Carbon emission regulation method and platform for low-carbon industrial park construction based on big data analysis

Abstract

The application provides a low-carbon industrial park construction carbon emission regulation and control method and platform based on big data analysis, relates to the technical field of carbon emission regulation and control, and comprises the following steps: performing zero-carbon adaptability analysis on multiple devices in the industrial park; performing zero-carbon regulation and control analysis on zero-carbon device clusters according to current carbon emission data sets of the industrial park; performing scene application carbon emission mining according to non-zero-carbon device clusters; identifying emission reduction targets for non-zero-carbon device clusters according to expected carbon emission data sets and current carbon emission data sets; performing carbon emission sensitivity testing according to control index sets of the emission reduction target devices; based on the emission reduction target, performing optimization adjustment on the emission reduction target devices according to an emission reduction regulation and control first factor and an emission reduction regulation and control second factor; and performing self-adaptive carbon emission regulation and control on the industrial park according to zero-carbon regulation and control strategies and emission reduction regulation and control strategies. Through the application, precise regulation and control can be performed according to actual carbon emission of devices, and the technical effect of improving overall carbon emission efficiency of the park can be achieved.

Description

Technical Field

[0001] This application relates to the field of carbon emission control technology, and in particular to a carbon emission control method and platform for the construction of low-carbon industrial parks using big data analysis. Background Technology

[0002] Carbon emission management in industrial parks has become a crucial aspect of reducing overall carbon footprint. Currently, many industrial parks have begun to adopt clean energy, energy efficiency optimization, and carbon emission monitoring to reduce carbon emissions. However, existing technologies still have many shortcomings in carbon emission control, making it difficult to meet the low-carbon operation requirements of industrial parks in complex scenarios.

[0003] Currently, existing technologies mainly rely on traditional carbon emission monitoring platforms. These platforms typically focus on single devices or fixed areas, lacking the ability to analyze the overall carbon emissions of all equipment in the entire industrial park. Furthermore, traditional carbon emission monitoring technologies often employ periodic sampling, resulting in delayed data updates and hindering real-time carbon emission control. Simultaneously, traditional methods for carbon emission optimization often rely on rules of thumb or fixed threshold settings, lacking the ability to dynamically adapt to the operating environment and actual emissions, making it difficult to accurately match carbon reduction measures to actual needs. Moreover, current low-carbon management methods in industrial parks fail to effectively integrate zero-carbon and non-zero-carbon equipment, failing to achieve differentiated carbon emission control. While some parks have introduced zero-carbon equipment, such as photovoltaic power generation and energy storage platforms, their potential has not been fully realized in actual operation, and their synergistic optimization capabilities with other high-carbon-emission equipment are insufficient. In addition, carbon emission optimization for non-zero-carbon equipment is usually limited to the individual device level, lacking a full life-cycle carbon management strategy and failing to form a platform-based carbon emission optimization path.

[0004] In summary, existing technologies suffer from a lack of capability to analyze the overall carbon emissions of all equipment in the industrial park, making it difficult to accurately implement carbon emission optimization measures and further impacting the efficiency and effectiveness of low-carbon management in industrial parks. Summary of the Invention

[0005] The purpose of this application is to provide a method and platform for carbon emission control in the construction of low-carbon industrial parks based on big data analysis, in order to solve the technical problem in existing technologies where the lack of ability to analyze the overall carbon emissions of all equipment in the park makes it difficult to accurately implement carbon emission optimization measures, which further affects the efficiency and effectiveness of low-carbon management in industrial parks.

[0006] In view of the above problems, this application provides a method and platform for controlling carbon emissions in the construction of low-carbon industrial parks based on big data analysis.

[0007] Firstly, this application provides a carbon emission control method for the construction of low-carbon industrial parks based on big data analysis. This method is implemented through a big data analysis platform for carbon emission control in low-carbon industrial park construction. The method includes: performing zero-carbon adaptability analysis on multiple devices in the industrial park to obtain zero-carbon device clusters and non-zero-carbon device clusters; performing zero-carbon control analysis on the zero-carbon device clusters based on the current carbon emission dataset of the industrial park to obtain a zero-carbon control strategy; performing scenario application carbon emission mining on the non-zero-carbon device clusters to determine a desired carbon emission dataset; identifying emission reduction targets for the non-zero-carbon device clusters based on the desired carbon emission dataset and the current carbon emission dataset to determine the emission reduction targets corresponding to the target devices; conducting carbon emission sensitivity testing based on the control index set of the target devices to determine a first emission reduction control factor and a second emission reduction control factor; optimizing and adjusting the target devices based on the emission reduction targets, according to the first and second emission reduction control factors, to obtain an emission reduction control strategy; and performing adaptive carbon emission control on the industrial park based on the zero-carbon control strategy and the emission reduction control strategy.

[0008] Secondly, this application also provides a carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis, used to execute the carbon emission control method for the construction of low-carbon industrial parks based on big data analysis as described in the first aspect, including: a zero-carbon fitness analysis module, used to perform zero-carbon fitness analysis on multiple devices in the industrial park to obtain zero-carbon device clusters and non-zero-carbon device clusters; a zero-carbon control analysis module, used to perform zero-carbon control analysis on the zero-carbon device clusters based on the current carbon emission dataset of the industrial park to obtain zero-carbon control strategies; a scenario application carbon emission mining module, used to perform scenario application carbon emission mining based on the non-zero-carbon device clusters to determine the expected carbon emission dataset; and an emission reduction target identification module, used to... The emission reduction targets for the non-zero carbon equipment cluster are identified based on the expected carbon emission dataset and the current carbon emission dataset, and the emission reduction targets corresponding to the target equipment are determined. A carbon emission sensitivity testing module is used to perform carbon emission sensitivity testing based on the control index set of the target equipment to determine the first emission reduction control factor and the second emission reduction control factor. An optimization adjustment module is used to optimize the emission reduction target equipment based on the emission reduction targets and the first and second emission reduction control factors to obtain an emission reduction control strategy. An adaptive carbon emission control module is used to adaptively control the carbon emission of the industrial park based on the zero-carbon control strategy and the emission reduction control strategy.

[0009] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goal of carbon emission management and dynamic optimization control of all equipment in the park, it achieves the technical effect of precise control based on the actual carbon emission of the equipment, improving the overall carbon emission efficiency of the park, and ensuring that the carbon emission of key equipment is minimized or zero in different scenarios.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 A flowchart illustrating the carbon emission control method for building a low-carbon industrial park based on big data analysis in this application;

[0013] Figure 2 A schematic diagram of the structure for building a carbon emission control platform for the low-carbon industrial park based on big data analysis in this application.

