Carbon emission real-time monitoring and predicting system based on big data

Through real-time monitoring and prediction systems of big data technology, carbon emission prediction models are constructed using carbon emission measured values ​​and activity data, solving the problem of large carbon emission prediction errors in the existing technology, and achieving accurate prediction of enterprise carbon emissions and carbon neutrality Achievement of goals.

CN118982106AActive Publication Date: 2024-11-19HONG KONG CHINA (SHENZHEN) CARBON ASSET OPERATION CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411040890.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-19
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

The existing technology cannot accurately predict carbon emissions when the production activities are not over, resulting in large errors in annual carbon emission forecasts, which may exceed corporate carbon emission indicators, resulting in companies being unable to achieve carbon neutrality and rising production costs.

Method used

Adopt a real-time monitoring and prediction system for carbon emissions based on big data, obtain the actual carbon emission measured values ​​and activity data through the data acquisition module, calculate emission factors, build a carbon emission prediction model, and use the model to monitor and predict carbon emissions in a timely manner. Update emission factors to reduce errors.

Benefits of technology

It has achieved accurate predictions of corporate carbon emissions, helping companies control annual carbon emissions, promote carbon neutrality, and reduce production costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982106A_ABST
    Figure CN118982106A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of carbon emission monitoring, and particularly relates to a carbon emission real-time monitoring and prediction system based on big data, which comprises a data acquisition module used for acquiring a carbon emission measured value; the data acquisition module is also used for acquiring activity data including direct activity data and indirect activity data, and determining corresponding emission factors including direct emission factors and indirect emission factors; the data processing module is used for calculating a carbon emission calculation value according to the activity data and the emission factor; by comparing the carbon emission measured value with the carbon emission calculated value calculated based on the activity data and the emission factor, the emission factor closer to the actual production of the enterprise is obtained, so that the carbon emission prediction model related to the enterprise production activity data is established based on the emission factor, and after the monthly production task of the enterprise is obtained, the carbon emission prediction value can be correspondingly obtained. Therefore, the carbon emission of the enterprise is predicted, the annual carbon emission of the enterprise is favorably controlled, and the carbon neutralization of the enterprise is promoted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of carbon emission monitoring, and specifically is a real-time monitoring and prediction system for carbon emission based on big data. Background Art

[0002] Carbon emissions refer to the process of directly or indirectly producing carbon dioxide (CO2) and other greenhouse gases and emitting them into the atmosphere through the burning of fossil fuels or other means in human activities such as production, transportation, and consumption. The increase of these greenhouse gases will lead to an enhanced greenhouse effect in the earth's atmosphere, which will in turn cause a series of environmental problems such as global climate change and rising temperatures. Controlling and reducing carbon emissions is one of the major challenges facing the world today. It requires the joint efforts of countries, enterprises, and individuals to reduce the impact on the environment and respond to the risks brought by climate change through measures such as adopting clean energy, improving energy efficiency, and improving production and consumption patterns. Therefore, enterprises need to strictly control carbon emissions in order to achieve the goal of energy conservation and emission reduction. At this stage, enterprises have fixed carbon emission targets each year. If they exceed the targets, they need to purchase carbon emission targets from other enterprises to achieve the goal of carbon neutrality.

[0003] In order to control carbon emissions more accurately, enterprises need to obtain real-time carbon emissions accurately. Based on the above, the existing technology for collecting carbon emissions includes real-time collection, that is, using a continuous emission monitoring system to monitor the CO2 concentration in the flue gas, and then calculating the carbon emissions based on the total gas volume; the other is to use emission factor calculation, that is, calculate the carbon emissions based on activity data * emission factor;

[0004] Due to the existing technology, real-time collection is used, and carbon emissions can only be converted after the production activities are completed, that is, the flue gas is exhausted; and the emission factor is the default value, which is obtained from the corresponding carbon accounting guidelines or standards; therefore, in order to obtain the predicted carbon emissions before the production activities are completed, it is only possible to calculate and predict through the emission factor method; and the emission factor is not absolutely accurate, that is, after using the emission factor method to predict carbon emissions, there may be differences from the actual measured carbon emissions. If an annual carbon emissions forecast is required, the accumulated error will be too large, which may exceed the company's carbon emission indicators, resulting in the company's inability to achieve carbon neutrality and an increase in production costs.

