Ecological carbon sink measurement and estimation data fusion platform for thermal power industry

Abstract

The invention discloses an ecological carbon sink measurement and estimation data fusion platform for the thermal power industry, and belongs to the technical field of data fusion. The method is realized through five steps of a data acquisition module, a carbon sink measurement and calculation module, a prediction model construction module, a data fusion module and a decision support module. According to the invention, through butt joint with a thermal power enterprise energy management system, production data including generating capacity and coal consumption are acquired in real time, and the timeliness of the data is greatly improved. Ecological environment data and meteorological data around a thermal power enterprise are comprehensively collected by using a satellite remote sensing technology and a ground sensor, and the comprehensiveness and accuracy of the data are ensured. According to the method, a dynamic adjustment mechanism is adopted, and the pre-estimation model is continuously optimized according to real-time data feedback, so that the model can adapt to the change of the environment. And time sequence analysis and regression analysis are combined to form an integrated model, so that the accuracy and reliability of a pre-estimation result are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data fusion, and in particular to an ecological carbon sink measurement and estimation data fusion platform for the thermal power industry. Background Art

[0002] In the current context of global climate change, the control and management of carbon emissions has become an important task for all walks of life. As an important part of traditional energy, thermal power generation has a large amount of carbon emissions, which has a significant impact on the ecological environment. Therefore, how to effectively evaluate and estimate the carbon sink of thermal power companies and then formulate a scientific carbon emission reduction strategy is an urgent problem to be solved.

[0003] Existing carbon sink estimation methods mainly rely on quantitative statistics and experimental data, but due to the limited frequency and coverage of data collection, the timeliness and accuracy of the estimation results are low. At the same time, traditional methods rarely combine machine learning algorithms to predict carbon sinks, making it difficult to adapt to the dynamic changes in the ecological environment. In addition, the existing carbon sink estimation platform lacks standardized data interfaces, resulting in low data sharing efficiency and a relatively lack of data visualization functions, making it difficult for users to intuitively understand the estimation results and estimated data. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an ecological carbon sink measurement and estimation data fusion platform for the thermal power industry. By real-time collection of production data, ecological environment data and meteorological data of thermal power enterprises, and combining satellite remote sensing and ground sensor data, it ensures that the data is comprehensive, accurate and updated in real time, and displays the measurement results and estimated data through data visualization tools to facilitate user understanding and decision-making.

[0005] The above object of the present invention is achieved through the following technical solutions:

[0006] An ecological carbon sink measurement and estimation data fusion platform for the thermal power industry includes the following steps:

[0007] 1) Data collection module: collect production data of thermal power enterprises, surrounding ecological environment data, meteorological data, increase remote sensing and ground sensor data collection, and establish a real-time data update mechanism to reflect the dynamic changes of the ecological environment;

[0008] 2) Carbon sink calculation module: Calculate the carbon sink of the ecosystem around the thermal power company based on the collected data, combine the comprehensive assessment of soil carbon pool changes, introduce machine learning algorithms to predict carbon sinks, and use historical data to train the model to improve accuracy;

[0009] 3) Estimation model building module: construct an ecological carbon sink estimation model, establish a dynamic adjustment mechanism, combine time series analysis and regression analysis for estimation, and form an integrated model to improve accuracy and reliability;

[0010] 4) Data fusion module: Design standardized data interfaces to achieve seamless connection, add data visualization functions, and display carbon sink calculation results and estimated data in charts to facilitate user understanding and decision-making;

[0011] 5) Decision support module: Build a decision support system based on a decision tree, combine carbon sinks and enterprise operation data to provide carbon reduction strategy evaluation and selection, and add an economic benefit analysis module to evaluate economic impact to help enterprises make cost-effective decisions.

[0012] Furthermore, in the step 1), production data of thermal power enterprises are collected, ecological and environmental data around thermal power enterprises are collected, meteorological data are obtained, and the collection of remote sensing data and ground sensor data is increased to improve the timeliness and accuracy of the data, establish a real-time data update mechanism, and ensure that the data acquisition module can update data at a higher frequency to reflect the dynamic changes of the ecological environment.

