A carbon emission index intelligent deployment method and system based on big data analysis

Abstract

The present application belongs to the technical field of carbon emission monitoring, and particularly relates to a carbon emission index intelligent allocation method and system based on big data analysis. The method comprises obtaining the total demand in a target consumption period and calibrating it as a benchmark value, calculating the deviation and outputting a control suggestion; correcting the benchmark value to a total control amount based on a correction model; determining the total allocation according to the proportional relationship between the continuous control period and the intermittent period, and determining the execution amount of each period in combination with the distribution of the intermittent period; calculating the difference between the predicted amount and the actual amount of the last control period as an evaluation parameter, and comparing the evaluation parameter with the time error tolerance to determine whether the total allocation of the current control period needs to be corrected. The present application can balance carbon emission control and production operation, ensure the real-time and effectiveness of the control scheme, and reduce the risk of resource waste or emission exceeding.

Description

Technical Field

[0001] This invention belongs to the field of carbon emission monitoring technology, specifically relating to a method and system for intelligent allocation of carbon emission indicators based on big data analysis. Background Technology

[0002] With increasing focus on sustainable development and environmental protection, management through total emission control and market transactions has gradually become the norm. This approach effectively guides enterprises to reduce carbon emissions, achieving a green and low-carbon transformation. It provides flexibility for businesses while also offering economic impetus for the country to achieve carbon neutrality goals, demonstrating significant value in environmental governance and industrial upgrading.

[0003] Current carbon emission management systems simply compare actual emissions from carbon emission points with their rated quotas within a preset time period. This static approach cannot adapt to the dynamic changes in carbon emissions during industrial production, resulting in lag and inaccuracy in regulation. Furthermore, due to a lack of detailed analysis and prediction capabilities for real-time emission data, when actual emissions significantly exceed or fall below the quota within a certain period, the system often can only impose rough restrictions or allow them to run rampant, failing to achieve smooth and continuous dynamic adjustments.

[0004] To address the aforementioned issues, this invention provides a method and system for intelligent allocation of carbon emission quotas based on big data analysis. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for intelligent allocation of carbon emission indicators based on big data analysis. By acquiring historical carbon emission data from various carbon emission points, the system can determine the user's carbon emission trend and then output control suggestions based on the user's carbon emission trend to dynamically control the equipment.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for intelligent allocation of carbon emission quotas includes: Determine the total allocation amount for the current control cycle, including assessment parameters based on a comparison of the predicted and actual usage amounts for the previous control cycle, and adjust the baseline allocation accordingly. Based on the determined total allocation and the analysis results of historical carbon emission data, the implementation amount for each period within the current regulation cycle is determined. The determination of the results of the analysis of historical carbon emission data includes: Historical carbon emission data of carbon emission points are obtained; emission change trends of each carbon emission point are calculated based on trend analysis models, and the presence of intermittent patterns is determined based on emission change trends; if intermittent patterns exist, the intermittent periods within the corresponding control cycle are collected; if no intermittent patterns exist, the control cycle is defined as a continuous control period.

[0007] Preferably, determining whether there is an intermittent pattern based on emission change trends includes: By setting statistical nodes, the total carbon emissions within the estimated period are obtained and compared with the set benchmark threshold. If the total carbon emissions are higher than the benchmark threshold, it is judged as a continuous trend; otherwise, it is judged as an intermittent trend.

[0008] Preferably, based on the determined total allocation and the analysis results of historical carbon emission data, the execution amount for each period within the current control cycle is determined, including: determining the execution amount for each period according to the ratio between continuous control periods and intermittent periods, combined with the distribution of intermittent periods.

[0009] Preferably, the distribution of the intermittent periods includes: The interval period is divided into one or more main intervals with a duration greater than half of the total interval period, and one or more secondary intervals; and the determination of the execution usage for each period further includes proportionally allocating the total allocation to the main intervals and secondary intervals.

[0010] Preferably, the baseline allocation is corrected based on the evaluation parameters obtained by comparing the predicted and actual usage of the previous control cycle, including: comparing the evaluation parameters with the time error tolerance to determine whether the total allocation for the current control cycle needs to be corrected.

[0011] Preferably, the method further includes: Obtain the total demand within the target usage period and set the total demand as a benchmark value; calculate the deviation based on the benchmark value and output adjustment suggestions; and adjust the benchmark value to the total control usage based on the correction model, so as to serve as the benchmark allocation.

