Convention and exhibition center carbon footprint real-time monitoring platform based on digital twinning

Abstract

The invention relates to the technical field of convention and exhibition carbon footprint monitoring, in particular to a digital twinning-based convention and exhibition center carbon footprint real-time monitoring platform, which is constructed in a customized manner according to emission characteristics and influence factors of different types of carbon sources in a convention and exhibition scene through four types of models. The real-time target ensures that a carbon footprint result can be output in time by optimizing data acquisition, preprocessing, fusion and calculation of delay of each link, and the setting of double targets not only meets the requirements of double-carbon assessment, green exhibition authentication and the like on data accuracy, but also adapts to the real-time control requirement on carbon emission change in an exhibition dynamic scene, so that the real-time control of the carbon emission change is realized. According to the method, a two-dimensional core guarantee is provided for the monitoring effect, multi-target strategy optimization and deduction are carried out in a carbon footprint digital twin in an exhibition center by combining an improved algorithm based on a carbon footprint monitoring precision target and a real-time target, and dynamic updating of a carbon footprint real-time monitoring strategy is achieved.

Description

Technical Field

[0001] This invention relates to the field of carbon footprint monitoring technology for convention and exhibition centers, and more specifically, to a real-time carbon footprint monitoring platform for convention and exhibition centers based on digital twins. Background Technology

[0002] As a field characterized by high population density and dynamic activities, the exhibition and convention industry has an increasingly prominent need for carbon footprint monitoring. However, existing technologies have significant limitations in carbon source accounting. Traditional carbon footprint monitoring solutions are rather vague in classifying carbon sources in exhibition centers, failing to fully incorporate the differentiated emission characteristics of the four core carbon sources—energy consumption, personnel flow, vehicle flow, and equipment operation—in the exhibition scenario. Furthermore, they lack customized model designs for dynamic scenarios such as the "exhibition period / off-season," resulting in incomplete carbon source coverage, a disconnect between accounting logic and actual scenarios, and an inability to accurately reflect the true carbon emissions of exhibition centers.

[0003] Existing carbon footprint monitoring technologies for exhibitions and conventions suffer from shortcomings in balancing accuracy and real-time performance. Some solutions, in pursuit of higher accuracy, employ complex data acquisition and calculation processes, resulting in significant delays in carbon footprint output and an inability to promptly capture dynamic changes such as sudden surges in visitor numbers and equipment load fluctuations at exhibition centers. Conversely, other solutions, aiming to reduce delays and simplify processes, lead to substantial discrepancies between calculated and actual carbon emissions. Furthermore, current technologies lack clear quantitative targets and correlation optimization mechanisms for accuracy and real-time performance, hindering the dynamic adjustment of monitoring strategies based on the specific needs of each exhibition and convention scenario.

[0004] Traditional carbon footprint monitoring for exhibitions and conventions also suffers from insufficient adaptability of technical means. Most solutions do not incorporate digital twin technology, making it difficult to construct virtual scenarios that closely match the physical space, carbon source distribution, and dynamic behavior of the exhibition center, and thus impossible to simulate and extrapolate the monitoring process. Furthermore, the application of optimization algorithms is limited, with most adopting fixed monitoring strategies and lacking dynamic optimization algorithms that can adapt to the carbon emission characteristics of different stages of the exhibition (such as the setup period, exhibition days, and off-peak periods). This results in poor flexibility of the monitoring strategy, an inability to update it in a timely manner according to the changing trends of carbon sources, and low overall monitoring efficiency. Summary of the Invention

[0005] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a real-time carbon footprint monitoring platform for convention and exhibition centers based on digital twins.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A real-time carbon footprint monitoring platform for convention and exhibition centers based on digital twins, including

[0008] The carbon footprint digital twin module is used to construct a digital twin of the convention center's carbon footprint.

