and the carbon emissions of the tertiary industry are 600 tons (1000*60%).

[0070] Step S13: Calculate the weighted average carbon emission intensity. Based on the data from steps S11 and S12, using the weighted average formula, the weighted average carbon emission intensity is: (Carbon emissions from the primary industry / Proportion of output value from the primary industry + Carbon emissions from the secondary industry / Proportion of output value from the secondary industry + Carbon emissions from the tertiary industry / Proportion of output value from the tertiary industry) / Total GDP. Substituting the values, we get: (6.670.0667 + 166.670.3333 + 6000.6) / 15000 = 0.0549 tons / 10,000 yuan.

[0071] In step S2, since the regional size, population size and industrial structure information of each carbon emission regulatory area that meets the carbon emission intensity standard may differ, the carbon emission standards for them will also differ. Therefore, in step S2, it is necessary to cluster each carbon emission regulatory area that meets the carbon emission intensity standard according to its respective attribute status in order to more accurately screen whether each carbon emission regulatory area meets the carbon emission requirements.

[0072] Specifically, regional scale information includes the land area of ​​each carbon emission monitoring sub-region. The larger the land area, the higher the corresponding carbon emission quota. Population scale information includes the population density of each carbon emission monitoring sub-region. A higher population density results in greater carbon dioxide emissions, thus requiring a higher carbon emission quota. Industrial structure information includes energy utilization information, industry type information, etc. Different industrial structures have different corresponding carbon emission quotas.

[0073] In an optional example, for ease of analysis, this invention uses Logistic regression analysis to calculate the carbon emission evaluation coefficients for each carbon emission regulatory sub-region, and performs cluster analysis based on the carbon emission evaluation coefficients.

[0074] Specifically, before determining the carbon emission assessment coefficient, all the main factors affecting carbon emissions are first set as the set x, and each main factor is represented as {x1, x2, ..., x...}. n}, where n is the number of major influencing factors, and n is a positive integer. The exponential expression for the Logistic regression analysis method is:

[0075]

[0076] In the formula, C is the carbon emission evaluation coefficient, Q is a constant term, that is, the adjustment range required when all representative major influencing factors are absent, and Q is the coefficient of all minor influencing factors {x1, x2, ..., x...} n} represents the number of main influencing factors, {g1, g2, ..., g n} represents the regression coefficients of each variable.

[0077] The carbon emission evaluation coefficient of this invention is calculated in the range of (0,1). The larger the carbon emission evaluation coefficient, the greater the impact of the carbon emission supervision area on the incremental carbon emissions. In this case, the carbon emission standard of the carbon emission supervision area should be increased.

[0078] The main factors influencing carbon emissions include, but are not limited to: whether the region is large, medium, or small; whether it is densely populated; whether clean energy is the primary energy source; and whether the secondary industry is the primary industry.

[0079] It should be noted that the criteria for determining whether an area is large, medium, or small vary depending on the specific scenario in which the carbon emission regulatory sub-region is defined. For example, if the carbon emission regulatory area is a district, and the carbon emission regulatory sub-region is each community, then the size of the area is determined based on the community size criteria. Conversely, if the carbon emission regulatory sub-region is each enterprise, then it is defined based on the enterprise's size criteria, which are not specifically defined here. Similarly, the definition of dense population also changes depending on the scenario in which the carbon emission regulatory sub-region is defined.

[0080] Those skilled in the art will readily recognize that the use of clean energy as a primary energy source is a crucial factor influencing carbon emissions and therefore requires separate consideration. Similarly, the secondary sector, namely industry, typically contributes the most to carbon emissions. This is because industrial production consumes vast amounts of energy, including fossil fuels, resulting in substantial carbon emissions. Therefore, industry as a contributing factor also needs to be considered separately.

[0081] In this embodiment, the value of the regression coefficient is set according to the impact of the main influencing factors on carbon emissions. When the main influencing factors lead to an increase in carbon emission standards, the regression coefficient g > 0; when the main influencing factors lead to a decrease in carbon emission standards, the regression coefficient g < 0.

[0082] It is obvious that the larger the region, the denser the population, and the more the secondary industry is the main industry, the higher the carbon emission standard should be. When clean energy is the main energy source, the carbon emission standard should be lower.

