CN117850273A - Digital twin system for controlling carbon emission of building - Google Patents

Abstract

The present invention relates to an intelligent carbon emission management and control system, and discloses a digital twin system for controlling building carbon emissions, including: a building emission data acquisition module, which is responsible for collecting energy usage data of various energy-consuming equipment in the building, and obtains energy consumption data in real time by connecting sensors, smart electric meter equipment, smart water meter equipment and remote heat flow meters, including: electricity, fuel consumption, central heating heat consumption, water consumption and renewable energy consumption used in the building; a building carbon emission data processing module, which can convert various energy consumption data of the building into corresponding carbon emission data; a carbon emission early warning and decision-making module, which uses machine learning to make decisions and make decisions to control carbon emissions that exceed the standard.

Description

A digital twin system for controlling carbon emissions in buildings

Technical Field

The present invention relates to an intelligent carbon emission management and control system, and in particular to a digital twin system for controlling building carbon emissions.

Background technique

Carbon emissions refer to carbon dioxide and other greenhouse gases released into the atmosphere during the burning of fossil fuels or other activities. The release of these greenhouse gases is one of the main causes of global warming and climate change. Carbon emissions can come from a variety of activities, including industrial production, transportation, energy production, and agriculture. Managing and reducing carbon emissions is important for mitigating climate change.

Energy consumption in buildings is one of the main sources of greenhouse gas emissions. Buildings require heating, cooling, and lighting, and these processes usually rely on burning fossil fuels or using electricity. At the same time, buildings also release a lot of carbon dioxide during the production and transportation of cement, but it is difficult to accurately calculate the relevant carbon emissions, and there is a certain lag. Therefore, a digital twin system for controlling building carbon emissions is proposed.

Summary of the invention

The purpose of the present invention is to track building carbon emissions in real time and avoid the lag in carbon calculation, and a digital twin system for controlling building carbon emissions is proposed.

In order to achieve the above object, the present invention adopts the following technical solutions:

Building emission data collection module, which is responsible for collecting energy usage data of various energy-consuming devices in the building. By connecting sensors, smart electric meter equipment, smart water meter equipment and remote heat flow meter, it can obtain real-time energy consumption data, including: electricity consumption, fuel consumption, central heating heat consumption, water consumption and renewable energy consumption used in the building;

Building carbon emission data processing module, which can convert various energy consumption data of buildings into corresponding carbon emission data;

Carbon emission early warning and decision-making module, which can set early warning thresholds and rules, analyze data analysis units, generate various reports and analysis results to conduct early warning units, and provide decision support units for managers of buildings or organizations;

The computing module of the digital twin model converts the data in the actual scene into a computing model and performs simulation calculations. By connecting with the data of the actual scene, the mapping between the model and the actual scene is realized. At the same time, the real-time data can be integrated with the model to provide a more intuitive display of the building status and user interaction.

Real-time carbon emission visualization module, which is used to visualize the carbon emissions of buildings. This module can combine the real-time data of buildings with carbon emission models to generate visualization charts and dynamic images;

The model simulation module collects various data in the actual scene, including building structure, energy usage and indoor environmental parameters. These data will be used as the input of the digital twin model for model establishment and simulation. The digital twin model can be updated later to add or delete equipment, adjust control strategies, and change the use of the building;

The building emission data acquisition module acquires the building emission data in real time, obtains the energy consumption and emission of the building, and transmits the data to the building carbon emission data processing module. The building carbon emission data processing module converts the building energy consumption data into carbon emission data, performs data analysis, and transmits the processed data to the calculation module of the digital twin model. The calculation module of the digital twin model automates the data collection, model building and simulation calculation processes in the actual scene, so as to realize efficient and accurate assessment and prediction of the energy consumption and carbon emission of the building, and transmits the data to the real-time carbon emission visualization module. The real-time carbon emission visualization module The real-time data of the building is combined with the carbon emission model to provide users with an intuitive and easy-to-understand display of energy consumption and carbon emissions, mark the energy consumption characteristics and energy-saving and emission reduction potential of the building, and transmit the data back to the computing module of the digital twin model. The carbon emission early warning and decision-making module uses real-time monitoring, data analysis, early warning prompts and decision support to promptly detect abnormal carbon emission values, take effective measures to reduce carbon emissions and energy consumption, and transmit the data to the computing module of the digital twin model. The model simulation module automates the data collection, model building and simulation calculation processes in the actual scenario, and transmits the data to the computing module of the digital twin model.

