Office building carbon management method and system based on digital twinning

Abstract

The embodiment of the invention provides an office building carbon management method and system based on digital twinning, and belongs to the technical field of carbon management. The office building carbon management method comprises the following steps: performing three-dimensional modeling on the appearance, space, equipment, lines and pipelines of an office building, accessing data information of various systems in the building, and restoring the real operation condition of the building in a digital space; energy consumption conditions in the building are obtained, and corresponding carbon emission factors are obtained according to different energy types; according to the obtained energy consumption condition and the corresponding carbon emission factor, the carbon emission condition of the building is obtained through calculation; according to the energy consumption condition of the equipment of the building, the carbon emission is distributed to the corresponding building equipment; and the carbon emission condition of the building equipment of the building is collected and monitored in real time. According to the office building carbon management method, the carbon emission of the building can be effectively monitored, and risk prompting can be carried out on abnormal energy consumption in the three-dimensional model.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon management, and in particular to a carbon management method and system for office buildings based on digital twins. Background Art

[0002] Carbon emissions is a general term or abbreviation for greenhouse gas emissions. The most important greenhouse gas is carbon dioxide, so the word carbon is used as a representative. Among various industries, the construction industry consumes about 30%-40% of the world's energy and emits almost 30% of the world's greenhouse gases. Therefore, it is very necessary to effectively monitor and analyze building carbon emissions and provide basic data to achieve carbon reduction goals. At present, the construction process of smart buildings and smart parks has been significantly accelerated. The transformation of smart parks is booming, and the demand for the construction of building carbon emission monitoring and management systems is growing. However, in the existing technology, there is no more comprehensive and sophisticated means to manage building carbon emissions. Summary of the invention

[0003] The purpose of an embodiment of the present invention is to provide an office building carbon management method and system based on digital twins, which can effectively monitor the carbon emissions of the building and provide risk warnings for abnormal energy consumption in a three-dimensional model.

[0004] In order to achieve the above objectives, an embodiment of the present invention provides an office building carbon management method and system based on digital twins, and the office building carbon management method includes:

[0005] Carry out 3D modeling of the office building's appearance, space, equipment, lines and pipelines, and access the data information of various systems in the building to restore the real operation of the building in a digital space;

[0006] Obtaining energy consumption in the building and obtaining corresponding carbon emission factors according to different energy types;

[0007] Calculate the building's carbon emissions based on the energy consumption and corresponding carbon emission factors;

[0008] According to the energy consumption of the building equipment, carbon emissions are allocated to the corresponding building equipment and marked on the building equipment of the corresponding digital twin building;

[0009] Collect and monitor the carbon emissions of building equipment in real time, and provide risk warnings on the digital twin building to guide energy management or equipment maintenance.

[0010] Optionally, the energy consumption includes: water, electricity and natural gas.

[0011] Optionally, real-time collection and monitoring of carbon emissions of building equipment in the building, and risk warnings on the digital twin building to guide energy management or equipment maintenance, including:

[0012] Obtaining historical data on carbon emissions in the building;

[0013] Preprocessing the historical data to obtain historical data that meets the requirements;

[0014] Performing a unit root test on the preprocessed historical data, and making the historical data stable by a difference method, and obtaining the value of a difference parameter;

[0015] Processing the stabilized historical data to obtain regression parameters and moving average parameters;

[0016] Constructing an ARIMA forecasting model based on the regression parameters, moving average parameters and historical data;

[0017] Bring the collected historical data into the ARIMA forecasting model to obtain the first forecast value;

[0018] Subtract the first predicted value from the actual collected value to obtain a residual value;

[0019] Training a first prediction model according to the residual value;

[0020] Bringing the currently collected data into the ARIMA prediction model to obtain a second prediction value and bringing the residual value into the first prediction model to obtain a residual prediction value;

[0021] Adding the second predicted value to the residual predicted value to obtain a final predicted value;

[0022] According to the final prediction value, when it is determined that the final prediction value exceeds a preset threshold, a risk warning is issued on the digital twin building.

