Edge computing gateway device for multi-mode energy carbon emission comprehensive monitoring

Abstract

The invention discloses an edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring, and relates to the related technical field of carbon emission monitoring, and the device comprises a carbon emission data obtaining module which is used for obtaining a plurality of carbon emission sources and a plurality of carbon emission monitoring index sets of an industrial park; the priority evaluation module is used for carrying out priority evaluation to obtain a plurality of monitoring index sequences; the carbon emission source analysis module is used for analyzing and acquiring a plurality of predicted emission trends and a plurality of emission fluctuation degrees; and the carbon emission monitoring module is used for configuring an optimized data acquisition strategy of the edge computing gateway and executing carbon emission monitoring in a preset time zone. The technical problem that the carbon emission monitoring response speed is poor due to the fact that the monitoring range is limited, the index priority is unknown, data processing lags behind and an acquisition strategy is rigid in the prior art is solved, and the technical effects of comprehensive and accurate monitoring, resource optimization configuration, real-time trend prediction, strategy dynamic adjustment and carbon emission monitoring response speed improvement are achieved.

Description

Technical Field

[0001] This application relates to the technical field of carbon emission monitoring, and specifically to an edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring. Background Art

[0002] Industrial parks, as the concentrated areas of industrial production activities, are the key targets for carbon emission control. The accurate monitoring and effective management of their carbon emissions are crucial for achieving the carbon emission reduction goal. However, there are significant deficiencies in the existing industrial park carbon emission monitoring in terms of data processing and analysis capabilities, making it difficult to meet the complex requirements of multi-modal data processing. On the one hand, traditional carbon emission monitoring cannot comprehensively reflect the true carbon emission status of industrial parks. At the same time, there is no scientific priority evaluation mechanism for different carbon emission monitoring indicators, resulting in the inability to reasonably allocate resources during data collection, causing both resource waste and affecting the monitoring efficiency and the accuracy of monitoring results. On the other hand, the existing carbon emission monitoring relies on cloud computing, with a large delay in the data transmission process, being unable to predict and analyze the carbon emission trend in a timely manner, difficult to quickly respond to sudden carbon emission fluctuations, lacking accurate analysis of the emission trend and fluctuation degree of carbon emission sources, and unable to flexibly adjust the data collection strategy according to the actual situation.

[0003] Therefore, in the current related technologies, there are technical problems such as limited monitoring scope, unclear indicator priorities, lagging data processing, rigid collection strategies, resulting in poor response speed of carbon emission monitoring. Summary of the Invention

[0004] This application provides an edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring, solving the technical problems in the existing technology such as limited monitoring scope, unclear indicator priorities, lagging data processing, rigid collection strategies, resulting in poor response speed of carbon emission monitoring, and achieving the technical effects of comprehensive and accurate monitoring, optimized resource allocation, real-time trend prediction, dynamic adjustment of strategies, and improvement of the response speed of carbon emission monitoring.

[0005] This application provides an edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring. The device includes: a carbon emission data acquisition module for acquiring multiple carbon emission sources and multiple carbon emission monitoring index sets in an industrial park; a priority evaluation module for sequentially evaluating the priorities of multiple carbon emission monitoring indexes in the multiple carbon emission monitoring index sets to obtain multiple monitoring index sequences; a carbon emission source analysis module for analyzing and obtaining multiple predicted emission trends and multiple emission fluctuation degrees of the multiple carbon emission sources in a preset time zone based on the carbon emission monitoring logs of the industrial park; a carbon emission monitoring module for configuring an optimized data acquisition strategy for the edge computing gateway according to the multiple monitoring index sequences, multiple predicted emission trends and multiple emission fluctuation degrees, and performing carbon emission monitoring in the preset time zone, where the data acquisition strategy includes monitoring index types, data acquisition frequencies and key feature screening thresholds.

[0006] In a possible implementation, the edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring also performs the following processing: randomly selecting a first carbon emission monitoring index set of a first carbon emission source to obtain multiple first carbon emission monitoring indexes; obtaining multiple first unit monitoring data amounts of the multiple first carbon emission monitoring indexes; respectively evaluating the index correlation degrees and data credibility of the multiple first carbon emission monitoring indexes according to the carbon emission monitoring logs of the first carbon emission source to determine multiple first index correlation degrees and multiple first data credibility; respectively evaluating the priorities of the multiple first carbon emission monitoring indexes according to the multiple first unit monitoring data amounts, multiple first index correlation degrees and multiple first data credibility, constructing a first monitoring index sequence, and sequentially analyzing to obtain multiple monitoring index sequences.

[0007] In a possible implementation, the edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring also performs the following processing: configuring data volume weights, correlation weights and credibility weights based on the coefficient of variation method according to the carbon emission monitoring logs of the first carbon emission source and the performance of the edge computing gateway; after performing dimensionless processing on the multiple first unit monitoring data amounts, multiple first index correlation degrees and multiple first data credibility, obtaining multiple first priorities by weighted averaging based on the data volume weights, correlation weights and credibility weights, where the priority is negatively correlated with the unit monitoring data amount and positively correlated with the index correlation degree and data credibility; arranging the multiple first carbon emission monitoring indexes in descending order of the first priority based on the multiple first priorities to obtain a first monitoring index sequence.

[0008] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring also performs the following processing: randomly select a first carbon emission source, and obtain the first carbon emission monitoring log of the first carbon emission source; based on the preset time zone, retrieve the same time periods within a preset time range in the first carbon emission monitoring log to obtain multiple sample first carbon emission amount monitoring sequences; analyze the multiple sample first carbon emission amount monitoring sequences to obtain a first predicted emission trend and a first emission fluctuation degree, and sequentially analyze to obtain multiple predicted emission trends and multiple emission fluctuation degrees of the multiple carbon emission sources.

