An edge-computing-based carbon emission monitoring and early warning analysis system and method thereof

Abstract

This invention discloses a carbon emission monitoring, early warning, and analysis system and method based on edge computing, comprising: a data acquisition subsystem for acquiring urban air data based on time nodes; an edge computing subsystem connected to the data acquisition subsystem for constructing a spatiotemporal analysis model of carbon emissions based on urban space and the urban air data; a cloud computing subsystem connected to the edge computing subsystem for analyzing urban carbon emissions based on the spatiotemporal analysis model of carbon emissions and obtaining analysis results; and a monitoring and early warning subsystem connected to the cloud computing subsystem for issuing early warnings of urban carbon emissions based on the analysis results. This invention, by combining a three-dimensional model and a prediction model, can more effectively monitor and predict urban carbon emissions; and by analyzing carbon emissions through time nodes, it can effectively identify and issue early warnings for key carbon emission areas.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of carbon emission monitoring, and particularly relates to a carbon emission monitoring and early warning analysis system based on edge computing and a method thereof. BACKGROUND

[0002] Since the 21st century, with the continuous advancement of urbanization and the continuous migration of the labor population, the energy consumption in urban areas has increased substantially, which has led to the rapid growth of greenhouse gas emissions, including carbon dioxide. This has brought about the climate deterioration crisis that cannot be ignored for human society. With the rise of Internet of Things, big data technology, and especially low-power wide-area Internet of Things technology, it has become an inevitable trend to realize precise monitoring and early warning of carbon emissions through emerging technologies, comprehensive energy management and control, and fine management of comprehensive energy.

[0003] Although the current carbon emission monitoring technology can monitor to a certain extent, it cannot control the overall carbon emissions of the city. At the same time, most monitoring methods only predict the carbon emissions and do not calculate the areas that need to be managed in the city. In addition, due to the great difference in carbon emission data at different time nodes, the carbon emission monitoring and early warning method at the time point still needs to be improved. SUMMARY

[0004] The purpose of the present application is to provide a carbon emission monitoring and early warning analysis system based on edge computing and a method thereof to solve the problems existing in the prior art.

[0005] To achieve the above purpose, the present application provides a carbon emission monitoring and early warning analysis system based on edge computing, comprising:

[0006] A data acquisition subsystem is configured to acquire city air data based on time nodes;

[0007] An edge computing subsystem is connected to the data acquisition subsystem and configured to construct a carbon emission spatio-temporal analysis model based on city space and the city air data;

[0008] A cloud computing subsystem is connected to the edge computing subsystem and configured to analyze city carbon emissions based on the carbon emission spatio-temporal analysis model and obtain an analysis result;

[0009] A monitoring and early warning subsystem is connected to the cloud computing subsystem and configured to give early warning of city carbon emissions based on the analysis result.

[0010] Preferably, the data acquisition subsystem comprises:

[0011] A sensor arrangement module is configured to arrange greenhouse gas concentration sensors based on city space distribution;

[0012] A sensor module is configured to acquire data from the greenhouse gas concentration sensor based on a time node to generate the urban air data.

[0013] Preferably, the edge computing subsystem comprises:

[0014] A screening module is configured to screen the urban air data to obtain time-varying air data.

[0015] An urban space acquisition module is configured to acquire urban space data based on historical data.

[0016] A model construction module is configured to construct the carbon emission spatio-temporal analysis model based on the time-varying air data and the urban space data.

[0017] Preferably, the model construction module comprises:

[0018] An urban model construction unit is configured to construct an urban three-dimensional model based on the urban space data.

[0019] A gas flow model construction unit is configured to construct an air flow prediction model based on the time-varying air data.

[0020] A model matching unit is configured to perform parameter matching between the urban three-dimensional model and the air flow prediction model to obtain the carbon emission spatio-temporal analysis model.

[0021] Preferably, the cloud computing subsystem comprises:

[0022] A grading module is configured to grade urban carbon emission areas based on the carbon emission spatio-temporal analysis model to obtain urban carbon emission grading results.

[0023] A prediction module is configured to predict urban carbon emission concentration based on the carbon emission spatio-temporal analysis model to obtain prediction results.

[0024] An integration module is configured to integrate and analyze the urban carbon emission grading results and the prediction results to obtain analysis results.

[0025] A cloud storage module is configured to transmit the analysis results to a database for storage.

[0026] Preferably, the grading module comprises:

[0027] A threshold range setting unit is configured to set a carbon emission threshold range according to a carbon emission degree ladder.

[0028] A labeling unit is configured to color label the carbon emission spatio-temporal analysis model based on the threshold range to obtain a labeled model.

[0029] The carbon emission analysis module is configured to analyze the carbon emission of the city based on the labeling model, and obtain the carbon emission classification result of the city.