[0013] Furthermore, in the step 2), the carbon sink of the ecosystem around the thermal power enterprise is calculated based on the collected data, and the total carbon sink of the ecosystem is comprehensively evaluated in combination with the changes in the soil carbon pool; a machine learning algorithm is introduced to predict the carbon sink, and the model is trained using historical data to improve the accuracy of carbon sink measurement.

[0014] Furthermore, in the step 3), an ecological carbon sink estimation model is constructed, a dynamic adjustment mechanism is established, and the estimation model is continuously optimized according to real-time data feedback to ensure that the model can adapt to changes in the ecological environment. The estimation is combined with time series analysis and regression analysis to form an integrated model to improve the accuracy and reliability of the estimation.

[0015] Furthermore, in step 4), a standardized data interface is designed to ensure that data between different systems can be seamlessly connected, improve the efficiency of data sharing, increase data visualization functions, and display carbon sink calculation results and estimated data in the form of charts to facilitate user understanding and decision-making.

[0016] Furthermore, in step 5), a decision support system based on a decision tree is constructed, which combines carbon sink data and enterprise operation data to provide thermal power companies with evaluation and selection of multiple carbon emission reduction strategies, and adds an economic benefit analysis module to evaluate the economic impact of different carbon emission reduction strategies to help companies make more cost-effective decisions.

[0017] Furthermore, the remote sensing data is sourced from satellites and drones. The remote sensing data is set to be updated every 6 days, and a data quality control process is established, including data verification, outlier processing and data cleaning, to ensure the accuracy and reliability of the data.

[0018] Furthermore, random forest and support vector machine were selected as the main algorithms, which were trained using meteorological, ecological, and production data from the past three years, tree-based feature importance evaluation was used for feature selection, and grid search method was used for parameter tuning.

[0019] Furthermore, Tableau was selected as a data visualization tool to design an intuitive dashboard to display carbon sink measurement results and estimated data to facilitate user understanding and decision-making.

[0020] Furthermore, the CART algorithm was used to construct the decision tree, the feature selection was based on information gain, the node splitting criterion was the Gini coefficient, and the pruning strategy adopted the post-pruning method.

[0021] In summary, the present invention includes at least one of the following beneficial technical effects:

[0022] 1) The present invention obtains production data in real time, including power generation and coal consumption, by connecting with the energy management system of thermal power enterprises, greatly improving the timeliness of data. By using satellite remote sensing technology and ground sensors, the ecological environment data and meteorological data around thermal power enterprises are comprehensively collected to ensure the comprehensiveness and accuracy of the data.

[0023] 2) The present invention combines vegetation carbon sink and soil carbon sink to comprehensively evaluate the carbon sink of the ecosystem surrounding the thermal power enterprise to ensure the comprehensiveness of the measurement results.

[0024] 3) The present invention adopts a dynamic adjustment mechanism to continuously optimize the prediction model based on real-time data feedback, so that the model can adapt to changes in the environment. Combining time series analysis and regression analysis to form an integrated model greatly improves the accuracy and reliability of the prediction results.

[0025] 4) Design standardized data interfaces to achieve seamless data connection and efficient sharing. Use data visualization tools to display carbon sink calculation results and estimated data in charts to facilitate user understanding and decision-making.

[0026] 5) A decision support system based on a decision tree, combined with carbon sink data and enterprise operation data, provides evaluation and selection of multiple carbon reduction strategies. An economic benefit analysis module is added to help enterprises evaluate the economic impact of different carbon reduction strategies and make more cost-effective decisions. DETAILED DESCRIPTION

[0027] An ecological carbon sink measurement and estimation data fusion platform for the thermal power industry includes the following steps:

[0028] 1. Implementation of data acquisition module

[0029] 1) Production data collection

[0030] Connect with the energy management system of thermal power companies to obtain data such as power generation and coal consumption in real time. Collect desulfurization and denitrification data and operating parameters through sensors installed on production equipment. Classify, store and pre-process the collected production data to remove abnormal values ​​and noise to ensure data accuracy and reliability.