[0012] This invention also discloses a carbon emission quota intelligent allocation system based on big data analysis, used to execute the aforementioned carbon emission quota intelligent allocation method based on big data analysis, comprising: The emissions data acquisition module is used to acquire historical carbon emission data from carbon emission points and the actual usage in the previous regulation cycle; The deviation assessment module is used to calculate assessment parameters by comparing the predicted dosage with the actual dosage in the previous control cycle. And the indicator allocation decision module, which is configured to: in response to the assessment parameters provided by the deviation assessment module and in combination with the historical carbon emission data provided by the emission data acquisition module, determine the total allocation for the current control cycle and the execution amount for each period within the current control cycle.

[0013] Preferably, the indicator allocation decision module is further configured to determine the execution usage as follows: Historical carbon emission data is analyzed to determine if there are intermittent patterns; and if intermittent patterns exist, the total amount is allocated to each period based on the distribution of the identified intermittent periods.

[0014] Preferably, the indicator allocation decision module is configured to divide the intermittent period into a main intermittent period and a secondary intermittent period, and allocate the total allocation amount to the main intermittent period and the secondary intermittent period in proportion.

[0015] Preferably, the deviation assessment module is configured to compare the assessment parameters with the time error tolerance to determine whether the total allocation of the current control cycle needs to be corrected.

[0016] Beneficial effects: 1. This invention obtains historical carbon emission data from multiple carbon emission points and calculates emission change trends based on a trend analysis model to determine whether there is an intermittent pattern. If an intermittent pattern exists, the intermittent period within the corresponding control cycle is collected. If no intermittent pattern exists, it is designated as a continuous control period, thereby achieving accurate identification of the periodic characteristics of carbon emissions and providing a data foundation for subsequent refined allocation, thus avoiding the drawbacks of the extensive management of carbon emission patterns in traditional methods.

[0017] 2. This invention obtains the total demand within the target usage period, calibrates it as a benchmark value, calculates the deviation based on the demand data to output control recommendations, and corrects the benchmark value to the total control usage based on a calibration model; it determines the type of deviation by judging the relationship between the total control usage and the total demand, so that when formulating carbon emission control strategies, actual production needs and usage plans are fully considered to achieve a balance between carbon emission control and production operation, and avoids the impact of excessive control on normal production.

[0018] 3. This invention determines the total allocation based on the ratio between continuous control periods and intermittent periods, and determines the execution amount for each period based on the distribution of intermittent periods. By calculating the difference between the predicted amount and the actual amount in the previous control cycle, and comparing this difference with the time error tolerance as an evaluation parameter, it is determined whether the total allocation of the current control cycle needs to be corrected, thereby achieving adaptive allocation of carbon emission indicators and reducing the risk of resource waste or emission exceedance caused by prediction deviations. Attached Figure Description

[0019] Figure 1This is a flowchart of the method of the present invention; Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely for explaining the invention and are not intended to limit the scope of protection of the invention.

[0021] Example 1: Please refer to Figure 1 As shown, this embodiment provides a method for intelligent allocation of carbon emission quotas based on big data analysis, including the following steps: S1. Data collection and trend analysis; By deploying sensing devices at multiple carbon emission points, historical carbon emission data of each carbon emission point is automatically collected and acquired. The historical carbon emission data includes at least the emission amount and corresponding operating conditions within a predetermined time period, and the continuous statistical period covers the preset duration.

[0022] The collected raw data is transmitted to a unified area for preprocessing, which includes: Remove obvious outliers caused by sensor malfunctions or communication abnormalities; Furthermore, data of different dimensions are uniformly mapped to a standardized numerical range through specific mathematical transformations to obtain standardized sample data, ensuring the accuracy and comparability of subsequent calculations.

[0023] Based on preset trend calculation rules, the time series data of each carbon emission point is processed to calculate its emission change trend. The trend calculation rules refer to the preset logic and calculation steps used to analyze the direction and magnitude of emission changes in time series data. They output a continuous value representing the direction and magnitude of change by calculating the difference or ratio of emissions between adjacent statistical periods.

[0024] Specifically, the trend calculation rules are as follows: By calculating the difference or ratio of emissions between adjacent statistical periods, a continuous value that can characterize the direction and magnitude of change is output; by statistically analyzing the sequence of continuous values ​​within a continuous observation period, it is analyzed whether it exhibits the characteristics of frequent alternation between positive and negative values, and whether the absolute value of the numerical change exceeds the preset magnitude threshold multiple times. If the characteristics are significant, it is determined that there is an intermittent pattern in carbon emission points; conversely, if the numerical changes are stable or continuous in one direction, it is determined that there is no intermittent pattern.