[0009] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring also performs the following processing: in a two-dimensional coordinate system, construct multiple sample first carbon emission curves according to the multiple sample first carbon emission amount monitoring sequences, and perform curve fitting to determine a first fitted carbon emission curve; calculate a first increase ratio based on the first fitted carbon emission curve, and set it as the first predicted emission trend; calculate the mean values of the multiple sample first carbon emission amount monitoring sequences respectively to obtain multiple sample first carbon emission amount means, and calculate the mean value again to obtain a first predicted carbon emission amount; perform emission fluctuation degree analysis based on the multiple sample first carbon emission amount means, and calculate a first emission fluctuation degree, where the emission fluctuation degree is the ratio of the standard deviation of the multiple sample first carbon emission amount means to the first predicted carbon emission amount.

[0010] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring also performs the following processing: map to obtain a first edge computing gateway of the first carbon emission source; analyze and determine a first fluctuation scale according to the first predicted emission trend, the first predicted carbon emission amount, and the first emission fluctuation degree; adjust a first initial data collection scheme according to the first fluctuation scale to obtain a first optimized data collection scheme; sequentially analyze to obtain multiple optimized data collection schemes of multiple edge computing gateways, and construct an optimized data collection strategy.

[0011] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring also performs the following processing: calculate the ratio of the first predicted carbon emission amount to the historical first carbon emission amount mean of the first carbon emission source, and set it as the first emission scale; calculate the ratio of the first predicted emission trend to the historical first emission trend mean to obtain a trend adjustment coefficient; calculate the ratio of the first emission fluctuation degree to the historical first emission fluctuation degree mean to obtain an emission fluctuation adjustment coefficient; use the trend adjustment coefficient and the emission fluctuation adjustment coefficient to perform double compensation on the first emission scale, and output a first fluctuation scale.

[0012] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring further performs the following processing: configuring a first initial data acquisition scheme, where the first initial data acquisition scheme includes the number of selected first monitoring indicators, the first data acquisition frequency, and the first key feature screening threshold; adjusting the number of selected first monitoring indicators according to the first fluctuation scale to determine the first optimized number of selections, and selecting the first optimized number of monitoring indicators from the first monitoring indicator sequence to obtain the first monitoring indicator type; adjusting the first data acquisition frequency according to the first fluctuation scale to determine the first optimized acquisition frequency; adjusting the first key feature screening threshold according to the first fluctuation scale to determine the first optimized feature screening threshold; and constructing a first optimized data acquisition scheme based on the first monitoring indicator type, the first optimized acquisition frequency, and the first optimized feature screening threshold.

[0013] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring further performs the following processing: setting the reciprocal of the first fluctuation scale as the first threshold adjustment coefficient, and adjusting the first key feature screening threshold to obtain the first optimized feature screening threshold.

[0014] In a possible implementation, the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring further performs the following processing: when performing carbon emission monitoring according to the first monitoring indicator type and the first optimized acquisition frequency, determining whether the deviation of the monitoring data under adjacent monitoring nodes is greater than the first optimized feature screening threshold. If it is greater, retaining the monitoring data under the adjacent monitoring nodes as key data; if it is less, discarding the monitoring data under the adjacent monitoring nodes, and iteratively performing determination and screening.

[0015] It is intended to use the edge computing gateway device for multimodal energy carbon emission comprehensive monitoring proposed in this application, a carbon emission data acquisition module for acquiring multiple carbon emission sources and multiple carbon emission monitoring indicator sets in an industrial park; a priority evaluation module for performing priority evaluation to obtain multiple monitoring indicator sequences; a carbon emission source analysis module for analyzing and obtaining multiple predicted emission trends and multiple emission fluctuation degrees; and a carbon emission monitoring module for configuring an optimized data acquisition strategy for the edge computing gateway and performing carbon emission monitoring in a preset time zone. This solves the technical problems in the prior art, such as limited monitoring scope, unclear indicator priorities, lagging data processing, and rigid acquisition strategies, which lead to poor response speed of carbon emission monitoring, and achieves the technical effects of comprehensive and accurate monitoring, optimized resource allocation, real-time trend prediction, dynamic adjustment of strategies, and improvement of the response speed of carbon emission monitoring. Description of the Drawings

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the devices according to the embodiments of the present application. It should be understood that the operations above or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0017] Figure 1 Schematic structural diagram of the edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring provided by the embodiments of the present application.

[0018] Figure 2 Schematic diagram of the execution process of the priority evaluation module in the edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring provided by the embodiments of the present application.

[0019] Explanation of reference numerals: Carbon emission data acquisition module 10, priority evaluation module 20, carbon emission source analysis module 30, carbon emission monitoring module 40. Detailed implementation manners

[0020] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specific implementation manners of the present application are given.

[0021] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0022] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, apparatus, product or server comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0023] The embodiment of this application provides an edge computing gateway device for comprehensive monitoring of multi-modal energy carbon emissions, as Figure 1 shown. The device includes: A carbon emission data acquisition module 10, configured to acquire a plurality of carbon emission sources and a plurality of carbon emission monitoring index sets in an industrial park.

[0024] Preferably, to acquire a plurality of carbon emission sources and a plurality of carbon emission monitoring index sets in an industrial park, by comprehensively identifying various carbon emission sources to cover all-dimensional emission entities in the park, each carbon emission source may include multiple emission monitoring indexes. The more indexes there are, the higher the accuracy of carbon emission monitoring and analysis. Specifically, a carbon emission source refers to a specific object that generates carbon dioxide or other greenhouse gas emissions in an industrial park, including production equipment, energy facilities (heating stations, substations, self-provided power plants, etc. in the park), building systems (heating, air conditioning, lighting, etc. of buildings such as office buildings and factories), transportation tools (fuel or gas-powered transportation vehicles such as freight vehicles, forklifts, and construction machinery in the park), industrial production processes (chemical synthesis, iron and steel smelting, cement production, etc.), and waste treatment (sewage treatment plants, solid waste landfills, etc.). Among them, production equipment includes industrial equipment that directly burns fossil fuels (coal, natural gas, oil) to generate carbon emissions, such as boilers, kilns, and reaction kettles.