[0083] The logical components of the carbon emission evaluation coefficient C calculated in this invention are as follows: First, the indicators, i.e., the factors that lead to changes in carbon emission standards (in this invention, the impact of regional scale information, population scale information, and industrial structure information on carbon emission standards); second, the weights of these indicators, i.e., the proportion of each major influencing factor; and third, the calculation equations, i.e., the mathematical calculation process used to obtain the result, i.e., the carbon emission evaluation coefficient C obtained by calculating the indicators with their respective weights through the calculation equations.

[0084] The data from the specific environment obtained in the sample are transformed and processed into a data language that can be recognized by computer software. Secondly, these evaluation factors are analyzed using SPSS software to perform Logistic regression analysis, and factors and their weights that are significantly correlated with the results are screened out. Thirdly, the evaluation factors and weights are substituted into the Logistic regression equation for calculation, thereby obtaining the results.

[0085] Q is a constant term, and Q is the coefficient of all minor influencing factors. Specifically, the main influencing factors collected in this application are representative influencing factors. These main influencing factors have a significant impact on carbon emission standards. However, in the actual use of this application, there are other minor influencing factors that are not representative (such as the degree of urbanization, etc.) that also have an impact on carbon emission standards. This impact is relatively small. Therefore, the Logistic regression analysis method is modified by setting a constant term Q. When there are no representative main influencing factors, the carbon emission evaluation coefficient C is determined by the constant term Q.

[0086] It should be noted that the sample used in the Logistic regression analysis method of this invention can be adjusted and selected according to the actual carbon emission regulatory area. Furthermore, different calculated carbon emission evaluation coefficients correspond to different carbon emission standards, and the standard settings vary depending on the actual sample selection.

[0087] For example, if the carbon emission monitoring area is set as a factory, the carbon emission standards for various factories can be determined according to the Chinese national standard "Energy Consumption Limits per Unit Product of Industrial Enterprises".

[0088] In an optional example, if five levels of factory carbon emission standards are set, then the carbon emission standards for each carbon emission regulatory area, combined with the carbon emission assessment coefficient, are shown in the table below:

[0089] Carbon emission assessment coefficient Carbon emission standards ≥0.7999 Level 5 0.5999～0.7998 Level 4 0.3999～0.5998 Level 3 0.1999～0.3998 Level 2 0.0001～0.1998 Level 1

[0090] In the table, carbon emission standards 1 to 5 correspond to five different levels of carbon emission for factories, with level 5 being the highest.

[0091] It should be noted that since carbon emission standards change significantly with policy, this invention is only for illustrative purposes. Specific carbon emission standards are set according to actual circumstances and will not be elaborated upon here.

[0092] In step S2, after calculating and obtaining the carbon emission evaluation coefficients for each carbon emission regulatory sub-region, the k-means clustering algorithm is used to perform cluster analysis on the carbon emission standards of each carbon emission regulatory sub-region based on the carbon emission evaluation coefficients. The specific steps are as follows:

[0093] Step S21: Determine the number K of cluster centers for the K-means algorithm using the silhouette coefficient method;

[0094] Step S22: Use the KMEANS algorithm to cluster the data to obtain K carbon emission standard clusters.

[0095] It should be noted that the specific process of step S21 is as follows:

[0096] Step S211: Given a K value, use the KMEANS algorithm to cluster the data and calculate the silhouette coefficient of the carbon emission assessment coefficient for each carbon emission monitoring sub-region. The specific calculation expression is as follows:

[0097] S(i)=[b(i)-a(i)] / max{a(i),b(i)}

[0098] In the formula, S(i) is the profile coefficient, a(i) is the average distance between the carbon emission evaluation coefficient of each carbon emission regulatory sub-region and all other points in the same cluster, and b(i) is the minimum average distance between the carbon emission evaluation coefficient of each carbon emission regulatory sub-region and all other points in all other clusters.

[0099] Step S212: For each cluster, calculate the average profile coefficient of all carbon emission evaluation coefficients of the cluster to obtain the average profile coefficient of the cluster.

[0100] Step S213: Calculate the average of the average profile coefficients of all clusters to obtain the average profile coefficients under the current K value;

[0101] Step S214: Repeat the steps to calculate the average profile coefficient for different K values;

[0102] Step S215: Select the K value with the largest average profile coefficient as the final K value.