[0005] To this end, the present invention provides a real-time monitoring and prediction system for carbon emissions based on big data. Summary of the invention

[0006] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0007] The technical solution adopted by the present invention to solve its technical problem is: a real-time monitoring and prediction system for carbon emissions based on big data described in the present invention includes a data acquisition module for obtaining actual carbon emission values; and is also used to obtain activity data, including direct activity data and indirect activity data, and determine corresponding emission factors, including direct emission factors and indirect emission factors;

[0008] Data processing module, used to calculate carbon emission values ​​based on activity data and emission factors;

[0009] The calculation module is used to calculate the difference between the measured carbon emission value and the calculated carbon emission value, and output the result:

[0010] When the difference between the measured carbon emission value and the calculated carbon emission value is less than or equal to the threshold, the emission factor is determined;

[0011] When the difference between the measured carbon emission value and the calculated carbon emission value is greater than the threshold, the emission factor is updated;

[0012] The model building module builds a carbon emission prediction model based on the updated emission factors and historical carbon emission measured values.

[0013] Preferably, the carbon emission calculation value is calculated as follows:

[0014] Obtain activity data, including directly controlled carbon emissions and indirectly controlled carbon emissions;

[0015] Obtain the corresponding emission factors;

[0016] According to the formula:

[0017] V = S × R;

[0018] Among them, V represents carbon emissions, S represents activity data, and R represents the corresponding emission factor;

[0019] Based on the formula, direct carbon emissions and indirect carbon emissions are calculated separately, and then the sum of direct carbon emissions and indirect carbon emissions is calculated as the carbon emissions calculation value.

[0020] Preferably, the method for constructing the carbon emission prediction model is:

[0021] Data collection;

[0022] Data preprocessing;

[0023] Build the model;

[0024] Training and optimizing models;

[0025] The expression of the carbon emission prediction model is:

[0026]

[0027] Among them, A represents the predicted value of carbon emissions, Si·(Ri·e kt ) represents the predicted carbon emissions; Si represents any activity data, Ri represents any emission factor, k represents the growth coefficient of any emission factor; t represents time.

[0028] Preferably, the carbon emission prediction model outputs a carbon emission prediction value based on future production indicators;

[0029] An analysis module is also included to analyze the accuracy of the carbon emission forecast values.

[0030] Preferably, the method by which the analysis module analyzes the accuracy of the carbon emission prediction value is:

[0031] Obtaining a predicted carbon emission value corresponding to the measured carbon emission value;

[0032] The predicted carbon emission value and the measured carbon emission value are represented as A(X,Y) and B(x,y) respectively; X represents the predicted direct emission value, x represents the measured direct emission value; Y represents the predicted indirect emission value, y represents the measured indirect emission value;

[0033] According to the formula:

[0034]

[0035] Among them, U represents the carbon emission range, and δ represents the error coefficient;

[0036] The ratio of the carbon emission prediction value A is calculated according to the formula and expressed as

[0037] When the ratio of the carbon emission prediction value A is within the carbon emission interval U, it means that the carbon emission prediction value A is accurate;

[0038] When the ratio of the carbon emission prediction value A is not within the carbon emission interval U, it means that the carbon emission prediction value A is inaccurate and the carbon emission prediction model needs to be optimized.

[0039] Preferably, the analysis module is also used to analyze defects in the carbon emission prediction model when the carbon emission prediction value A is inaccurate.

[0040] Preferably, the method by which the analysis module analyzes defects in the carbon emission prediction model is:

[0041] Obtain the ratio of the corresponding carbon emission prediction value A;

[0042] Compare Aω with the upper and lower limits of the carbon emission range U;

[0043] When Aω>Umax, it indicates that there is a defect that the predicted value of indirect emission is too small;

[0044] When Aω<Umin, it means that there is a defect that the direct emission prediction value is too small;

[0045] Among them, Umax represents the upper limit of the carbon emission range, and Umin represents the lower limit of the carbon emission range.

[0046] Preferably, it also includes a cloud for storing information output by the data acquisition module, the data processing module, the calculation module and the analysis module.