[0009] The carbon footprint vector fusion module is used to collect energy modal data, personnel modal data, vehicle modal data, and equipment modal data in real time. It preprocesses each modal data and then fuses the preprocessed modal data to generate a carbon footprint fusion vector in real time. ;

[0010] The carbon footprint real-time monitoring strategy update module defines the carbon footprint monitoring accuracy target. Real-time objectives A reward function for real-time carbon footprint monitoring is constructed based on the accuracy and real-time performance targets of carbon footprint monitoring. ; Multi-objective strategy optimization and deduction were performed on the carbon footprint digital twin at the convention center, and the real-time carbon footprint monitoring strategy was updated based on the improved particle swarm optimization algorithm.

[0011] Furthermore, the following steps will be taken to construct a digital twin of the carbon footprint of the convention center:

[0012] Step 1: Collect static basic data about the convention center, and standardize the collected static basic data to construct a carbon source coding system;

[0013] Step 2: Construct a physical space geometric model of the convention center based on static basic data; establish carbon source models for energy consumption, personnel, vehicles, and equipment operation; define time-dimensional and scenario-dimensional behavioral rules; and finally define a data mapping mechanism to construct a digital twin of the convention center's carbon footprint.

[0014] Furthermore, energy consumption carbon source models include electricity carbon emission models and gas carbon emission models. Electricity carbon emission model: ; Let be the carbon emission coefficient of electricity at time t. The regional benchmark coefficient is the average carbon emission coefficient of the regional power grid. For the proportion of green electricity; The real-time power at time t is the actual active power consumed in the convention center at time t, which is collected through the power system. The time interval is the time unit for carbon emission calculation; Gas emission model: ; The carbon emission coefficient per unit calorific value of natural gas; Let be the amount of gas consumed at time t; For combustion efficiency.

[0015] Furthermore, the personnel-related carbon source model includes an on-site air conditioning load carbon emission model and a personnel respiration carbon emission model; the air conditioning load carbon emission model ; The average energy consumption per unit of time induced by air conditioning; Let t be the total number of people participating in all activities within the convention center at time t; Energy efficiency coefficient of air conditioning system; carbon emission model of personnel respiration. ; This represents the carbon emission coefficient per capita per unit of time emitted by breathing.

[0016] Furthermore, vehicle carbon source model ; This represents the total number of gasoline-powered vehicles. Carbon emissions per 100 kilometers for the kth vehicle; Let represent the mileage traveled by the kth fuel-powered vehicle within the "target statistical period".

[0017] Furthermore, the equipment operation carbon source model includes an air conditioning operation carbon source model and a lighting operation carbon source model; the air conditioning operation carbon source model... ; Let be the active power of the compressor in the air conditioning system at time t; The total active power of all fans in the air conditioning system at time t; the carbon source model for lighting operation. m represents the total number of all lighting fixtures categorized within the convention center. The rated power of the i-th type of luminaire; Let t represent the on / off state of the i-th type of lamp at time t, with a value of "1" or "0", where "1" indicates that the lamp is on and "0" indicates that it is off.

[0018] Furthermore, the target for carbon footprint monitoring accuracy S=4, The contribution weight of the s-th type of carbon source. ,, Let be the calculated carbon emission value of the s-th type of carbon source at time t; Let be the actual carbon emissions of the s-th type of carbon source at time t.

[0019] Furthermore, real-time objectives D=4; The importance weight of the d-th stage; This represents the actual delay of the d-th stage at time t.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] The platform of this invention uses four types of models to customize the emission characteristics and influencing factors of different types of carbon sources in the exhibition scenario. The energy consumption carbon source model considers green electricity correction to reflect the actual emission reduction effect. The personnel-related carbon source model takes into account the dual impact of air conditioning load and respiratory emissions. The vehicle carbon source model combines vehicle type and mileage for detailed calculation. The equipment operation carbon source model focuses on the real-time power changes of core energy-consuming equipment, effectively solving the problems of vague classification and incomplete coverage in traditional carbon source accounting.

