Edge calculation carbon emission equipment with display screen

Abstract

The invention relates to the technical field of carbon emission management, in particular to edge calculation carbon emission equipment with a display screen. The technical problems are that a traditional carbon emission monitoring method is difficult to realize real-time monitoring and quick response, during large-scale data processing, calculation bottleneck is often faced, analysis efficiency and precision are influenced, intelligent analysis means are lacked, and valuable carbon emission modes and trends are difficult to mine from mass data; according to the technical scheme, the edge calculation carbon emission equipment with the display screen comprises a data acquisition module, an edge calculation module, a cloud calculation module, an intelligent decision early warning module and an API interface, the carbon emission management device integrating real-time monitoring, intelligent analysis and early warning decision is developed, and the intelligence and the high efficiency of carbon emission management are remarkably improved by integrating multiple modules of data acquisition, edge calculation, cloud calculation, intelligent decision early warning and an API interface.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission management, and in particular to an edge computing carbon emission device with a display screen. Background Art

[0002] As global climate change becomes increasingly severe, carbon emission management has become the focus of attention of governments and enterprises around the world. Traditional carbon emission monitoring methods mainly rely on centralized data processing and analysis, which has several significant defects. First, since data needs to be transmitted from various monitoring points to the central data center, there is a large delay in data transmission, making it difficult to achieve real-time monitoring and rapid response. Second, the centralized processing model has high requirements for computing resources, and often faces computing bottlenecks when processing large-scale data, affecting analysis efficiency and accuracy. Third, traditional methods lack intelligent analysis methods, making it difficult to mine valuable carbon emission patterns and trends from massive data, thus limiting the effective formulation of energy-saving and emission reduction strategies.

[0003] In areas such as industrial manufacturing, energy management and smart cities, accurate monitoring and efficient management of carbon emissions are crucial to achieving sustainable development goals; however, the data in these areas are often scattered and complex, requiring a solution that can integrate multiple data sources and achieve cross-domain collaborative management; therefore, the development of an edge computing carbon emission device that integrates real-time monitoring, intelligent analysis, and early warning decision-making has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to overcome the problems that traditional carbon emission monitoring methods are difficult to achieve real-time monitoring and rapid response, often face computing bottlenecks when processing large-scale data, which affects analysis efficiency and accuracy, lack intelligent analysis methods, and find it difficult to extract valuable carbon emission patterns and trends from massive data.

[0005] The technical solution of the present invention is: an edge computing carbon emission device with a display screen, comprising:

[0006] The data collection module is used to collect carbon emission related data in real time using sensors deployed at each monitoring point, and to preliminarily process the data collected by the sensors and transmit them to the edge computing node;

[0007] Edge computing modules are deployed near the source of data generation to perform data preprocessing, real-time analysis and preliminary decision-making, reduce data transmission delays, and use deep learning models to perform intelligent analysis of carbon emission data, identify abnormal patterns, and improve monitoring accuracy;

[0008] The cloud computing module is used to store long-term historical data, conduct big data analysis, support model training and algorithm optimization, and build advanced analysis models and decision support systems based on cloud computing resources to provide a basis for remote management and strategy formulation;

[0009] The intelligent decision-making and early warning module is used to combine the analysis results of edge computing and cloud computing to establish an intelligent decision-making model, realize functions such as carbon emission threshold early warning and energy-saving and emission reduction strategy recommendation, and provide a visual interface to display real-time monitoring data, early warning information and decision-making suggestions, so that managers can respond quickly;

[0010] API interface is used to support integration with smart cities, industrial manufacturing, and energy management systems to achieve data sharing and functional complementarity.

[0011] Preferably, the data acquisition module uses sensors deployed at each monitoring point to collect carbon emission related data in real time, and the data collected by the sensors is preliminarily processed and transmitted to the edge computing node; the edge computing module is deployed near the source of data generation to perform data preprocessing, real-time analysis and preliminary decision-making, reduce data transmission delays, and use deep learning models to intelligently analyze carbon emission data, identify abnormal patterns, and improve monitoring accuracy; the cloud computing module stores long-term historical data, performs big data analysis, supports model training and algorithm optimization, and builds advanced analysis models and decision support systems based on cloud computing resources to provide a basis for remote management and strategy formulation; the intelligent decision-making and early warning module combines the analysis results of edge computing and cloud computing to establish an intelligent decision-making model to realize functions such as carbon emission threshold early warning and energy-saving and emission reduction strategy recommendations, provide a visual interface, display real-time monitoring data, early warning information and decision-making suggestions, and facilitate managers to respond quickly; the API interface supports integration with smart cities, industrial manufacturing, and energy management systems to achieve data sharing and functional complementarity.