[0014] Figure labeling: Zero-carbon adaptability analysis module 11, Zero-carbon regulation analysis module 12, Scenario application carbon emission mining module 13, Emission reduction target identification module 14, Carbon emission sensitivity testing module 15, Optimization adjustment module 16, Adaptive carbon emission regulation module 17. Detailed Implementation

[0015] This application addresses the technical problem in existing technologies where the lack of comprehensive carbon emission analysis capabilities for all equipment within the industrial park hinders the precise implementation of carbon emission optimization measures, thus impacting the efficiency and effectiveness of low-carbon management. It provides a method and platform for carbon emission control in the construction of low-carbon industrial parks based on big data analysis. The goal is to achieve precise control based on actual equipment emissions, thereby improving the overall carbon emission efficiency of the park and ensuring that carbon emissions from key equipment are minimized or reduced to zero under different scenarios.

[0016] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0017] Example 1, please refer to the appendix. Figure 1 This application provides a method for carbon emission control in the construction of low-carbon industrial parks based on big data analysis, which is applied to a big data analysis-based carbon emission control platform for the construction of low-carbon industrial parks. The method specifically includes the following steps:

[0018] S1: Conduct zero-carbon adaptability analysis on multiple pieces of equipment in the industrial park to obtain zero-carbon equipment clusters and non-zero-carbon equipment clusters.

[0019] Further, S1 includes: S11: collecting current application scenario information of the multiple devices to obtain multiple device application scenarios; S12: evaluating the zero-carbon adaptability of the multiple device application scenarios to obtain multiple scenario zero-carbon adaptability; S13: extracting the first scenario zero-carbon adaptability based on the multiple scenario zero-carbon adaptability, and determining whether the first scenario zero-carbon adaptability is greater than or equal to a predetermined zero-carbon adaptability; S14: if the first scenario zero-carbon adaptability is greater than or equal to the predetermined zero-carbon adaptability, recording the device corresponding to the first scenario zero-carbon adaptability as a zero-carbon device, and adding the zero-carbon device to the zero-carbon device cluster; S15: if the first scenario zero-carbon adaptability is less than the predetermined zero-carbon adaptability, recording the device corresponding to the first scenario zero-carbon adaptability as a non-zero-carbon device, and adding the non-zero-carbon device to the non-zero-carbon device cluster.

[0020] Specifically, in industrial parks, numerous pieces of equipment participate in production, office work, or other functions, each with different energy consumption patterns and carbon emissions. Zero-carbon adaptability analysis assesses the adaptability of multiple pieces of equipment in low-carbon or zero-carbon environments, i.e., whether they can operate on clean energy or have low carbon emission levels. To conduct zero-carbon adaptability analysis, it's essential to first understand the actual usage scenarios of the equipment, i.e., their application scenarios, ensuring the assessment is based on real operational data to improve the accuracy of the analysis. Application scenarios refer to the equipment's operating mode, usage frequency, energy consumption structure, etc.

[0021] Zero-carbon adaptability is evaluated for each application scenario, resulting in multiple scenario-based zero-carbon adaptability scores. Zero-carbon adaptability refers to whether a device's carbon emission level in a given scenario meets zero-carbon requirements. For example, if a device should not generate carbon emissions in specific scenarios such as standby, idling, or shutdown, or if the device should not generate carbon emissions in its application scenario, then its zero-carbon adaptability is high. Conversely, if a device should generate carbon emissions in its application scenario, its zero-carbon adaptability is low. Through this evaluation, each device receives an adaptability score in different scenarios for subsequent classification and decision-making.

[0022] From the fitness results of multiple scenarios, the zero-carbon fitness of one scenario is randomly extracted and referred to as the first scenario zero-carbon fitness. Then, the first scenario zero-carbon fitness is compared with a predetermined zero-carbon fitness, which is a benchmark used to determine whether a device is zero-carbon. For example, if the predetermined zero-carbon fitness is 80%, and a device's first scenario zero-carbon fitness is 90%, it indicates that the device has good zero-carbon capabilities in this scenario.

[0023] If the zero-carbon adaptability in the first scenario is greater than or equal to the predetermined zero-carbon adaptability, it indicates that the device possesses good zero-carbon capabilities. The device corresponding to the zero-carbon adaptability in the first scenario is designated as a zero-carbon device and categorized into a zero-carbon device cluster. A zero-carbon device cluster is a collection of multiple zero-carbon devices. For example, if a wind turbine achieves 100% zero-carbon adaptability, it will be classified into the zero-carbon device cluster because it operates entirely on clean energy and emits no carbon.

[0024] If the zero-carbon adaptability of the first scenario is less than the predetermined zero-carbon adaptability, it indicates that it still has high carbon emissions or relies on traditional energy sources. Equipment corresponding to the zero-carbon adaptability of the first scenario is denoted as non-zero-carbon equipment, and these non-zero-carbon equipment are grouped into a non-zero-carbon equipment cluster. A non-zero-carbon equipment cluster is a collection of multiple non-zero-carbon equipment. For example, a diesel generator may have a zero-carbon adaptability of only 30%, and therefore would be grouped into a non-zero-carbon equipment cluster for subsequent modification or optimization.

[0025] S2: Based on the current carbon emission dataset of the industrial park, perform zero-carbon regulation analysis on the zero-carbon equipment cluster to obtain a zero-carbon regulation strategy.

[0026] Further, S2 includes: S21: performing feature recognition on the current carbon emission dataset based on the zero-carbon device cluster to obtain carbon emission data of multiple zero-carbon devices; S22: determining whether the carbon emission data of the multiple zero-carbon devices is zero; S23: if any one of the carbon emission data of the multiple zero-carbon devices is not zero, obtaining a zero-carbon control device; S24: performing zero-carbon control on the zero-carbon control device to generate the zero-carbon control strategy.

[0027] Specifically, zero-carbon control analysis is performed on the zero-carbon equipment cluster based on the industrial park's current carbon emission dataset. The current carbon emission dataset includes the current carbon emission data for each piece of equipment in the industrial park. Feature identification is performed on the current carbon emission dataset based on the zero-carbon equipment cluster to obtain carbon emission data for multiple zero-carbon equipment. Feature identification refers to extracting information related to zero-carbon equipment from the dataset, such as the equipment's electricity consumption, energy source, and actual carbon emissions. Zero-carbon equipment carbon emission data refers to the carbon emissions generated by these devices during operation. For example, a wind turbine's carbon emissions may be close to zero, while an electric forklift may still have a small amount of carbon emissions due to the use of some fossil fuels during charging. Through feature identification, the carbon emission information of zero-carbon equipment can be accurately screened, providing data support for subsequent analysis.

[0028] This step involves determining whether the carbon emission data of multiple zero-carbon devices are truly zero, and whether their carbon emission values ​​are indeed zero. Ideally, zero-carbon devices should produce no carbon emissions. However, in practical applications, factors such as the operating environment and energy structure may lead to some carbon emissions. For example, a device might have zero carbon emissions during the day when using solar power, but at night, when powered by a backup power grid, it might produce a small amount of carbon emissions. Therefore, the purpose of this step is to confirm whether the zero-carbon devices have truly achieved a zero-carbon state, or whether some carbon emissions still exist.