[0022] By clearly defining the accuracy and real-time targets for carbon footprint monitoring, this approach breaks away from the limitations of traditional monitoring that solely pursues accuracy or focuses only on efficiency. The accuracy target quantifies the closeness between calculated and actual carbon emission values, ensuring that the monitoring results accurately reflect the carbon emission level of the convention center. The real-time target optimizes the latency of each stage of data acquisition, preprocessing, fusion, and calculation, ensuring timely output of carbon footprint results. The dual-target setting not only meets the requirements for data accuracy in assessments and green exhibition certifications but also adapts to the real-time control needs of carbon emission changes in dynamic convention and exhibition scenarios, providing a dual-dimensional core guarantee for monitoring effectiveness. Based on the accuracy and real-time targets for carbon footprint monitoring, and combined with improved algorithms, multi-target strategy optimization and deduction are performed in the digital twin of the convention center's carbon footprint, realizing the dynamic updating of the real-time carbon footprint monitoring strategy. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the principle of a real-time carbon footprint monitoring platform for convention centers based on digital twins.

[0024] Figure 2 A schematic diagram illustrating the construction principle of a digital twin of the carbon footprint of a convention and exhibition center.

[0025] Figure 3 A schematic diagram illustrating the principle of updating the carbon footprint real-time monitoring strategy. Detailed Implementation

[0026] Reference Figures 1 to 3 A real-time carbon footprint monitoring platform for convention centers based on digital twins, including

[0027] Carbon footprint digital twin module: Construct a digital twin of the carbon footprint of the convention center.

[0028] The specific steps for constructing a digital twin of the carbon footprint of a convention and exhibition center are as follows:

[0029] Step 1: Collect static basic data about the convention center, and standardize the collected static basic data to construct a carbon source coding system.

[0030] Static basic data includes building data, carbon source attribute data, and spatial data. Building data: The building structure parameters of the convention center (total building area, number / area of ​​exhibition halls, floor height, thermal conductivity coefficient of wall materials, etc.) and CAD drawings of equipment layout (location of air conditioning room, capacity of power distribution room, and routing of water supply and drainage network) are exported from the BIM model. Carbon source attribute data: Physical parameters of fixed carbon sources (such as rated power of air conditioners, thermal efficiency of gas boilers, number of charging piles) and static carbon emission coefficients (average carbon emission coefficient of regional power grid, carbon emission coefficient of natural gas combustion). Spatial data: Three-dimensional point cloud data of the venues in the convention center are obtained through laser scanning, and the geographical location of the venues and the surrounding traffic network are determined by combining them with GIS maps (for vehicle carbon emission calculation).

[0031] Standardization process: The BIM model is converted to glTF format (lightweight 3D model), the parameters are unified in JSON format, and the spatial coordinates adopt WGS84 coordinate system + local Cartesian coordinate system (to facilitate the location of carbon source points).

[0032] Construct a carbon source coding system: Assign a unique ID to each carbon source (e.g., “E-001” represents power distribution room No. 1, “P-002” represents the pedestrian flow monitoring point at the entrance of exhibition hall No. 2), and associate it with its spatial location, physical attributes, and system (energy / personnel / vehicles, etc.).

[0033] Step Two: Construct a physical space geometric model of the convention center based on static foundational data (the physical space geometric model includes a building structure model, an equipment layout model, and a dynamic area model; the building structure model includes the enclosure structure such as walls, floors, and roofs, and labels the thermal parameters of materials (such as insulation layer thickness and heat transfer coefficient) to calculate the additional energy consumption and carbon emissions caused by building heat dissipation; the equipment layout model accurately restores the spatial location of air conditioning vents, lighting fixtures, power distribution boxes, and gas pipeline interfaces, and associates equipment IDs with the carbon emission model of the physical model layer; the dynamic area model marks temporary carbon source activity areas (such as exhibition booth construction areas and temporary catering areas), and supports dynamic model expansion (temporary carbon source points can be added through drag-and-drop operations)); establish energy consumption carbon source models, personnel-related carbon source models, vehicle carbon source models, and equipment operation carbon source models; define time-dimensional behavior rules and scene-dimensional behavior rules, and finally define a data mapping mechanism (data is synchronized to the digital twin according to the sensor sampling frequency) to construct a digital twin of the convention center's carbon footprint.