[0012] Preferably, the data acquisition module includes a sensor network unit and an Internet of Things gateway unit; the sensor network unit is deployed at various monitoring points, including factory emission outlets, major traffic arteries, and inside buildings; the sensors collect various data related to carbon emissions in real time, including CO2 concentration, temperature, humidity, and energy consumption data; the Internet of Things gateway unit is used to be deployed between the sensor network and the edge computing node, acting as a bridge, responsible for preliminary processing of the data collected by the sensor, and transmitting it to the edge computing node for further analysis. The Internet of Things gateway unit has functions such as data cleaning and format conversion, which can ensure the accuracy and consistency of the data. The spring performs preliminary screening and compression of the data to reduce the load and delay of data transmission. The Internet of Things gateway unit supports low-power wide area network and local area network communication methods to adapt to data transmission needs in different scenarios.

[0013] Preferably, the data acquisition module comprises the following steps when working:

[0014] S101: The sensor network unit continuously monitors carbon emission-related data in the environment, including CO2 concentration, temperature, etc. The data is collected in real time and stored in a memory inside the sensor;

[0015] S102: The IoT gateway unit periodically reads data from the sensor and performs preliminary processing, including data cleaning and format conversion operations. At the same time, the IoT gateway unit performs preliminary screening and compression on the data to reduce the load of data transmission;

[0016] S103: The data after preliminary processing is transmitted to the edge computing node by the IoT gateway through low-power wide area network and local area network communication;

[0017] S104: After the edge computing node receives the data transmitted by the IoT gateway, the data is stored in the storage system of the edge computing node.

[0018] Preferably, the edge computing module includes an edge computing node, a data preprocessing unit, a deep learning algorithm unit and a communication coordination unit; the edge computing node is deployed close to the data source for real-time processing and analysis of data from sensors and other data sources; the data preprocessing unit is used to perform preliminary processing on the received data in the edge computing node, including data cleaning, format conversion, and anomaly detection; the deep learning unit uses a recurrent neural network model to process time series data and data with sequence characteristics, so as to analyze trends and patterns in carbon emission data and identify abnormal emission events; the communication coordination unit is used to handle data transmission, synchronization and collaboration between nodes.

[0019] Preferably, when the edge computing module is working, the following steps are included:

[0020] S201: The edge computing node receives data from sensors and data sources through the IoT gateway, the data including carbon emission concentration, temperature, humidity, and energy consumption indicators;

[0021] S202: After receiving the data, the edge computing node first performs data preprocessing operations, including removing noise, filling missing values, and converting data formats;

[0022] S203: The edge computing node loads the pre-trained RNN model and initializes the model. The RNN model can process sequence data and capture the time dependency in the data.

[0023] S204: extracting key features from the preprocessed data and using them as inputs of the RNN model, the features including observation values ​​and timestamps at each time point in the time series data;

[0024] S205: The RNN model performs inference calculations on the input features and outputs prediction results and analysis conclusions;

[0025] S206: The edge computing node performs further processing and decision-making based on the output results of the RNN model. When an abnormal emission event is detected, the node triggers an early warning mechanism and takes emission reduction measures;

[0026] S207: The edge computing node uploads the processed data, analysis results or key events to the cloud computing center for storage.

[0027] Preferably, the cloud computing module includes a data center unit and an intelligent decision-making cloud platform; the data center unit is responsible for storing long-term historical carbon emission data, and is used to clean, integrate and format the data; the intelligent decision-making cloud platform is used to provide a decision support system based on cloud computing resources, providing managers with a scientific basis for remote management and strategy formulation, and providing a user access interface so that managers can access the system through the cloud to view analysis results and decision recommendations.

[0028] Preferably, when the cloud computing module is working, the following steps are included:

[0029] S301: The cloud computing module first receives part of the processing results and original data uploaded by the edge computing module;

[0030] S302: Using computing resources of the data center to train the recurrent neural network RNN ​​model;

[0031] S303: Use the trained RNN model to conduct in-depth analysis on carbon emission data, identify time series features and trends in the data, and perform carbon emission prediction and anomaly detection based on the analysis results;

[0032] S304: The intelligent decision cloud platform formulates carbon emission warning information and energy conservation and emission reduction strategy decision suggestions based on the analysis results of the RNN model;

[0033] S305: Issue decision-making recommendations and implement emission reduction measures to relevant parties through the user interface.