[0031] 2) Collection of ecological environment data

[0032] Use satellite remote sensing technology to obtain information on vegetation coverage and forest types around thermal power companies. Determine soil types and physical and chemical properties through field surveys and sampling. Establish ecological and environmental monitoring stations to regularly collect air, soil, and water quality data to provide basic data support for carbon sink calculations.

[0033] 3) Meteorological data collection

[0034] Connect with the data platform of the meteorological department to obtain meteorological data on temperature, precipitation, and sunshine time. Install small meteorological stations around thermal power companies to conduct real-time meteorological monitoring and improve the timeliness of data.

[0035] 2. Implementation of the carbon sink calculation module

[0036] 1) Calculation of vegetation carbon sink

[0037] For forest ecosystems, the stock method is used to calculate the carbon storage of forest vegetation based on the stock volume and biomass expansion factor of the forest. For grassland and farmland ecosystems, the biomass method is used to estimate the carbon sink by measuring the biomass and carbon content of vegetation. Taking into account the growth cycle and photosynthesis efficiency of different vegetation types, the carbon absorption capacity is corrected to improve the accuracy of the measurement.

[0038] 2) Soil carbon sink calculation

[0039] Analyze soil samples and determine soil organic carbon content and soil bulk density parameters. Establish a soil carbon pool model based on soil type and depth to calculate soil carbon storage. Consider the impact of factors such as soil respiration and land use changes on soil carbon pools, and dynamically adjust soil carbon sink calculation results.

[0040] 3) Total carbon sink assessment

[0041] The vegetation carbon sink and soil carbon sink are superimposed to comprehensively evaluate the total carbon sink of the ecosystem around the thermal power plant. The total carbon sink is corrected and optimized by considering the interaction and feedback mechanism of the ecosystem.

[0042] 3. Implementation of the estimation model building module

[0043] 1) Data preparation

[0044] Collect historical production data, ecological environment data and carbon sink data to establish a data set. Clean and preprocess the data to remove outliers and missing values ​​to ensure data quality. Divide the data set into training set, validation set and test set for model training, validation and evaluation.

[0045] 2) Model selection and training

[0046] Select appropriate machine learning algorithms, such as support vector machines, random forests, and deep learning, to build an ecological carbon sink estimation model. Adjust the parameters and structure of the model according to the data characteristics and prediction objectives. Use the training set to train the model, and continuously adjust the model's weights and biases through the optimization algorithm so that the model can accurately fit the historical data.

[0047] 3) Model verification and optimization

[0048] Use the validation set to validate the trained model and evaluate the performance and generalization ability of the model. According to the validation results, adjust the parameters and structure of the model to improve the accuracy and stability of the model. Use cross-validation, grid search and other methods to optimize the model and select the best combination of model parameters.

[0049] 4) Model prediction and update

[0050] Use the trained model to predict future carbon sink conditions. Continuously update the model based on new data to improve the model's prediction accuracy and timeliness.

[0051] 4. Implementation of data fusion module

[0052] 1) Data fusion algorithm

[0053] The carbon sink calculation results and estimated data are fused by using data fusion algorithms such as weighted average method and principal component analysis method. The weights of different data are determined according to the reliability and importance of the data. Considering the time series characteristics of the data, the time series analysis method is used to smooth the fused data, remove noise and fluctuations, and improve the stability of the data.

[0054] 2) Data visualization

[0055] Use data visualization tools such as Echarts and D3.js to display the fused data in the form of charts, maps, etc. Select appropriate visualization methods such as bar charts, line charts, and pie charts according to user needs and data characteristics. Provide an interactive visualization interface, where users can click and zoom to gain an in-depth understanding of the details and changing trends of carbon sink data.

[0056] 3) Data interface design

[0057] Design data interfaces to facilitate data interaction and sharing with other systems. Use standardized data formats and communication protocols to ensure data compatibility and scalability. Provide data query and download functions so that users can obtain carbon sink data for specific time periods and regions according to their needs.

[0058] 5. Implementation of decision support module

[0059] 1) Carbon emission reduction decision support

[0060] Based on the ecological carbon sink data and the production situation of thermal power companies, analyze the carbon emission reduction potential of enterprises. Propose targeted carbon emission reduction suggestions, such as optimizing energy structure, improving energy utilization efficiency, and strengthening carbon capture and storage. Evaluate the cost-effectiveness and feasibility of different carbon emission reduction measures to provide reference for enterprises to formulate carbon emission reduction strategies.

