Carbon emission tracking system based on Internet of Things technology

Abstract

The invention provides a carbon emission tracking system based on the Internet of Things technology, and relates to the technical field of carbon emission tracking. Comprising a data collection and extraction module used for collecting ecological change data, carbon emission concentration and historical emission data in a target range. And the carbon data modeling analysis module is used for acquiring carbon emission associated data, constructing a GWO-Prophet model optimized by an improved grey wolf algorithm, inputting the associated data and outputting carbon emission influence data. And the regional carbon strategy making module is used for dividing regions according to the carbon emission concentration and influence data, obtaining carbon emission characteristic data through characteristic analysis, and making tracking strategies for different regions according to the carbon emission characteristic data. And the feedback adjustment module is used for judging whether the tracking strategy reaches an expected target or not and taking corresponding measures. According to the method, the model parameters are optimized and adjusted, so that the prediction accuracy of the model and the adaptability to carbon emission conditions of different regions are improved, the tracking strategy is formulated according to different risk levels, and the pertinence and effectiveness of the strategy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission tracking, and in particular to a carbon emission tracking system based on Internet of Things technology. Background Art

[0002] As the global climate change problem becomes increasingly serious, the monitoring and management of carbon emissions has become a key measure to address climate change. The development of Internet of Things technology has provided new means and ways to track carbon emissions, and various sensor devices can realize the real-time collection and transmission of carbon emission-related data.

[0003] In the existing carbon emission tracking research and practice, there are many problems that need to be solved. First, the understanding of the factors and laws affecting carbon emissions is still incomplete. And due to the lack of deep integration and analysis of multi-source data, it is difficult to fully and accurately explore the factors affecting carbon emissions and the internal laws, which limits the effective management and precise regulation of carbon emissions.

[0004] Secondly, the existing carbon emission prediction models have problems with poor prediction accuracy and adaptability in practical applications. During the construction process of many models, the parameter settings are relatively fixed, and there is a lack of effective optimization mechanisms, making it difficult to adapt to the complex changes in carbon emissions in different regions and time periods. For example, in some regions with rapid economic development and continuous adjustment of industrial structure, traditional models cannot reflect the dynamic trend of carbon emissions in a timely manner, resulting in a large deviation between the prediction results and the actual situation, and unable to provide reliable support for carbon emission planning and decision-making.

[0005] Furthermore, the carbon emission tracking strategy lacks specificity. At present, when formulating carbon emission tracking strategies, a "one-size-fits-all" approach is often adopted, without fully considering the differences in economic development levels, industrial structures, energy structures, etc. between different regions. This makes it difficult to effectively control some high-carbon emission risk areas, while some low-carbon emission areas may implement overly strict measures, resulting in a waste of resources. This lack of targeted tracking strategy makes it difficult to achieve efficient management of carbon emissions and cannot meet the actual needs of carbon emission control.

[0006] To sum up, in order to more effectively respond to climate change and achieve accurate monitoring, prediction and management of carbon emissions, there is an urgent need for a carbon emission tracking system based on Internet of Things technology that can comprehensively analyze the factors affecting carbon emissions, optimize the prediction model, and formulate targeted tracking strategies to improve the efficiency and effectiveness of carbon emission management. Summary of the invention

[0007] The present invention provides a carbon emission tracking system based on the Internet of Things technology, which is used to solve the defects of the prior art in that the factors affecting carbon emissions and their laws are not fully understood, the model prediction and adaptability are poor, and the tracking strategy lacks pertinence.

[0008] The present invention provides a carbon emission tracking system based on Internet of Things technology, including: A data collection and extraction module, configured to collect industry data of various enterprises and individuals in the target scope, and collect ecological change data caused by environmental changes, and extract carbon emission concentration data and historical emission data from the industry data.

[0009] A carbon data modeling and analysis module, configured to use the correlation analysis method and combine with the ecological change data to process the historical emission data to obtain carbon emission correlation data, construct a Prophet model, input the historical emission data for training, and use the improved grey wolf optimization algorithm to optimize the Prophet model to obtain the GWO-Prophet model, input the carbon emission correlation data, and output to obtain carbon emission impact data.