[0034] Preferably, the intelligent decision-making and early warning module includes a decision model unit and a user interface unit; the decision model unit combines the analysis results of edge computing and cloud computing to conduct in-depth mining and intelligent analysis of carbon emission data, and generate carbon emission early warning information and energy-saving and emission reduction strategies; the user interface unit is used to support the interaction between users and the system, including setting early warning thresholds, viewing historical data, exporting reports, and providing a visual interface to display real-time monitoring data, early warning information and decision-making recommendations.

[0035] Preferably, the intelligent decision-making warning module comprises the following steps when working:

[0036] S401: The intelligent decision-making and early warning module receives processed carbon emission data from the edge computing module and the cloud computing module, including real-time monitoring data, historical data, and analysis and prediction results;

[0037] S402: Integrate the data, normalize the data, and convert them into dimensionless values;

[0038] S403: Extract time series features from carbon emission data, including trend, seasonality, and periodicity;

[0039] S404: Calculate the statistics of the data, including mean, variance, maximum value, and minimum value, to reflect the overall distribution and fluctuation of the data;

[0040] S405: Select a linear regression model, set the target variable to carbon emissions, set the independent variables to production volume and energy consumption, and the basic form of the model is:

[0041] y=β0+β1x1+β2x2+......+β n x n +∈;

[0042] Where y is the target variable, x1, x2, ..., x n are the independent variables, β1, β2, ..., β n are model parameters, ∈ is the error term;

[0043] S406: Use the least squares method to estimate the model parameters and minimize the sum of squares of the error terms, that is:

[0044]

[0045] Among them, yi is the actual observed value, is the model prediction value; by solving the above optimization problem, the estimated value of the model parameters is obtained;

[0046] S407: Use the trained model to predict carbon emission data, including carbon emission trends and abnormal emission events in the future;

[0047] S408: Identify abnormal values ​​and abnormal trends in carbon emission data through model analysis, and discover potential emission problems in a timely manner;

[0048] S409: Generate carbon emission warning information and energy-saving and emission reduction strategy decision-making suggestions based on the model's prediction and anomaly detection results, providing managers with scientific and reasonable decision-making basis;

[0049] S410: Visually display the prediction results, anomaly detection results, etc. of the model in the form of charts and curves.

[0050] Preferably, the API interface is used to integrate carbon emission monitoring data with systems in the fields of smart cities, industrial manufacturing, and energy management to achieve cross-domain data sharing and collaborative management. It can adjust urban traffic flow, optimize industrial production processes, and regulate energy distribution based on carbon emissions.

[0051] Beneficial effects of the present invention:

[0052] 1. Both the edge computing module and the cloud computing module use deep learning models to intelligently analyze carbon emission data, which can accurately identify abnormal patterns and trends, improving the accuracy and reliability of monitoring; this helps managers understand carbon emissions more accurately and provides a scientific basis for formulating effective energy-saving and emission reduction strategies;

[0053] 2. The sensors deployed at each monitoring point collect carbon emission-related data in real time, and use the edge computing module for preliminary processing and analysis, which greatly reduces data transmission delay and realizes real-time monitoring of carbon emissions. This helps to detect emission anomalies in a timely manner and provides the possibility for rapid response and processing.

[0054] 3. Through the API interface, the present invention can be seamlessly integrated with smart cities, industrial manufacturing, energy management systems, etc., to achieve cross-domain data sharing and collaborative management; this helps to adjust urban traffic flow, optimize industrial production processes, and regulate energy distribution according to carbon emissions, thereby achieving more efficient resource utilization and environmental protection;

[0055] 4. The intelligent decision-making and early warning module provides a visual interface to display real-time monitoring data, early warning information and decision-making suggestions, so that managers can quickly understand the carbon emissions situation and make decisions. At the same time, the user interface supports functions such as setting early warning thresholds, viewing historical data, and exporting reports, which improves the convenience and efficiency of management.