[0030] Preferably, the monitoring and early warning subsystem comprises:

[0031] The display module is configured to display the carbon emission spatio-temporal analysis model and the analysis result.

[0032] The monitoring module is configured to monitor the carbon emission of the city based on the carbon emission spatio-temporal analysis model.

[0033] The early warning module is configured to early warn the carbon emission of the city based on the analysis result.

[0034] To achieve the above-mentioned purpose, the application further provides a carbon emission monitoring and early warning analysis method based on edge computing, comprising:

[0035] Obtaining city air data based on time nodes and edge detection data stations;

[0036] Constructing a carbon emission spatio-temporal analysis model based on city space and the city air data;

[0037] Analyzing the carbon emission of the city based on the carbon emission spatio-temporal analysis model, and obtaining an analysis result;

[0038] The analysis result early warns the carbon emission of the city.

[0039] The technical effect of the application is:

[0040] 1. The application can more effectively monitor and predict the carbon emission of the city by combining the three-dimensional model and the prediction model.

[0041] 2. The application can effectively identify and early warn the key areas of carbon emission by analyzing the carbon emission based on time nodes. DETAILED DESCRIPTION

[0042] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application and are incorporated herein in their entirety. The application illustratively described herein suitably can be practiced in the absence of any element or step not specifically disclosed. In the accompanying drawings:

[0043] Figure 1 FIG. 1 is a schematic diagram of a carbon emission monitoring and early warning analysis system in an embodiment of the application;

[0044] Figure 2 FIG. 2 is a flow chart of a carbon emission monitoring and early warning analysis method in an embodiment of the application. DETAILED DESCRIPTION

[0045] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0046] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0047] Example 1

[0048] like Figure 1 As shown, this embodiment provides a carbon emission monitoring, early warning, and analysis system based on edge computing, including:

[0049] The data acquisition subsystem is used to acquire urban air data based on time points;

[0050] An edge computing subsystem, connected to the data acquisition subsystem, is used to construct a spatiotemporal analysis model of carbon emissions based on urban space and urban air data;

[0051] A cloud computing subsystem, connected to the edge computing subsystem, is used to analyze urban carbon emissions based on the spatiotemporal analysis model of carbon emissions and obtain analysis results;

[0052] A monitoring and early warning subsystem, connected to the cloud computing subsystem, is used to issue early warnings for urban carbon emissions based on the analysis results.

[0053] To further optimize the solution, the data acquisition subsystem includes:

[0054] Sensor deployment module for deploying greenhouse gas concentration sensors based on urban spatial distribution;

[0055] The sensor module is used to acquire data from the greenhouse gas concentration sensor based on time points and generate the city air data.

[0056] The carbon-rich components either transform into hydrocarbons or aldehydes (gases) with lower carbon content, or into more complex particulate matter (PM) with higher carbon content, or into solid soot particles (also PM), or into carbon monoxide (CO), a combustion intermediate. Therefore, incomplete combustion products caused by insufficient oxygen are another mechanism for hydrocarbon (HC) emissions, and also the only mechanism for soot and particulate matter (PM) emissions and carbon monoxide (CO) emissions. Soot generation requires a severe lack of oxygen, so it is mainly generated in non-homogeneous combustion diesel engines. Gasoline engines, because the fuel and air are homogeneously mixed before combustion, and the mixture is generally not too rich, generally do not produce soot, and particulate matter (PM) emissions are also very low (but if oil enters the mixture, such as in a two-stroke gasoline engine that burns oil due to a faulty piston ring or by burning a mixture of oil, soot and particulate matter will also be produced).

[0057] Additionally, if a gasoline engine's fuel supply system malfunctions, leading to uncontrolled fuel supply, soot will also be produced. Nitrogen oxides (NOx) are generated by the reaction of oxygen and nitrogen in the air, including NO and NO2, with NO being the predominant component. However, oxygen and nitrogen in the air do not undergo a chemical reaction under atmospheric conditions. It is only because the high-temperature environment (1200–2400°C) created by combustion provides the conditions for the reaction to produce NO and NO2 that nitrogen oxide (NOx) emissions occur. This is the formation mechanism of nitrogen oxide (NOx) emissions. Lead salts come directly from fuel.

[0058] Further optimization of the scheme, the edge computing subsystem includes:

[0059] The filtering module is used to filter the urban air data to obtain time-varying air data;

[0060] The urban spatial acquisition module is used to acquire urban spatial data based on historical data;

[0061] The model building module is used to build the spatiotemporal analysis model of carbon emissions based on the time-varying air data and the urban spatial data.

[0062] To further optimize the solution, the module construction module includes:

[0063] The city model building unit is used to build a three-dimensional city model based on the urban spatial data.