[0025] Preferably, the carbon emission monitoring index set includes multi-dimensional and multi-modal monitoring parameters of different carbon emission sources, which are used to quantify the carbon emission level and evaluate the emission intensity. Specifically, it includes direct emission indicators obtained through metering devices, reflecting the amount of greenhouse gases generated by carbon emission sources, such as the mass or volume emissions of gases such as CO2, CH4, N2O, etc., and the carbon emissions per unit product or per unit output value; indirect emission indicators, reflecting energy consumption or process parameters related to carbon emission sources, such as energy consumption indicators such as electricity consumption, water consumption, steam consumption, etc., process parameters such as reaction temperature, pressure, raw material ratio, etc., and equipment operation status such as equipment load rate, start-stop frequency, energy efficiency level; environmental management indicators, reflecting the environmental impact of carbon emissions, such as the CO2 concentration, PM2.5 concentration, etc. in the atmosphere around the industrial park, and carbon emission reduction target indicators such as the carbon emission reduction rate per unit output value and the clean energy substitution ratio. Taking the boiler in the industrial park as an example, its carbon emission is determined by various factors such as its combustion efficiency, fuel type, and types of emitted gases. The monitoring indicators may include CO2 concentration, NO x emission, PM2.5 concentration, boiler exhaust gas temperature, energy (natural gas or coal) consumption, flow rate and pressure of boiler exhaust gas, etc.

[0026] The priority evaluation module 20 is used to sequentially evaluate the priorities of multiple carbon emission monitoring indicators in the multiple carbon emission monitoring index sets to obtain multiple monitoring indicator sequences.

[0027] Furthermore, the specific configuration of the priority evaluation module 20 further includes randomly selecting the first carbon emission monitoring index set of the first carbon emission source to obtain multiple first carbon emission monitoring indicators; obtaining multiple first unit monitoring data volumes of the multiple first carbon emission monitoring indicators; according to the carbon emission monitoring log of the first carbon emission source, respectively evaluating the index correlation degree and data credibility of the multiple first carbon emission monitoring indicators to determine multiple first index correlation degrees and multiple first data credibilities; respectively evaluating the priorities of the multiple first carbon emission monitoring indicators according to the multiple first unit monitoring data volumes, multiple first index correlation degrees and multiple first data credibilities, constructing the first monitoring indicator sequence, and sequentially analyzing to obtain multiple monitoring indicator sequences.

[0028] Preferably, the first carbon emission source is a specific emission source randomly selected from multiple carbon emission sources in the industrial park (such as a certain boiler, a certain production line, etc.). The first carbon emission monitoring index set is a set of all monitoring indexes configured for this emission source. The first carbon emission monitoring index set consists of multiple first carbon emission monitoring indexes. Taking a single emission source as the smallest analysis unit, the priority of its monitoring indexes is evaluated one by one, and finally the index priority sequence of the entire park is formed; then, the historical data flow statistics are directly obtained through sensors or device interfaces, that is, the first unit monitoring data volume corresponding to each first carbon emission monitoring index, which represents the data volume generated by a single index per unit time. For example, if the CO2 emission index generates 100 monitoring data per hour, its corresponding unit monitoring data volume is 100 pieces / hour. Among them, the unit monitoring data volume directly affects the data transmission cost, storage pressure and computing load of the edge computing gateway.

[0029] Preferably, obtain the carbon emission monitoring log of the first carbon emission source, which includes the historical monitoring data and related information of the first carbon emission source (such as a certain boiler), such as the time series data of each index, the equipment operation record (such as start and stop time, load status), the sensor calibration record, the data transmission status (such as whether there is a network disconnection resulting in data loss), and the manually marked abnormal events (such as equipment failure, process adjustment, etc.); then, according to the carbon emission monitoring log, evaluate the index correlation degree of multiple first carbon emission monitoring indexes respectively, that is, calculate the correlation coefficient (such as Pearson coefficient) between each carbon emission monitoring index and the carbon emission. The closer the absolute value of the coefficient is to 1, the higher the correlation degree. Furthermore, use a value from 0 to 1 to represent the correlation degree (such as 0.8 represents a strong correlation, 0.3 represents a weak correlation). The higher the value, the more important the index is for carbon emission analysis.

[0030] Preferably, according to the carbon emission monitoring logs, credibility assessments are respectively conducted on multiple first carbon emission monitoring indicators, including assessing the accuracy (the degree of proximity between the carbon emission monitoring indicator data and the true value), integrity (the continuity of the carbon emission monitoring indicator data in the time series, whether there are any missing or interrupted data), and timeliness (the degree of delay of the data from collection to transmission to the edge computing gateway) of each carbon emission monitoring indicator. Specifically, the accuracy assessment refers to detecting and comparing the monitoring data through manual sampling, calculating the error rate, or analyzing whether the data of the same indicator at different monitoring points match; the integrity assessment includes counting the proportion of the missing duration of the indicator data within a certain period (such as the past 30 days), as well as the number of data collection interruptions and the duration caused by reasons such as equipment failures and network outages; the timeliness assessment refers to calculating the time difference between the sensor collection time and the gateway reception time, or monitoring whether the carbon emission monitoring indicators are stably collected at a preset frequency (such as once per minute), and whether there are frequency fluctuations (such as occasional missed collections resulting in longer intervals). Then, a credibility value ranging from 0 to 1 is used to represent the credibility (for example, 0.9 represents high credibility, and 0.5 represents medium credibility), and the higher the value, the more reliable the data quality.

[0031] Preferably, priority evaluations are respectively conducted on multiple first carbon emission monitoring indicators according to multiple first unit monitoring data volumes, multiple first indicator correlation degrees, and multiple first data credibilities. Specifically, weights for multiple first unit monitoring data volumes, multiple first indicator correlation degrees, and multiple first data credibilities are set according to business requirements. A negative value for the unit data volume indicates that the larger the data volume, the higher the negative impact on resource consumption, and the lower the priority may be; then, weighted calculations are performed and sorted from high to low according to the priority scores to construct the first monitoring indicator sequence of this carbon emission source. Finally, all carbon emission sources in the industrial park are evaluated and calculated to obtain the indicator priority sequence corresponding to each emission source, and ultimately multiple monitoring indicator sequences are formed.