[0056] 5. Cloud computing modules support model training and algorithm optimization, and can build advanced analysis models and decision support systems based on long-term historical data; this helps to continuously improve the intelligence level of carbon emission management and provide stronger support for remote management and strategy formulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 What is shown is a schematic diagram of the three-dimensional structure of the edge computing carbon emission device with a display screen of the present invention;

[0058] Figure 2 What is shown is a schematic diagram of the working process of each module of the edge computing carbon emission device with a display screen of the present invention. DETAILED DESCRIPTION

[0059] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0060] See also Figure 1-2 The present invention provides an embodiment: an edge computing carbon emission device with a display screen, comprising:

[0061] The data collection module is used to collect carbon emission related data in real time using sensors deployed at each monitoring point, and to preliminarily process the data collected by the sensors and transmit them to the edge computing node;

[0062] Edge computing modules are deployed near the source of data generation to perform data preprocessing, real-time analysis and preliminary decision-making, reduce data transmission delays, and use deep learning models to perform intelligent analysis of carbon emission data, identify abnormal patterns, and improve monitoring accuracy;

[0063] The cloud computing module is used to store long-term historical data, conduct big data analysis, support model training and algorithm optimization, and build advanced analysis models and decision support systems based on cloud computing resources to provide a basis for remote management and strategy formulation;

[0064] The intelligent decision-making and early warning module is used to combine the analysis results of edge computing and cloud computing to establish an intelligent decision-making model, realize functions such as carbon emission threshold early warning and energy-saving and emission reduction strategy recommendation, and provide a visual interface to display real-time monitoring data, early warning information and decision-making suggestions, so that managers can respond quickly;

[0065] API interface is used to support integration with smart cities, industrial manufacturing, and energy management systems to achieve data sharing and functional complementarity.

[0066] Preferably, the data acquisition module uses sensors deployed at each monitoring point to collect carbon emission related data in real time, and the data collected by the sensors is preliminarily processed and transmitted to the edge computing node; the edge computing module is deployed near the source of data generation to perform data preprocessing, real-time analysis and preliminary decision-making, reduce data transmission delays, and use deep learning models to intelligently analyze carbon emission data, identify abnormal patterns, and improve monitoring accuracy; the cloud computing module stores long-term historical data, performs big data analysis, supports model training and algorithm optimization, and builds advanced analysis models and decision support systems based on cloud computing resources to provide a basis for remote management and strategy formulation; the intelligent decision-making and early warning module combines the analysis results of edge computing and cloud computing to establish an intelligent decision-making model to realize functions such as carbon emission threshold early warning and energy-saving and emission reduction strategy recommendations, provide a visual interface, display real-time monitoring data, early warning information and decision-making suggestions, and facilitate managers to respond quickly; the API interface supports integration with smart cities, industrial manufacturing, and energy management systems to achieve data sharing and functional complementarity.

[0067] Preferably, the data acquisition module includes a sensor network unit and an Internet of Things gateway unit; the sensor network unit is deployed at various monitoring points, including factory emission outlets, major traffic arteries, and inside buildings; the sensors collect various data related to carbon emissions in real time, including CO2 concentration, temperature, humidity, and energy consumption data; the Internet of Things gateway unit is used to be deployed between the sensor network and the edge computing node, acting as a bridge, responsible for preliminary processing of the data collected by the sensor, and transmitting it to the edge computing node for further analysis. The Internet of Things gateway unit has functions such as data cleaning and format conversion, which can ensure the accuracy and consistency of the data. The spring performs preliminary screening and compression of the data to reduce the load and delay of data transmission. The Internet of Things gateway unit supports low-power wide area network and local area network communication methods to adapt to data transmission needs in different scenarios.

[0068] Preferably, the data acquisition module comprises the following steps when working:

[0069] S101: The sensor network unit continuously monitors carbon emission-related data in the environment, including CO2 concentration, temperature, etc. The data is collected in real time and stored in a memory inside the sensor;

[0070] S102: The IoT gateway unit periodically reads data from the sensor and performs preliminary processing, including data cleaning and format conversion operations. At the same time, the IoT gateway unit performs preliminary screening and compression on the data to reduce the load of data transmission;

[0071] S103: The data after preliminary processing is transmitted to the edge computing node by the IoT gateway through low-power wide area network and local area network communication;

[0072] S104: After the edge computing node receives the data transmitted by the IoT gateway, the data is stored in the storage system of the edge computing node.