[0103] This allows for the clustering of various carbon emission regulatory areas into a single cluster center.

[0104] In step S3, after obtaining K carbon emission standard clusters through clustering, the actual carbon emissions of each carbon emission monitoring sub-region within the K carbon emission standard clusters are compared with the carbon emission standard corresponding to the cluster center to determine whether the carbon emissions of each carbon emission monitoring sub-region exceed the standard.

[0105] If the actual carbon emissions exceed the corresponding carbon emission standards, it indicates that the carbon emissions in the monitored area are exceeding the standards. The area will be marked as a high-carbon emission monitored area, and an alarm will be triggered to prompt relevant staff to make subsequent optimizations and adjustments.

[0106] This invention comprehensively calculates the carbon emission evaluation coefficients of each carbon emission monitoring area, and then clusters them according to these coefficients and compares them with the corresponding carbon emission standards. This allows for a more accurate analysis of the carbon emission status of each monitoring area and enables the marking and alarming of these areas. This avoids the drawback of existing carbon emission monitoring methods that require individual analysis of each monitoring area. This method is faster and more convenient, and also helps to understand the similarity of each monitoring area, facilitating subsequent adjustments to the overall structure within the carbon emission monitoring area.

[0107] In step S4, the early warning information within the carbon emission regulatory area refers to the information of small areas marked as high-carbon emission regulatory areas. The ratio of high-carbon emission regulatory areas to the total number of carbon emission regulatory areas is calculated and denoted as RR. Obviously, the larger the ratio of high-carbon emission regulatory areas to the total number of carbon emission regulatory areas, the greater the future carbon emission risk within the carbon emission regulatory area. Simultaneously, population flow information within the carbon emission regulatory area also needs to be obtained, i.e., population flow value, and denoted as PM. The larger the population flow value, the greater the demand for carbon emissions, and the greater the risk of carbon emissions. Conversely, if the population flow value is negative, i.e., population outflow, the risk of carbon emissions decreases accordingly. Therefore, in step S4, the future risk coefficient RC is calculated using the formula based on the population flow value PM and the ratio RR of high-carbon emission regulatory areas to the total number of carbon emission regulatory areas. The specific calculation expression is as follows:

[0108] RC=ln)αRR+βPM+1)

[0109] In the formula, α and β are the preset proportional coefficients of the ratio RR of high carbon emission regulatory areas to the total carbon emission regulatory areas and the population mobility value PM, respectively, and α>β>0.

[0110] By comparing the future risk coefficient RC with the standard risk threshold, the future risk situation within the carbon emission regulatory area can be determined.

[0111] If the future risk coefficient RC is greater than or equal to the standard risk threshold, it indicates that the carbon emission regulatory area is at high risk of failing to meet the carbon emission standards in the future. At this time, the carbon emission regulatory area will be marked as a high-risk area and an early warning will be issued to prompt relevant personnel to make overall optimization and adjustments.

[0112] If the future risk coefficient RC is less than the standard risk threshold, it means that the risk of carbon emissions not meeting the standards in the carbon emission regulatory area is relatively small in the future. At this time, the carbon emission regulatory area will be marked as a low-risk area.

[0113] This invention combines high-carbon emission monitoring areas with future population flow patterns to comprehensively analyze the carbon emission compliance risks of the monitored areas over a future period. Based on the actual carbon emission situation, it can make a more comprehensive prediction of the future and help relevant personnel to make overall optimizations and adjustments in advance when there are significant risks.

[0114] Example 2

[0115] The above embodiment 1 details a method for monitoring, analyzing, and modeling carbon emissions from the energy and electricity sector according to the present invention. This embodiment, in order to implement the method described in embodiment 1, introduces an energy and electricity carbon emission monitoring, analysis, and modeling device, such as... Figure 2As shown, it includes: a data acquisition and analysis module, a clustering evaluation module, an early warning module, and a carbon emission trend prediction module;

[0116] The data acquisition and analysis module divides the carbon emission regulatory area into several carbon emission regulatory sub-areas, calculates the carbon emission intensity of each carbon emission regulatory sub-area, and determines whether the carbon emission intensity of each carbon emission regulatory sub-area meets the standards.