[0032] Furthermore, the specific configuration of the priority evaluation module 20 also includes configuring the data volume weight, correlation degree weight, and credibility weight based on the coefficient of variation method according to the carbon emission monitoring logs of the first carbon emission source and the performance of the edge computing gateway; after dimensionless processing of the multiple first unit monitoring data volumes, multiple first indicator correlation degrees, and multiple first data credibilities, multiple first priorities are obtained by weighted calculation based on the data volume weight, correlation degree weight, and credibility weight. Among them, the priority is negatively correlated with the unit monitoring data volume and positively correlated with the indicator correlation degree and data credibility; based on the multiple first priorities, the multiple first carbon emission monitoring indicators are arranged from largest to smallest according to the first priority to obtain the first monitoring indicator sequence.

[0033] Preferably, the coefficient of variation method determines weights based on the dispersion degree of the data itself and is applicable to measuring the relative importance of different indicators. Among them, the data volume weight reflects the occupancy pressure of the unit monitoring data volume on the resources of the edge computing gateway (such as storage and transmission bandwidth). The larger the data volume, the greater the impact on the gateway performance, and the priority needs to be adjusted through weights; the correlation weight measures the degree of tight correlation between the indicator and the core characteristics of carbon emissions (for example, the direct correlation between energy consumption data and carbon emissions is usually higher than that of environmental temperature and humidity data). The higher the correlation of the indicator, the greater the contribution to carbon emissions monitoring, and the weight should be higher; the credibility weight evaluates the reliability of the indicator data (such as sensor accuracy and historical data integrity). Data with low credibility may introduce noise, and its weight needs to be reduced to avoid interfering with the monitoring results.

[0034] Preferably, according to the carbon emissions monitoring log of the first carbon emission source and the performance of the edge computing gateway, the data volume weight, the correlation weight, and the credibility weight are configured based on the coefficient of variation method. Specifically, analyze the carbon emissions monitoring log, count the historical data fluctuation conditions of each indicator (such as data missing rate and outlier frequency), and combine the performance parameters of the edge computing gateway (such as the maximum data processing capacity and storage capacity) to calculate the data volume weight, the correlation weight, and the credibility weight through the coefficient of variation method. For example, if the data volume of a certain carbon emissions monitoring indicator fluctuates greatly and occupies a lot of gateway resources, its data volume weight may be higher; if an indicator has a strong correlation with the carbon emissions trend (such as fuel consumption), its correlation weight is higher.

[0035] Preferably, dimensionless processing is performed on multiple first unit monitoring data volumes, multiple first indicator correlations, and multiple first data credibilities, that is, they are converted into dimensionless values that can be directly compared through standardization methods (such as normalization and Z-score standardization) to avoid the influence of dimensional differences on the calculation results; then, multiple first priorities are obtained through weighted calculation based on the data volume weight, the correlation weight, and the credibility weight. Among them, the priority is negatively correlated with the unit monitoring data volume and positively correlated with the indicator correlation and data credibility. That is to say, the larger the unit monitoring data volume, the lower the priority (because a high data volume may increase the gateway burden and resource allocation needs to be weighed); the higher the indicator correlation and data credibility, the higher the priority (these indicators are more critical for the effectiveness and accuracy of carbon emissions monitoring). Finally, all the first carbon emissions monitoring indicators are arranged from high to low according to the calculated first priorities to form a first monitoring indicator sequence, so as to realize the differential management of carbon emissions monitoring indicators, ensure that the edge computing gateway preferentially processes the data most valuable for carbon emissions monitoring under limited resources, and improve the monitoring efficiency and accuracy.

[0036] The carbon emission source analysis module 30 is used to analyze and obtain multiple predicted emission trends and multiple emission fluctuation degrees of the multiple carbon emission sources in a preset time period based on the carbon emissions monitoring log of the industrial park.

[0037] Furthermore, the specific configuration of the carbon emission source analysis module 30 further includes randomly selecting a first carbon emission source and obtaining the first carbon emission monitoring log of the first carbon emission source; performing retrieval of the same time period within a preset time range in the first carbon emission monitoring log based on the preset time zone to obtain multiple sample first carbon emission amount monitoring sequences; analyzing and obtaining a first predicted emission trend and a first emission fluctuation degree according to the multiple sample first carbon emission amount monitoring sequences, and sequentially analyzing to obtain multiple predicted emission trends and multiple emission fluctuation degrees of the multiple carbon emission sources.

[0038] Preferably, among multiple carbon emission sources in an industrial park (such as factory workshops, energy equipment, transportation vehicles, etc.), randomly select one as the first carbon emission source (such as the boiler system of a certain factory), and obtain the first carbon emission monitoring log of this carbon emission source, that is, the record set of its historical carbon emission data, including time stamps, carbon emission amounts, and related influencing factors (such as production load, energy consumption, equipment operating status, etc.); then set the time zone according to the region where the industrial park is located or business requirements, and configure a preset time range (such as the past 1 year, 1 quarter, 1 month, etc.) to limit the retrieval of historical data. Furthermore, within the preset time range, extract carbon emission data of repeated time periods at fixed intervals (such as 8:00 - 10:00 every day, weekdays every week, etc.) to form multiple sample first carbon emission amount monitoring sequences.

[0039] Preferably, according to multiple sample first carbon emission amount monitoring sequences, fit the long-term trend of carbon emission amount changing with time through time series analysis (such as moving average, exponential smoothing, etc.) to obtain a first predicted emission trend and a first emission fluctuation degree. Specifically, perform time series modeling on each sample sequence (such as the emission amount at the same time period every day), extract the trend term (such as rising, falling, stable), and comprehensively analyze the trend characteristics of all samples to obtain the overall predicted trend of this carbon emission source within the same time period. For example, if most sample sequences show that the carbon emission amount in the morning period increases linearly with the increase in production load, the predicted trend is "emission amount increases within the time period". Then calculate statistical indicators such as standard deviation, coefficient of variation, range, etc. for the emission amount data of multiple sample sequences, and calculate to obtain the first emission fluctuation degree, which reflects the dispersion degree or stability of the carbon emission amount within the same time period, and reflects the volatility of the emission process (such as sudden peaks, abnormal fluctuations, etc.). The larger the value, the more intense the emission fluctuation; the smaller the value, the more stable the emission. Analyze and calculate all carbon emission sources (such as the first, second, and third carbon emission sources) in the industrial park in sequence to obtain multiple predicted emission trends and multiple emission fluctuation degrees. Furthermore, form an overall carbon emission characteristic map of the industrial park to identify high-trend growth sources (such as production lines with continuously increasing emissions) and high-fluctuation sources (such as intermittently operating equipment) for the purpose of carbon emission control and energy optimization scheduling.