[0029] If the carbon emission data of any one of the multiple zero-carbon devices is not zero, indicating that some zero-carbon devices are still emitting carbon, further screening is needed to identify these devices and determine the zero-carbon control devices. Zero-carbon control devices refer to those devices that should theoretically achieve zero carbon emissions but still emit carbon in actual operation. The purpose of identifying zero-carbon control devices is to provide target objects for the next step of zero-carbon control strategies, in order to optimize their operating modes or adjust their energy sources.

[0030] Once the zero-carbon control equipment is identified, it needs to be controlled in a zero-carbon manner. Zero-carbon control refers to reducing or even eliminating the carbon emissions of these devices by optimizing their operation, adjusting the energy structure, or introducing new technologies, thus generating a zero-carbon control strategy.

[0031] S3: Based on the non-zero carbon device cluster, perform scenario application carbon emission mining to determine the expected carbon emission dataset.

[0032] Further, S3 includes: S31: taking the application scenario corresponding to the nth non-zero carbon device in the non-zero carbon device cluster as the nth target application scenario, where n is a positive integer; S32: performing normal carbon emission sample retrieval on the nth non-zero carbon device according to the nth target application scenario to obtain the normal carbon emission sample set of the nth device; S33: performing central value calculation on the normal carbon emission sample set of the nth device to obtain the expected carbon emission data of the nth device, and adding the expected carbon emission data of the nth device to the expected carbon emission dataset.

[0033] Specifically, carbon emission mining is performed based on the application scenarios of non-zero carbon device clusters. Application scenario carbon emission mining refers to analyzing the carbon emission patterns of these devices in their actual application scenarios to determine the desired carbon emission dataset. Each device in the non-zero carbon device cluster has a specific application scenario. For example, boilers are used for heating, forklifts for material handling, and air conditioners for temperature control. The application scenario corresponding to the nth non-zero carbon device in the cluster is defined as the nth target application scenario. The nth non-zero carbon device refers to a randomly selected device in this cluster. Here, n is a positive integer. The application scenario corresponding to this device is defined as the nth target application scenario, i.e., the usage environment in which the device operates under specific conditions. The specific usage scenarios of each device are clearly defined to facilitate subsequent analysis of its carbon emissions.

[0034] After identifying the nth target application scenario, it is necessary to perform a normal carbon emission sample retrieval for the equipment's carbon emissions under that scenario to obtain the nth equipment normal carbon emission sample set. Normal carbon emission sample retrieval refers to searching for carbon emission data consistent with the normal operating conditions of the equipment in historical operational data. For example, the carbon emission data of a gas-fired boiler may differ under full-load, half-load, and standby conditions; therefore, the retrieval needs to filter out carbon emission data specific to the target scenario to ensure data accuracy. The nth equipment normal carbon emission sample set refers to multiple carbon emission sample data collected during this process, such as a collection of carbon emission records for the equipment under the same environment over the past month. This data reflects the actual carbon emission level of the equipment, providing a basis for further calculations.

[0035] Central tendency calculation is performed based on the normal carbon emission sample set of the nth device. This involves using statistical methods to obtain a value that represents the carbon emission characteristics of the device, such as calculating the mean, median, or mode, to obtain the expected carbon emission data for the nth device. The expected carbon emission data for the nth device refers to the anticipated carbon emission value calculated based on the normal carbon emission sample under the device's target application scenario. The expected carbon emission data for the nth device is added to the expected carbon emission dataset to assess whether the device's carbon emissions exceed a reasonable range.

[0036] S4: Identify emission reduction targets for the non-zero carbon equipment cluster based on the expected carbon emission dataset and the current carbon emission dataset, and determine the emission reduction targets corresponding to the emission reduction target equipment.

[0037] Further, S4 includes: S41: Extracting the carbon emission data of the nth non-zero carbon device corresponding to the current carbon emission dataset; S42: Determining whether the carbon emission data of the nth device meets the expected carbon emission data of the nth device; S43: If the carbon emission data of the nth device does not meet the expected carbon emission data of the nth device, adding the nth non-zero carbon device to the emission reduction target device, and performing a difference analysis between the expected carbon emission data of the nth device and the carbon emission data of the nth device to generate the emission reduction target.

[0038] Specifically, based on the expected carbon emission dataset and the current carbon emission dataset, emission reduction targets are identified for non-zero carbon equipment clusters to determine the corresponding emission reduction targets for the target equipment. Target equipment refers to equipment whose actual carbon emissions are higher than the expected carbon emissions, while the emission reduction targets are specific emission reduction requirements formulated for these devices, such as reducing energy consumption or optimizing emission control strategies.

[0039] Based on the current carbon emission dataset, extract the carbon emission data for the nth non-zero carbon device. The nth non-zero carbon device is a random device within the cluster of non-zero carbon devices, used to identify different devices. The carbon emission data for the nth device refers to the carbon emissions of that device under its current operating conditions. For example, the carbon emission data for a gas-fired boiler might be 250 kg, while the carbon emission data for a diesel generator might be 350 kg. The purpose of extracting this data is to subsequently compare it with the expected carbon emission data to determine whether the device has achieved the ideal carbon emission level.

[0040] Determine whether the carbon emission data of device n meets the expected carbon emission data for device n. After obtaining the carbon emission data of device n, it is necessary to compare it with the corresponding expected carbon emission data. Meeting the expected carbon emission data means that the actual carbon emissions of the device are within a reasonable range and do not exceed the set target value; if it does not meet the target, it means that the carbon emissions of the device exceed the standard and additional measures need to be taken for optimization.

[0041] If the carbon emission data of device n does not meet its expected carbon emission data, the nth non-zero carbon device is added to the emission reduction target devices. If the actual carbon emission of a device is higher than its expected carbon emission data, then the device needs to be classified as an emission reduction target device, that is, included in the key emission reduction management scope. A difference analysis is performed on the expected carbon emission data and the actual carbon emission data of device n, i.e., the difference between the actual carbon emission data and the expected carbon emission data of the device, to assess the specific situation of excessive carbon emissions and generate emission reduction targets.

[0042] S5: Conduct carbon emission sensitivity tests based on the control index set of the emission reduction target equipment to determine the first emission reduction regulation factor and the second emission reduction regulation factor.

[0043] Further, S5 includes: S51: performing carbon emission sensitivity tests on the control index set according to a predetermined step size sequence to obtain multiple carbon emission sensitivity test sequences; S52: performing lumped value calculations on the multiple carbon emission sensitivity test sequences to obtain multiple index carbon emission sensitivity coefficients; S53: classifying the control index set according to the multiple index carbon emission sensitivity coefficients to obtain the first emission reduction regulation factor that is greater than or equal to the predetermined carbon emission sensitivity coefficient, and the second emission reduction regulation factor that is less than the predetermined carbon emission sensitivity coefficient.