[0023] Optionally, preprocessing the historical data to obtain historical data that meets the requirements includes:

[0024] Acquiring the historical data;

[0025] Determine whether there are missing values ​​in the historical data;

[0026] In the case where there are missing values ​​in the historical data, time-marking the historical data to obtain coordinate points about time and historical data, and determine the time point of the missing data;

[0027] Calculate the centroid weight of each coordinate point according to formula (1):

[0028]

[0029] Among them, x i ,y i Indicates the coordinate point, i, j indicates the subscript, w i Represents x i ,y i The centroid weight of the coordinate point, k represents the number of historical data;

[0030] Substitute the time point of the missing data into formula (2) to obtain the final missing data:

[0031]

[0032] The final missing data is added to the historical data to obtain historical data that meets the requirements.

[0033] Optionally, the regression parameters and moving average parameters obtained by processing the stable historical data include:

[0034] Acquiring stable historical data;

[0035] Draw an autocorrelation graph and a partial autocorrelation graph based on the historical data;

[0036] Obtaining autoregressive parameters and moving average parameters of historical data according to the autocorrelation diagram and partial autocorrelation;

[0037] Construct Akaike Information Criterion and Bayesian Information Criterion according to different autoregressive parameters and moving average parameters;

[0038] The autoregressive parameter and moving average parameter that are optimal according to the Akaike information criterion and the Bayesian information criterion are determined to be the optimal parameters.

[0039] Optionally, constructing an ARIMA forecasting model according to the regression parameter, the moving average parameter and the historical data includes:

[0040] Obtaining the regression parameters, moving average parameters and historical data;

[0041] Construct the ARIMA forecasting model according to formula (3):

[0042]

[0043] Among them, y i and i-1 are the current time value and past time value of historical data respectively, e i and e i-r are the current time error and the past time error respectively, a r and b r are the coefficients of the autoregressive model and the moving average model respectively, p is the regression parameter, and q is the moving average parameter.

[0044] Optionally, the first prediction model is an LSTM model.

[0045] Optionally, when it is determined, based on the final prediction value, that the final prediction value exceeds a preset threshold, providing a risk warning on the digital twin building includes:

[0046] Obtaining the final prediction value;

[0047] Determine the exceedance of equipment in the building based on the final predicted value and historical data;

[0048] Identify the equipment in the building that exceeds the conventional carbon emission threshold and mark the corresponding equipment in the digital twin building to alert staff.

[0049] On the other hand, the present invention also provides an office building carbon management system based on digital twins, the office building carbon management system comprising:

[0050] Data collection module, used to collect energy consumption information of various equipment in office buildings;

[0051] The comprehensive processing module is used to obtain energy consumption information and execute the office building carbon management method as described above.

[0052] Through the above technical scheme, the present invention provides a carbon management method and system for office buildings based on digital twins. By three-dimensionally modeling the appearance, space, equipment, lines and pipelines of office buildings, and accessing the data information of various systems in the building, the real operation of the building can be restored in the digital space, and then the energy consumption in the building can be obtained, and the corresponding carbon emission factors can be obtained according to different energy types. According to the obtained energy consumption and the corresponding carbon emission factors, the carbon emissions of the building can be calculated. According to the energy consumption of the equipment in the building, the carbon emissions can be allocated to the corresponding building equipment, and can be marked on the building equipment of the corresponding digital twin building to intuitively display the carbon emissions in the building. The carbon emissions of the building equipment of the building are collected and monitored in real time, and risk warnings can be given on the digital twin building, so as to guide energy control or equipment maintenance. The office building carbon management method can effectively monitor the carbon emissions of the building and give risk warnings for abnormal energy use in the three-dimensional model.