[0040] Furthermore, the specific configuration of the carbon emission source analysis module 30 further includes: within a two-dimensional coordinate system, constructing multiple sample first carbon emission curves based on the multiple sample first carbon emission monitoring sequences, and performing curve fitting to determine the first fitted carbon emission curve; calculating a first increase ratio based on the first fitted carbon emission curve, and setting it as the first predicted emission trend; calculating the mean of each of the multiple sample first carbon emission monitoring sequences to obtain multiple sample first carbon emission means, and then calculating the mean again to obtain the first predicted carbon emission; performing emission fluctuation analysis based on the multiple sample first carbon emission means, and calculating a first emission fluctuation degree, where the emission fluctuation degree is the ratio of the standard deviation of the multiple sample first carbon emission means to the first predicted carbon emission.

[0041] Preferably, with the horizontal axis representing time (such as in minutes, hours, or days) and the vertical axis representing carbon emissions, a two-dimensional coordinate system is constructed. Each sample sequence (such as the emission data at the same time period of a certain day) is plotted as a line graph, with the horizontal axis corresponding to the time point and the vertical axis corresponding to the emissions at that moment, to obtain multiple sample first carbon emission curves. Through a mathematical method (such as the least squares method), curve fitting is performed on the multiple sample curves to obtain a smooth curve (i.e., the first fitted carbon emission curve) that can reflect the overall trend, eliminating the interference of random fluctuations, and used to characterize the typical emission trend of this carbon emission source within the preset time period.

[0042] Preferably, based on the calculation of the first fitted carbon emission curve, a first increase ratio is obtained, that is, the first increase ratio = (emissions at the end point of the fitted curve - emissions at the starting point of the fitted curve) / emissions at the starting point of the fitted curve × 100%. If the result is positive, it indicates an increasing emission trend; if it is negative, it indicates a decreasing trend; if it is close to 0, it is a stable trend. And the first increase ratio is set as the first predicted emission trend. Then, double mean calculation is performed, that is, calculating the mean of the emissions for each sample sequence (such as the time period data of a certain day), and then calculating the mean of all the sample means again to obtain the first predicted carbon emission, which reflects the average emission level of this carbon emission source within the preset time period and serves as the emission prediction benchmark for the same time period in the future.

[0043] Preferably, the emission fluctuation degree is analyzed based on the first carbon emission means of multiple samples, that is, the standard deviation of the first carbon emission means of multiple samples is used as the numerator, and the first predicted carbon emission is used as the denominator, and the ratio of the two is calculated as the first emission fluctuation degree. Among them, the numerator (standard deviation) is used to measure the absolute dispersion degree of each sample mean from the overall mean. The larger the standard deviation, the greater the difference in emissions among different samples; the denominator (predicted carbon emission) converts the absolute dispersion degree into a relative value to eliminate the influence of the emission magnitude on the fluctuation assessment. Among them, the fluctuation degree reflects the stability of carbon emissions. If the fluctuation degree is low (such as less than 10%), it indicates that the emission process has strong regularity and is less affected by random factors; if the fluctuation degree is high (such as greater than 40%), it indicates that there are significant uncertainties in emissions, which may be caused by equipment start-stop, raw material changes, process adjustments, etc.

[0044] The carbon emission monitoring module 40 is used to configure the optimized data acquisition strategy of the edge computing gateway according to the multiple monitoring index sequences, multiple predicted emission trends, and multiple emission fluctuation degrees, and perform the carbon emission monitoring in the preset time zone. Among them, the data acquisition strategy includes the monitoring index type, data acquisition frequency, and key feature screening threshold.

[0045] Furthermore, the specific configuration of the carbon emission monitoring module 40 also includes mapping and obtaining the first edge computing gateway of the first carbon emission source; determining the first fluctuation scale according to the first predicted emission trend, the first predicted carbon emission, and the first emission fluctuation degree analysis; adjusting the first initial data acquisition plan according to the first fluctuation scale to obtain the first optimized data acquisition plan; sequentially analyzing and obtaining the optimized data acquisition plans of multiple edge computing gateways to construct an optimized data acquisition strategy.

[0046] Preferably, the optimized data acquisition strategy of the edge computing gateway is configured according to the multiple monitoring index sequences, multiple predicted emission trends, and multiple emission fluctuation degrees, that is, the edge computing gateway constructs a dynamic data acquisition strategy by integrating the monitoring index sequence, predicted emission trend, and emission fluctuation degree, specifically including the screening of the monitoring index type, the configuration of the data acquisition frequency, and the optimization of the key feature screening threshold. Among them, the screening of the monitoring index type includes preferentially collecting high-priority indicators (such as indicators with a correlation degree > 0.8 and a credibility > 0.9) to ensure that the core characteristics of carbon emissions are effectively monitored; for low-priority indicators (such as indicators with a correlation degree < 0.3 or a credibility < 0.6), suspend the collection or only trigger the collection when the equipment is abnormal.

[0047] Preferably, the configuration of the data acquisition frequency includes increasing the acquisition frequency of key indicators if the emission trend is rising, and decreasing the acquisition frequency of non-key indicators if the emission trend is falling; if the emission fluctuation degree > 30%, the acquisition frequency of all indicators ≥ 1 time / minute, and if the emission fluctuation degree < 10%, the acquisition frequency of conventional indicators ≤ 1 time / 5 minutes. The optimization of the key feature screening threshold includes adjusting the anomaly detection threshold and setting the data compression threshold. For example, the anomaly detection threshold is dynamically adjusted based on historical emission data, with a normal fluctuation range of mean ± 2 standard deviations. When the fluctuation degree increases, the threshold is relaxed (such as ± 3 standard deviations) to reduce false alarms, and when the fluctuation degree decreases, the threshold is tightened (such as ± 1.5 standard deviations) to improve sensitivity; for indicators with slow changes (such as the temperature of a steadily operating device), a larger differential threshold is set to reduce the data transmission volume.