[0047] Preferably, it also includes an early warning module, which outputs an alarm signal based on the analysis results of the defects of the carbon emission prediction model:

[0048] When the direct emission forecast value is too small, an alarm signal of the direct emission factor being too small is output to the cloud;

[0049] When the predicted value of indirect emissions is too small, an alarm signal of the indirect emission factor being too small is output to the cloud.

[0050] Preferably, when the cloud receives an alarm signal, an expression of the carbon emission prediction model is updated;

[0051] The expression of the carbon emission prediction model is updated as follows:

[0052]

[0053] Among them, (1+α)k represents the updated growth coefficient.

[0054] The beneficial effects of the present invention are as follows:

[0055] 1. The real-time monitoring and prediction system for carbon emissions based on big data described in the present invention obtains emission factors that are closer to the actual production of the enterprise by comparing the measured carbon emissions with the calculated carbon emissions based on activity data and emission factors, thereby establishing a carbon emissions prediction model related to the enterprise's production activity data based on the emission factors. When the enterprise's monthly production task is known, the corresponding carbon emission prediction value can be obtained, thereby realizing the prediction of the enterprise's carbon emissions, which is beneficial for the enterprise to control its annual carbon emissions and promote enterprise carbon neutrality.

[0056] 2. The real-time monitoring and prediction system for carbon emissions based on big data described in the present invention calculates the carbon emission interval and uses the carbon emission interval as a threshold for judging whether the carbon emission prediction value A is accurate. When the ratio of the carbon emission prediction value A is within the carbon emission interval U, it means that the carbon emission prediction value A is accurate. When the ratio of the carbon emission prediction value A is not within the carbon emission interval U, it means that the carbon emission prediction value A is inaccurate. When the ratio of the carbon emission prediction value A is greater than the upper limit of the carbon emission interval U, it means that the indirect emission factor is too small, that is, the defect is that the indirect emission prediction value is too small. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described below in conjunction with the accompanying drawings.

[0058] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0059] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0060] like Figure 1 As shown, a real-time monitoring and prediction system for carbon emissions based on big data according to an embodiment of the present invention includes a data acquisition module for obtaining actual carbon emission values; and is also used to obtain activity data, including direct activity data and indirect activity data, and determine corresponding emission factors, including direct emission factors and indirect emission factors;

[0061] Data processing module, used to calculate carbon emission values ​​based on activity data and emission factors;

[0062] The calculation module is used to calculate the difference between the measured carbon emission value and the calculated carbon emission value, and output the result:

[0063] When the difference between the measured carbon emission value and the calculated carbon emission value is less than or equal to the threshold, the emission factor is determined;

[0064] When the difference between the measured carbon emission value and the calculated carbon emission value is greater than the threshold, the emission factor is updated;

[0065] The model building module builds a carbon emission prediction model based on the updated emission factors and historical carbon emission measured values.

[0066] Due to the existing technology, real-time collection is used, and carbon emissions can only be converted after the production activities are completed, that is, the flue gas is exhausted; and the emission factor is the default value, which is obtained from the corresponding carbon accounting guidelines or standards; therefore, in order to obtain the predicted carbon emissions before the production activities are completed, it is only possible to calculate and predict through the emission factor method; and the emission factor is not absolutely accurate, that is, after using the emission factor method to predict carbon emissions, there may be differences from the actual measured carbon emissions. If an annual carbon emissions forecast is required, the accumulated error will be too large, which may exceed the company's carbon emission indicators, resulting in the company's inability to achieve carbon neutrality and an increase in production costs.

[0067] As an embodiment of the present invention, in the application stage, the CO2 concentration and flue gas flow rate in the exhaust gas of the emission subject are measured in real time through the data acquisition module, that is, the continuous emission monitoring system (CEMS); then the total CO2 emission is converted according to the total flue gas flow rate obtained, and it is used as the carbon emission; in this way, real-time monitoring is performed; however, real-time monitoring cannot accurately predict carbon emissions, and it is unclear whether the annual carbon emissions will exceed the target. If it exceeds the target, it is necessary to purchase carbon emission indicators from other enterprises, resulting in a substantial increase in production costs;