[0010] A regional carbon strategy formulation module, configured to divide the target scope into multiple regions according to the carbon emission concentration data and combine with the carbon emission impact data, use the feature analysis method to observe the carbon emissions of each region to obtain corresponding carbon emission feature data, and formulate corresponding tracking strategies for different regions according to the carbon emission feature data.

[0011] According to the carbon emission tracking system based on Internet of Things technology provided by the present invention, the steps of obtaining carbon emission correlation data include: Extract the emission data of various greenhouse gases covering different time periods from the historical emission data as the time period emission data, and at the same time extract the ecological index data composed of temperature, precipitation and vegetation coverage rate within different time periods from the ecological change data.

[0012] Remove the outliers in the time period emission data and the ecological index data, and use the Z-score method for in-depth cleaning.

[0013] Use the Spearman rank correlation coefficient to calculate the correlation coefficient between the time period emission data and the ecological index data to obtain the correlation coefficient value.

[0014] According to the correlation coefficient value, deeply analyze the correlation degree between the ecological change data and the carbon emission data, select the ecological change data with the deepest correlation degree as the ecological correlation data, and integrate the ecological correlation data with the historical emission data to obtain the carbon emission correlation data.

[0015] According to the carbon emission tracking system based on Internet of Things technology provided by the present invention, the formula expression of the correlation coefficient value is:

[0016] In the formula, is the correlation coefficient value, is the number of samples, is the th observation value in the time period emission data, is the rank in the time period emission data, is the fixed coefficient, is the th observation value in the ecological index data, is the rank in the ecological index data, is the rank difference.

[0017] A carbon emission tracking system based on Internet of Things technology provided by the present invention, the steps of obtaining the GWO-Prophet model include: Set the number of grey wolf individuals in the wolf pack. For each grey wolf individual, randomly generate a set of parameter values within a preset value range to generate a position vector of the grey wolf individual.

[0018] Divide the historical emission data into a training set and a test set. For each grey wolf individual, use its corresponding parameter values to construct a Prophet model, input the training set into the Prophet model for training, and then make predictions on the test set to obtain predicted values.

[0019] Use the root mean square error to calculate the fitness function according to the predicted values and the true values in the test set.

[0020] Calculate the fitness value of each grey wolf individual according to the fitness function, sort all grey wolf individuals in ascending order according to the fitness value, and select the three grey wolf individuals with the smallest fitness values as the optimal solution, the sub-optimal solution, and the third-optimal solution.

[0021] Calculate the distance vectors between each grey wolf individual and the optimal solution, the sub-optimal solution, and the third-optimal solution to obtain the optimal distance, the sub-optimal distance, and the third-optimal distance.

[0022] Calculate the position update vectors between each grey wolf individual and the optimal solution, the sub-optimal solution, and the third-optimal solution to obtain the optimal update vector, the sub-optimal update vector, and the third-optimal distance vector.

[0023] According to the optimal distance, the sub-optimal distance, the third-optimal distance, the optimal update vector, the sub-optimal update vector, and the third-optimal distance vector, determine the updated position of the th grey wolf individual.

[0024] Repeat the above steps until the preset number of iterations is reached, and select the parameter combination corresponding to the grey wolf individual with the highest fitness value among all fitness values to construct the GWO-Prophet model.

[0025] According to the carbon emission tracking system based on Internet of Things technology provided by the present invention, the formula for updating the position is expressed as:

[0026] In the formula, is the optimal update vector, is the sub-optimal update vector, is the third-optimal distance vector, is the update position.

[0027] According to a carbon emission tracking system based on Internet of Things technology provided by the present invention, the steps of obtaining carbon emission impact data include: Extract ecological data, carbon emission growth rate, and cumulative emissions from carbon emission-related data to construct an input feature matrix, input the input feature matrix into the GWO-Prophet model, and predict the carbon emission situation to obtain a prediction result.

[0028] Analyze the prediction result, and obtain the carbon emission change amount and the analysis result of sensitive factors of carbon emission under different ecological change scenarios from the influence degree of different input features on the carbon emission prediction result to generate carbon emission impact data.

[0029] According to a carbon emission tracking system based on Internet of Things technology provided by the present invention, the steps of dividing multiple regions include: Analyze the relationship between carbon emission impact data and carbon emission concentration, and obtain an analysis result by studying the carbon emission situation in regions with a heavy industry-based industrial structure and the relationship between the proportion of different energy uses in the energy structure and carbon emission concentration.