[0048] Preferably, a mapping relationship between carbon emission sources and their corresponding edge computing gateways is established. Each carbon emission source (such as a boiler, production line) corresponds to one or more edge computing gateways, which are responsible for local data acquisition and preprocessing. For a randomly selected first carbon emission source (such as a certain key boiler), the execution entity for its data acquisition is determined through mapping, that is, the first edge computing gateway; then, based on the first predicted emission trend, the first predicted carbon emission amount, and the first emission fluctuation degree, the first fluctuation scale is analyzed and determined, that is, by comprehensively considering the first predicted emission trend, the first predicted carbon emission amount, and the first emission fluctuation degree, the fluctuation scale of carbon emissions is judged. For example, if the trend is rising and the fluctuation degree is large, it indicates unstable emissions and a large fluctuation scale; if the trend is stable and the fluctuation degree is small, it indicates stable emissions and a small fluctuation scale.

[0049] Preferably, the first initial data acquisition plan is adjusted according to the first fluctuation scale. Among them, the initial data acquisition plan refers to the preset acquisition rules, such as collecting all indicators every 30 minutes. Specifically, if the fluctuation scale is large, the acquisition frequency is increased (such as adjusted from 30 minutes to 10 minutes), the monitoring indicators are refined (such as adding associated indicators such as equipment operation status, fuel consumption, etc.), and the key feature screening threshold is reduced (such as retaining more detailed data to avoid filtering important fluctuation information); if the fluctuation scale is small, the acquisition frequency is decreased (such as adjusted from 30 minutes to 1 hour), the monitoring indicators are simplified (only retaining carbon emission amount and emission concentration), and the key feature screening threshold is increased (filtering noise data and focusing on the main trend). Through dynamic adjustment, the first optimized data acquisition plan is obtained to ensure better conformity to the actual emission characteristics and balance data accuracy and computational resource efficiency.

[0050] Preferably, the edge computing gateway corresponding to each carbon emission source is repeatedly analyzed to generate multiple optimized data acquisition schemes (for example, gateway X is responsible for high-fluctuation sources and uses high-frequency acquisition; gateway Y is responsible for stable sources and uses low-frequency acquisition). Finally, all the optimized data acquisition schemes are integrated into a data acquisition strategy, and the types of monitoring indicators (the list of indicators to be collected in different scenarios), the data acquisition frequency (the frequency rule for dynamic adjustment), and the key feature screening threshold (the criteria for data filtering and feature extraction) are clarified, thereby improving the efficiency and accuracy of carbon emission monitoring.

[0051] Preferably, according to the determined optimized data acquisition strategy, carbon emission monitoring in a preset time zone is performed, that is, the configured acquisition strategy is deployed to the edge node to achieve local data processing and reduce the dependence on the cloud. For example, an edge gateway is deployed in the industrial park power distribution room to process power consumption and carbon emission data in real time; the time zone is divided according to the business activity rules (such as production time zone, non-production time zone), and the strategy is executed differentially. And after each preset time zone monitoring is completed, the edge computing gateway automatically evaluates the strategy effect. If the actual emission fluctuation degree is different from the prediction by more than 20%, the weight is recalculated and the acquisition frequency is adjusted. If a certain indicator has not detected an anomaly for three consecutive time zones, its acquisition priority is reduced. Thus, it realizes the transformation from extensive data acquisition to precise intelligent monitoring, ensuring the efficient and reliable carbon emission monitoring and management in the industrial park.

[0052] Furthermore, the specific configuration of the carbon emission monitoring module 40 further includes calculating the ratio of the first predicted carbon emission amount to the historical average value of the first carbon emission amount of the first carbon emission source, which is set as the first emission scale; calculating the ratio of the first predicted emission trend to the historical average value of the first emission trend to obtain a trend adjustment coefficient; calculating the ratio of the first emission fluctuation degree to the historical average value of the first emission fluctuation degree to obtain an emission fluctuation adjustment coefficient; using the trend adjustment coefficient and the emission fluctuation adjustment coefficient to perform double compensation on the first emission scale and output the first fluctuation scale.

[0053] Preferably, calculate the ratio of the first predicted carbon emissions to the average historical first carbon emissions of the first carbon emission source as the first emission scale. If the first emission scale is greater than 1, it indicates that the current predicted emissions are higher than the historical average level. If the first emission scale is equal to 1, it indicates that it is on par with the historical level. If the first emission scale is less than 1, it indicates that it is lower than the historical level. Calculate the ratio of the first predicted emission trend to the average historical first emission trend to obtain the trend adjustment coefficient. The first predicted emission trend is the growth rate obtained through curve fitting, and the average historical first emission trend is the average of the emission trends over a certain period in the past. Calculate the ratio of the first emission volatility to the average historical first emission volatility to obtain the emission volatility adjustment coefficient. The first emission volatility represents the degree of fluctuation of the current emissions, and the average historical first emission volatility represents the average of the historical volatilities. Finally, use the trend adjustment coefficient and the emission volatility adjustment coefficient to perform double compensation on the first emission scale, that is, the first fluctuation scale = trend adjustment coefficient × emission volatility adjustment coefficient × first emission scale. Among them, if the current emission trend is significantly higher than the historical average (such as increased production leading to accelerated emissions), the evaluation value of the fluctuation scale is amplified to prompt enhanced monitoring. If the current fluctuation amplitude increases (such as frequent equipment start-stop), the fluctuation scale is further amplified to reflect the increased uncertainty in the emission process.