The above technical solution further includes:

The building emission data acquisition module is responsible for collecting energy usage data of various energy-consuming equipment, lighting, air conditioning, and heating in the building, and through connecting sensors, smart meter equipment, smart water meter equipment, and remote heat flow meters, it obtains real-time energy consumption data, including: electricity, fuel consumption, central heating heat consumption, water consumption, and renewable energy consumption used in the building. In addition to energy consumption data, this module can also collect operating status data of various equipment in the building, and use these data, including the switch status, temperature, humidity, and pressure parameters of the equipment, to analyze the performance and efficiency of the equipment, help analyze the relationship between energy consumption and environmental conditions, and interact with the energy management system and the building automation system to achieve energy consumption monitoring and control.

The building carbon emission data processing module converts the energy consumption data to convert various energy consumption data of the building, including electricity, fuel, central heating, water and renewable energy used in the building, into corresponding carbon emission data. At the same time, according to different energy types, the energy consumption is converted into carbon emissions with reference to national and regional carbon emission standards or calculation methods. At the same time, the emission factors of different energy types are updated, and the emission factors will also change due to the influence of time, location and energy source. The emission factors are updated regularly during the processing process, and the management of multiple emission factor libraries is supported. A carbon emission analysis report is generated, data analysis and decision support are provided, and the processed carbon emission data is transmitted to the energy management system and the building automation system for energy consumption control, or data is interacted with the carbon trading market to realize the trading and management of carbon emissions, convert the energy consumption data of the building into carbon emission data, and perform data analysis and prediction, thereby providing data support and basis for carbon emission management and energy conservation and emission reduction.

The carbon emission early warning and decision-making module transmits the data to the data analysis unit. The data analysis unit uses the gradient descent iterative method to find the local minimum of the function. It reduces the gradient of the function by continuously adjusting the value of the parameter, thereby gradually approaching the minimum value. A possible formula of the gradient descent method is as follows: Among them, θ is the parameter vector, α is the learning rate, f(θ) is the function to be optimized, /> is the gradient of f(θ) with respect to θ. For example, suppose we have a linear regression function f(θ) = θ_0 + θ_1*x. We hope to find θ_0 and θ_1 that minimize f(θ). We can use gradient descent to iteratively update θ_0 and θ_1. For θ_0 and θ_1, their gradients are and/> Therefore, we can use the following formula to update θ_0 and θ_1, θ_0 = θ_0-α*(1), θ_1 = θ_1-α*x, where α is the learning rate and x is the input feature. By continuously iteratively updating θ_0 and θ_1, we can gradually approach the minimum value of f(θ).

The data analysis unit transmits the iterated data to the early warning unit, and the early warning unit predicts the building carbon emissions through a linear regression model by predicting the relationship between a response variable and one or more prediction variables. The formula of the linear regression model is as follows;

y＝θ_0+θ_1*x+θ_2*x ² +...+θ_n*x ⁿ , where y is the response variable, x is the predictor variable, θ_0,θ_1,...,θ_n are model parameters. When training the model, you need to use a data set to estimate these parameters. A common method is the least squares method, which estimates the parameters by minimizing the squared error between the predicted value and the actual value. Suppose we have a simple data set with only one predictor variable x and one response variable y. We can use a linear regression model to establish the relationship between them. Suppose we use the least squares method to estimate the model parameters, then we have the following formula, θ_1＝( 1/m)*Σ(x_i-μ_x)*(y_i-μ_y), θ_0＝μ_y-θ_1*μ_x, where m is the number of samples, x_i and y_i are the prediction variable and response variable of the ith sample, μ_x and μ_y are the means of the prediction variable and response variable, respectively. By calculating these formulas, we can get the parameters θ_0 and θ_1 of the model, so that we can use the model to predict new response variable values and transmit the data to the decision support unit to detect whether the carbon emissions meet the standards and limit the excessive carbon emissions in the building.