[0117] The clustering evaluation module calculates the carbon emission evaluation coefficient for the carbon emission regulatory micro-regions that meet the standards, and clusters each carbon emission regulatory micro-region according to the carbon emission evaluation coefficient to determine the carbon emission standards for each carbon emission regulatory micro-region.

[0118] The early warning module is used to analyze and process the actual carbon emissions of each clustered category of carbon emission monitoring area and to mark and issue early warnings.

[0119] The carbon emission trend prediction module acquires early warning information within the carbon emission regulatory area, combines it with population flow information within the carbon emission regulatory area to determine future carbon emission trends, and completes carbon emission database modeling and analysis.

[0120] In a preferred embodiment, the clustering evaluation module calculates the carbon emission evaluation coefficient for carbon emission regulatory micro-regions that meet the standards. The specific process is as follows:

[0121] Before determining the carbon emission assessment coefficients, all the main factors affecting carbon emissions are first set as the set x, and each main factor is represented as {x1, x2, ..., x...}. n}, where n is the number of major influencing factors, and n is a positive integer. The exponential expression for the Logistic regression analysis method is:

[0122]

[0123] In the formula, C is the carbon emission evaluation coefficient, Q is a constant term, representing the adjustment required when all representative major influencing factors are absent, i.e., Q represents the coefficients of all minor influencing factors {x1, x2, ..., x...}. n} represents the number of main influencing factors, {g1, g2, ..., g n} represents the regression coefficients of each major influencing factor.

[0124] In a preferred embodiment, the clustering evaluation module calculates and obtains the carbon emission evaluation coefficients of each carbon emission regulatory sub-region, and then uses the k-means clustering algorithm to perform cluster analysis on the carbon emission evaluation coefficients of each carbon emission regulatory sub-region. Through cluster analysis, each carbon emission regulatory sub-region is clustered at a cluster center to obtain K carbon emission standard clusters.

[0125] In a preferred embodiment, the specific steps of the cluster evaluation module in performing cluster analysis on the carbon emission evaluation coefficients of each carbon emission monitoring sub-region using the k-means clustering algorithm are as follows:

[0126] The number of cluster centers K in the K-means algorithm is determined using the silhouette coefficient method.

[0127] The KMEANS algorithm was used to cluster the carbon emission evaluation coefficients of each carbon emission regulatory area to obtain K carbon emission standard clusters.

[0128] In a preferred embodiment, the cluster evaluation module determines the cluster centers of each carbon emission regulatory sub-region after identifying them, and then determines the carbon emission standards for each carbon emission regulatory sub-region based on the carbon emission standards corresponding to the cluster centers.

[0129] In a preferred embodiment, after obtaining K carbon emission standard clusters based on clustering, the early warning module compares the actual carbon emissions of each carbon emission monitoring area within the K carbon emission standard clusters with the carbon emission standard corresponding to the cluster center:

[0130] If the actual carbon emissions of a carbon emission monitoring area exceed the corresponding carbon emission standard, the carbon emission monitoring area will be marked as a high-carbon emission monitoring area and an alarm will be triggered.

[0131] In a preferred embodiment, the early warning module calculates the ratio of high-carbon emission monitoring areas to the total carbon emission monitoring areas and labels it as RR; obtains the population flow value within the carbon emission monitoring area and labels it as PM; and calculates the future risk coefficient RC based on the population flow value PM and the ratio of high-carbon emission monitoring areas to the total carbon emission monitoring areas RR using a formula. The specific calculation expression is as follows.

[0132] RC = ln(αRR + βPM + 1)

[0133] In the formula, α and β are the preset proportional coefficients of the ratio RR of high carbon emission regulatory areas to the total carbon emission regulatory areas and the population mobility value PM, respectively, and α>β>0.

[0134] In a preferred embodiment, the early warning module compares the future risk coefficient RC with a standard risk threshold:

[0135] If the future risk coefficient RC is greater than or equal to the standard risk threshold, the carbon emission regulatory area will be marked as a high-risk area and an early warning will be issued.

[0136] If the future risk coefficient RC is less than the standard risk threshold, the carbon emission regulatory area will be marked as a low-risk area.