[0053] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0055] Figure 1 is a flow chart of a carbon management method for an office building based on digital twin according to one embodiment of the present invention;

[0056] Figure 2 is a first flow chart of risk warning of a carbon management method for an office building based on digital twin according to an embodiment of the present invention;

[0057] Figure 3 is a flowchart of pre-processing of a carbon management method for an office building based on a digital twin according to an embodiment of the present invention;

[0058] Figure 4 is a flowchart of obtaining regression parameters and moving average parameters of a carbon management method for an office building based on digital twin according to an embodiment of the present invention;

[0059] Figure 5 is a flowchart of constructing an ARIMA prediction model for an office building carbon management method based on digital twins according to an embodiment of the present invention;

[0060] Figure 6 This is a second flowchart of a risk warning of a carbon management method for an office building based on a digital twin according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0062] Figure 1 is a flow chart of a carbon management method for office buildings based on digital twins according to an embodiment of the present invention. In the present invention, the process may include:

[0063] In step S1, three-dimensional modeling is performed on the appearance, space, equipment, lines and pipelines of the office building, and data information of various systems in the building is connected to restore the actual operation status of the building in the digital space.

[0064] In step S2, the energy consumption in the building is obtained, and corresponding carbon emission factors are obtained according to different energy types.

[0065] In step S3, the carbon emission of the building is calculated based on the acquired energy consumption and the corresponding carbon emission factor.

[0066] In step S4, carbon emissions are allocated to corresponding building equipment according to the energy consumption of the building equipment and marked on the building equipment of the corresponding digital twin building.

[0067] In step S5, the carbon emissions of the building equipment in the building are collected and monitored in real time, and risk warnings are issued on the digital twin building to guide energy consumption control or equipment maintenance.

[0068] In the present invention, when conducting building carbon management, the appearance, space, equipment, lines and pipelines of the office building can be three-dimensionally modeled, and the data information of various systems in the building can be accessed to restore the real operation of the building in the digital space. The energy consumption in the building is obtained, and the corresponding carbon emission factor can be obtained according to different energy types. According to the obtained energy consumption and the corresponding carbon emission factor, the carbon emission of the building can be calculated. The carbon emission of the building is mapped to the building in the corresponding digital space to intuitively display the carbon emission of the building. According to the energy consumption of the equipment in the building, the carbon emissions can be allocated to the corresponding building equipment, and can be marked on the building equipment of the corresponding digital twin building, and its carbon emissions can be intuitively observed on each building equipment. The carbon emissions of the building equipment of the building are collected and monitored in real time, and risk warnings can be issued on the digital twin building, so as to guide energy management or equipment maintenance.

[0069] In one embodiment of the present invention, the energy consumption may include consumption of resources such as water, electricity, and natural gas.

[0070] In one embodiment of the present invention, Figure 2 As shown, the first process of risk warning may include:

[0071] In step S6, historical data of carbon emissions in the building is obtained.

[0072] In step S7, the historical data is preprocessed to obtain historical data that meets the requirements.

[0073] In step S8, a unit root test is performed on the preprocessed historical data, and the historical data is made stable by the difference method to obtain the value of the difference parameter.

[0074] In step S9, the historical data after stabilization is processed to obtain regression parameters and moving average parameters.

[0075] In step S10, an ARIMA forecasting model is constructed according to the regression parameters, the moving average parameters and the historical data.

[0076] In step S11, the collected historical data is introduced into the ARIMA forecasting model to obtain a first forecast value.

[0077] In step S12, the first predicted value is subtracted from the actual collected value to obtain a residual value.

[0078] In step S13, a first prediction model is trained according to the residual value.

[0079] In step S14, the currently collected data is brought into the ARIMA prediction model to obtain a second prediction value, and the residual value is brought into the first prediction model to obtain a residual prediction value.

[0080] In step S15, the second prediction value is added to the residual prediction value to obtain a final prediction value.

[0081] In step S16, based on the final prediction value, when it is determined that the final prediction value exceeds a preset threshold, a risk warning is issued on the digital twin building.