The model simulation module collects various data in actual scenarios through sensors and monitoring equipment, including building structure, energy usage and indoor environmental parameters, and uses the building emission data collection module as the input of the model for model establishment and simulation. Based on the collected data, a digital twin model is constructed using modeling software or a specific algorithm. The model usually includes information on the building's geometry, material properties, energy system, equipment and control system, and corresponds to the actual scenario. By simulating and calculating the digital twin model, the building's energy usage and indoor environmental changes, temperature, humidity, and air quality in different time periods can be simulated. The digital twin model can also predict the building's energy consumption and carbon emissions under different energy-saving and emission reduction measures, thereby evaluating the effectiveness of different measures.

The computing module of the digital twin model converts the physical properties, energy system, and control strategy factors in the actual scene into a computing model and performs simulation calculations. Through these calculations, the behavior of the building under different working conditions, temperature changes, energy consumption, and air flow can be simulated based on physical laws, numerical methods, and machine learning techniques. Through simulation calculations, the impact of different design schemes, operating strategies, and control algorithms on building performance and energy efficiency can be evaluated, and the data of the actual scene can be connected to achieve mapping between the model and the actual scene, which includes inputting real-time sensor data into the digital twin model to update the model status and parameters to keep it consistent with the actual scene.

The real-time carbon emission visualization module generates visualization charts and dynamic images based on real-time data and carbon emission models, presents the energy consumption and carbon emissions of the building in an intuitive manner, and provides users with a more intuitive display form. It uses real-time data and carbon emission models to display carbon emissions and energy consumption in different time periods, and can also generate real-time dynamic images.

The present invention has the following beneficial effects:

1. In the present invention, the digital twin system for controlling building carbon emissions is proposed, which collects various data obtained from the building emission data acquisition module, and transmits the data to the early warning unit in the carbon emission early warning and decision-making module to issue an early warning prompt for excessive carbon emissions.

2. In the present invention, the digital twin system for controlling building carbon emissions is proposed. By acquiring data on carbon emissions that exceed the standard, machine learning is used to make decisions and control the carbon emissions that exceed the standard.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a system block diagram of a digital twin system for controlling building carbon emissions proposed by the present invention.

In the figure: 1. Building emission data collection module; 2. Building carbon emission data processing module; 3. Carbon emission early warning and decision-making module; 4. Digital twin model calculation module; 5. Real-time carbon emission visualization module; 6. Model simulation module; 7. Data analysis unit; 8. Early warning unit; 9. Decision support unit.

Detailed ways

Embodiment 1

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

As shown in FIG1 , the digital twin system for controlling building carbon emissions proposed by the present invention includes: a building emission data acquisition module 1, which is responsible for collecting energy usage data of various energy-consuming devices in the building, and obtains energy consumption data in real time by connecting sensors, smart electric meter equipment, smart water meter equipment and remote heat flow meters, including: electricity, fuel consumption, central heating heat consumption, water consumption and renewable energy consumption used in the building; a building carbon emission data processing module 2; a carbon emission early warning and decision-making module 3, which can set early warning thresholds and rules, analyze the data analysis unit 7, generate various reports and analysis results to perform early warning unit 8, and provide decision support unit 9 for managers of buildings or organizations;

The calculation module 4 of the digital twin model converts the data in the actual scene into a calculation model and performs simulation calculations. By docking with the data of the actual scene, the mapping between the model and the actual scene is realized. At the same time, the real-time data can be integrated with the model to provide a more intuitive building status display and user interaction; the real-time carbon emission visualization module 5 is used to present the carbon emissions of the building in a visual way. This module can combine the real-time data of the building with the carbon emission model to generate visual charts and dynamic images; the model simulation module 6 collects various data in the actual scene, including building structure, energy usage and indoor environmental parameters. These data will be used as inputs of the digital twin model for model establishment and simulation. The digital twin model can be updated later, and equipment can be added or deleted, control strategies can be adjusted, and the use of the building can be changed; the building emission data collection module 1 collects building emission data;