[0030] According to the analysis result, set corresponding weights for each influencing factor in the carbon emission impact data, and calculate the comprehensive score for each position within the target range according to the carbon emission concentration data, each influencing factor, and the weight.

[0031] According to the comprehensive score, divide each position within the target range into multiple evaluation levels, and use the hierarchical clustering method to classify the scoring levels that meet the preset interval into the same category, so as to form multiple intervals.

[0032] According to a carbon emission tracking system based on Internet of Things technology provided by the present invention, the formula expression of the comprehensive score is:

[0033] In the formula, is the weight, is the comprehensive score, is the data obtained by standardizing the carbon emission concentration data, is the th standardized data of the influencing factor, is the th weight of the influencing factor.

[0034] A carbon emission tracking system based on Internet of Things technology provided by the present invention, the steps of obtaining carbon emission characteristic data include: Install carbon emission monitoring equipment and energy metering equipment within the target range to record the energy consumption to obtain monitoring data, and collect carbon emission data generated by population and economy to obtain factor data.

[0035] Combine the monitoring data to draw a time series graph of carbon emissions, observe the change trend of carbon emissions in different time periods to obtain spatio-temporal characteristics, analyze the main sources of carbon emissions according to the factor data, and further subdivide the energy types to obtain source data.

[0036] Study the relationship between different factors and carbon emissions according to the spatio-temporal characteristics and source data, and consider the impact of geographical environment on carbon emissions to obtain carbon emission characteristic data.

[0037] A carbon emission tracking system based on Internet of Things technology provided by the present invention, the steps of obtaining a tracking strategy include: By analyzing the dynamic relationship between carbon emissions, industrial development and energy consumption during the rapid economic growth stage, and studying the differences in residential energy consumption and carbon emissions under different climate conditions, obtain the logic and change trend behind the carbon emission characteristic data of each region.

[0038] Classify the carbon emission characteristic data from the aspects of time, source and influencing factors to obtain key element data, set evaluation indicators according to the key element data, and evaluate the carbon emission risks of different regions according to the evaluation indicators and preset ratios, and divide them into multiple risk levels.

[0039] Set corresponding tracking plans according to different risk levels, set corresponding tracking periods through the risk levels and carbon emission characteristic data of each region, and adjust the tracking plans according to the tracking periods to obtain a tracking strategy.

[0040] A carbon emission tracking system based on Internet of Things technology provided by the present invention, by obtaining industry data and ecological change data, extracting carbon emission concentration data and historical emission data from them, combining correlation analysis and ecological change data to process historical emission data, constructing and optimizing the Prophet model to obtain the GWO-Prophet model, so as to output carbon emission impact data. Divide regions according to carbon emission concentration and impact data, analyze carbon emission characteristics and formulate tracking strategies. Real-time track carbon emission situations and adjust strategies according to the results. This system realizes the integration and in-depth analysis of multi-source data through Internet of Things technology, solves the deficiencies of traditional methods in data processing, prediction accuracy, consideration of spatial heterogeneity, real-time dynamic tracking and data quality guarantee, and achieves effects such as improving prediction accuracy, enhancing analysis ability, realizing precise regional management and dynamic optimization, and promotes the realization of sustainable development. Description of the Drawings

[0041] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a schematic structural diagram of a carbon emission tracking system based on Internet of Things technology provided by an embodiment of the present invention; Figure 2 is Figure 1 a flowchart for the carbon data modeling and analysis module to obtain carbon emission impact data; Figure 3 is Figure 1 a flowchart for the regional carbon strategy formulation module to obtain a tracking strategy. Detailed implementation manners

[0043] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0044] The following will describe Figures 1 - 3 a carbon emission tracking system based on Internet of Things technology of the present invention.

[0045] As Figure 1 shown, a carbon emission tracking system based on Internet of Things technology provided by an embodiment of the present invention includes: A data collection and extraction module, configured to collect industry data of various enterprises and individuals within the target scope, and collect ecological change data caused by environmental changes, and extract carbon emission concentration data and historical emission data from the industry data.