[0064] A digital twin model is a digital simulation model that can model and simulate a physical system in a computer, and continuously update predictions and evaluate performance through real-time data acquisition and analysis. The following are simple steps for building a digital twin model:

[0065] Define the modeling scope: Determine the digital twin model to be built.

[0066] Data collection: Collect various data related to the established model, including physical parameters, environmental conditions, and operational status data. In this application, these data are obtained from multiple sources, including sensors, equipment, and monitoring systems.

[0067] Establish a physical model: Input the collected data into computer software to establish a mathematical model based on physical principles.

[0068] Simulation: Using a pre-established model, digital simulation is performed on a computer. This process can simulate and predict operating conditions and performance under different conditions;

[0069] Validation and calibration: Through real-time data acquisition and analysis, the established model and simulation results are verified to ensure they match actual conditions, and calibration and optimization are performed. This process continuously improves the model's accuracy and effectiveness.

[0070] Application and Updates: Apply the digital twin model to the actual operating system and continuously monitor and update the data.

[0071] A gas flow model building unit is used to build an air flow prediction model based on the time-varying air data.

[0072] The construction of the prediction model involves: determining the network structure: based on actual needs, determining the required number of input, hidden, and output layers and nodes.

[0073] Initializing weights and biases: Weights and biases are core parameters of a neural network and need to be initialized with small, random values. Weights and biases control the strength and direction of signal transmission between neurons.

[0074] Forward propagation computation: Starting from the input layer, the prediction is calculated by computing the weighted sum of each neuron and passing it to the next layer.

[0075] Define the loss function: The loss function measures the difference between the predicted result and the actual result. Commonly used loss functions include mean squared error (MSE) and cross-entropy;

[0076] Backpropagation optimization: The contribution of each parameter to the loss function is calculated using the backpropagation algorithm, and then the values ​​of the weights and biases are updated according to the gradient descent algorithm to minimize the loss function.

[0077] Repeated iteration: Through multiple forward and backward propagation optimizations, the values ​​of weights and biases are continuously updated until the loss function converges.

[0078] The model matching unit is used to match the parameters of the city 3D model and the air flow prediction model to obtain the carbon emission spatiotemporal analysis model.

[0079] The cloud computing subsystem, further optimized as described above, includes:

[0080] The classification module is used to classify and label urban carbon emission areas based on the spatiotemporal analysis model of carbon emissions, and obtain urban carbon emission classification results.

[0081] The prediction module is used to predict urban carbon emission concentrations based on the spatiotemporal analysis model of carbon emissions and obtain prediction results.

[0082] An integration module is used to integrate and analyze the city's carbon emission classification results and the prediction results to obtain analysis results;

[0083] The cloud storage module is used to transmit the analysis results to the database for storage.

[0084] The database in this application is in XML format;

[0085] Building an XML database typically involves the following steps:

[0086] Determining the data structure based on carbon emission environmental requirements: Data in an XML database is stored in the form of XML documents, therefore, it is necessary to determine the data structure and define a Document Type Definition (DTD) or XML Schema (XSD) to describe the data format and rules. These templates include elements, attributes, namespaces, etc.

[0087] Design document template: Based on the data structure, create and design an XML document template, that is, define the various elements, attributes and relationships between them in the XML document.

[0088] Determine the storage solution: Select a suitable XML database system based on application requirements, such as eXist-db, BaseX, or MarkLogic. Some database management systems also support data import and querying in XML format, such as Oracle and Microsoft SQL Server.

[0089] Inserting and retrieving data: Use the provided API or query language, such as XQuery or XPath, to insert data into the database and retrieve and query data from the database. Note that the XML data stored in the database should conform to a predefined DTD or XSD specification.

[0090] Perform maintenance and optimization: periodically back up and maintain the database, and optimize query statements and indexes to improve index efficiency and query speed.

[0091] The scheme is further optimized, and the hierarchical module includes:

[0092] The threshold range setting unit is used to set the carbon emission threshold range in stages according to the carbon emission level.

[0093] A labeling unit is used to color-label the spatiotemporal analysis model of carbon emissions based on the threshold range to obtain a labeled model.

[0094] The carbon emission analysis module is used to analyze the city's carbon emissions based on the labeled model and obtain the city's carbon emission classification results.

[0095] The monitoring and early warning subsystem, further optimized, includes:

[0096] A display module is used to display the spatiotemporal analysis model of carbon emissions and the analysis results;

[0097] The monitoring module is used to monitor urban carbon emissions based on the aforementioned spatiotemporal analysis model for carbon emissions.