[0034] The physical space geometric modeling of the convention center adopts a layered modeling strategy and "BIM+GIS+point cloud fusion" technology. The "BIM+GIS+point cloud fusion" technology uses the BIM model as the basic framework, integrates GIS geographic information (surrounding roads, parking lots), and corrects building details (such as the position of exhibition hall columns and the size of doors and windows) through point cloud data to ensure that the geometric accuracy error is ≤0.5 meters. The layered modeling strategy is to model in three levels: "building body - functional zoning - carbon source points". The building body (overall appearance and structure), functional zoning (exhibition hall, office area, parking lot, etc., with marked area boundaries), and carbon source points (sensor locations, equipment installation points, marked with three-dimensional coordinates).

[0035] Time-dimensional behavioral rules are defined as follows: Periodic rules: Preset equipment operating times (e.g., air conditioning runs from 8:00 to 22:00 during the exhibition period and from 8:00 to 18:00 during the off-season) and lighting switching times (e.g., lighting is turned on from 8:00 to 22:00 during the exhibition period and from 8:00 to 18:00 during the off-season).

[0036] Scene-level behavior rules are defined as follows: Empty window scene: Trigger "low load mode" (air conditioning temperature setting is increased by 2℃, and only the channel lights are kept on).

[0037] Energy consumption carbon source models include electricity carbon emission models and gas carbon emission models. Electricity carbon emission model: ; Let be the carbon emission coefficient of electricity at time t. The regional benchmark coefficient is the average carbon emission coefficient of the regional power grid (that is, the amount of carbon dioxide emissions generated by a specific regional power grid for every 1 kilowatt-hour of electricity produced within a certain period, obtained from the power trading platform). To determine the percentage of green electricity used, if the convention center uses green electricity, it needs to use [amount missing]. Make corrections. ; The time interval corresponding to time t at the convention center The total amount of green electricity actually consumed within the region; The convention center at the same time interval Total electrical energy consumed internally; The real-time power at time t is the actual active power consumed in the convention center at time t, which is collected by the power system (intelligent power sensors and three-phase smart meters (deployed in the power distribution room, regional power distribution box, and power supply end of key equipment)). The time interval, i.e., the time unit for carbon emission calculation, is manually set based on "monitoring accuracy requirements" and "data update frequency"; Gas carbon emission model: ; Carbon emission coefficient per unit calorific value of gas (i.e., the mass of carbon dioxide produced by the oxidation of carbon elements when a unit volume (or mass) of gas is completely burned in the convention center). The gas consumption at time t (collected in real time by gas metering equipment in the convention center). The combustion efficiency (i.e., the median value of the combustion efficiency of each gas equipment in the convention center) is calculated by statistically analyzing the models of gas equipment (such as gas boilers and commercial gas stoves) in the convention center, querying the "rated combustion efficiency" of each model (e.g., the rated efficiency of boilers is mostly 92%-95%, and that of gas stoves is 90%-92%), and taking the median value according to the equipment type.

[0038] The personnel-related carbon source model includes an on-site air conditioning load carbon emission model and a personnel respiratory carbon emission model; the air conditioning load carbon emission model ; The average energy consumption per unit time for air conditioning is calculated as follows (data collection method: select typical exhibition days in the same season (e.g., summer cooling season) of the past year, and collect 3 sets of core data: total energy consumption of air conditioning system during the time period). (Data obtained from power sensors in the air conditioning room); Average number of visitors at the convention center during the same period (Average value taken from camera count data); Air conditioner running time (e.g., 8:00-22:00, a total of 14 hours); The formula is derived by reverse calculation using "personnel-related air conditioning energy consumption = total air conditioning energy consumption - basic energy consumption without personnel": ,in, This is the basic energy consumption of air conditioning when the venue is "empty" (calculated using data from the vacancy period). The total number of all personnel at the convention center at time t (counted using cameras deployed within the convention center); personnel respiratory carbon emission model. ; The average carbon emission coefficient per unit time of breathing is a core constant obtained by converting the measured data of "the hourly breathing emissions of adults". The average carbon emission coefficient per unit time of breathing is a commonly used measured constant in the industry.