[0044] Further, S51 includes: S511: reading the current control decision and current carbon emission data of the equipment corresponding to the emission reduction target equipment; S512: extracting a first control indicator according to the control indicator set; S513: using the first control indicator as a floating variable, randomly perturbing the current control decision of the equipment according to the predetermined step size sequence to obtain multiple perturbation control decisions; S514: performing carbon emission prediction on the emission reduction target equipment according to the multiple perturbation control decisions to obtain multiple carbon emission prediction data; S515: evaluating the carbon emission change intensity of the multiple carbon emission prediction data according to the current carbon emission data of the equipment to obtain multiple carbon emission change intensities; S516: outputting the multiple carbon emission change intensities as a first carbon emission sensitive test sequence, and adding the first carbon emission sensitive test sequence to the multiple carbon emission sensitive test sequences.

[0045] Specifically, this involves reading the current control decisions and current carbon emission data of the equipment corresponding to the emission reduction target equipment. The current control decisions refer to the operating parameters or control strategies of the equipment in its current state, such as the opening degree of the gas valve of a gas boiler, the speed of an electric motor, or the temperature setpoint of an air conditioner.

[0046] Equipment with emission reduction targets refers to equipment whose actual carbon emissions exceed the expected value, requiring emission reduction measures. Current carbon emission data for equipment refers to the carbon emissions of that equipment under current operating conditions. Once this data is obtained, adjustments can be made to the equipment's operation to optimize carbon emission levels.

[0047] Based on the set of control indicators, the first control indicator is extracted. The set of control indicators refers to the collection of key parameters affecting equipment operation. For example, a gas-fired boiler may include multiple control indicators such as gas flow rate, combustion temperature, and flue gas concentration. The first control indicator is the first parameter selected for adjustment and optimization; for example, gas flow rate can be chosen as the optimization target. The purpose of extracting this indicator is to subsequently adjust the equipment operating parameters to analyze their impact on carbon emissions.

[0048] Using the primary control index as a floating variable—a variable that can be adjusted within a certain range, such as the gas flow rate of a gas-fired boiler, which can vary between 0 and 100 kg / h—multiple perturbation control decisions are obtained by randomly perturbing the current control decision of the equipment according to a predetermined step size sequence. The predetermined step size sequence refers to the set of values ​​for adjusting the control variable at fixed intervals; for example, if the step size is set to 10 kg / h, the gas flow rate can vary between values ​​such as 50 kg / h, 60 kg / h, and 70 kg / h. Random perturbation involves adding random variations to these fixed step sizes to simulate different control strategies; for example, the gas flow rate can be adjusted to 65 kg / h or 75 kg / h. In this way, multiple perturbation control decisions, i.e., different combinations of control parameters, can be obtained for subsequent carbon emission prediction.

[0049] Carbon emission predictions are performed on target equipment based on multiple disturbance control decisions, resulting in multiple carbon emission prediction data sets. Carbon emission prediction refers to using mathematical models or data analysis methods to predict the carbon emissions of equipment under different control parameters. For example, if the gas flow rate increases to 65 kg / h, the predicted carbon emission is 250 kg / h, while if it decreases to 55 kg / h, the predicted carbon emission is 220 kg / h. Multiple carbon emission prediction data sets refer to the set of carbon emission results under different disturbance conditions, used to evaluate which control strategies are more conducive to emission reduction.

[0050] Based on the current carbon emission data of the equipment, the intensity of carbon emission change is evaluated for multiple predicted carbon emission data, resulting in multiple carbon emission change intensities. The current carbon emission data represents the actual carbon emission value under operating conditions, while the predicted carbon emission data is the expected carbon emission value calculated based on different disturbance control decisions. The evaluation of carbon emission change intensity refers to calculating the degree of carbon emission change before and after the disturbance. For example, if the current carbon emission data of the equipment is 250 kg, and the predicted carbon emission data under different control decisions are 240 kg, 230 kg, and 260 kg, then the corresponding carbon emission change intensities can be expressed as a decrease of 10 kg, a decrease of 20 kg, and an increase of 10 kg. Multiple carbon emission change intensities refer to the set of carbon emission change intensities calculated under all disturbance scenarios, used to analyze the impact of different control decisions on carbon emissions.

[0051] The output of multiple carbon emission change intensities is designated as the first carbon emission sensitivity test sequence. This sequence refers to a series of sensitivity analysis results regarding the equipment's carbon emissions to changes in control parameters. The first carbon emission sensitivity test sequence is a set of currently calculated test data, representing how different adjustments to a control variable affect carbon emissions, such as the increase or decrease in carbon emissions when the gas flow rate is adjusted. The first carbon emission sensitivity test sequence is then added to multiple carbon emission sensitivity test sequences. Multiple carbon emission sensitivity test sequences refer to multiple data sets obtained after performing similar analyses on different control variables; for example, in addition to gas flow rate, the impact of combustion temperature and air supply on carbon emissions can also be tested. By collecting all the sensitivity test data, a complete equipment carbon emission characteristic analysis system can be established, assisting in the formulation of optimal emission reduction strategies.

[0052] Central mean squared value (CMS) calculations were performed on multiple carbon emission sensitivity test sequences to obtain carbon emission sensitivity coefficients for various indicators. CMS calculation involves statistically analyzing these data to obtain numerical values ​​representing the overall trend, such as the average, median, or weighted average. The carbon emission sensitivity coefficients for multiple indicators represent the calculated impact of each control indicator on carbon emissions. For example, if a change in gas flow rate leads to an average reduction of 30 kg in carbon emissions, while a change in combustion temperature leads to a reduction of 20 kg, the corresponding carbon emission sensitivity coefficients are 30 and 20, respectively. These coefficients are used to assess the importance of each control parameter in the emission reduction process.

[0053] The control index set is classified based on the carbon emission sensitivity coefficients of multiple indicators to obtain the first emission reduction control factor (greater than or equal to a predetermined carbon emission sensitivity coefficient) and the second emission reduction control factor (less than the predetermined carbon emission sensitivity coefficient). The control index set refers to the set of all parameters affecting equipment operation, such as the gas flow rate, combustion temperature, and air supply of a boiler. These control indicators are classified based on their respective carbon emission sensitivity coefficients, i.e., their degree of influence on carbon emissions. The predetermined carbon emission sensitivity coefficient is a set threshold, such as 25. If the carbon emission sensitivity coefficient of a control indicator is greater than or equal to 25, it indicates a significant impact on carbon emissions and requires key control; this is called the first emission reduction control factor. If it is less than 25, it indicates a smaller impact and can be used as a secondary control parameter; this is called the second emission reduction control factor. For example, if the carbon emission sensitivity coefficient of gas flow rate is 30 and the carbon emission sensitivity coefficient of combustion temperature is 20, then gas flow rate belongs to the first factor, and combustion temperature belongs to the second factor. This classification helps to determine the main emission reduction control directions, thereby optimizing the equipment operation strategy. Table 1 shows the most recent carbon emission sensitivity test record for the target equipment, calculated based on the current control decisions and current carbon emission data of the equipment corresponding to the emission reduction target, using disturbance control decisions and carbon emission prediction results.