[0073] Preferably, the edge computing module includes an edge computing node, a data preprocessing unit, a deep learning algorithm unit and a communication coordination unit; the edge computing node is deployed close to the data source for real-time processing and analysis of data from sensors and other data sources; the data preprocessing unit is used to perform preliminary processing on the received data in the edge computing node, including data cleaning, format conversion, and anomaly detection; the deep learning unit uses a recurrent neural network model to process time series data and data with sequence characteristics, so as to analyze trends and patterns in carbon emission data and identify abnormal emission events; the communication coordination unit is used to handle data transmission, synchronization and collaboration between nodes.

[0074] Preferably, when the edge computing module is working, the following steps are included:

[0075] S201: The edge computing node receives data from sensors and data sources through the IoT gateway, the data including carbon emission concentration, temperature, humidity, and energy consumption indicators;

[0076] S202: After receiving the data, the edge computing node first performs data preprocessing operations, including removing noise, filling missing values, and converting data formats;

[0077] S203: The edge computing node loads the pre-trained RNN model and initializes the model. The RNN model can process sequence data and capture the time dependency in the data.

[0078] S204: extracting key features from the preprocessed data and using them as inputs of the RNN model, the features including observation values ​​and timestamps at each time point in the time series data;

[0079] S205: The RNN model performs inference calculations on the input features and outputs prediction results and analysis conclusions;

[0080] S206: The edge computing node performs further processing and decision-making based on the output results of the RNN model. When an abnormal emission event is detected, the node triggers an early warning mechanism and takes emission reduction measures;

[0081] S207: The edge computing node uploads the processed data, analysis results or key events to the cloud computing center for storage.

[0082] Preferably, the cloud computing module includes a data center unit and an intelligent decision-making cloud platform; the data center unit is responsible for storing long-term historical carbon emission data, and is used to clean, integrate and format the data; the intelligent decision-making cloud platform is used to provide a decision support system based on cloud computing resources, providing managers with a scientific basis for remote management and strategy formulation, and providing a user access interface so that managers can access the system through the cloud to view analysis results and decision recommendations.

[0083] Preferably, when the cloud computing module is working, the following steps are included:

[0084] S301: The cloud computing module first receives part of the processing results and original data uploaded by the edge computing module;

[0085] S302: Using computing resources of the data center to train the recurrent neural network RNN ​​model;

[0086] S303: Use the trained RNN model to conduct in-depth analysis on carbon emission data, identify time series features and trends in the data, and perform carbon emission prediction and anomaly detection based on the analysis results;

[0087] S304: The intelligent decision cloud platform formulates carbon emission warning information and energy conservation and emission reduction strategy decision suggestions based on the analysis results of the RNN model;

[0088] S305: Issue decision-making recommendations and implement emission reduction measures to relevant parties through the user interface.

[0089] Preferably, the intelligent decision-making and early warning module includes a decision model unit and a user interface unit; the decision model unit combines the analysis results of edge computing and cloud computing to conduct in-depth mining and intelligent analysis of carbon emission data, and generate carbon emission early warning information and energy-saving and emission reduction strategies; the user interface unit is used to support the interaction between users and the system, including setting early warning thresholds, viewing historical data, exporting reports, and providing a visual interface to display real-time monitoring data, early warning information and decision-making recommendations.

[0090] Preferably, the intelligent decision-making warning module comprises the following steps when working:

[0091] S401: The intelligent decision-making and early warning module receives processed carbon emission data from the edge computing module and the cloud computing module, including real-time monitoring data, historical data, and analysis and prediction results;

[0092] S402: Integrate the data, normalize the data, and convert them into dimensionless values;

[0093] S403: Extract time series features from carbon emission data, including trend, seasonality, and periodicity;

[0094] S404: Calculate the statistics of the data, including mean, variance, maximum value, and minimum value, to reflect the overall distribution and fluctuation of the data;

[0095] S405: Select a linear regression model, set the target variable to carbon emissions, set the independent variables to production volume and energy consumption, and the basic form of the model is:

[0096] y=β0+β1x1+β2x2+......+β n x n +∈;

[0097] Where y is the target variable, x1, x2, ..., x n are the independent variables, β1, β2, ..., β n are model parameters, ∈ is the error term;

[0098] S406: Use the least squares method to estimate the model parameters and minimize the sum of squares of the error terms, that is:

[0099]

[0100] Among them, yi is the actual observed value, is the model prediction value; by solving the above optimization problem, the estimated value of the model parameters is obtained;

[0101] S407: Use the trained model to predict carbon emission data, including carbon emission trends and abnormal emission events in the future;

[0102] S408: Identify abnormal values ​​and abnormal trends in carbon emission data through model analysis, and discover potential emission problems in a timely manner;

[0103] S409: Generate carbon emission warning information and energy-saving and emission reduction strategy decision-making suggestions based on the model's prediction and anomaly detection results, providing managers with scientific and reasonable decision-making basis;

[0104] S410: Visually display the prediction results, anomaly detection results, etc. of the model in the form of charts and curves.