[0039] Vehicle carbon source model ; This represents the total number of gasoline-powered vehicles. The carbon emission per 100 kilometers for vehicle k is determined by identifying vehicle type (e.g., sedan, SUV, truck) using vehicle identification devices in the convention center's parking lot, and setting different carbon emission per 100 kilometers for different vehicle types. For the kth fuel-powered vehicle, the mileage driven within the "target statistical period" (e.g., exhibition setup period / exhibition day) is calculated by identifying the vehicle's license plate number and determining the vehicle's location based on the license plate number. If the vehicle's location is in the same city as the exhibition center (e.g., Beijing), the default mileage for that vehicle is set to 25km. If the vehicle's registered location is in a different city than the convention center, then the center-to-center distance between the vehicle's registered location and the city where the convention center is located is calculated and set as the vehicle's distance. ).

[0040] The equipment operation carbon source model includes an air conditioning operation carbon source model and a lighting operation carbon source model; the air conditioning operation carbon source model ; Let be the active power of the compressor in the air conditioning system at time t; The total active power of all fans (indoor and outdoor fans) in the air conditioning system at time t; lighting operation carbon source model. m represents the total number of all lighting fixtures categorized within the convention center. The rated power of the i-th type of luminaire; Let t represent the on / off state of the i-th type of lamp at time t, with a value of "1" or "0". "1" indicates that the lamp is on (consuming electrical energy), and "0" indicates that it is off (not consuming electrical energy).

[0041] The carbon footprint vector fusion module collects energy mode data in real time (including real-time power). , , Gas consumption ), personnel modal data (including the total number of all personnel involved in activities within the convention center). Vehicle modal data (including carbon emissions per 100 kilometers for the kth vehicle) The mileage of the kth fuel-powered vehicle within the "target statistical period" (e.g., the exhibition setup period / exhibition days). ) and equipment modal data (including , , The data for each modality is preprocessed (including data denoising, missing value completion, and format standardization). The preprocessed data for each modality is then fused to generate a carbon footprint fusion vector in real time. .

[0042] The preprocessed modal data are fused together, and a carbon footprint fusion vector is generated in real time using a "cross-modal attention fusion network" based on Transformer. The details are as follows: Where A=4, Let a be the attention weight for the a-th modality. Attention weights are allocated differently in different scenarios, as shown in the following example: In an exhibition scenario, , , , (Carbon sources are mainly "energy consumption, personnel connections, and vehicle traffic," with equipment modes as a secondary factor); In the absence of activity, , , , (The carbon sources are mainly "basic energy consumption and low-load equipment operation", and carbon emissions from personnel / vehicles are negligible). This represents the data for the a-th mode.

[0043] The carbon footprint real-time monitoring strategy update module defines the carbon footprint monitoring accuracy target. Real-time objectives A reward function for real-time carbon footprint monitoring is constructed based on the accuracy and real-time performance targets of carbon footprint monitoring. ; Since monitoring accuracy is more important than real-time performance, the value of y1 can be 0.6 and the value of y2 can be 0.4. Multi-objective strategy optimization and deduction are performed on the carbon footprint digital twin at the convention center, and the real-time carbon footprint monitoring strategy is updated based on the improved particle swarm optimization algorithm.