[0046] As Figure 2 shown, a carbon data modeling and analysis module, configured to use a correlation analysis method and combine ecological change data to process historical emission data to obtain carbon emission correlation data, construct a Prophet model, input historical emission data for training, and use an improved grey wolf optimization algorithm to optimize the Prophet model to obtain a GWO-Prophet model, input carbon emission correlation data, and output carbon emission impact data.

[0047] The steps for obtaining carbon emission correlation data include: Extract the emission data of various greenhouse gases covering different time periods from historical emission data as the time period emission data, and at the same time extract the ecological index data composed of temperature, precipitation, and vegetation coverage rate within different time periods from the ecological change data.

[0048] Remove the outliers in the time period emission data and the ecological index data, and use the Z-score method for in-depth cleaning.

[0049] Calculate the correlation coefficient between the time period emission data and the ecological index data using the Spearman rank correlation coefficient to obtain the correlation coefficient value, and the formula is expressed as:

[0050] In the formula, is the correlation coefficient value, is the number of samples, is the th observation value in the time period emission data, is the rank in the time period emission data, is a fixed coefficient, is the th observation value in the ecological index data, is the rank in the ecological index data, is the rank difference.

[0051] According to the correlation coefficient value, deeply analyze the degree of association between the ecological change data and the carbon emission data, select the ecological change data with the deepest degree of association as the ecological association data, and integrate the ecological association data with the historical emission data to obtain the carbon emission association data.

[0052] The steps to obtain the GWO-Prophet model include: Set the number of gray wolf individuals in the wolf pack. For each gray wolf individual, randomly generate a set of parameter values within the preset value range to generate a position vector of a gray wolf individual.

[0053] Divide the historical emission data into a training set and a test set. For each gray wolf individual, use its corresponding parameter values to construct a Prophet model, input the training set into the Prophet model for training, and then predict the test set to obtain the predicted values.

[0054] Calculate the fitness function using the root mean square error based on the predicted values and the true values in the test set, and the formula is expressed as:

[0055] In the formula, is the fitness function, is the position vector, is the number of samples in the test set, is the true value of the is the predicted value of the

[0056] Calculate the fitness value of each gray wolf individual according to the fitness function, sort all gray wolf individuals in ascending order according to the fitness value, and select the three gray wolf individuals with the smallest fitness values as the optimal solution, sub-optimal solution, and third-optimal solution.

[0057] Calculate the distance vectors between each gray wolf individual and the optimal solution, sub-optimal solution, and third-optimal solution to obtain the optimal distance, sub-optimal distance, and third-optimal distance. The formula is expressed as:

[0058]

[0059]

[0060] In the formula, is the optimal distance, is the sub-optimal distance, is the third-optimal distance, , and are random vectors, is the position vector of the th gray wolf individual, is the position vector of the optimal solution, is the position vector of the sub-optimal solution,

[0061] Calculate the position update vectors between each gray wolf individual and the optimal solution, sub-optimal solution, and third-optimal solution to obtain the optimal update vector, sub-optimal update vector, and third-optimal distance vector. The formula is expressed as:

[0062]

[0063]

[0064] In the formula, is the optimal update vector, is the sub-optimal update vector, is the third-optimal distance vector, , and are random vectors.

[0065] According to the optimal distance, sub-optimal distance, third-optimal distance, optimal update vector, sub-optimal update vector, and third-optimal distance vector, determine the The formula for the updated position of an individual gray wolf is expressed as:

[0066] In the formula, is the optimal update vector, is the sub - optimal update vector, is the third - optimal distance vector, is the updated position.

[0067] Repeat the above steps until the preset number of iterations is reached, and select the parameter combination corresponding to the gray wolf individual with the highest fitness value among all fitness values to construct the GWO - Prophet model.

[0068] As Figure 3 shown, the regional carbon strategy formulation module is used to divide the target range into multiple regions according to the carbon emission concentration data and combined with the carbon emission impact data, observe the carbon emissions of each region using the feature analysis method to obtain the corresponding carbon emission feature data, and formulate corresponding tracking strategies for different regions according to the carbon emission feature data.

[0069] The steps to obtain the carbon emission impact data include: Extract ecological data, carbon emission growth rate, and cumulative emissions from the carbon emission - related data to construct an input feature matrix, input the input feature matrix into the GWO - Prophet model, and predict the carbon emission situation to obtain the prediction results.