[0068] Based on the above, in one embodiment of the present invention, by comparing the measured carbon emission values ​​with the calculated carbon emission values ​​based on activity data and emission factors, an emission factor that is closer to the actual production of the enterprise is obtained, so as to establish a carbon emission prediction model related to the enterprise's production activity data based on the emission factor. When the monthly production task of the enterprise is known, the corresponding carbon emission prediction value can be obtained, thereby realizing the prediction of the enterprise's carbon emissions, which is beneficial for the enterprise to control its annual carbon emissions and promote carbon neutrality of the enterprise;

[0069] The calculation method of the carbon emission calculation value is:

[0070] Obtain activity data, including directly controlled carbon emissions and indirectly controlled carbon emissions;

[0071] Obtain the corresponding emission factors;

[0072] According to the formula:

[0073] V = S × R;

[0074] Among them, V represents carbon emissions, S represents activity data, and R represents the corresponding emission factor;

[0075] Based on the formula, direct carbon emissions and indirect carbon emissions are calculated separately, and then the sum of direct carbon emissions and indirect carbon emissions is calculated as the carbon emissions calculation value.

[0076] As an embodiment of the present invention, the calculated carbon emission value follows carbon emission = activity data * emission factor. Under normal circumstances, since the emission factors corresponding to the direct carbon emission and indirect carbon emission of an enterprise are different, it is necessary to calculate the direct carbon emission and the indirect carbon emission separately, and then add the two together to obtain the total carbon emission of the enterprise over a period of time, that is, the calculated carbon emission value. It is worth noting that the calculated carbon emission value here may have errors with the actual carbon emission value collected by the continuous emission monitoring system (CEMS). When the difference is less than or equal to the threshold, it is determined that the calculated carbon emission value is equal to the actual carbon emission value, that is, the emission factor is accurate. When the difference is greater than the threshold, it is determined that the calculated carbon emission value is not equal to the actual carbon emission value, that is, the emission factor is inaccurate.

[0077] In addition, in order to facilitate the updating of emission factors, including direct emission factors and indirect emission factors, it is necessary to separately compare the direct carbon emission calculated value and the direct carbon emission measured value; the indirect carbon emission calculated value and the indirect carbon emission measured value. Based on this, inaccurate emission factors can be updated to obtain updated emission factors that are in line with the current production of the enterprise.

[0078] The method for constructing the carbon emission prediction model is as follows:

[0079] Data collection;

[0080] Data preprocessing;

[0081] Build the model;

[0082] Training and optimizing models;

[0083] The expression of the carbon emission prediction model is:

[0084]

[0085] Among them, A represents the predicted value of carbon emissions, Si·(Ri·e kt ) represents the predicted carbon emissions; Si represents any activity data, Ri represents any emission factor, k represents the growth coefficient of any emission factor; t represents time.

[0086] As an embodiment of the present invention, the construction of the carbon emission prediction model specifically includes:

[0087] Data collection: Collect the carbon emission data of enterprises in the past few years, including direct emissions (such as combustion equipment) and indirect emissions (such as electricity consumption);

[0088] Data preprocessing: clean the data, process missing values, and detect outliers to ensure data quality;

[0089] Construct the model, expressed as

[0090] Training and optimizing the model, dividing the processed historical data into two parts, one part is used to build the model, and the other part is used as a training set to train the model and optimize the parameters based on the training results, specifically optimizing the growth coefficient of any emission factor.

[0091] By using the above-mentioned carbon emission prediction model, after obtaining the company's monthly production task, you only need to input the corresponding activity data to obtain the carbon emission prediction value based on the carbon emission prediction model, thereby predicting the company's annual carbon emissions and avoiding the company's annual carbon emissions exceeding the carbon emission indicators.

[0092] The carbon emission prediction model outputs a carbon emission prediction value based on future production indicators;

[0093] An analysis module is also included to analyze the accuracy of the carbon emission forecast values.

[0094] Based on the above, according to the company's future production tasks, they can be input as parameters into the prediction model to obtain carbon emission prediction values, which is conducive to predicting the company's carbon emissions and avoiding the company's carbon emissions exceeding the carbon emission indicators; in addition, since the carbon emission prediction model takes precedence over the actual carbon emission measurements, the carbon emission prediction values ​​are not necessarily accurate. Equipment aging, material updates, technological innovations, etc. may cause inconsistencies between the actual carbon emission values ​​and the carbon emission prediction values. Therefore, the carbon emission prediction model needs to be updated regularly to obtain carbon emission prediction values ​​that are closer to the actual carbon emission values.