[0025] Intermittent patterns refer to the significant, discontinuous, periodic, or irregular fluctuations in emissions from carbon emission points over a period of time. This is manifested in frequent alternations between positive and negative values, with the absolute value of the changes exceeding a preset threshold multiple times.

[0026] To further enhance the accuracy of trend judgment, this method also introduces a long-term trend auxiliary judgment mechanism. That is, by setting fixed statistical nodes, the total carbon emissions in the future estimated period are aggregated and calculated, and compared with the benchmark threshold set according to industry standards, historical average emissions or policy requirements, so as to help judge whether the carbon emission points show a continuous trend or an intermittent trend.

[0027] The estimated time period is based on historical data and current operating conditions, and is derived from future emission periods through calculation methods such as trend extrapolation. Specifically, the benchmark threshold is a reference value used to measure whether total carbon emissions are within a normal range or whether control measures are needed.

[0028] If the estimated total carbon emissions are greater than the baseline threshold, it is determined that the carbon emission point shows a continuous trend, that is, it is likely to maintain a high emission state during the estimated period, indicating that the emission change is stable or unidirectional and continuous, without significant intermittent fluctuations.

[0029] If the estimated total carbon emissions are less than or equal to the baseline threshold, it is judged as an intermittent trend, indicating that its emissions fluctuate or have periodic troughs, thus providing evidence for subsequent identification of intermittent patterns.

[0030] S2, Intermittent pattern extraction; For carbon emission points identified as exhibiting intermittent patterns, further identification of specific periods of low emissions is needed, specifically: Collect and analyze the operating load data and production equipment status information of carbon emission points during the same period of the current regulation cycle; By comparing real-time operating load data with preset low load thresholds, all periods when the load is below the threshold are identified. This is then cross-validated by combining production equipment operating information, and the confirmed low-carbon emission periods are integrated into intermittent periods that can be used for regulation.

[0031] The production equipment operating status information specifically refers to the records of whether the equipment is in standby or stopped state.

[0032] Furthermore, the low load threshold is a preset reference value used to determine whether the equipment's operating load is at a low level. When the real-time operating load is lower than this threshold, it indicates that the equipment may be in a low-emission state.

[0033] For carbon emission points that are determined to lack intermittent patterns, their entire regulation cycle is directly defined as a continuous regulation period, which usually corresponds to the period when emission peaks are concentrated.

[0034] In practical applications, when the daily average emissions of carbon emission points continue to rise by a percentage greater than a preset percentage for several consecutive days, this percentage is preferably 85%, and the period in which the emission peaks are concentrated is defined as the continuous control period.

[0035] The identified intermittent periods are divided into specific segments: Calculate the total duration of all intermittent periods and define the single continuous period with a duration greater than half of the total duration as the main intermittent period, which usually has greater regulatory potential. The remaining time periods with a duration less than or equal to half the total duration are defined as secondary intervals, which typically have less regulatory potential than the primary intervals.

[0036] This division of primary and secondary intermittent periods provides a clear basis for subsequent differentiated resource allocation based on different priorities.

[0037] S3. Total Statistics and Classification Determination; The total demand within the target usage period is obtained from external data sources such as energy management systems, and this total demand is set as the benchmark value for subsequent calculations. By comparing the benchmark value with the expected demand data of each carbon emission point, the deviation between the two is calculated. The deviation is used as input, and a preset regulation suggestion generation rule is applied to output preliminary regulation suggestions.

[0038] The regulation suggestion generation rule refers to the preset logical judgment and numerical calculation process. Specifically, the rule comprehensively considers the demand data, the calculated deviation, and the preset equipment load constraints. Through a series of logical judgments and numerical calculations, it generates a regulation scheme that can both meet basic production needs and achieve the goal of reducing energy consumption. Preferably, equipment load constraints are equipment operation limitations that must be considered when formulating control schemes, such as the minimum operating power of the equipment and the maximum number of start-stop cycles, in order to ensure the stability of the production process and the safety of the equipment.

[0039] Furthermore, a sample library containing data from multiple historical sample periods is established and dynamically maintained to improve the accuracy of total demand forecasting. The sample library is used to support the forecasting and trend identification of total demand.

[0040] At the start of each new cycle, the latest sample data is added to the buffer data area for trend identification, and the data sequence is sorted according to date. The buffer data area is a temporary storage area.