[0070] Analyze the prediction results, and obtain the carbon emission change amount and the analysis results of the sensitive factors of carbon emissions under different ecological change scenarios from the influence degree of different input features on the carbon emission prediction results to generate the carbon emission impact data.

[0071] The steps to divide into multiple regions include: Analyze the relationship between the carbon emission impact data and the carbon emission concentration, and obtain the analysis results by studying the carbon emission situation in regions with a mainly heavy - industry - based industrial structure and the relationship between the proportion of different energy uses in the energy structure and the carbon emission concentration.

[0072] According to the analysis results, set corresponding weights for each influencing factor in the carbon emission impact data. For each position within the target range, the formula for calculating the comprehensive score based on the carbon emission concentration data, each influencing factor, and the weight is expressed as:

[0073] In the formula, is the weight, is the comprehensive score, is the data obtained by standardizing the carbon emission concentration data, is the The standardized data of the influencing factors is the weight of the influencing factor

[0074] According to the comprehensive score, each location within the target range is divided into multiple evaluation levels, and the hierarchical clustering method is used to classify the scoring levels that meet the preset interval into the same category, thereby forming multiple intervals.

[0075] The steps to obtain the carbon emission characteristic data include: Install carbon emission monitoring equipment and energy metering equipment within the target range to record the energy consumption to obtain monitoring data, and collect the carbon emission data generated by population and economy to obtain factor data.

[0076] Combine the monitoring data to draw a time series graph of carbon emissions, observe the change trend of carbon emissions in different time periods to obtain spatio-temporal characteristics, analyze the main sources of carbon emissions based on the factor data, and further subdivide the energy types to obtain source data.

[0077] Study the relationship between different factors and carbon emissions based on the spatio-temporal characteristics and source data, and consider the impact of the geographical environment on carbon emissions to obtain the carbon emission characteristic data.

[0078] The steps to obtain the tracking strategy include: By analyzing the dynamic relationship between carbon emissions, industrial development, and energy consumption during the stage of rapid economic growth, and studying the differences in residential energy consumption and carbon emissions under different climate conditions, the logic and change trend behind the carbon emission characteristic data of each region are obtained.

[0079] Classify the carbon emission characteristic data from the aspects of time, source, and influencing factors to obtain the key element data, set evaluation indicators based on the key element data, and evaluate the carbon emission risks of different regions according to the evaluation indicators and preset ratios, and divide them into multiple risk levels. It is divided into three risk levels: high, medium, and low. For example, high-risk regions may show characteristics such as high and continuously increasing carbon emission intensity, large contribution rate of the main carbon emission sources and dependence on high-carbon energy, and extensive economic development model. Low-risk regions may have characteristics such as low and stable carbon emission intensity, optimized energy structure, and decoupling of economic development and carbon emissions.

[0080] Set corresponding tracking plans according to different risk levels. Based on the risk level and carbon emission characteristic data of each region, set the corresponding tracking period, and adjust the tracking plan according to the tracking period to obtain the tracking strategy. High-risk area tracking strategy: In high-risk areas, significantly increase the quantity and types of carbon emission monitoring equipment to achieve full-scale, real-time, and high-precision monitoring of large-scale steel and chemical enterprises, busy transportation hubs, etc. At the same time, establish a dedicated monitoring data management platform to ensure the timely transmission, storage, and analysis of data. Formulate strict carbon emission limit standards, clarify emission reduction targets and timetables. Require relevant enterprises and departments to formulate detailed and feasible emission reduction plans covering multiple aspects such as technological upgrading, process improvement, and energy management, and regularly submit emission reduction progress reports. Medium-risk area tracking strategy: Build a normalized carbon emission monitoring system, reasonably arrange the monitoring frequency (such as a comprehensive monitoring once every quarter) to ensure that the changing trend of carbon emissions can be detected in a timely manner. At the same time, strengthen the analysis and interpretation of monitoring data to provide a scientific basis for decision-making. Formulate incentive policies such as tax incentives, financial subsidies, and green credit to encourage enterprises and residents to actively adopt energy-saving and emission-reduction measures. Low-risk area tracking strategy: Continue to maintain stable monitoring of carbon emissions to ensure that the carbon emission level remains continuously stable at a low level. At the same time, summarize the low-carbon development experience and models within the region to form promotable cases and standards. Set up a special fund to increase support for the research and application of low-carbon technologies, encourage enterprises and research institutions to carry out cutting-edge low-carbon technology research, and promote technological innovation and progress in the low-carbon field in the region.