[0054] Table 1: Record of the most recent carbon emission sensitivity test of equipment targeting emission reduction

[0055] Device ID Device 1 Device 2 Device 3 Device 4 Device 5 Current control decision 37.454012 95.071431 73.199394 59.865848 15.601864 Current carbon emission data 7.799726 2.904181 43.308807 30.055751 35.403629 Disturbance control decision 1 42.865702 38.536350 41.783364 39.618688 42.865702 Disturbance control decision 2 119.469628 99.951070 114.589988 104.830709 119.469628 Disturbance control decision 3 94.848247 77.529165 90.518476 81.858935 94.848247 Disturbance control decision 4 69.112631 61.715205 67.263274 63.564561 69.112631 Disturbance control decision 5 24.238363 17.329164 22.511064 19.056464 24.238363 Predicted carbon emission data 1 21.597251 18.318092 29.620728 47.444277 34.211651 Predicted carbon emission data 2 14.561457 22.803499 2.322521 48.281602 22.007625 Predicted carbon emission data 3 30.592645 39.258798 30.377243 40.419867 6.101912 Predicted carbon emission data 4 6.974693 9.983689 8.526206 15.230688 24.758846 Predicted carbon emission data 5 14.607232 25.711722 3.252580 4.883606 1.719426 Carbon emission change intensity 1 13.797525 15.413912 13.688079 17.388526 1.191978 Carbon emission change intensity 2 6.761731 19.899319 40.986287 18.225851 13.396004 Carbon emission change intensity 3 22.792919 36.354617 12.931565 10.364117 29.301717 Carbon emission change intensity 4 0.825033 7.079508 34.782601 14.825062 10.644783 Carbon emission change intensity 5 6.807506 22.807541 40.056228 25.172145 33.684203

[0056] The units of the values ​​in different columns of the table are as follows: Current control decision and disturbance control decision: no unit (representing the numerical value of the control parameter); Current carbon emission data and predicted carbon emission data: kilograms of carbon dioxide; Carbon emission change intensity: kilograms of carbon dioxide.

[0057] S6: Based on the emission reduction target, optimize the emission reduction target equipment according to the first emission reduction regulation factor and the second emission reduction regulation factor to obtain an emission reduction regulation strategy.

[0058] Further, S6 includes: S61: using the equipment application scenario corresponding to the emission reduction target equipment as the emission reduction control constraint scenario; S62: using the first emission reduction control factor as a non-fixed variable and the second emission reduction control factor as a fixed variable; S63: based on the emission reduction control constraint scenario, randomly adjusting the current control decision of the equipment according to the non-fixed variable and the fixed variable to obtain the emission reduction control space; S64: performing optimization analysis on the emission reduction control space according to the emission reduction target to generate the emission reduction control strategy.

[0059] Further, S64 includes: S641: Extracting a first emission reduction control decision based on the emission reduction control space; S642: Predicting carbon emissions of the emission reduction target equipment based on the first emission reduction control decision to obtain a first carbon emission prediction result; S643: Performing a difference analysis between the expected carbon emission data of the equipment corresponding to the emission reduction target equipment and the first carbon emission prediction result to obtain a first emission reduction achievement target; S644: If the first emission reduction achievement target satisfies the emission reduction target, outputting the first emission reduction control decision as the emission reduction control strategy; S645: If the first emission reduction achievement target does not satisfy the emission reduction target, eliminating the first emission reduction control decision, and continuing to iteratively optimize the emission reduction control space based on the emission reduction target until the emission reduction control strategy is generated.

[0060] Specifically, the application scenarios of the equipment corresponding to the emission reduction targets are considered as emission reduction control constraints. Emission reduction target equipment refers to equipment whose carbon emissions exceed the expected value, requiring emission reduction measures. The equipment application scenario refers to the specific environment and purpose in which the equipment operates; for example, an industrial boiler may be used for heating, steam production, or auxiliary power supply. Emission reduction control constraints mean that when optimizing emission reduction strategies, the actual operating environment of the equipment must be considered to ensure that adjusting parameters does not affect the normal function of the equipment. For example, if the boiler is used for heating, its minimum heating temperature cannot be lower than a certain set value; otherwise, it will affect production or residents' lives. The purpose of using the equipment application scenario as the emission reduction control constraint scenario is to ensure that the emission reduction plan is feasible in the actual environment without affecting the normal operation of the equipment.

[0061] The first emission reduction control factor is treated as a non-fixed variable, while the second emission reduction control factor is treated as a fixed variable. The first emission reduction control factor refers to control parameters with a significant impact on carbon emissions, such as the gas flow rate of a gas-fired boiler, which has a high carbon emission sensitivity coefficient and can therefore be the primary control target. Non-fixed variables are parameters that can be adjusted within a certain range, such as the gas flow rate, which can vary between 50 kg / h and 100 kg / h. The second emission reduction control factor refers to control parameters with a smaller impact on carbon emissions, such as the boiler's air supply, which has a low carbon emission sensitivity coefficient and can therefore be used as an auxiliary control parameter. Fixed variables are parameters that remain unchanged during the optimization process, such as a fixed air supply of 800 cubic meters per hour, while the gas flow rate is optimized as an adjustable parameter. This approach ensures that the optimization process focuses on the most important variables, improving emission reduction efficiency.

[0062] Based on emission reduction and control constraints, the current control decisions of the equipment are stochastically adjusted according to non-fixed and fixed variables to obtain the emission reduction and control space. The emission reduction and control constraints specify the operating conditions that must be followed during the optimization process, such as the boiler's minimum heating temperature not being lower than 60 degrees Celsius. The current control decision of the equipment refers to the control strategy of the equipment under its current operating state, such as setting the gas flow rate to 70 kg / h and the air supply to 800 cubic meters / h. Stochastic adjustment refers to randomly adjusting non-fixed variables within a certain range; for example, the gas flow rate can be increased to 75 kg / h or decreased to 65 kg / h to observe the impact on carbon emissions. The emission reduction and control space refers to all possible combinations of control parameters; for example, the gas flow rate can be 60, 65, 70, or 75 kg / h, while the air supply is fixed at 800 cubic meters / h. These combinations constitute an optimization space used to find the optimal emission reduction scheme.

[0063] Based on the emission reduction control space, the first emission reduction control decision is extracted. The emission reduction control space refers to the optimization range formed by different combinations of control parameters. The first emission reduction control decision refers to a specific control scheme selected within this space. The purpose of extracting this decision is to select a feasible control scheme for subsequent carbon emission prediction and to evaluate its emission reduction effect.