[0061] 2) Ecological restoration suggestions

[0062] Analyze the current status and problems of the ecosystem around thermal power companies, and put forward suggestions for ecological restoration, such as afforestation, grassland restoration, and wetland protection. Evaluate the carbon sequestration benefits and ecological benefits of ecological restoration measures, and provide guidance for companies to implement ecological restoration.

[0063] 3) Effect evaluation and feedback

[0064] Establish an effect evaluation index system to evaluate the implementation effects of carbon emission reduction measures and ecological restoration measures. According to the evaluation results, timely adjust the decision support plan to improve the scientificity and effectiveness of decision-making. Collect user feedback, continuously improve the functions and performance of the platform, and provide better services to users.

[0065] Example 1: Ecological carbon sink calculation platform based on cloud computing

[0066] 1. Data collection module: The cloud computing platform is used for data collection, which collects the production data of thermal power enterprises, the surrounding ecological environment data, and meteorological data in real time, and stores and processes them in the cloud to ensure the high availability and security of the data.

[0067] 2. Carbon sink estimation module: Introduce deep learning algorithms to predict carbon sinks and use the powerful computing power of cloud computing to process large-scale data.

[0068] 3. Estimation model construction module: Build a dynamic adjustment mechanism based on cloud services, update model parameters in real time, and combine time series analysis and deep learning for estimation.

[0069] 4. Data fusion module: Design standardized cloud data interface to achieve seamless connection with other systems and enhance data sharing capabilities.

[0070] 5. Decision support module: A cloud computing-based decision support system that provides real-time carbon reduction strategy evaluation.

[0071] Differences from the original plan:

[0072] Structural / composition differences: Example 1 uses a cloud computing platform for data processing and storage, while the original solution uses a local server.

[0073] Differences in functional / technical effects: The introduction of cloud computing has improved the efficiency and security of data processing, while the application of deep learning algorithms has improved the accuracy of carbon sink predictions.

[0074] Example 2: Ecological carbon sink calculation platform based on the Internet of Things

[0075] 1. Data collection module: Through IoT devices (such as smart sensors), the production data of thermal power companies, surrounding ecological environment data and meteorological data are collected in real time to enhance the real-time nature of data collection.

[0076] 2. Carbon sink calculation module: Combined with IoT data, machine learning algorithms (such as random forests) are used to calculate and predict carbon sinks.

[0077] 3. Estimation model construction module: Establish a dynamic adjustment mechanism and continuously optimize the estimation model based on the data feedback from the Internet of Things.

[0078] 4. Data fusion module: Design standardized interfaces for the Internet of Things to ensure seamless data connection between different devices.

[0079] 5. Decision support module: Build a data analysis system based on the Internet of Things to provide real-time carbon reduction strategy evaluation.

[0080] Differences from the original plan:

[0081] Structural / composition differences: Example 2 introduces Internet of Things technology and collects data through smart sensors.

[0082] Differences in functional / technical effects: The application of the Internet of Things improves the real-time and accuracy of data collection, making carbon sink calculation more timely and effective.

[0083] Example 3: Ecological carbon sink calculation platform based on big data analysis

[0084] 1. Data collection module: Integrate the production data of thermal power companies, surrounding ecological environment data and meteorological data through big data technology, and establish a data lake to store and process massive data.

[0085] 2. Carbon sink calculation module: Use Hadoop to calculate carbon sinks and conduct a comprehensive assessment based on changes in soil carbon pools.

[0086] 3. Estimation model building module: Build a dynamic adjustment mechanism based on big data, combining regression analysis and machine learning for estimation.

[0087] 4. Data fusion module: Design standardized interfaces for big data to ensure efficient sharing and processing of data.

[0088] 5. Decision support module: A decision support system based on big data analysis that provides evaluation of multiple carbon reduction strategies.

[0089] Differences from the original plan:

[0090] Structural / compositional differences: Example 3 uses big data technology for data processing and analysis.