[0095] The method by which the analysis module analyzes the accuracy of the carbon emission prediction value is:

[0096] Obtaining a predicted carbon emission value corresponding to the measured carbon emission value;

[0097] The predicted carbon emission value and the measured carbon emission value are represented as A(X,Y) and B(x,y) respectively; X represents the predicted direct emission value, x represents the measured direct emission value; Y represents the predicted indirect emission value, y represents the measured indirect emission value;

[0098] According to the formula:

[0099]

[0100] Among them, U represents the carbon emission range, and δ represents the error coefficient;

[0101] The ratio of the carbon emission prediction value A is calculated according to the formula and expressed as

[0102] When the ratio of the carbon emission prediction value A is within the carbon emission interval U, it means that the carbon emission prediction value A is accurate;

[0103] When the ratio of the carbon emission prediction value A is not within the carbon emission interval U, it means that the carbon emission prediction value A is inaccurate and the carbon emission prediction model needs to be optimized.

[0104] Based on the above, when the carbon emission prediction model is used to predict the carbon emissions of an enterprise in any month, the carbon emission prediction value is obtained, which is represented by A. In addition, after the end of the month, the continuous emission monitoring system (CEMS) is used to obtain the measured carbon emission value of the enterprise in that month, which is represented by B. By judging whether the ratio of the measured carbon emission value B is within the carbon emission interval U, the accuracy of the carbon emission prediction value A can be judged. Among them, it is worth noting that when the carbon emission prediction value A is significantly different from the carbon emission measured value B, it is directly judged that there is an abnormality in direct carbon emissions or an abnormality in indirect carbon emissions;

[0105] The formula can only be used to calculate the carbon emission range when the predicted carbon emission value A is similar to the measured carbon emission value B. Since both the predicted carbon emission value and the measured carbon emission value are composed of direct emissions and indirect emissions, the ratio is used to analyze the analogy between the two. Based on the above, the carbon emission range is calculated and used as the threshold to determine whether the predicted carbon emission value A is accurate. When the ratio of the predicted carbon emission value A is within the carbon emission range U, it means that the predicted carbon emission value A is accurate. When the ratio of the predicted carbon emission value A is not within the carbon emission range U, it means that the predicted carbon emission value A is inaccurate.

[0106] The analysis module is also used to analyze the defects of the carbon emission prediction model when the carbon emission prediction value A is inaccurate.

[0107] As an embodiment of the present invention, when the carbon emission prediction value A is inaccurate after analysis, it is necessary to analyze the defects of the carbon emission prediction model accordingly, specifically the emission factor defects. The errors caused by activity data can be reflected intuitively and do not need to be judged by the prediction model. By obtaining the emission factor defects and updating the emission factors accordingly, the carbon emission prediction value can be made closer to the actual carbon emission value, which is beneficial to the prediction of carbon emissions.

[0108] The method for the analysis module to analyze the defects of the carbon emission prediction model is:

[0109] Obtain the ratio of the corresponding carbon emission prediction value A;

[0110] Compare Aω with the upper and lower limits of the carbon emission range U;

[0111] When Aω>Umax, it indicates that there is a defect that the predicted value of indirect emission is too small;

[0112] When Aω<Umin, it means that there is a defect that the direct emission prediction value is too small;

[0113] Among them, Umax represents the upper limit of the carbon emission range, and Umin represents the lower limit of the carbon emission range.

[0114] As an embodiment of the present invention, when the ratio of the carbon emission prediction value A is greater than the upper limit of the carbon emission interval U, it means that the denominator of the carbon emission prediction value A is too small or the numerator of the carbon emission prediction value A is too large, and the numerator of the carbon emission prediction value A is too large, that is, the direct emission factor is too large. Based on practical considerations, the trend of emission factors changing over time will only increase. Therefore, based on the previous direct emission factors, there is no possibility that the direct emission factor is too large. Therefore, there is only the possibility that the indirect emission factor is too small, that is, the defect is that the indirect emission prediction value is too small;

[0115] Similarly, when the ratio of the carbon emission prediction value A is less than the lower limit of the carbon emission interval U, there is only the defect that the direct emission prediction value is too small; after analyzing the defects of the carbon emission prediction model, the emission factor is updated accordingly to make the carbon emission prediction value equal to the carbon emission actual value, which is beneficial for enterprises to predict carbon emissions.