[0054] Furthermore, the specific configuration of the carbon emission monitoring module 40 further includes configuring a first initial data collection scheme. Among them, the first initial data collection scheme includes the number of first monitoring indicators selected, the first data collection frequency, and the first key feature screening threshold. Adjust the number of first monitoring indicators selected according to the first fluctuation scale to determine the first optimized selection quantity, and select the first optimized selection quantity of monitoring indicators from the first monitoring indicator sequence to obtain the first monitoring indicator type. Adjust the first data collection frequency according to the first fluctuation scale to determine the first optimized collection frequency. Adjust the first key feature screening threshold according to the first fluctuation scale to determine the first optimized feature screening threshold. Construct a first optimized data collection scheme based on the first monitoring indicator type, the first optimized collection frequency, and the first optimized feature screening threshold.

[0055] Preferably, configure the first initial data collection scheme with the number of first monitoring indicators selected, the first data collection frequency, and the first key feature screening threshold. Among them, the number of first monitoring indicators selected is the total number of indicators to be collected as preset (such as initially selecting 20 indicators, including emissions, energy consumption, equipment status, etc.). The first data collection frequency is a fixed collection interval (such as once per hour) or a cycle (such as 8 times per day). The first key feature screening threshold is a preset standard for data filtering or feature extraction, such as only retaining data points with a fluctuation amplitude > 5%, or compressing index values with a change < 2%.

[0056] Preferably, the number of the first monitoring indicators is adjusted according to the first fluctuation scale. Specifically, through the formula , where k is an adjustment coefficient (set according to the business scenario). When the fluctuation scale > 1, the optimized quantity increases, and new highly correlated indicators (such as fuel composition, process temperature, etc.) are added. For example, when the fluctuation scale = 2 and the initial quantity is 10, the first optimized selection quantity is 10×(1 + 0.5×2) = 20 indicators; when the fluctuation scale ≤ 1, the optimized quantity decreases, and non-critical indicators may be reduced after actual rounding. Then, the first N indicators (where N is a positive integer representing the optimized quantity) are selected from the monitoring indicator sequence (sorted by priority) to obtain the first type of monitoring indicators, ensuring that high-value indicators are collected first.

[0057] Preferably, the first data collection frequency is adjusted according to the first fluctuation scale to determine the first optimized collection frequency. Specifically, the larger the fluctuation scale, the larger the first optimized collection frequency. If the fluctuation scale exceeds the threshold, a high-frequency collection mode is triggered, such as real-time collection; conversely, the smaller the fluctuation scale, the smaller the first optimized collection frequency. If the fluctuation scale is below the threshold, an energy-saving mode is entered, such as collecting once every 4 hours. The first critical feature screening threshold is adjusted according to the first fluctuation scale to determine the first optimized feature screening threshold. Specifically, the larger the fluctuation scale, the smaller the first optimized feature screening threshold, that is, smaller-amplitude fluctuation data is retained to improve the monitoring accuracy; the smaller the fluctuation scale, the larger the first optimized feature screening threshold, that is, more noise data is filtered to reduce invalid storage. Finally, the first type of monitoring indicators, the first optimized collection frequency, and the first optimized feature screening threshold are combined to construct the first optimized data collection scheme, that is, a personalized data collection strategy for the first carbon emission source.

[0058] Furthermore, the specific configuration of the carbon emission monitoring module 40 further includes setting the reciprocal of the first fluctuation scale as the first threshold adjustment coefficient to adjust the first critical feature screening threshold to obtain the first optimized feature screening threshold.

[0059] Preferably, the reciprocal of the first fluctuation scale is set as the first threshold adjustment coefficient, that is, the larger the fluctuation scale, the smaller the threshold adjustment coefficient, and the optimized threshold is looser (allowing larger data fluctuations); the smaller the fluctuation scale, the larger the threshold adjustment coefficient, and the optimized threshold is stricter (limiting the data fluctuation range); then the first critical feature screening threshold is adjusted to obtain the first optimized feature screening threshold. Specifically, the expression of the first optimized feature screening threshold is: ; where, based on the real-time fluctuation characteristics of carbon emissions, the data screening criteria are adaptively adjusted to improve the efficiency and reliability of the edge computing gateway while ensuring the monitoring accuracy.

[0060] Further, the specific configuration of the carbon emission monitoring module 40 further includes that when monitoring carbon emissions according to the first monitoring index type and the first optimized acquisition frequency, it is determined whether the monitoring data deviation under adjacent monitoring nodes is greater than the first optimized feature screening threshold. If it is greater, the monitoring data under the adjacent monitoring nodes is retained as key data. If it is less, the monitoring data under the adjacent monitoring nodes is discarded, and the determination and screening are iteratively performed.

[0061] Preferably, when monitoring carbon emissions according to the first monitoring index type and the first optimized acquisition frequency, it is determined whether the monitoring data deviation under adjacent monitoring nodes is greater than the first optimized feature screening threshold. Among them, adjacent monitoring nodes refer to two consecutive data acquisition points in the time series. The monitoring data deviation refers to the numerical difference of the same index between adjacent nodes. The first optimized feature screening threshold is a threshold dynamically adjusted according to the fluctuation scale. Specifically, if the monitoring data deviation under adjacent monitoring nodes is greater than the first optimized feature screening threshold, the monitoring data under the adjacent monitoring nodes is retained as key data; if the monitoring data deviation under adjacent monitoring nodes is less than the first optimized feature screening threshold, the monitoring data under the adjacent monitoring nodes is discarded; and the determination and screening are iteratively performed, that is, all adjacent monitoring nodes are judged, and data is screened pair by pair, and finally a key data sequence containing only significant fluctuations is retained; thereby enabling the edge computing gateway to capture the most valuable emission fluctuation information with the smallest amount of data to ensure the efficiency and reliability of carbon emission monitoring and management in the industrial park.