[0064] Based on the first emission reduction control decision, carbon emission prediction is performed on the target equipment to obtain the first carbon emission prediction result. Carbon emission prediction is based on the selected control decision and estimates the carbon emission level of the equipment under new control parameters through calculation or simulation. For example, if the gas flow rate is set to 70 kg / h, the predicted carbon emission may be 330 kg / h. The first carbon emission prediction result refers to the preliminary estimate obtained from this prediction process, which is used for subsequent analysis.

[0065] The first emission reduction target is achieved by performing a difference analysis between the expected carbon emission data of the equipment corresponding to the emission reduction target and the first carbon emission prediction result. The expected carbon emission data of the equipment refers to the ideal carbon emission level that the equipment should achieve, for example, 300 kg. The difference analysis involves comparing the first carbon emission prediction result with the expected carbon emission data of the equipment and calculating the difference between them. For example, if the first carbon emission prediction result is 330 kg and the expected carbon emission data is 300 kg, the difference is 30 kg. The first emission reduction target achievement result is the result of this difference calculation, used to assess whether the current regulatory decisions meet the emission reduction requirements.

[0066] If the first emission reduction target is achieved, the first emission reduction control decision will be output as the emission reduction control strategy. The emission reduction target refers to the carbon emission standard that the equipment needs to meet, such as reducing it to below 300 kg. If achieving the first emission reduction target means that the first carbon emission prediction result is less than or equal to the expected carbon emission data of the equipment, such as a prediction result of 290 kg, which meets the target requirement, then the current first emission reduction control decision is considered an effective solution and will be used as the final emission reduction control strategy, directly applied to equipment operation optimization.

[0067] If the initial emission reduction target is not met, the first emission reduction control decision is discarded. The emission reduction control space is then iteratively optimized based on the emission reduction target until an emission reduction control strategy is generated. If achieving the initial emission reduction target indicates that the current emission reduction control decision cannot meet the target—for example, if the predicted carbon emissions are still 330 kg, higher than the target value of 300 kg—then the current decision is discarded. Iterative optimization refers to continuing to adjust parameters within the emission reduction control space, for example, reducing the gas flow rate to 65 kg / h and re-predicting carbon emissions until an optimal solution that meets the emission reduction target is found. For example, if reducing the gas flow rate to 65 kg / h results in a predicted carbon emission of 295 kg, meeting the target requirement, then this control scheme is ultimately determined as the emission reduction control strategy.

[0068] S7: Adaptive carbon emission control is performed on the industrial park according to the zero-carbon control strategy and the emission reduction control strategy.

[0069] Specifically, zero-carbon control strategies refer to optimizing the operation of equipment that has already met zero-carbon emission standards to ensure that its carbon emissions remain at zero. For example, a photovoltaic power station operates on solar power during the day and adjusts the usage strategy of its energy storage equipment at night to ensure continuous zero-carbon operation. Emission reduction control strategies refer to gradually reducing carbon emissions for equipment whose carbon emissions have not met expected standards by optimizing control parameters. For example, adjusting the gas flow rate of a gas boiler to reduce its carbon emissions to meet target requirements. An industrial park refers to an area composed of multiple industrial, commercial, or public facilities, such as an industrial park containing manufacturing plants, logistics centers, and office buildings. Its internal equipment is diverse, and its carbon emission situation is complex. Adaptive carbon emission control refers to combining zero-carbon control strategies and emission reduction control strategies in a dynamic adjustment process to optimize the carbon emissions of the entire industrial park to an optimal state. For example, during peak hours, zero-carbon equipment is prioritized for power supply, and the power of high-energy-consuming equipment is appropriately limited. During low-carbon emission periods, the operation of high-energy-consuming equipment is optimized to minimize carbon emissions.

[0070] In summary, the carbon emission control method for low-carbon industrial park construction based on big data analysis provided in this application has the following technical effects: by achieving the technical goal of carbon emission management and dynamic optimization control of all equipment in the park, it can achieve precise control based on the actual carbon emission of the equipment, improve the overall carbon emission efficiency of the park, and ensure that the carbon emission of key equipment is minimized or zero in different scenarios.

[0071] Example 2: Based on the same inventive concept as the carbon emission control method for low-carbon industrial park construction using big data analysis in the foregoing examples, this application also provides a carbon emission control platform for low-carbon industrial park construction using big data analysis. Please refer to the appendix. Figure 2The system includes: a zero-carbon fitness analysis module 11, used to perform zero-carbon fitness analysis on multiple devices in the industrial park to obtain zero-carbon device clusters and non-zero-carbon device clusters; a zero-carbon regulation analysis module 12, used to perform zero-carbon regulation analysis on the zero-carbon device clusters based on the current carbon emission dataset of the industrial park to obtain zero-carbon regulation strategies; a scenario application carbon emission mining module 13, used to perform scenario application carbon emission mining on the non-zero-carbon device clusters to determine the expected carbon emission dataset; and an emission reduction target identification module 14, used to analyze the non-zero-carbon device clusters based on the expected carbon emission dataset and the current carbon emission dataset. The system includes: emission reduction target identification, which identifies the emission reduction targets corresponding to the target equipment; a carbon emission sensitivity testing module 15, which performs carbon emission sensitivity testing based on the control index set of the target equipment to determine the first emission reduction control factor and the second emission reduction control factor; an optimization adjustment module 16, which optimizes the target equipment based on the emission reduction targets and the first and second emission reduction control factors to obtain an emission reduction control strategy; and an adaptive carbon emission control module 17, which performs adaptive carbon emission control of the industrial park based on the zero-carbon control strategy and the emission reduction control strategy.

[0072] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: collecting current application scenario information of the multiple devices to obtain multiple device application scenarios; evaluating the zero-carbon adaptability of the multiple device application scenarios to obtain multiple scenario zero-carbon adaptability; extracting the zero-carbon adaptability of the first scenario based on the multiple scenario zero-carbon adaptability, and determining whether the first scenario zero-carbon adaptability is greater than or equal to a predetermined zero-carbon adaptability; if the first scenario zero-carbon adaptability is greater than or equal to the predetermined zero-carbon adaptability, recording the device corresponding to the first scenario zero-carbon adaptability as a zero-carbon device, and adding the zero-carbon device to the zero-carbon device cluster; if the first scenario zero-carbon adaptability is less than the predetermined zero-carbon adaptability, recording the device corresponding to the first scenario zero-carbon adaptability as a non-zero-carbon device, and adding the non-zero-carbon device to the non-zero-carbon device cluster.