[0082] In the present invention, when the risk warning of carbon emissions in a building is given, the historical data of carbon emissions in the building can be obtained first, and then the historical data can be preprocessed to obtain historical data that meets the requirements. After obtaining the historical data that meets the requirements, the historical data can be subjected to a unit root test, and the historical data can be made stable by the difference method. In the process of differentiating the historical data to make it stable, the value of the difference parameter can be obtained. After the historical data is stable, the stable historical data can be processed to obtain regression parameters and moving average parameters. According to the regression parameters, the average moving parameters and the historical data, an ARIMA prediction model can be constructed. After the ARIMA prediction model is constructed, the ARIMA prediction model can be pre-trained first, and the existing data can be sent to the ARIMA prediction model to meet the requirements. Then the collected historical data can be brought into the ARIMA prediction model to obtain a first prediction value. After obtaining the first prediction value, the corresponding first prediction value can be subtracted from the actual collected data to obtain a residual value. Construct a first prediction model, which is also a model after multiple residual values ​​are brought into the training. After training the first prediction model, the currently collected data can be brought into the ARIMA prediction model to obtain the second prediction value, and the residual value can be obtained. The residual value can be brought into the first prediction model to obtain the residual prediction value. According to the second prediction value and the residual prediction value, the second prediction value plus the residual prediction value can obtain the final prediction value. According to the final prediction value, it can be determined whether the final prediction value exceeds the preset threshold. When the final prediction value does not exceed the preset threshold, no risk warning can be issued. When the final prediction value exceeds the preset threshold, a risk warning can be issued on the digital twin building to intuitively display the carbon emissions of the building.

[0083] In one embodiment of the present invention, Figure 3 As shown, the pre-processing process may include:

[0084] In step S17, historical data is acquired.

[0085] In step S18, it is determined whether there are missing values ​​in the historical data.

[0086] In step S19, when there are missing values ​​in the historical data, the historical data is time-annotated to obtain coordinate points about time and historical data, and to determine the time point of the missing data.

[0087] In step S20, the centroid weight of each coordinate point is calculated according to formula (1):

[0088]

[0089] Among them, x i ,yi Indicates the coordinate point, i, j indicates the subscript, w i Represents x i ,y i The centroid weight of the coordinate point, k represents the number of historical data.

[0090] In step S21, the time point of the missing data is substituted into formula (2) to obtain the final missing data:

[0091]

[0092] In step S22, the final missing data is supplemented into the historical data to obtain historical data that meets the requirements.

[0093] Obtain historical data and determine whether there are missing values ​​in the historical data. If there are no missing values ​​in the historical data, the historical data can be directly differentiated to make it stable. When there are missing values ​​in the historical data, the historical data can be time-annotated to obtain the coordinate points about time and historical data. According to the obtained coordinate points, the time coordinates of the missing data can be determined. According to the formula (1), the centroid weight of each coordinate point can be obtained, and then the corresponding time point of the missing data can be substituted into the formula (2) to obtain the final accurate data. According to the final missing data obtained, it can be supplemented into the historical data, so that the historical data that meets the requirements can be obtained. This method can comprehensively consider the trend and overall performance of the historical data, so that the obtained data can be more in line with the integrity of the historical data.

[0094] In one embodiment of the present invention, Figure 4 As shown, the process of obtaining regression parameters and moving average parameters may include:

[0095] In step S23, stable historical data is obtained.

[0096] In step S24, an autocorrelation graph and a partial autocorrelation graph are drawn based on the historical data.

[0097] In step S25, the autoregressive parameters and moving average parameters of the historical data are obtained according to the autocorrelation diagram and the partial autocorrelation.

[0098] In step S26, Akaike information criterion and Bayesian information criterion are constructed according to different autoregressive parameters and moving average parameters.

[0099] In step S27, the autoregressive parameters and moving average parameters that are optimal according to the Akaike information criterion and the Bayesian information criterion are determined as the optimal parameters.

[0100] In the present invention, when constructing an ARIMA forecasting model, it is necessary to first obtain stable historical data, and then an autocorrelation graph and a partial autocorrelation graph can be drawn based on the historical data. By observing the autocorrelation graph and the partial autocorrelation graph, the autoregressive parameters and moving average parameters of the historical data can be obtained. According to different autoregressive parameters and moving average parameters, the Akaike information criterion and the Bayesian information criterion can be constructed, and according to the optimal model of the Akaike information criterion and the Bayesian information criterion, the optimal parameters of the autoregressive parameters and the moving average parameters can be obtained. When obtaining the optimal model of the Akaike information criterion and the Bayesian information criterion, the model with the smallest Akaike information criterion or the Bayesian information criterion can be selected as the model, and the corresponding parameters are the optimal parameters.