[0137] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0138] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described device embodiments can be referred to the specific working process of the aforementioned method embodiments, which will not be repeated here.

[0139] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0140] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or modules may be electrical, mechanical, or other forms.

[0142] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0143] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0144] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring, analyzing, and modeling carbon emissions from energy and electricity, characterized in that, Includes the following steps; The carbon emission regulatory area is divided into several carbon emission regulatory sub-areas, and the carbon emission intensity of each carbon emission regulatory sub-area is calculated and it is determined whether the carbon emission intensity of each carbon emission regulatory sub-area meets the standards. Calculate the carbon emission evaluation coefficient for each carbon emission regulatory area that meets the standard, and cluster each carbon emission regulatory area according to the carbon emission evaluation coefficient to determine the carbon emission standard for each carbon emission regulatory area. The actual carbon emissions of each clustered carbon emission monitoring area are analyzed and processed, and then marked and warned. Obtain early warning information within the carbon emission regulatory area, combine it with population flow information within the carbon emission regulatory area to determine future carbon emission trends, and complete carbon emission database modeling and analysis; The specific process for calculating the carbon emission assessment coefficient for small carbon emission regulatory areas that meet the standards is as follows: Before determining the carbon emission assessment coefficients, all factors that have a major impact on carbon emissions are first set as... The set, with each major influencing factor represented as follows: Where n is the number of main influencing factors involved, and n is a positive integer, the exponential expression for the Logistic regression analysis method is: ； In the formula, C is the carbon emission evaluation coefficient, Q is a constant term, which is the adjustment required when all representative major influencing factors are absent, and Q is the coefficient of all minor influencing factors. These are the regression coefficients for each of the main influencing factors; After calculating and obtaining the carbon emission evaluation coefficients of each carbon emission monitoring area, the k-means clustering algorithm is used to perform cluster analysis on the carbon emission evaluation coefficients of each carbon emission monitoring area. Through cluster analysis, each carbon emission monitoring area is clustered at the cluster center to obtain K carbon emission standard clusters. The specific steps for using the k-means clustering algorithm to perform cluster analysis on the carbon emission assessment coefficients of each carbon emission monitoring sub-region are as follows: The number of cluster centers K in the K-means algorithm is determined using the silhouette coefficient method. The K-means algorithm was used to cluster the carbon emission evaluation coefficients of each carbon emission monitoring area to obtain K carbon emission standard clusters. After identifying the cluster centers of each carbon emission regulatory sub-region, the carbon emission standards for each carbon emission regulatory sub-region are determined based on the carbon emission standards corresponding to the cluster centers.

2. The energy and power carbon emission monitoring, analysis, and modeling method according to claim 1, characterized in that: After obtaining K carbon emission standard clusters through clustering, the actual carbon emissions of each carbon emission monitoring sub-region within the K carbon emission standard clusters are compared with the carbon emission standard corresponding to the cluster center: If the actual carbon emissions of a carbon emission monitoring area exceed the corresponding carbon emission standard, the carbon emission monitoring area will be marked as a high-carbon emission monitoring area and an alarm will be triggered.

3. The energy and power carbon emission monitoring, analysis, and modeling method according to claim 2, characterized in that: Calculate the ratio of high-carbon emission regulatory areas to the total carbon emission regulatory areas and label it as RR. Obtain the population flow value within the carbon emission regulatory area and label it as PM. Based on the population flow value PM and the ratio of high-carbon emission regulatory areas to the total carbon emission regulatory areas RR, calculate the future risk coefficient RC using the following formula. ； In the formula, and These are the preset proportions of the ratio (RR) of high-carbon emission regulatory micro-regions to the total carbon emission regulatory micro-regions, and the population mobility value (PM). .

4. The energy and electricity carbon emission monitoring, analysis, and modeling method according to claim 3, characterized in that: Compare the future risk coefficient RC with the standard risk threshold: If the future risk coefficient RC is greater than or equal to the standard risk threshold, the carbon emission regulatory area will be marked as a high-risk area and an early warning will be issued. If the future risk coefficient RC is less than the standard risk threshold, the carbon emission regulatory area will be marked as a low-risk area.