[0073] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: conducting carbon emission sensitivity tests on the control index set according to a predetermined step size sequence to obtain multiple carbon emission sensitivity test sequences; calculating the ensemble value of each of the multiple carbon emission sensitivity test sequences to obtain multiple indicator carbon emission sensitivity coefficients; classifying the control index set according to the multiple indicator carbon emission sensitivity coefficients to obtain the first emission reduction control factor that is greater than or equal to the predetermined carbon emission sensitivity coefficient, and the second emission reduction control factor that is less than the predetermined carbon emission sensitivity coefficient.

[0074] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: reading the current control decisions and current carbon emission data of the equipment corresponding to the emission reduction target equipment; extracting a first control indicator based on the control indicator set; using the first control indicator as a floating variable, randomly perturbing the current control decisions of the equipment according to the predetermined step size sequence to obtain multiple perturbed control decisions; predicting carbon emissions of the emission reduction target equipment based on the multiple perturbed control decisions to obtain multiple carbon emission prediction data; evaluating the carbon emission change intensity of the multiple carbon emission prediction data based on the current carbon emission data of the equipment to obtain multiple carbon emission change intensities; outputting the multiple carbon emission change intensities as a first carbon emission sensitive test sequence, and adding the first carbon emission sensitive test sequence to the multiple carbon emission sensitive test sequences.

[0075] Furthermore, the carbon emission control platform for the construction of the low-carbon industrial park based on big data analysis is also used for: taking the equipment application scenario corresponding to the emission reduction target equipment as the emission reduction control constraint scenario; taking the first emission reduction control factor as a non-fixed variable and the second emission reduction control factor as a fixed variable; based on the emission reduction control constraint scenario, randomly adjusting the current control decision of the equipment according to the non-fixed variable and the fixed variable to obtain the emission reduction control space; and performing optimization analysis on the emission reduction control space according to the emission reduction target to generate the emission reduction control strategy.

[0076] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: extracting a first emission reduction control decision based on the emission reduction control space; predicting carbon emissions of the emission reduction target equipment based on the first emission reduction control decision to obtain a first carbon emission prediction result; performing a difference analysis between the expected carbon emission data of the equipment corresponding to the emission reduction target equipment and the first carbon emission prediction result to obtain a first emission reduction achievement target; if the first emission reduction achievement target meets the emission reduction target, outputting the first emission reduction control decision as the emission reduction control strategy; if the first emission reduction achievement target does not meet the emission reduction target, eliminating the first emission reduction control decision, and continuing to iteratively optimize the emission reduction control space based on the emission reduction target until the emission reduction control strategy is generated.

[0077] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: performing feature identification on the current carbon emission dataset based on the zero-carbon equipment cluster to obtain carbon emission data of multiple zero-carbon equipment; determining whether the carbon emission data of the multiple zero-carbon equipment is zero; if any one of the carbon emission data of the multiple zero-carbon equipment is not zero, obtaining a zero-carbon control device; performing zero-carbon control on the zero-carbon control device to generate the zero-carbon control strategy.

[0078] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: taking the application scenario corresponding to the nth non-zero carbon device within the non-zero carbon device cluster as the nth target application scenario, where n is a positive integer; performing normal carbon emission sample retrieval on the nth non-zero carbon device according to the nth target application scenario to obtain the normal carbon emission sample set of the nth device; performing central value calculation on the normal carbon emission sample set of the nth device to obtain the expected carbon emission data of the nth device, and adding the expected carbon emission data of the nth device to the expected carbon emission dataset.

[0079] Furthermore, the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis is also used for: extracting the carbon emission data of the nth non-zero carbon device corresponding to the current carbon emission dataset; determining whether the carbon emission data of the nth device meets the expected carbon emission data of the nth device; if the carbon emission data of the nth device does not meet the expected carbon emission data of the nth device, adding the nth non-zero carbon device to the emission reduction target device, and performing a difference analysis between the expected carbon emission data of the nth device and the carbon emission data of the nth device to generate the emission reduction target.

[0080] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The carbon emission control method and specific examples for the construction of low-carbon industrial parks based on big data analysis in the aforementioned embodiment 1 are also applicable to the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis in this embodiment. Through the foregoing detailed description of the carbon emission control method for the construction of low-carbon industrial parks based on big data analysis, those skilled in the art can clearly understand the carbon emission control platform for the construction of low-carbon industrial parks based on big data analysis in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0081] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for controlling carbon emissions in the construction of low-carbon industrial parks based on big data analysis, characterized in that: include: Zero-carbon adaptability analysis was conducted on multiple pieces of equipment in the industrial park to obtain zero-carbon equipment clusters and non-zero-carbon equipment clusters; Based on the current carbon emission dataset of the industrial park, the zero-carbon equipment cluster is analyzed for zero-carbon regulation to obtain a zero-carbon regulation strategy; Based on the non-zero carbon device cluster, carbon emission mining is performed for scenario applications to determine the expected carbon emission dataset. Based on the expected carbon emission dataset and the current carbon emission dataset, the emission reduction targets of the non-zero carbon equipment cluster are identified, and the emission reduction targets corresponding to the emission reduction target equipment are determined. Carbon emission sensitivity tests are conducted based on the control index set of the emission reduction target equipment to determine the first emission reduction regulation factor and the second emission reduction regulation factor. Based on the emission reduction target, the emission reduction target equipment is optimized and adjusted according to the first emission reduction regulation factor and the second emission reduction regulation factor to obtain the emission reduction regulation strategy. The industrial park is subject to adaptive carbon emission control based on the zero-carbon control strategy and the emission reduction control strategy. Zero-carbon adaptability analysis was conducted on multiple pieces of equipment in the industrial park to obtain zero-carbon equipment clusters and non-zero-carbon equipment clusters, including: Collect current application scenario information of the multiple devices to obtain application scenarios for multiple devices; The zero-carbon adaptability is evaluated for each application scenario, and the zero-carbon adaptability of multiple scenarios is obtained. Zero-carbon adaptability refers to whether the carbon emission level of the equipment in the scenario meets the zero-carbon requirements. Based on the zero-carbon fitness of the multiple scenarios, extract the zero-carbon fitness of the first scenario, and determine whether the zero-carbon fitness of the first scenario is greater than or equal to the predetermined zero-carbon fitness. If the zero-carbon adaptability of the first scenario is greater than or equal to the predetermined zero-carbon adaptability, the device corresponding to the zero-carbon adaptability of the first scenario is recorded as a zero-carbon device, and the zero-carbon device is added to the zero-carbon device cluster; If the zero-carbon adaptability of the first scenario is less than the predetermined zero-carbon adaptability, the device corresponding to the zero-carbon adaptability of the first scenario is recorded as a non-zero-carbon device, and the non-zero-carbon device is added to the non-zero-carbon device cluster. Carbon emission sensitivity tests are conducted based on the control index set of the emission reduction target equipment to determine the first emission reduction regulation factor and the second emission reduction regulation factor, including: The control index set is subjected to carbon emission sensitivity testing according to a predetermined step size sequence to obtain multiple carbon emission sensitivity test sequences. Mass values ​​were calculated for the multiple carbon emission sensitivity test sequences to obtain carbon emission sensitivity coefficients for multiple indicators. The control index set is classified according to the carbon emission sensitivity coefficients of the multiple indicators to obtain the first emission reduction regulation factor that is greater than or equal to the predetermined carbon emission sensitivity coefficient, and the second emission reduction regulation factor that is less than the predetermined carbon emission sensitivity coefficient.