[0101] In one embodiment of the present invention, Figure 5 As shown, the process of building an ARIMA forecasting model can include:

[0102] In step S28, regression parameters, moving average parameters and historical data are obtained.

[0103] In step S29, an ARIMA forecasting model is constructed according to formula (3):

[0104]

[0105] Among them, y i and i-1 are the current time value and past time value of historical data respectively, e i and e i-r are the current time error and the past time error respectively, a r and b r are the coefficients of the autoregressive model and the moving average model respectively, p is the regression parameter, and q is the moving average parameter.

[0106] In the present invention, after obtaining the regression parameters, moving average parameters and historical data, an ARIMA prediction model can be constructed. The model can predict the carbon emissions of a building based on historical data, so that the general trend of the carbon emissions of the building can be known.

[0107] In one embodiment of the present invention, the first prediction model may be an LSTM model. The LSTM model can construct the neuron parameters in its model based on a large amount of historical data, capture the features in the time series, and thus accurately predict the residual value of carbon emissions. The predicted amount of carbon emissions obtained by the ARIMA prediction model and the residual prediction value obtained by the first prediction model can predict the carbon emissions of the building with high accuracy, so that it can be judged in advance whether the carbon emissions of the building exceed the standard based on the predicted value, so as to provide risk warnings in advance.

[0108] In one embodiment of the present invention, Figure 6 As shown, the second process of risk warning may include:

[0109] In step S30, the final prediction value is obtained.

[0110] In step S31, the excess condition of the equipment in the building is determined based on the final prediction value and historical data.

[0111] In step S32, the equipment in the building that exceeds the conventional carbon emission threshold is determined, and the corresponding equipment in the digital twin building is marked to alert the staff.

[0112] In the present invention, when providing risk warnings for digital twin buildings, the final prediction value can be obtained first, and the exceeding conditions of the equipment in the building can be determined based on the final prediction value and historical data. Because the final prediction value can also be obtained by superimposing the carbon emissions of various equipment in the building, when it is obtained that the carbon emissions of the building exceed a certain amount, it can be determined first that the carbon emissions of the building exceed the standard, and then the equipment that exceeds the conventional carbon emission threshold can be further determined based on the carbon emissions of various monitored equipment in the building, and the corresponding equipment in the digital twin building can be marked to remind the staff to pay attention.

[0113] On the other hand, the present invention also provides an office building carbon management system based on digital twins, the office building carbon management system comprising: a data acquisition module and a comprehensive processing module. The data acquisition module can be used to collect energy consumption information of various equipment in the office building. The comprehensive processing module can be used to obtain energy consumption information and execute the office building carbon management method as described above.

[0114] Through the above technical scheme, the present invention provides a carbon management method and system for office buildings based on digital twins. By three-dimensionally modeling the appearance, space, equipment, lines and pipelines of office buildings, and accessing the data information of various systems in the building, the real operation of the building can be restored in the digital space, and then the energy consumption in the building can be obtained, and the corresponding carbon emission factors can be obtained according to different energy types. According to the obtained energy consumption and the corresponding carbon emission factors, the carbon emissions of the building can be calculated. According to the energy consumption of the equipment in the building, the carbon emissions can be allocated to the corresponding building equipment, and can be marked on the building equipment of the corresponding digital twin building to intuitively display the carbon emissions in the building. The carbon emissions of the building equipment of the building are collected and monitored in real time, and risk warnings can be given on the digital twin building, so as to guide energy control or equipment maintenance. The office building carbon management method can effectively monitor the carbon emissions of the building and give risk warnings for abnormal energy use in the three-dimensional model.

[0115] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0116] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0119] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0120] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0121] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0122] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0123] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A carbon management method for office buildings based on digital twins, characterized in that: The office building carbon management approach includes: Carry out 3D modeling of the office building's appearance, space, equipment, lines and pipelines, and access the data information of various systems in the building to restore the real operation of the building in a digital space; Obtaining energy consumption in the building and obtaining corresponding carbon emission factors according to different energy types; Calculate the building's carbon emissions based on the energy consumption and corresponding carbon emission factors; According to the energy consumption of the building equipment, carbon emissions are allocated to the corresponding building equipment and marked on the building equipment of the corresponding digital twin building; Collect and monitor the carbon emissions of building equipment in real time, and provide risk warnings on the digital twin building to guide energy management or equipment maintenance.