[0041] When making predictions, historical data close to the target prediction date are extracted from the buffer data area, preferably daily data from the previous few days or the same period last year. The demand trend of the target sample day is predicted by using weighted average or trend extrapolation calculation methods.

[0042] If the system verification finds that the current date does not match the target sample day data, such as missing or incorrect data, a preset shifting operation will be performed, namely: Use data from the previous period to replace or adjust the data, and then re-verify it to ensure the continuity and reliability of the trend judgment.

[0043] S4. Usage benefit analysis; Based on the established baseline value, it is corrected to obtain the final total amount of control. This correction process is completed according to the preset baseline value correction calculation rules.

[0044] The benchmark value correction calculation rule is a preset calculation method, specifically: It receives multiple input parameters such as historical deviation, current production load, and market carbon price fluctuations, and generates correction factors through weighted calculations to dynamically adjust the benchmark value to obtain a total control amount that better reflects the actual situation.

[0045] The correction factor is applied to the baseline value, for example, through multiplication or addition, to dynamically adjust the baseline value and obtain a dynamically adjusted total control amount that is more in line with the actual situation. After obtaining the total control amount, it is compared with the obtained total demand to determine the type of deviation. If the total amount of carbon emission quotas allocated exceeds the total demand, the deviation type is determined to be positive, indicating that the actual carbon emission quotas allocated exceed the expected demand. If the total amount of carbon emission quotas used for regulation is less than the total demand, the deviation type is determined to be negative, indicating that the actual carbon emission quotas allocated have failed to meet the expected demand.

[0046] The determination of this type of deviation will serve as the basis for subsequent fine-tuning of the control strategy.

[0047] S5. Execution quantity determination; Based on the proportion of continuous control periods and intermittent periods in the entire control cycle, the total allocation to the intermittent periods is determined. Combining the determined distribution of primary and secondary intermittent periods, the total allocation is further refined to each specific execution period. The specific allocation process is as follows: consult the preset intermittent execution ratio table, which stores different priority allocation ratios. The intermittent execution ratio table specifies the proportion of the total allocation that each primary and secondary intermittent period should occupy, based on the classification of primary and secondary intermittent periods. Primary intermittent periods are of high priority, and secondary intermittent periods are of low priority.

[0048] The intermittent execution ratio table specifies the proportion of the total allocation to be allocated to each entity, and is used to guide the detailed allocation of carbon emission quotas.

[0049] The total allocation is divided according to the proportion of the total allocation due, and the calculated share, i.e. the amount to be used, is clearly marked to each main interval and secondary interval, forming a detailed execution plan.

[0050] S6. Deviation correction judgment and periodic update; After each regulation cycle ends, the difference between the predicted and actual carbon emissions at each emission point in the previous regulation cycle is calculated, and the difference is defined as an evaluation parameter to measure the degree of agreement between prediction and execution.

[0051] The absolute value of the evaluation parameter is compared with a preset allowable deviation threshold to determine whether the allocation scheme for the current control cycle needs to be corrected. The allowable deviation threshold refers to the preset maximum permissible error value used to determine whether the evaluation parameter is within an acceptable range. If the absolute value of the evaluation parameter exceeds this threshold, the correction process needs to be initiated.

[0052] If the evaluation parameter is less than the allowable deviation threshold, it indicates that the forecast and implementation of the previous adjustment period are basically in line with the actual situation, and no correction is needed. The allocation plan for the current adjustment cycle will be implemented as originally planned. If the evaluation parameter is greater than the allowable deviation threshold, it indicates a significant deviation, and a correction process needs to be initiated. The correction process is as follows: The calculated difference, i.e. the portion of the evaluation parameter that exceeds the threshold, is multiplied by a preset offset parameter, which is used as a weighting factor, to obtain the basic correction value. The offset parameter refers to the preset value used as a weighting factor to convert the portion of the evaluation parameter that exceeds the allowable deviation threshold into the basic correction value.

[0053] The base correction value can be further adjusted by multiplying it by an additional correction factor based on the urgency of the current production plan or changes in equipment operating status, ultimately yielding the final correction value used to update the total allocation for the next control cycle.

[0054] The corrected values ​​will be used to regenerate the corrected allocation scheme. Specifically, they will be redistributed to the main and secondary intermittent segments of the next control cycle according to preset rules, thereby achieving closed-loop correction of historical deviations.