[0105] Preferably, the API interface is used to integrate carbon emission monitoring data with systems in the fields of smart cities, industrial manufacturing, and energy management to achieve cross-domain data sharing and collaborative management. It can adjust urban traffic flow, optimize industrial production processes, and regulate energy distribution based on carbon emissions.

[0106] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. An edge computing carbon emission device with a display screen; characterized in that: Included are: The data collection module is used to collect carbon emission related data in real time using sensors deployed at each monitoring point, and to preliminarily process the data collected by the sensors and transmit them to the edge computing node; Edge computing modules are deployed near the source of data generation to perform data preprocessing, real-time analysis and preliminary decision-making, reduce data transmission delays, and use deep learning models to perform intelligent analysis of carbon emission data, identify abnormal patterns, and improve monitoring accuracy; The cloud computing module is used to store long-term historical data, conduct big data analysis, support model training and algorithm optimization, and build advanced analysis models and decision support systems based on cloud computing resources to provide a basis for remote management and strategy formulation; The intelligent decision-making and early warning module is used to combine the analysis results of edge computing and cloud computing to establish an intelligent decision-making model, realize functions such as carbon emission threshold early warning and energy-saving and emission reduction strategy recommendation, and provide a visual interface to display real-time monitoring data, early warning information and decision-making suggestions, so that managers can respond quickly; API interface is used to support integration with smart cities, industrial manufacturing, and energy management systems to achieve data sharing and functional complementarity.

2. The edge computing carbon emission device with a display screen according to claim 1, characterized in that: The data acquisition module includes a sensor network unit and an IoT gateway unit; the sensor network unit is deployed at various monitoring points, including factory emission outlets, major traffic arteries, and inside buildings; the sensors collect various data related to carbon emissions in real time, including CO2 concentration, temperature, humidity, and energy consumption data; the IoT gateway unit is used to be deployed between the sensor network and the edge computing node, acting as a bridge, responsible for preliminary processing of the data collected by the sensor and transmitting it to the edge computing node for further analysis. The IoT gateway unit has functions such as data cleaning and format conversion, which can ensure the accuracy and consistency of the data. The spring performs preliminary screening and compression of the data to reduce the load and delay of data transmission. The IoT gateway unit supports low-power wide area network and local area network communication methods to adapt to data transmission needs in different scenarios.

3. The edge computing carbon emission device with a display screen according to claim 2 is characterized in that: When the data acquisition module is working, it includes the following steps: S101: The sensor network unit continuously monitors carbon emission-related data in the environment, including CO2 concentration, temperature, etc. The data is collected in real time and stored in a memory inside the sensor; S102: The IoT gateway unit periodically reads data from the sensor and performs preliminary processing, including data cleaning and format conversion operations. At the same time, the IoT gateway unit performs preliminary screening and compression on the data to reduce the load of data transmission; S103: The data after preliminary processing is transmitted to the edge computing node by the IoT gateway through low-power wide area network and local area network communication; S104: After the edge computing node receives the data transmitted by the IoT gateway, the data is stored in the storage system of the edge computing node.

4. The edge computing carbon emission device with a display screen according to claim 3 is characterized in that: The edge computing module includes edge computing nodes, data preprocessing units, deep learning algorithm units, and communication coordination units; Edge computing nodes are deployed close to data sources to process and analyze data from sensors and other data sources in real time. The data preprocessing unit is used to perform preliminary processing on the received data in the edge computing node, including data cleaning, format conversion, and anomaly detection; the deep learning unit uses a recurrent neural network model to process time series data and data with sequence characteristics to analyze the trends and patterns of carbon emission data and identify abnormal emission events; The communication coordination unit is used to handle data transmission, synchronization and collaboration between nodes.