[0091] Differences in functional / technical effects: The application of big data technology can process larger-scale data, improve the accuracy and reliability of carbon sink measurement, and enhance the depth and breadth of decision-making support.

[0092] The embodiments of this specific implementation method are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, all equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An ecological carbon sink measurement and estimation data fusion platform for the thermal power industry, characterized by The steps include: 1) Data collection module: collect production data of thermal power enterprises, surrounding ecological environment data, meteorological data, increase remote sensing and ground sensor data collection, and establish a real-time data update mechanism to reflect the dynamic changes of the ecological environment; 2) Carbon sink calculation module: Calculate the carbon sink of the ecosystem around the thermal power company based on the collected data, combine the comprehensive assessment of soil carbon pool changes, introduce machine learning algorithms to predict carbon sinks, and use historical data to train the model to improve accuracy; 3) Estimation model building module: construct an ecological carbon sink estimation model, establish a dynamic adjustment mechanism, combine time series analysis and regression analysis for estimation, and form an integrated model to improve accuracy and reliability; 4) Data fusion module: Design standardized data interfaces to achieve seamless connection, add data visualization functions, and display carbon sink calculation results and estimated data in charts to facilitate user understanding and decision-making; 5) Decision support module: Build a decision support system based on a decision tree, combine carbon sinks and enterprise operation data to provide carbon reduction strategy evaluation and selection, and add an economic benefit analysis module to evaluate economic impact to help enterprises make cost-effective decisions.

2. According to claim 1, an ecological carbon sink measurement and estimation data fusion platform for the thermal power industry is characterized in that In the step 1), the production data of the thermal power enterprises are collected, the ecological environment data around the thermal power enterprises are collected, the meteorological data are obtained, and the collection of remote sensing data and ground sensor data is increased to improve the timeliness and accuracy of the data, establish a real-time data update mechanism, and ensure that the data acquisition module can update the data at a higher frequency to reflect the dynamic changes of the ecological environment.

3. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 1 is characterized in that In the step 2), the carbon sink of the ecosystem around the thermal power enterprise is calculated based on the collected data, and the total carbon sink of the ecosystem is comprehensively evaluated in combination with the changes in the soil carbon pool; a machine learning algorithm is introduced to predict the carbon sink, and the model is trained using historical data to improve the accuracy of carbon sink measurement.

4. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 1 is characterized in that In the step 3), an ecological carbon sink estimation model is constructed, a dynamic adjustment mechanism is established, and the estimation model is continuously optimized according to real-time data feedback to ensure that the model can adapt to changes in the ecological environment. The estimation is combined with time series analysis and regression analysis to form an integrated model to improve the accuracy and reliability of the estimation.

5. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 1 is characterized in that In the step 4), a standardized data interface is designed to ensure that data between different systems can be seamlessly connected, improve the efficiency of data sharing, increase data visualization functions, and display carbon sink calculation results and estimated data in the form of charts to facilitate user understanding and decision-making.

6. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 1 is characterized in that In the step 5), a decision support system based on a decision tree is constructed, which combines carbon sink data and enterprise operation data to provide thermal power companies with evaluation and selection of multiple carbon emission reduction strategies, and adds an economic benefit analysis module to evaluate the economic impact of different carbon emission reduction strategies to help companies make more cost-effective decisions.

7. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 2 is characterized in that The remote sensing data comes from satellites and drones. The remote sensing data is set to be updated every 6 days, and a data quality control process is established, including data verification, outlier processing and data cleaning, to ensure the accuracy and reliability of the data.

8. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 3 is characterized in that Random forest and support vector machine were selected as the main algorithms, and the meteorological, ecological, and production data of the past three years were used for training. Tree-based feature importance evaluation was used for feature selection, and the grid search method was used for parameter tuning.

9. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 5 is characterized in that Tableau was selected as the data visualization tool to design an intuitive dashboard to display carbon sink measurement results and estimated data to facilitate user understanding and decision-making.

10. The ecological carbon sink calculation and estimation data fusion platform for the thermal power industry according to claim 6, characterized in that The CART algorithm is used to construct the decision tree. The feature selection is based on information gain, the node splitting criterion is the Gini coefficient, and the post-pruning method is used as the pruning strategy.