[0055] S7. Output a new cycle control plan; Based on the revised allocation data, the system automatically re-plans the available duration and corresponding execution volume of each intermittent period for the next control cycle, and generates a new, visualized control scheduling chart.

[0056] The control and scheduling chart can support display at different time granularities such as daily, weekly, and monthly, and can provide standardized data interfaces to push control plans to the enterprise energy consumption monitoring platform in real time for synchronous deployment and execution, thereby completing the closed-loop operation of the entire control cycle.

[0057] Example 2: Please refer to Figure 2 As shown, this embodiment provides a carbon emission quota intelligent allocation system based on big data analysis, used to execute the aforementioned carbon emission quota intelligent allocation method based on big data analysis, including the following modules: The emissions data acquisition module is configured to acquire historical carbon emission data from carbon emission points and the actual usage in the previous regulation cycle.

[0058] In the specific execution process, the emission data acquisition module connects to various sensors, monitoring equipment or internal enterprise data systems through interfaces to collect carbon emission data from each carbon emission point in real time or periodically.

[0059] Historical carbon emission data includes, but is not limited to, information such as emission amount, emission time, and emission source, and is stored in the data storage unit of the system to form historical carbon emission data.

[0060] The emissions data acquisition module is also responsible for obtaining the actual carbon consumption at each emission point at the end of the previous regulation cycle. The actual consumption data will serve as the basis for subsequent assessments and corrections.

[0061] The deviation assessment module is configured to calculate assessment parameters based on a comparison between the predicted dosage and the actual dosage for the previous control cycle.

[0062] In the specific execution process, the deviation assessment module receives the actual usage of the previous control cycle provided by the emission data acquisition module. At the same time, the system stores or generates the predicted usage for the previous control cycle. The deviation assessment module compares the predicted usage with the actual usage. Specifically, the evaluation parameters can be obtained by calculating the difference, percentage deviation, or other statistical indicators between the two. The evaluation parameters reflect the degree of deviation between the forecast and the actual situation in the previous control cycle.

[0063] Furthermore, the deviation assessment module is further configured to compare the assessment parameters with the time error tolerance to generate a judgment result indicating whether the total allocation of the current control cycle needs to be corrected, and to provide the judgment result to the indicator allocation decision module. For example, if the assessment parameters exceed the preset time error tolerance, it is judged that correction is needed; otherwise, it is judged that no correction is needed.

[0064] The indicator allocation decision module is configured to: determine the total allocation amount for the current control cycle and the execution amount for each period within the current control cycle in response to the assessment parameters provided by the deviation assessment module and in combination with the historical carbon emission data provided by the emission data acquisition module.

[0065] In the specific execution process, the indicator allocation decision module receives the evaluation parameters and judgment results provided by the deviation evaluation module.

[0066] If the judgment result indicates that correction is needed, the indicator allocation decision module will adjust the benchmark allocation based on the evaluation parameters to determine the total allocation amount for the current control cycle. Specifically: If the actual usage in the previous adjustment cycle was significantly higher than the predicted usage, the assessment parameters will indicate that the baseline allocation needs to be lowered or other adjustments need to be made.

[0067] In some implementations, the modification may include: The assessment parameters are compared with the time error tolerance to determine whether the total allocation of the current control cycle needs to be corrected. If corrections are needed, the baseline allocation will be adjusted according to the specific values ​​of the evaluation parameters and the preset correction rules, such as by reducing or increasing it proportionally.

[0068] In a further implementation, before determining the benchmark allocation, the indicator allocation decision module can first obtain the total demand within the target usage period and set the total demand as the benchmark value; calculate the deviation based on the benchmark value and output the control suggestion; and correct the benchmark value to the total control usage based on the correction model, so as to serve as the benchmark allocation.

[0069] After determining the total allocation, the indicator allocation decision module further analyzes historical carbon emission data to determine whether there is an intermittent pattern. Specifically, the indicator allocation decision module obtains historical carbon emission data of carbon emission points, calculates the emission change trend of each carbon emission point based on the trend analysis model, and determines whether there is an intermittent pattern based on the emission change trend. For example, by setting statistical nodes, the total carbon emission within the estimated period is obtained and compared with the set benchmark threshold. If the total carbon emission is higher than the benchmark threshold, it is judged as a continuous trend; otherwise, it is judged as an intermittent trend. If an intermittent pattern exists, the intermittent period within the corresponding control cycle is collected. If no intermittent pattern exists, the control cycle is defined as a continuous control period. If an intermittent pattern exists, the total allocation is distributed to each period based on the distribution of the identified intermittent periods. Specifically, the indicator allocation decision module determines the execution amount for each period based on the ratio between the continuous control period and the intermittent period, combined with the distribution of the intermittent periods. The distribution of the intermittent periods may include dividing the intermittent period into one or more main intermittent segments with a duration greater than half of the total intermittent period, and one or more secondary intermittent segments. Determining the execution amount for each period further includes distributing the total allocation proportionally to the main intermittent segments and secondary intermittent segments. For example, the main intermittent segments may receive a higher proportion of allocation to address their more significant intermittent characteristics.