The energy consumption and emission of the building are obtained in real time, and the data is transmitted to the building carbon emission data processing module 2. The building carbon emission data processing module 2 converts the energy consumption data of the building into carbon emission data, performs data analysis, and transmits the processed data to the calculation module 4 of the digital twin model. The calculation module 4 of the digital twin model automates the data collection, model building and simulation calculation processes in the actual scene to achieve efficient and accurate assessment and prediction of the energy consumption and carbon emissions of the building, and transmits the data to the real-time carbon emission visualization module 5. The real-time carbon emission visualization module 5 combines the real-time data of the building with the carbon emission model to provide users with an intuitive and easy-to-understand display of energy consumption and carbon emissions, annotates the energy consumption characteristics and energy-saving and emission reduction potential of the building, and transmits the data back to the calculation module 4 of the digital twin model. The carbon emission early warning and decision-making module 3 provides real-time monitoring, data analysis, early warning prompts and decision support;

Timely discover abnormal carbon emission values, take effective measures to reduce carbon emissions, reduce energy consumption, and transmit data to the calculation module 4 of the digital twin model. The model simulation module 6 automates the data collection, model building and simulation calculation processes in the actual scene, and transmits the data to the calculation module 4 of the digital twin model. The building emission data collection module 1 is responsible for collecting the energy usage data of various energy-consuming equipment, lighting, air conditioning, and heating in the building, and obtains energy consumption data in real time by connecting sensors, smart meter equipment, smart water meter equipment and remote heat flow meters, including: electricity, fuel consumption, central heating heat consumption, water consumption and renewable energy used in buildings. In addition to energy consumption data, this module can also collect the operating status data of various equipment in the building, and use these data, including the switch status, temperature, humidity, and pressure parameters of the equipment, to analyze the performance and efficiency of the equipment;

Helps analyze the relationship between energy consumption and environmental conditions, and exchanges data with energy management systems and building automation systems to achieve monitoring and control of energy consumption. Building carbon emission data processing module 2 converts energy consumption data to convert various types of building energy consumption data, including electricity, fuel, central heating, water, and renewable energy used in buildings, into corresponding carbon emission data. At the same time, according to different energy types, with reference to national and regional carbon emission standards or calculation methods, energy consumption is converted into carbon emissions, and emission factors of different energy types are updated at the same time. Emission factors will also change due to time, location, and energy source. Emission factors are updated regularly during the processing process, and support the management of multiple emission factor libraries to generate carbon emission analysis reports.

Provide data analysis and decision support, transmit the processed carbon emission data to the energy management system and building automation system for energy consumption control, or interact with the carbon trading market for data, realize carbon emission trading and management, convert the building's energy consumption data into carbon emission data, and perform data analysis and prediction, so as to provide data support and basis for carbon emission management and energy conservation and emission reduction. The model simulation module 6 collects various data in actual scenes through sensors and monitoring equipment, including building structure, energy usage and indoor environmental parameters, and uses the building emission data collection module 1 as the input of the model for model establishment and simulation. Based on the collected data, a digital twin model is constructed using modeling software or specific algorithms, and the model usually includes information on the building's geometric structure, material properties, energy system, equipment and control system;

And corresponding to the actual scene, by simulating the digital twin model, the energy usage of the building and the changes in the indoor environment, temperature, humidity, and air quality in different time periods can be simulated. The digital twin model can also predict the energy consumption and carbon emissions of the building under different energy-saving and emission reduction measures, so as to evaluate the effects of different measures. The calculation module 4 of the digital twin model converts the physical properties, energy system, and control strategy factors in the actual scene into a calculation model and performs simulation calculations. Through these calculations, the behavior of the building under different working conditions can be simulated based on physical laws, numerical methods, and machine learning techniques;

For example, temperature changes, energy consumption, air flow, and through simulation calculations, the impact of different design schemes, operating strategies and control algorithms on building performance and energy efficiency can be evaluated, and the data of the actual scene can be connected to achieve the mapping between the model and the actual scene. This includes inputting real-time sensor data into the digital twin model to update the model status and parameters to keep it consistent with the actual scene. The real-time carbon emission visualization module 5 generates visual charts and dynamic images based on real-time data and carbon emission models to present the energy consumption and carbon emissions of the building in an intuitive way. At the same time, it can also generate real-time dynamic images to provide users with a more intuitive display form. Based on real-time data and carbon emission models, it displays carbon emissions and energy consumption in different time periods. At the same time, it can also generate real-time dynamic images.