[0062] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0063] The above specific implementation manners do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An edge computing gateway device for comprehensive monitoring of multi-modal energy carbon emissions, characterized in that The edge computing gateway device includes: A carbon emission data acquisition module, configured to acquire multiple carbon emission sources and multiple carbon emission monitoring index sets in an industrial park; A priority evaluation module, configured to sequentially evaluate the priorities of multiple carbon emission monitoring indexes in the multiple carbon emission monitoring index sets to obtain multiple monitoring index sequences; A carbon emission source analysis module, configured to analyze and obtain multiple predicted emission trends and multiple emission fluctuation degrees of the multiple carbon emission sources within a preset time zone based on the carbon emission monitoring logs of the industrial park; A carbon emission monitoring module, configured to configure an optimized data acquisition strategy for the edge computing gateway according to the multiple monitoring index sequences, multiple predicted emission trends, and multiple emission fluctuation degrees, and perform carbon emission monitoring in the preset time zone, where the data acquisition strategy includes monitoring index types, data acquisition frequencies, and key feature screening thresholds.

2. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 1, characterized in that The steps executed by the priority evaluation module include: Randomly select a first carbon emission monitoring index set of a first carbon emission source to obtain multiple first carbon emission monitoring indexes; Obtain multiple first unit monitoring data volumes of the multiple first carbon emission monitoring indexes; According to the carbon emission monitoring logs of the first carbon emission source, evaluate the index correlation degree and data credibility of the multiple first carbon emission monitoring indexes respectively to determine multiple first index correlation degrees and multiple first data credibility; Evaluate the priorities of the multiple first carbon emission monitoring indexes respectively according to the multiple first unit monitoring data volumes, multiple first index correlation degrees, and multiple first data credibility, construct a first monitoring index sequence, and sequentially analyze to obtain multiple monitoring index sequences.

3. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 2, wherein, The steps executed by the priority evaluation module include: Configure data volume weights, correlation degree weights, and credibility weights based on the coefficient of variation method according to the carbon emission monitoring logs of the first carbon emission source and the performance of the edge computing gateway; After performing dimensionless processing on the multiple first unit monitoring data volumes, multiple first index correlation degrees, and multiple first data credibility, weighted obtain multiple first priorities based on the data volume weights, correlation degree weights, and credibility weights, where the priority is negatively correlated with the unit monitoring data volume and positively correlated with the index correlation degree and data credibility; Based on the multiple first priorities, arrange the multiple first carbon emission monitoring indexes in descending order of the first priority to obtain a first monitoring index sequence.

4. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 1, characterized in that, The steps executed by the carbon emission source analysis module include: Randomly select a first carbon emission source and obtain the first carbon emission monitoring log of the first carbon emission source; Perform retrieval of the same time periods within a preset time range in the first carbon emission monitoring log based on the preset time zone to obtain multiple sample first carbon emission monitoring sequences; Analyze and obtain a first predicted emission trend and a first emission fluctuation degree according to the multiple sample first carbon emission monitoring sequences, and sequentially analyze to obtain multiple predicted emission trends and multiple emission fluctuation degrees of the multiple carbon emission sources.

5. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 4, characterized in that, The steps executed by the carbon emission source analysis module include: In a two-dimensional coordinate system, construct multiple sample first carbon emission curves according to the multiple sample first carbon emission monitoring sequences, and perform curve fitting to determine a first fitted carbon emission curve; Calculate the first increase ratio based on the first fitted carbon emission curve, which is set as the first predicted emission trend; Calculate the mean of each of the multiple sample first carbon emission monitoring sequences to obtain the means of the multiple sample first carbon emissions, and then calculate the mean again to obtain the first predicted carbon emission; Analyze the emission fluctuation degree based on the means of the multiple sample first carbon emissions, and calculate the first emission fluctuation degree. Here, the emission fluctuation degree is the ratio of the standard deviation of the means of the multiple sample first carbon emissions to the first predicted carbon emission.

6. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 5, characterized in that, The steps performed by the carbon emission monitoring module include: Map to obtain the first edge computing gateway of the first carbon emission source; Determine the first fluctuation scale based on the first predicted emission trend, the first predicted carbon emission, and the analysis of the first emission fluctuation degree; Adjust the first initial data collection plan according to the first fluctuation scale to obtain the first optimized data collection plan; Analyze to obtain the optimized data collection plans of multiple edge computing gateways in sequence, and construct an optimized data collection strategy.

7. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 6, wherein, The steps performed by the carbon emission monitoring module include: Calculate the ratio of the first predicted carbon emission to the historical mean of the first carbon emissions of the first carbon emission source, which is set as the first emission scale; Calculate the ratio of the first predicted emission trend to the historical mean of the first emission trends to obtain a trend adjustment coefficient; Calculate the ratio of the first emission fluctuation degree to the historical mean of the first emission fluctuation degrees to obtain an emission fluctuation adjustment coefficient; Use the trend adjustment coefficient and the emission fluctuation adjustment coefficient to perform double compensation on the first emission scale and output the first fluctuation scale.

8. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 7, characterized in that, The steps performed by the carbon emission monitoring module include: Configure the first initial data collection plan, where the first initial data collection plan includes the number of selected first monitoring indicators, the first data collection frequency, and the first key feature screening threshold; Adjust the number of selected first monitoring indicators according to the first fluctuation scale to determine the first optimized selection number, and select the first optimized selection number of monitoring indicators from the first monitoring indicator sequence to obtain the first monitoring indicator type; Adjust the first data collection frequency according to the first fluctuation scale to determine the first optimized collection frequency; Adjust the first key feature screening threshold according to the first fluctuation scale to determine the first optimized feature screening threshold; Construct the first optimized data collection plan based on the first monitoring indicator type, the first optimized collection frequency, and the first optimized feature screening threshold.

9. The edge computing gateway device for multi-modal energy carbon emission comprehensive monitoring according to claim 8, characterized in that, Set the reciprocal of the first fluctuation scale as the first threshold adjustment coefficient, and adjust the first key feature screening threshold to obtain the first optimized feature screening threshold.

10. The edge computing gateway device for comprehensive monitoring of multi-modal energy carbon emissions according to claim 9, characterized in that, When performing carbon emission monitoring according to the first monitoring indicator type and the first optimized collection frequency, determine whether the deviation of the monitoring data under adjacent monitoring nodes is greater than the first optimized feature screening threshold. If it is greater, retain the monitoring data under the adjacent monitoring nodes as key data. If it is less, discard the monitoring data under the adjacent monitoring nodes, and perform iterative judgment and screening.

Images