[0070] The above description is merely a preferred embodiment of this application and is not intended to limit this application. For those skilled in the art, this application can have various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for intelligent allocation of carbon emission quotas based on big data analysis, characterized in that, include: Determine the total allocation amount for the current control cycle, including assessment parameters based on a comparison of the predicted and actual usage amounts for the previous control cycle, and adjust the baseline allocation accordingly. Based on the determined total allocation and the analysis results of historical carbon emission data, the implementation amount for each period within the current regulation cycle is determined. The determination of the analysis results of historical carbon emission data includes: obtaining historical carbon emission data of carbon emission points; calculating the emission change trend of each carbon emission point based on the trend analysis model, and judging whether there is an intermittent pattern based on the emission change trend; and if there is an intermittent pattern, collecting the intermittent period within the corresponding control cycle; if there is no intermittent pattern, defining the control cycle as a continuous control period. Determining whether there is an intermittent pattern in emission change trends involves setting statistical nodes, obtaining the total carbon emissions within the estimated period, and comparing it with a set benchmark threshold. If the total carbon emissions are higher than the benchmark threshold, it is judged as a continuous trend; otherwise, it is judged as an intermittent trend. Based on the determined total allocation and the analysis results of historical carbon emission data, the execution amount for each period within the current control cycle is determined, including: determining the execution amount for each period based on the ratio between continuous control periods and intermittent periods, combined with the distribution of intermittent periods; The distribution of intermittent periods includes: dividing the intermittent periods into one or more main intermittent periods with a duration greater than half of the total intermittent period time, and the remaining one or more secondary intermittent periods; and determining the execution usage for each period further includes allocating the total allocation to the main intermittent periods and secondary intermittent periods proportionally; The method further includes: obtaining the total demand within the target usage period and calibrating the total demand as a benchmark value; calculating the deviation based on the benchmark value and outputting control suggestions; and correcting the benchmark value to the total control usage based on the correction model, so as to serve as the benchmark allocation.

2. The intelligent allocation method for carbon emission quotas based on big data analysis according to claim 1, characterized in that, The baseline allocation is adjusted based on the evaluation parameters obtained by comparing the predicted and actual usage of the previous control cycle. This includes comparing the evaluation parameters with the time error tolerance to determine whether the total allocation for the current control cycle needs to be adjusted.

3. A carbon emission quota intelligent allocation system based on big data analysis, used to execute the carbon emission quota intelligent allocation method based on big data analysis as described in claim 1 or 2, characterized in that, include: The emissions data acquisition module is used to acquire historical carbon emission data from carbon emission points and the actual usage in the previous regulation cycle; The deviation assessment module is used to calculate assessment parameters by comparing the predicted dosage with the actual dosage in the previous control cycle. And the indicator allocation decision module, which is configured to: in response to the assessment parameters provided by the deviation assessment module and in combination with the historical carbon emission data provided by the emission data acquisition module, determine the total allocation amount for the current control cycle and the execution amount for each period within the current control cycle.

4. The intelligent carbon emission quota allocation system based on big data analysis according to claim 3, characterized in that, When determining the amount to be allocated, the indicator allocation decision module is configured to: analyze historical carbon emission data to determine whether there is an intermittent pattern; and if there is an intermittent pattern, allocate the total amount to each time period according to the distribution of the identified intermittent periods.

5. The intelligent carbon emission quota allocation system based on big data analysis according to claim 4, characterized in that, The indicator allocation decision module is configured to divide the intermittent period into a main intermittent period and a secondary intermittent period, and allocate the total allocation amount to the main intermittent period and the secondary intermittent period proportionally.

6. The intelligent carbon emission quota allocation system based on big data analysis according to claim 5, characterized in that, The deviation assessment module is configured to compare the assessment parameters with the time error tolerance to determine whether the total allocation of the current control cycle needs to be corrected.

Images