The building emission data collection module 1 collects emission data in the building, obtains the energy consumption and emission of the building in real time, and transmits the data to the building carbon emission data processing module 2. The building carbon emission data processing module 2 receives and processes the building carbon emission data, receives and converts the energy consumption data of the building in real time, and transmits the processed data to the calculation module 4 of the digital twin model for data analysis. The calculation module 4 of the digital twin model automates the data collection, model building and simulation calculation processes in the actual scene;

It can realize efficient and accurate assessment and prediction of energy consumption and carbon emissions of buildings, and transmit the data to the real-time carbon emission visualization module 5. The real-time carbon emission visualization module 5 combines the real-time data of the building with the carbon emission model to provide users with an intuitive and easy-to-understand display of energy consumption and carbon emissions, and mark the energy consumption characteristics and energy-saving and emission reduction potential of the building. The carbon emission early warning and decision-making module 3 monitors the data in the building carbon emission data processing module 2 in real time, analyzes the data, provides early warning prompts and decision support through the calculation module 4 of the digital twin model, timely discovers abnormal carbon emission values, and takes effective measures to reduce carbon emissions;

To reduce energy consumption, the model simulation module 6 automates the data collection, model building and simulation calculation processes in the actual scene, and maps the simulation model with the data in the building carbon emission data processing module 2.

Embodiment 2

As shown in FIG1 , in the embodiment of the present invention, the carbon emission early warning and decision-making module 3 transmits data to the data analysis unit 7. The data analysis unit 7 uses the gradient descent iterative method to find the local minimum of the function. It reduces the gradient of the function by continuously adjusting the value of the parameter, thereby gradually approaching the minimum value. A possible formula of the gradient descent method is as follows: Among them, θ is the parameter vector, α is the learning rate, f(θ) is the function to be optimized, /> is the gradient of f(θ) with respect to θ. For example, suppose we have a linear regression function f(θ) = θ_0 + θ_1*x. We hope to find θ_0 and θ_1 that minimize f(θ). We can use gradient descent to iteratively update θ_0 and θ_1. For θ_0 and θ_1, their gradients are respectively/> and/> Therefore, we can use the following formula to update θ_0 and θ_1: θ_0 = θ_0-α*(1), θ_1 = θ_1-α*x, where α is the learning rate and x is the input feature. By continuously iteratively updating θ_0 and θ_1, we can gradually approach the minimum value of f(θ). The data analysis unit 7 transmits the iterated data to the early warning unit 8, which predicts building carbon emissions through a linear regression model.

By predicting the relationship between a response variable and one or more predictor variables, the formula of the linear regression model is as follows: y = θ_0 + θ_1*x + θ_2*x ² + ... + θ_n*x ⁿ , where y is the response variable, x is the predictor variable, θ_0, θ_1, ..., θ_n are model parameters. When training the model, you need to use a data set to estimate these parameters. A common method is the least squares method, which estimates parameters by minimizing the squared error between the predicted value and the actual value. Suppose we have a simple data set with only one predictor variable x and one response variable y. We can use a linear regression model to establish the relationship between them. Suppose we use the least squares method to estimate the model parameters, then we have the following formula: θ_1 = ( 1/m)*Σ(x_i-μ_x)*(y_i-μ_y), θ_0＝μ_y-θ_1*μ_x, where m is the number of samples, x_i and y_i are the prediction variable and response variable of the ith sample, μ_x and μ_y are the means of the prediction variable and response variable, respectively. By calculating these formulas, we can get the parameters θ_0 and θ_1 of the model, so that we can use the model to predict the new response variable value and transmit the data to the decision support unit 9 to detect whether the carbon emissions meet the standards and limit the excessive carbon emissions in the building.

The data analysis unit 7 acquires the data in the building carbon emission data processing module 2 in real time, and performs algorithm analysis on the data in the building carbon emission data processing module 2. It is responsible for collecting the building-related energy consumption data, equipment operation status data, and environmental parameter data, temperature, and humidity in real time, and uses the acquired data as the basis for early warning and decision-making. After comparing the acquired data with the emission factor, the early warning unit 8 marks the data that is too high and issues an early warning prompt for the data. The decision support unit 9 performs decision analysis on the data using algorithms and uses machine learning to adjust the excessively high building carbon emissions.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims (8)