[0116] It also includes a cloud for storing information output by the data acquisition module, the data processing module, the calculation module and the analysis module.

[0117] As an embodiment of the present invention, the cloud can store data, specifically data output by the data acquisition module, data processing module, calculation module and analysis module, including the company's monthly carbon emission forecast value and carbon emission actual value, as well as updated emission factors. After the updated emission factor appears, it can overwrite the previous emission factor, so as to avoid using the wrong emission factor in the subsequent carbon emission forecast process, which may cause data anomalies.

[0118] It also includes an early warning module, which outputs alarm signals based on the analysis results of defects in the carbon emission prediction model:

[0119] When the direct emission forecast value is too small, an alarm signal of the direct emission factor being too small is output to the cloud;

[0120] When the predicted value of indirect emissions is too small, an alarm signal of the indirect emission factor being too small is output to the cloud.

[0121] Based on the above, as an embodiment of the present invention, through the analysis of the defects of the carbon emission prediction model, when the analysis result is that the direct emission prediction value is too small, the corresponding direct emission factor is too small. At this time, the early warning module transmits the alarm signal of the small direct emission factor to the cloud. The cloud changes the direct emission factor to make the carbon emission prediction value equal to the carbon emission actual value. Similarly, when the indirect emission prediction value is too small, the alarm signal is transmitted to the cloud, and the indirect emission factor is modified accordingly to make the data normal.

[0122] When the cloud receives an alarm signal, an expression of the carbon emission prediction model is updated;

[0123] The expression of the carbon emission prediction model is updated as follows:

[0124]

[0125] Among them, (1+α)k represents the updated growth coefficient.

[0126] As an embodiment of the present invention, after the cloud receives the alarm signal, based on the analysis of the data and the study of the changing trend of the emission factor, the growth coefficient is changed to make the updated emission factor conform to the actual emission factor of the current enterprise production, so that the carbon emission prediction value is equal to the carbon emission actual value.

[0127] Working principle: By comparing the measured carbon emissions with the calculated carbon emissions based on activity data and emission factors, we can obtain emission factors that are closer to the actual production of the enterprise, and then establish a carbon emissions prediction model related to the enterprise's production activity data based on the emission factors. Once the enterprise's monthly production tasks are known, the corresponding carbon emissions prediction values ​​can be obtained, thereby realizing the prediction of the enterprise's carbon emissions, which is beneficial for the enterprise to control its annual carbon emissions and promote carbon neutrality.

[0128] By calculating the carbon emission interval, the carbon emission interval is used as the threshold for judging whether the carbon emission prediction value A is accurate. When the ratio of the carbon emission prediction value A is within the carbon emission interval U, it means that the carbon emission prediction value A is accurate. When the ratio of the carbon emission prediction value A is not within the carbon emission interval U, it means that the carbon emission prediction value A is inaccurate. When the ratio of the carbon emission prediction value A is greater than the upper limit of the carbon emission interval U, it means that the denominator of the carbon emission prediction value A is too small or the numerator of the carbon emission prediction value A is too large. The numerator of the carbon emission prediction value A is too large, that is, the direct emission factor is too large. Based on practical considerations, the trend of emission factors changing over time will only increase. Therefore, based on the previous direct emission factors, there is no possibility that the direct emission factor is too large. Therefore, there is only the possibility that the indirect emission factor is too small, that is, the defect is that the indirect emission prediction value is too small.

[0129] Similarly, when the ratio of the carbon emission prediction value A is less than the lower limit of the carbon emission interval U, there is only the defect that the direct emission prediction value is too small; after analyzing the defects of the carbon emission prediction model, the emission factor is updated accordingly to make the carbon emission prediction value equal to the carbon emission actual value, which is beneficial for enterprises to predict carbon emissions.