[0081] A feedback adjustment module is used to track the carbon emission situation of each region in real time according to the tracking strategy to obtain the tracking result, analyze the tracking result, judge whether the expected goal is achieved. If so, continue to adopt the tracking strategy; otherwise, adjust the tracking strategy to obtain the optimized strategy, and use the optimized strategy to continue to track the carbon emission situation of each region in real time.

[0082] The carbon emission tracking system based on Internet of Things technology provided in this embodiment deeply explores the relationships between data by using methods such as correlation analysis and feature analysis, and comprehensively understands the influencing factors and laws of carbon emissions. And build a Prophet model and optimize it using an improved grey wolf optimization algorithm to obtain the GWO-Prophet model. By optimizing and adjusting the model parameters, the prediction accuracy of the model and its adaptability to the carbon emission situation in different regions are significantly improved, solving the limitation problems of the model in practical applications. It also divides the target scope in detail, deeply analyzes the carbon emission characteristic data of each region, and formulates differentiated tracking strategies according to different risk levels, improving the pertinence and effectiveness of the strategies, and solving the problem of lack of pertinence in regional strategies. It can optimize resource allocation and improve management efficiency.

[0083] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0084] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A carbon emission tracking system based on Internet of Things technology, characterized in that: include: The data collection and extraction module is used to collect industry data of the industries engaged in by various enterprises and individuals within the target scope, collect ecological change data caused by environmental changes, and extract carbon emission concentration data and historical emission data from the industry data; A carbon data modeling and analysis module is used to use a correlation analysis method and combine the ecological change data to process the historical emission data to obtain carbon emission related data, build a Prophet model, input the historical emission data for training, and use an improved grey wolf optimization algorithm to optimize the Prophet model to obtain a GWO-Prophet model, input the carbon emission related data, and output the carbon emission impact data; The regional carbon strategy formulation module is used to divide the target range into multiple regions according to the carbon emission concentration data and in combination with the carbon emission impact data, observe the carbon emissions of each region using a characteristic analysis method to obtain corresponding carbon emission characteristic data, and formulate corresponding tracking strategies for different regions according to the carbon emission characteristic data.

2. According to claim 1, a carbon emission tracking system based on Internet of Things technology is characterized in that: The steps of obtaining the carbon emission related data include: Extracting emission data of various greenhouse gases covering different time periods from the historical emission data as time period emission data, and extracting ecological indicator data composed of temperature, precipitation and vegetation coverage in different time periods from the ecological change data; Remove outliers from the emission data and ecological indicator data for the time period, and use the Z-score method for deep cleaning; Using the Spearman rank correlation coefficient to calculate the correlation coefficient between the emission data in the time period and the ecological indicator data to obtain a correlation coefficient value; According to the correlation coefficient value, the correlation degree between the ecological change data and the carbon emission data is deeply analyzed, the ecological change data with the deepest correlation degree is selected as the ecological correlation data, and the ecological correlation data is integrated with the historical emission data to obtain the carbon emission correlation data.

3. According to claim 2, a carbon emission tracking system based on Internet of Things technology is characterized in that: The formula for the correlation coefficient value is expressed as: In the formula, is the correlation coefficient value, is the sample size, It is the emission data of the time period Observations, is the level of emission data in the time period, is a fixed coefficient, It is the first Observations, is the level in the ecological indicator data, It's a level difference.