5. The edge computing carbon emission device with a display screen according to claim 4, characterized in that: When the edge computing module is working, it includes the following steps: S201: The edge computing node receives data from sensors and data sources through the IoT gateway, the data including carbon emission concentration, temperature, humidity, and energy consumption indicators; S202: After receiving the data, the edge computing node first performs data preprocessing operations, including removing noise, filling missing values, and converting data formats; S203: The edge computing node loads the pre-trained RNN model and initializes the model. The RNN model can process sequence data and capture the time dependency in the data. S204: extracting key features from the preprocessed data and using them as inputs of the RNN model, the features including observation values ​​and timestamps at each time point in the time series data; S205: The RNN model performs inference calculations on the input features and outputs prediction results and analysis conclusions; S206: The edge computing node performs further processing and decision-making based on the output results of the RNN model. When an abnormal emission event is detected, the node triggers an early warning mechanism and takes emission reduction measures; S207: The edge computing node uploads the processed data, analysis results or key events to the cloud computing center for storage.

6. The edge computing carbon emission device with a display screen according to claim 5, characterized in that: The cloud computing module includes a data center unit and an intelligent decision-making cloud platform; the data center unit is responsible for storing long-term historical carbon emission data and for cleaning, integrating and formatting the data; the intelligent decision-making cloud platform is used to provide a decision support system based on cloud computing resources, providing managers with a scientific basis for remote management and strategy formulation, and providing a user access interface so that managers can access the system through the cloud to view analysis results and decision recommendations.

7. The edge computing carbon emission device with a display screen according to claim 6, characterized in that: When the cloud computing module is working, the following steps are included: S301: The cloud computing module first receives part of the processing results and original data uploaded by the edge computing module; S302: Using computing resources of the data center to train the recurrent neural network RNN ​​model; S303: Use the trained RNN model to conduct in-depth analysis on carbon emission data, identify time series features and trends in the data, and perform carbon emission prediction and anomaly detection based on the analysis results; S304: The intelligent decision cloud platform formulates carbon emission warning information and energy conservation and emission reduction strategy decision suggestions based on the analysis results of the RNN model; S305: Issue decision recommendations and implement emission reduction measures to relevant parties through the user interface.

8. The edge computing carbon emission device with a display screen according to claim 7, characterized in that: The intelligent decision-making and early warning module includes a decision-making model unit and a user interface unit; the decision-making model unit combines the analysis results of edge computing and cloud computing to conduct in-depth mining and intelligent analysis of carbon emission data, and generate carbon emission early warning information and energy-saving and emission reduction strategies; The user interface unit is used to support the interactive operations between users and the system, including setting warning thresholds, viewing historical data, exporting reports, and providing a visual interface to display real-time monitoring data, warning information, and decision-making recommendations.

9. The edge computing carbon emission device with a display screen according to claim 8, characterized in that: When the intelligent decision-making warning module is working, it includes the following steps: S401: The intelligent decision-making and early warning module receives processed carbon emission data from the edge computing module and the cloud computing module, including real-time monitoring data, historical data, and analysis and prediction results; S402: Integrate the data, normalize the data, and convert them into dimensionless values; S403: Extract time series features from carbon emission data, including trend, seasonality, and periodicity; S404: Calculate the statistics of the data, including mean, variance, maximum value, and minimum value, to reflect the overall distribution and fluctuation of the data; S405: Select a linear regression model, set the target variable to carbon emissions, set the independent variables to production volume and energy consumption, and the basic form of the model is: y=β0+β1x1+β2x2+......+β n x n +∈; Where y is the target variable, x1, x2, ..., x n are the independent variables, β1, β2, ..., β n are model parameters, ∈ is the error term; S406: Use the least squares method to estimate the model parameters and minimize the sum of squares of the error terms, that is: Among them, yi is the actual observed value, is the model prediction value; by solving the above optimization problem, the estimated value of the model parameters is obtained; S407: Use the trained model to predict carbon emission data, including carbon emission trends and abnormal emission events in the future; S408: Identify abnormal values ​​and abnormal trends in carbon emission data through model analysis, and discover potential emission problems in a timely manner; S409: Generate carbon emission warning information and energy-saving and emission reduction strategy decision-making suggestions based on the model's prediction and anomaly detection results, providing managers with scientific and reasonable decision-making basis; S410: Visually display the prediction results, anomaly detection results, etc. of the model in the form of charts and curves.

10. The edge computing carbon emission device with a display screen according to claim 9, characterized in that: The API interface is used to integrate carbon emission monitoring data with systems in the fields of smart cities, industrial manufacturing, and energy management to achieve cross-domain data sharing and collaborative management. It can adjust urban traffic flow, optimize industrial production processes, and regulate energy distribution based on carbon emissions.

Images