[0130] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A real-time monitoring and prediction system for carbon emissions based on big data, characterized in that: include: The data acquisition module is used to obtain the measured value of carbon emissions; it is also used to obtain activity data, including direct activity data and indirect activity data, and determine the corresponding emission factors, including direct emission factors and indirect emission factors; Data processing module, used to calculate carbon emission values ​​based on activity data and emission factors; The calculation module is used to calculate the difference between the measured carbon emission value and the calculated carbon emission value, and output the result: When the difference between the measured carbon emission value and the calculated carbon emission value is less than or equal to the threshold, the emission factor is determined; When the difference between the measured carbon emission value and the calculated carbon emission value is greater than the threshold, the emission factor is updated; The model building module builds a carbon emission prediction model based on the updated emission factors and historical carbon emission measured values.

2. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 1 is characterized by: The calculation method of the carbon emission calculation value is: Obtain activity data, including directly controlled carbon emissions and indirectly controlled carbon emissions; Obtain the corresponding emission factors; According to the formula: V = S × R; Among them, V represents carbon emissions, S represents activity data, and R represents the corresponding emission factor; Based on the formula, direct carbon emissions and indirect carbon emissions are calculated separately, and then the sum of direct carbon emissions and indirect carbon emissions is calculated as the carbon emissions calculation value.

3. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 2 is characterized by: The method for constructing the carbon emission prediction model is as follows: Data collection; Data preprocessing; Build the model; Training and optimizing models; The carbon emission prediction model is expressed as: Among them, A represents the predicted value of carbon emissions, Si·(Ri·e kt ) represents the predicted carbon emissions; Si represents any activity data, Ri represents any emission factor, k represents the growth coefficient of any emission factor; t represents time.

4. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 3 is characterized by: The carbon emission prediction model outputs a carbon emission prediction value based on future production indicators; An analysis module is also included to analyze the accuracy of the carbon emission forecast values.

5. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 4 is characterized by: The method by which the analysis module analyzes the accuracy of the carbon emission prediction value is: Obtaining a predicted carbon emission value corresponding to the measured carbon emission value; The predicted carbon emission value and the measured carbon emission value are represented as A(X,Y) and B(x,y) respectively; X represents the predicted direct emission value, x represents the measured direct emission value; Y represents the predicted indirect emission value, y represents the measured indirect emission value; According to the formula: Among them, U represents the carbon emission range, and δ represents the error coefficient; The ratio of the carbon emission prediction value A is calculated according to the formula and expressed as When the ratio of the carbon emission prediction value A is within the carbon emission interval U, it means that the carbon emission prediction value A is accurate; When the ratio of the carbon emission prediction value A is not within the carbon emission interval U, it means that the carbon emission prediction value A is inaccurate and the carbon emission prediction model needs to be optimized.

6. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 5 is characterized by: The analysis module is also used to analyze the defects of the carbon emission prediction model when the carbon emission prediction value A is inaccurate.

7. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 6 is characterized by: The method for the analysis module to analyze the defects of the carbon emission prediction model is: Obtain the ratio of the corresponding carbon emission prediction value A; Compare Aω with the upper and lower limits of the carbon emission range U; When Aω>Umax, it indicates that there is a defect that the predicted value of indirect emission is too small; When Aω<Umin, it means that there is a defect that the direct emission prediction value is too small; Among them, Umax represents the upper limit of the carbon emission range, and Umin represents the lower limit of the carbon emission range.

8. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 7 is characterized by: It also includes a cloud for storing information output by the data acquisition module, the data processing module, the calculation module and the analysis module.

9. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 8 is characterized by: It also includes an early warning module, which outputs alarm signals based on the analysis results of defects in the carbon emission prediction model: When the direct emission forecast value is too small, an alarm signal of the direct emission factor being too small is output to the cloud; When the predicted value of indirect emissions is too small, an alarm signal of the indirect emission factor being too small is output to the cloud.

10. The real-time monitoring and prediction system for carbon emissions based on big data according to claim 9 is characterized in that: When the cloud receives an alarm signal, an expression of a carbon emission prediction model is updated; The expression of the carbon emission prediction model is updated as follows: Among them, (1+α)k represents the updated growth coefficient.

Citation Information

Patent Citations

  • Enterprise carbon emission prediction system and method based on multivariate time series

    CN116882569A

  • Park carbon emission prediction method and system

    CN117196919A

  • Enterprise carbon emission accounting method and system

    CN117237160A

  • Carbon emission prediction and evaluation method and system based on transformer carbon accounting model

    CN117709555A

  • Production enterprise carbon emission metering method and device and computer equipment

    CN117952320A