4. The carbon emission tracking system based on Internet of Things technology according to claim 1 is characterized in that: The steps of obtaining the GWO-Prophet model include: Set the number of gray wolf individuals in the wolf pack, and for each gray wolf individual, randomly generate a set of parameter values ​​within a preset value range to generate a position vector of the gray wolf individual; The historical emission data is divided into a training set and a test set. For each individual gray wolf, the corresponding parameter value is used to construct the Prophet model, the training set is input into the Prophet model for training, and then the test set is predicted to obtain a predicted value; Calculate the fitness function based on the predicted value and the true value in the test set using a root mean square error; Calculating the fitness value of each gray wolf individual according to the fitness function, sorting all the gray wolf individuals in ascending order according to the fitness values, and selecting three gray wolf individuals with the smallest fitness values ​​as the optimal solution, the second optimal solution and the third optimal solution; Calculating the distance vectors between each gray wolf individual and the optimal solution, the suboptimal solution and the third optimal solution to obtain the optimal distance, the suboptimal distance and the third optimal distance; Calculate the position update vector between each gray wolf individual and the optimal solution, the suboptimal solution and the third optimal solution to obtain the optimal update vector, the suboptimal update vector and the third optimal distance vector; Determine the first The updated position of each individual gray wolf; Repeat the above steps until the preset number of iterations is reached, and select the parameter combination corresponding to the gray wolf individual with the highest fitness value among all to construct the GWO-Prophet model.

5. The carbon emission tracking system based on Internet of Things technology according to claim 4 is characterized in that: The formula for updating the position is expressed as: In the formula, is the optimal update vector, is the suboptimal update vector, is the triple optimal distance vector, It is the update location.

6. The carbon emission tracking system based on Internet of Things technology according to claim 1 is characterized in that: The steps of obtaining the carbon emission impact data include: Extracting ecological data, carbon emission growth rate and cumulative emission from the carbon emission related data to construct an input feature matrix, inputting the input feature matrix into the GWO-Prophet model, and predicting the carbon emission situation to obtain a prediction result; The prediction results are analyzed, and the carbon emission impact data are generated by obtaining the carbon emission changes under different ecological change scenarios and the results of the carbon emission sensitive factor analysis based on the influence of different input characteristics on the carbon emission prediction results.

7. The carbon emission tracking system based on Internet of Things technology according to claim 1 is characterized in that: The steps to divide into multiple areas include: Analyze the relationship between the carbon emission impact data and the carbon emission concentration, and obtain the analysis results by studying the carbon emission situation in regions where the industrial structure is dominated by heavy industry and the relationship between the proportion of different energy use in the energy structure and the carbon emission concentration; According to the analysis results, a corresponding weight is set for each influencing factor in the carbon emission impact data, and for each location within the target range, a comprehensive score is calculated based on the carbon emission concentration data, each influencing factor and the weight; According to the comprehensive score, each location within the target range is divided into multiple evaluation levels, and a hierarchical clustering method is used to classify the scoring levels that meet the preset intervals into the same category, thereby forming multiple intervals.

8. The carbon emission tracking system based on Internet of Things technology according to claim 7 is characterized in that: The formula for the comprehensive score is expressed as: In the formula, is the weight, is the comprehensive score, It is the data after the carbon emission concentration data is standardized. It is Standardized data of influencing factors, It is The weight of the influencing factors.

9. The carbon emission tracking system based on Internet of Things technology according to claim 1 is characterized in that: The steps of obtaining the carbon emission characteristic data include: Install carbon emission monitoring equipment and energy metering equipment within the target scope to record energy consumption to obtain monitoring data, and collect carbon emission data generated by population and economy to obtain factor data; Draw a time series graph of carbon emissions in combination with the monitoring data, observe the changing trend of carbon emissions in different time periods, obtain spatiotemporal characteristics, analyze the main sources of carbon emissions based on the factor data, and further subdivide the energy types to obtain source data; The relationship between different factors and carbon emissions is studied based on the spatiotemporal characteristics and the source data, and the carbon emission characteristic data is obtained by considering the impact of the geographical environment on carbon emissions.

10. The carbon emission tracking system based on Internet of Things technology according to claim 1 is characterized in that: The steps of obtaining the tracking strategy include: By analyzing the dynamic relationship between carbon emissions, industrial development and energy consumption during the rapid economic growth stage and studying the differences in residents' energy consumption and carbon emissions under different climate conditions, we can obtain the logic and changing trends behind the carbon emission characteristic data of each region. Classify the carbon emission characteristic data in terms of time, source and influencing factors to obtain key element data, set evaluation indicators according to the key element data, and evaluate the carbon emission risks of different regions according to the evaluation indicators and preset weights, and divide them into multiple risk levels; Corresponding tracking plans are set according to different risk levels, corresponding tracking cycles are set according to the risk levels of each area and the carbon emission characteristic data, and the tracking plans are adjusted according to the tracking cycles to obtain the tracking strategies.

Images