1. A digital twin system for controlling carbon emissions from a building, comprising:

building emission data acquisition module (1), this module is responsible for gathering the energy service conditions data of each energy consumption equipment of building, through connection sensor, smart electric meter equipment, intelligent water meter equipment and far heat transfer flowmeter, acquires the data of energy consumption in real time, includes: electric quantity, fuel consumption, central heating consumption, water consumption and renewable energy consumption for building;

the building carbon emission data processing module (2) can convert various energy consumption data of a building into corresponding carbon emission data;

the carbon emission early warning and decision making module (3) can set an early warning threshold value and a rule, analyze the data analysis unit (7) and generate various reports and analysis results so as to carry out an early warning unit (8), and provide a decision support unit (9) for a manager of a building or organization;

the calculation module (4) of the digital twin model converts the data in the actual scene into a calculation model, carries out simulation calculation, realizes the mapping between the model and the actual scene by docking with the data of the actual scene, and can fuse the real-time data with the model at the same time to provide more visual building state display and user interaction;

the real-time carbon emission visualization module (5) is used for displaying the carbon emission of the building in a visual mode, and can combine the real-time data of the building with the carbon emission model to generate a visual chart and a dynamic image;

the model simulation module (6) is used for establishing and simulating a digital twin model by collecting various data in an actual scene, including building structures, energy use conditions and indoor environment parameters, and using the data as input of the digital twin model, wherein the digital twin model can be updated in the later period, equipment can be added or deleted, a control strategy can be adjusted, and the use of the building can be changed;

the building emission data acquisition module (1) acquires the energy consumption and emission conditions of a building in real time by acquiring the building emission data, and transmits the data to the building carbon emission data processing module (2), the building carbon emission data processing module (2) converts the energy consumption data of the building into carbon emission data, analyzes the data, and transmits the processed data to the calculation module (4) of the digital twin model, the calculation module (4) of the digital twin model automatically acquires, establishes and simulates the data in an actual scene, realizes the high-efficiency and accurate evaluation and prediction of the energy consumption and the carbon emission of the building, and transmits the data to the real-time carbon emission visualization module (5), the real-time carbon emission visualization module (5) provides visual and understandable energy consumption and carbon emission conditions for users by combining the real-time data and the carbon emission model of the building, marks the energy consumption characteristics and the energy saving and emission reduction potential of the building, and transmits the data to the calculation module (4) of the digital twin model, the real-time carbon emission data and the carbon emission data analysis module (3) take early warning and the environmental protection by adopting the decision-making module and the real-time analysis module (6) to reduce the energy consumption and the carbon emission conditions in the actual environment, and reduce the environmental protection conditions, and transmitting the data to a calculation module (4) of the digital twin model.

2. A digital twin system for controlling carbon emissions in a building according to claim 1, wherein the building emission data collection module (1) is responsible for collecting energy usage data of various energy consuming devices, lighting, air conditioning and heating of the building, and obtaining the energy consumption data in real time by connecting a sensor, a smart meter device and a remote heat transfer flowmeter, and comprises: besides the energy consumption data, the module can collect running state data of various devices of the building, and the running state data comprises on-off state, temperature, humidity and pressure parameters of the devices, are used for analyzing the performance and efficiency of the devices, helping to analyze the relation between the energy consumption and the environmental conditions, and carrying out data interaction on an energy management system and a building automation system so as to realize monitoring and control of the energy consumption.

3. A digital twin system for controlling carbon emissions in a building according to claim 1, wherein the building carbon emissions data processing module (2) converts various types of energy consumption data of the building by converting the energy consumption data, comprising: the method comprises the steps of converting renewable energy sources used by electricity, fuel, central heating, water and buildings into corresponding carbon emission data, simultaneously converting the energy consumption into carbon emission according to different energy types and referring to carbon emission standards or calculation methods of countries and regions, updating emission factors of different energy types, wherein the emission factors are changed due to the influence of time, places and energy sources, periodically updating the emission factors in the treatment process, supporting the management of a plurality of emission factor libraries, generating a carbon emission analysis report, providing data analysis and decision support, transmitting the processed carbon emission data to an energy management system and a building automation system for energy consumption control or carrying out data interaction with a carbon transaction market, realizing the transaction and management of carbon emission, converting the energy consumption data of the building into carbon emission data, and carrying out data analysis and prediction, thereby providing data support and foundation for carbon emission management, energy conservation and emission reduction.