2. The office building carbon management method according to claim 1, characterized in that: The energy consumption includes: water, electricity and natural gas.

3. The office building carbon management method according to claim 1, characterized in that: Collect and monitor the carbon emissions of building equipment in real time, and issue risk warnings on the digital twin building to guide energy management or equipment maintenance, including: Obtaining historical data on carbon emissions in the building; Preprocessing the historical data to obtain historical data that meets the requirements; Performing a unit root test on the preprocessed historical data, and making the historical data stable by a difference method, and obtaining the value of a difference parameter; Processing the stabilized historical data to obtain regression parameters and moving average parameters; Constructing an ARIMA forecasting model based on the regression parameters, moving average parameters and historical data; Bring the collected historical data into the ARIMA forecasting model to obtain the first forecast value; Subtract the first predicted value from the actual collected value to obtain a residual value; Training a first prediction model according to the residual value; Bringing the currently collected data into the ARIMA prediction model to obtain a second prediction value and bringing the residual value into the first prediction model to obtain a residual prediction value; Adding the second predicted value to the residual predicted value to obtain a final predicted value; According to the final prediction value, when it is determined that the final prediction value exceeds a preset threshold, a risk warning is issued on the digital twin building.

4. The office building carbon management method according to claim 3, characterized in that: Preprocessing the historical data to obtain historical data that meets the requirements includes: Acquiring the historical data; Determine whether there are missing values ​​in the historical data; In the case where there are missing values ​​in the historical data, time-marking the historical data to obtain coordinate points about time and historical data, and determine the time point of the missing data; Calculate the centroid weight of each coordinate point according to formula (1): Among them, x i ,y i Indicates the coordinate point, i, j indicates the subscript, w i Represents x i ,y i The centroid weight of the coordinate point, k represents the number of historical data; Substitute the time point of the missing data into formula (2) to obtain the final missing data: The final missing data is added to the historical data to obtain historical data that meets the requirements.

5. The office building carbon management method according to claim 3, characterized in that: The regression parameters and moving average parameters obtained by processing the stable historical data include: Obtaining stable historical data; Draw an autocorrelation graph and a partial autocorrelation graph based on the historical data; Obtaining autoregressive parameters and moving average parameters of historical data according to the autocorrelation graph and partial autocorrelation; Construct Akaike Information Criterion and Bayesian Information Criterion according to different autoregressive parameters and moving average parameters; The autoregressive parameter and moving average parameter that are optimal according to the Akaike information criterion and the Bayesian information criterion are determined to be the optimal parameters.

6. The office building carbon management method according to claim 3, characterized in that: Constructing an ARIMA forecasting model based on the regression parameters, moving average parameters and historical data includes: Obtaining the regression parameters, moving average parameters and historical data; Construct the ARIMA forecasting model according to formula (3): Among them, y i and i-1 are the current time value and past time value of historical data respectively, e i and e i-r are the current time error and the past time error respectively, a r and b r are the coefficients of the autoregressive model and the moving average model respectively, p is the regression parameter, and q is the moving average parameter.

7. The office building carbon management method according to claim 3, characterized in that: The first prediction model is an LSTM model.

8. The office building carbon management method according to claim 3, characterized in that: When it is determined according to the final prediction value that the final prediction value exceeds a preset threshold, a risk warning is issued on the digital twin building including: Obtaining the final prediction value; Determine the exceedance of equipment in the building based on the final predicted value and historical data; Identify the equipment in the building that exceeds the conventional carbon emission threshold and mark the corresponding equipment in the digital twin building to alert staff.

9. An office building carbon management system based on digital twins, characterized in that: The office building carbon management system includes: Data collection module, used to collect energy consumption information of various equipment in office buildings; The comprehensive processing module is used to obtain energy consumption and execute the office building carbon management method as described in any one of claims 1-8.

Images