2. The carbon emission control method for low-carbon industrial park construction based on big data analysis as described in claim 1, characterized in that, Carbon emission sensitivity tests are performed on the control index set according to a predetermined step size sequence to obtain multiple carbon emission sensitivity test sequences, including: Read the current control decision and current carbon emission data of the equipment corresponding to the emission reduction target equipment; Based on the set of control indicators, extract the first control indicator; Using the first control index as a floating variable, the current control decision of the device is randomly perturbed according to the predetermined step size sequence to obtain multiple perturbation control decisions; Based on the multiple disturbance control decisions, carbon emission prediction is performed on the emission reduction target equipment to obtain multiple carbon emission prediction data. Based on the current carbon emission data of the device, the carbon emission change intensity is evaluated on the multiple carbon emission prediction data to obtain multiple carbon emission change intensities. The intensity of the multiple carbon emission changes is output as a first carbon emission sensitive test sequence, and the first carbon emission sensitive test sequence is added to the multiple carbon emission sensitive test sequences.

3. The carbon emission control method for low-carbon industrial park construction based on big data analysis as described in claim 1, characterized in that, Based on the emission reduction target, the emission reduction target equipment is optimized and adjusted according to the first emission reduction control factor and the second emission reduction control factor to obtain an emission reduction control strategy, including: The application scenarios of the equipment corresponding to the emission reduction target equipment are taken as emission reduction control constraint scenarios; The first emission reduction regulation factor is used as a non-fixed variable, and the second emission reduction regulation factor is used as a fixed variable; Based on the emission reduction and control constraints, the current control decision of the equipment is randomly adjusted according to the non-fixed variables and the fixed variables to obtain the emission reduction and control space. Based on the emission reduction target, the emission reduction control space is optimized to generate the emission reduction control strategy.

4. The carbon emission control method for low-carbon industrial park construction based on big data analysis as described in claim 3, characterized in that, Based on the emission reduction target, an optimization analysis is performed on the emission reduction control space to generate the emission reduction control strategy, including: Based on the emission reduction and control space, extract the first decision for emission reduction and control; Based on the first decision on emission reduction and regulation, carbon emission prediction is performed on the emission reduction target equipment to obtain a first carbon emission prediction result. The expected carbon emission data of the equipment corresponding to the emission reduction target equipment is compared with the first carbon emission prediction result to obtain the first emission reduction target. If the first emission reduction target is met, the first emission reduction control decision will be output as the emission reduction control strategy. If the first emission reduction target does not meet the emission reduction objective, the first emission reduction control decision is eliminated, and the emission reduction control space is iteratively optimized according to the emission reduction objective until the emission reduction control strategy is generated.

5. The carbon emission control method for low-carbon industrial park construction based on big data analysis as described in claim 1, characterized in that, Based on the current carbon emission dataset of the industrial park, the zero-carbon equipment cluster is analyzed for zero-carbon regulation to obtain zero-carbon regulation strategies, including: Based on the zero-carbon device cluster, feature identification is performed on the current carbon emission dataset to obtain carbon emission data for multiple zero-carbon devices. Determine whether the carbon emission data of the multiple zero-carbon devices is zero; If the carbon emission data of any one of the multiple zero-carbon devices is not 0, a zero-carbon control device is obtained. The zero-carbon control device is subjected to zero-carbon control to generate the zero-carbon control strategy.

6. The carbon emission control method for low-carbon industrial park construction based on big data analysis as described in claim 1, characterized in that, Based on the aforementioned non-zero carbon device cluster, scenario application carbon emission mining is performed to determine the expected carbon emission dataset, including: The application scenario corresponding to the nth non-zero carbon device in the non-zero carbon device cluster is taken as the nth target application scenario, where n is a positive integer; Based on the nth target application scenario, a normal carbon emission sample retrieval is performed on the nth non-zero carbon device to obtain the normal carbon emission sample set of the nth device. Based on the normal carbon emission sample set of the nth device, the central value is calculated to obtain the expected carbon emission data of the nth device, and the expected carbon emission data of the nth device is added to the expected carbon emission dataset.

7. The carbon emission control method for the construction of low-carbon industrial parks based on big data analysis as described in claim 1, characterized in that, Based on the expected carbon emission dataset and the current carbon emission dataset, emission reduction targets are identified for the non-zero carbon device cluster, and the emission reduction targets corresponding to the target devices are determined, including: Based on the current carbon emission dataset, extract the carbon emission data of the nth device corresponding to the nth non-zero carbon device; Determine whether the carbon emission data of the nth device meets the expected carbon emission data of the nth device; If the carbon emission data of the nth device does not meet the expected carbon emission data of the nth device, the nth non-zero carbon device is added to the emission reduction target device, and a difference analysis is performed between the expected carbon emission data of the nth device and the carbon emission data of the nth device to generate the emission reduction target.

8. A carbon emission control platform for the construction of a low-carbon industrial park based on big data analysis, characterized in that: The steps for implementing the carbon emission control method for the construction of a low-carbon industrial park based on big data analysis according to any one of claims 1 to 7 include: The zero-carbon adaptability analysis module is used to perform zero-carbon adaptability analysis on multiple devices in the industrial park to obtain zero-carbon device clusters and non-zero-carbon device clusters. The zero-carbon regulation and analysis module is used to perform zero-carbon regulation and analysis on the zero-carbon equipment cluster based on the current carbon emission dataset of the industrial park, and obtain a zero-carbon regulation and analysis strategy. The scenario application carbon emission mining module is used to perform scenario application carbon emission mining based on the non-zero carbon device cluster to determine the expected carbon emission dataset. The emission reduction target identification module is used to identify the emission reduction targets of the non-zero carbon equipment cluster based on the expected carbon emission dataset and the current carbon emission dataset, and to determine the emission reduction targets corresponding to the emission reduction target equipment. The carbon emission sensitivity testing module is used to perform carbon emission sensitivity testing based on the control index set of the emission reduction target equipment, and to determine the first emission reduction regulation factor and the second emission reduction regulation factor. The optimization adjustment module is used to optimize and adjust the emission reduction target equipment based on the emission reduction target, according to the first emission reduction control factor and the second emission reduction control factor, to obtain an emission reduction control strategy. An adaptive carbon emission control module is used to adaptively control the carbon emissions of the industrial park according to the zero-carbon control strategy and the emission reduction control strategy.

Images