4. A digital twin system for controlling carbon emissions in buildings according to claim 1, characterised in that the carbon emission pre-warning and decision module (3) passes the data to a data analysis unit (7), the data analysis unit (7) utilises a gradient descent method iterative method for finding a local minimum of the function which reduces the gradient of the function by continuously adjusting the value of the parameter so as to gradually approach the minimum, one possible formula for the gradient descent method being as follows:wherein θ is a parameter vector, α is a learning rate, f (θ) is a function to be optimized, +.>Is the gradient of f (θ) with respect to θ, for example, assuming we have a linear regression function f (θ) =θ_0+θ_1*x, we wish to find θ_0 and θ_1 that minimizes f (θ), we can iteratively update θ_0 and θ_1 using a gradient descent method, for θ_0 and θ_1, their gradients are respectivelyAnd->Thus we can update θ_0 and θ_1 using the following formula, θ_0=θ_0- α (1), θ_1=θ_1- α x, where α is the learning rate and x is the input feature, we can gradually approach the minimum value of f (θ) by iteratively updating θ_0 and θ_1.

5. A digital twin system for controlling building carbon emissions according to claim 4, in which the data analysis unit (7) passes the iterated data to the early warning unit (8), the early warning unit (8) predicts building carbon emissions by means of a linear regression model, the formula of which is given by predicting the relationship between one response variable and one or more predicted variables as y = θ0+ θ _1*x + θ _2*x ² +...+θ_n*x ⁿ Where y is the response variable, x is the predicted variable, θ_0, θ_1,..once.and θ_n is the model parameters that need to be estimated using the data set when training the model, a common method is least squares, which estimates the parameters by minimizing the square error between the predicted and actual values, assuming we have a simple data set where we can use a linear regression model with only one predicted variable x and one response variable yTo establish a relationship between them, assuming we use the least squares method to estimate model parameters, there is the following equation,

θ_1= (1/m) ×Σ (x_i- μ_x) (y_i- μ_y), θ_0=μ_y- θ_1×μ_x, where m is

The number of samples, x_i and y_i are respectively the predicted variable and the response variable of the ith sample, mu_x and mu_y are respectively the average values of the predicted variable and the response variable, and by calculating the formulas, we can obtain parameters theta_0 and theta_1 of the model, so that the model can be used for predicting new response variable values, and the data are transmitted to a decision support unit (9) for detecting whether the carbon emission meets the standard or not and limiting the out-of-standard carbon emission in the building.

6. The digital twin system for controlling carbon emission of a building according to claim 1, wherein the model simulation module (6) collects various data in an actual scene, including building structure, energy use condition and indoor environment parameters, by means of sensors and monitoring devices, the building emission data collection module (1) is used as input of a model for building and simulating the model, and based on the collected data, modeling software or a specific algorithm is used for building a digital twin model, and the model generally comprises information on geometric structure, material property, energy system, equipment and control system of the building, and corresponds to the actual scene, by performing simulation calculation on the digital twin model, the energy use condition and indoor environment change, temperature, humidity and air quality of the building in different time periods can be simulated, and the digital twin model can also predict the energy consumption and carbon emission condition of the building under different energy saving and emission reduction measures, so that effects of different measures can be evaluated.

7. A digital twin system for controlling carbon emissions in a building according to claim 1, in which the computation module (4) of the digital twin model converts physical properties, energy systems, control strategy factors in the actual scene into a computation model and performs simulation calculations, which can simulate the behavior of the building under different conditions, temperature variations, energy consumption, air flow, and through simulation calculations, can evaluate the influence of different design schemes, operation strategies and control algorithms on the performance and energy efficiency of the building and interface with the data of the actual scene, which comprises inputting real-time sensor data into the digital twin model to update model states and parameters to keep consistency with the actual scene.

8. A digital twin system for controlling carbon emissions in a building according to claim 1, wherein the real-time carbon emission visualization module (5) generates a visual chart, dynamic image, and presents the energy consumption and carbon emission of the building in an intuitive way based on the real-time data and the carbon emission model, providing a more intuitive presentation form for the user with the real-time data and the carbon emission model, and displaying the carbon emission and the energy consumption in different time periods.