[0098] The monitoring results are as follows: Energy Overview Carbon Emission Monitoring, Coal Consumption Carbon Emission Monitoring, Oil Consumption Carbon Emission Monitoring, and Natural Gas Consumption Carbon Emission Monitoring; The Electricity Carbon Monitoring Module is used to monitor carbon emissions from electricity across the province, thermal power plants, external power sources, various cities, industries, and key energy-consuming enterprises; The Zero Carbon Emission Reduction Monitoring Module is used to monitor carbon emission reduction from clean energy, hydropower, photovoltaic power, wind power, external power sources, battery storage, and charging piles and electric vehicles across the province.

[0099] The early warning module is used to issue early warnings about urban carbon emissions based on the analysis results.

[0100] The carbon emission calculation and analysis engine calculates and analyzes the results, visualizes them in three dimensions, and generates a report. In this embodiment, based on the carbon emission calculation and analysis engine, a lightweight BI engine is used to visualize the results in three dimensions and generate a calculation and analysis report. The three-dimensional presentation makes the results more intuitive, and the analysis report can provide the calculation basis, results, optimization suggestions, etc., providing support and basis for optimization.

[0101] Example 2

[0102] like Figure 2 As shown, this embodiment provides a carbon emission monitoring and early warning analysis method based on edge computing, including:

[0103] Urban air data is acquired based on time nodes and edge detection data stations;

[0104] A spatiotemporal analysis model for carbon emissions is constructed based on urban spatial data and urban air quality data.

[0105] The carbon emission spatiotemporal analysis model described above is used to analyze urban carbon emissions and obtain the analysis results.

[0106] The analysis results provide early warnings for urban carbon emissions.

[0107] The above description is merely a preferred embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A carbon emission monitoring, early warning, and analysis system based on edge computing, characterized in that, include: The data acquisition subsystem is used to acquire urban air data based on time points; An edge computing subsystem, connected to the data acquisition subsystem, is used to construct a spatiotemporal analysis model of carbon emissions based on urban space and urban air data; A cloud computing subsystem, connected to the edge computing subsystem, is used to analyze urban carbon emissions based on the spatiotemporal analysis model of carbon emissions and obtain analysis results; A monitoring and early warning subsystem, connected to the cloud computing subsystem, is used to issue early warnings for urban carbon emissions based on the analysis results; The edge computing subsystem includes: The filtering module is used to filter the urban air data to obtain time-varying air data; The urban spatial acquisition module is used to acquire urban spatial data based on historical data; The model building module is used to build the spatiotemporal analysis model of carbon emissions based on the time-varying air data and the urban spatial data; The model building module includes: The city model building unit is used to build a three-dimensional city model based on the urban spatial data. A gas flow model building unit is used to build an air flow prediction model based on the time-varying air data. The model matching unit is used to perform parameter matching between the city 3D model and the air flow prediction model to obtain the carbon emission spatiotemporal analysis model. The cloud computing subsystem includes: The classification module is used to classify and label urban carbon emission areas based on the spatiotemporal analysis model of carbon emissions, and obtain urban carbon emission classification results. The prediction module is used to predict urban carbon emission concentrations based on the spatiotemporal analysis model of carbon emissions and obtain prediction results. An integration module is used to integrate and analyze the city's carbon emission classification results and the prediction results to obtain analysis results; The cloud storage module is used to transmit the analysis results to the database for storage; The hierarchical module includes: The threshold range setting unit is used to set the carbon emission threshold range in stages according to the carbon emission level. A labeling unit is used to color-label the spatiotemporal analysis model of carbon emissions based on the threshold range to obtain a labeled model. The carbon emission analysis module is used to analyze the city's carbon emissions based on the labeled model and obtain the city's carbon emission classification results.

2. The carbon emission monitoring, early warning, and analysis system based on edge computing according to claim 1, characterized in that, The data acquisition subsystem includes: Sensor deployment module for deploying greenhouse gas concentration sensors based on urban spatial distribution; The sensor module is used to acquire data from the greenhouse gas concentration sensor based on time points and generate the city air data.

3. The carbon emission monitoring, early warning, and analysis system based on edge computing according to claim 1, characterized in that, The monitoring and early warning subsystem includes: A display module is used to display the spatiotemporal analysis model of carbon emissions and the analysis results; The monitoring module is used to monitor urban carbon emissions based on the aforementioned spatiotemporal analysis model for carbon emissions. The early warning module is used to issue early warnings about urban carbon emissions based on the analysis results.

4. An analysis method for a carbon emission monitoring and early warning system based on edge computing as described in any one of claims 1-3, characterized in that, Includes the following steps: Urban air data is acquired based on time nodes and edge detection data stations; A spatiotemporal analysis model for carbon emissions is constructed based on urban spatial data and urban air quality data. The carbon emission spatiotemporal analysis model described above is used to analyze urban carbon emissions and obtain the analysis results. The analysis results provide early warnings for urban carbon emissions.

Images