5. An energy and electricity carbon emission monitoring, analysis, and modeling device, characterized in that, include: The module includes data acquisition and analysis, clustering evaluation, early warning, and carbon emission trend prediction. The data acquisition and analysis module divides the carbon emission regulatory area into several carbon emission regulatory sub-areas, calculates the carbon emission intensity of each carbon emission regulatory sub-area, and determines whether the carbon emission intensity of each carbon emission regulatory sub-area meets the standards. The clustering evaluation module calculates the carbon emission evaluation coefficient for the carbon emission regulatory micro-regions that meet the standards, and clusters each carbon emission regulatory micro-region according to the carbon emission evaluation coefficient to determine the carbon emission standards for each carbon emission regulatory micro-region. The early warning module is used to analyze and process the actual carbon emissions of each clustered carbon emission monitoring area and mark and issue early warnings. The carbon emission trend prediction module acquires early warning information within the carbon emission regulatory area, combines it with population flow information within the carbon emission regulatory area to determine future carbon emission trends, and completes carbon emission database modeling and analysis. The clustering evaluation module calculates carbon emission evaluation coefficients for carbon emission regulatory micro-regions that meet the standards. The specific process is as follows: Before determining the carbon emission assessment coefficients, all factors that have a major impact on carbon emissions are first set as... The set, with each major influencing factor represented as follows: Where n is the number of main influencing factors involved, and n is a positive integer, the exponential expression for the Logistic regression analysis method is: ； In the formula, C is the carbon emission evaluation coefficient, Q is a constant term, which is the adjustment required when all representative major influencing factors are absent, and Q is the coefficient of all minor influencing factors. These are the regression coefficients for each of the main influencing factors; The clustering evaluation module calculates and obtains the carbon emission evaluation coefficients of each carbon emission monitoring sub-region, and then uses the k-means clustering algorithm to perform cluster analysis on the carbon emission evaluation coefficients of each carbon emission monitoring sub-region based on the carbon emission evaluation coefficients. Through cluster analysis, each carbon emission monitoring sub-region is clustered at the cluster center to obtain K carbon emission standard clusters. The specific steps of the clustering evaluation module in performing cluster analysis on the carbon emission evaluation coefficients of each carbon emission monitoring sub-region using the k-means clustering algorithm are as follows: The number of cluster centers K in the K-means algorithm is determined using the silhouette coefficient method. The K-means algorithm was used to cluster the carbon emission evaluation coefficients of each carbon emission monitoring area to obtain K carbon emission standard clusters. The clustering evaluation module determines the cluster centers of each carbon emission regulatory sub-region after identifying them, and then determines the carbon emission standards for each carbon emission regulatory sub-region based on the carbon emission standards corresponding to the cluster centers.

6. The energy and power carbon emission monitoring, analysis, and modeling device according to claim 5, characterized in that: The early warning module, after obtaining K carbon emission standard clusters through clustering, compares the actual carbon emissions of each carbon emission monitoring area within the K carbon emission standard clusters with the carbon emission standard corresponding to the cluster center: If the actual carbon emissions of a carbon emission monitoring area exceed the corresponding carbon emission standard, the carbon emission monitoring area will be marked as a high-carbon emission monitoring area and an alarm will be triggered.

7. The energy and power carbon emission monitoring, analysis, and modeling device according to claim 6, characterized in that: The early warning module calculates the ratio of high-carbon emission monitoring areas to the total carbon emission monitoring areas and labels it as RR. It also obtains the population flow value within the carbon emission monitoring area and labels it as PM. Based on the population flow value PM and the ratio of high-carbon emission monitoring areas to the total carbon emission monitoring areas RR, the future risk coefficient RC is calculated using a formula. The specific calculation expression is as follows. ； In the formula, and These are the preset proportions of the ratio (RR) of high-carbon emission regulatory micro-regions to the total carbon emission regulatory micro-regions, and the population mobility value (PM). .

8. The energy and power carbon emission monitoring, analysis, and modeling device according to claim 7, characterized in that: The early warning module compares the future risk coefficient RC with the standard risk threshold: If the future risk coefficient RC is greater than or equal to the standard risk threshold, the carbon emission regulatory area will be marked as a high-risk area and an early warning will be issued. If the future risk coefficient RC is less than the standard risk threshold, the carbon emission regulatory area will be marked as a low-risk area.

Images