[0044] Carbon footprint monitoring accuracy target S=4, The contribution weights of the s-th type of carbon source are respectively: energy carbon source weight, personnel carbon source weight, vehicle carbon source weight, and equipment carbon source weight. The weighting of different carbon sources is based on quantitative statistics of the convention center's "full-cycle historical carbon emission data" (allocation method: taking the actual carbon emission data of each carbon source (energy, personnel, vehicle, and equipment emissions) for the past year (covering the exhibition period and off-season); calculating the "annual average carbon emission percentage" of each type of carbon source (total carbon emissions of a certain type ÷ sum of the four types of carbon emissions); allocating weights according to the percentage, and making minor adjustments to ensure that the sum is 1 (e.g., energy accounts for approximately 60%). The staff accounts for approximately 20% → And so on) The calculated carbon emissions of the s-th type of carbon source at time t (calculated carbon emissions of energy carbon sources: Calculated carbon emissions from personnel carbon sources: Calculated carbon emissions from vehicle carbon sources: Calculated carbon emissions from the equipment's carbon source: ); Let t be the actual carbon emission value of the s-th type of carbon source at time t (actual carbon emission value of energy carbon source: actual value of electricity + actual value of gas; actual carbon emission value of personnel carbon source: actual value of air conditioning load + actual value of breathing; actual carbon emission value of equipment carbon source: actual value of air conditioning + actual value of lighting. The actual carbon emission values ​​of each are directly collected by relevant monitoring equipment and then calculated by combining them with fixed coefficients).

[0045] Real-time target D=4; The importance weight of stage d (including data fusion, carbon emission calculation, data acquisition, and data preprocessing) needs to meet the following requirements. (Assignment example: Data fusion) (Core, affecting feature accuracy), carbon emission calculation (Core, affecting the output results) Data acquisition (Basic) Data Preprocessing (Auxiliary)); The actual delay at time t for stage d is defined as follows: (Data acquisition delay: sensor sampling period (based on the "key modal sensor period" that has the greatest impact on carbon emission calculation, such as 10 seconds for power sensors during the exhibition period, prioritizing energy and personnel modalities; and 10 seconds for power sensors during the off-peak period, prioritizing energy and equipment modalities), (Preprocessing delay: denoising / completion time (taking the actual acquired multimodal raw data; running preprocessing algorithms (such as moving average denoising and linear interpolation completion); recording the time from data input to processing completion using a timing tool; taking the average of multiple measurements, which is the preprocessing delay), (Fusion delay: Transformer model inference time (preparing the preprocessed multimodal data, starting the trained Transformer fusion model, inputting data and starting timing; recording the model output carbon footprint fusion vector)). At the moment of calculation, the start and end time difference is calculated, and the average value is taken from multiple tests, which is the calculation delay. Calculation delay: the time consumed by carbon source model calculation (preparing input parameters for energy consumption carbon source model, personnel-related carbon source model, vehicle carbon source model, and equipment operation carbon source model; running the formulas of each model to calculate carbon emission values, and timing synchronously; recording the time from parameter input to calculation completion, and taking the average value from multiple tests, which is the carbon source model calculation time)).

[0046] Multi-objective strategy optimization and deduction were performed on the carbon footprint digital twin at the convention center. The real-time carbon footprint monitoring strategy was updated based on an improved particle swarm optimization algorithm, specifically as follows: Decision variables for the carbon footprint monitoring strategy were defined, including those for the data acquisition stage: sampling periods of different modal sensors (e.g., sampling frequencies of power and personnel counting sensors); and those for the preprocessing stage: algorithm complexity parameters (e.g., the window length for moving average denoising, the type of interpolation completion method; for example, setting the window length to 10 sampling points versus 3 sampling points results in differences in computational time and smoothness; cubic spline interpolation...). The differences between linear interpolation and linear interpolation can be seen in terms of computational speed and data trend alignment. Decision variables in the fusion stage include: structural parameters of the Transformer model (number of layers, number of attention heads; for example, 4-layer Transformers and 2-layer Transformers differ in feature extraction accuracy and inference speed; 8-head attention (fine-grained fusion) and 4-head attention (coarse-grained fusion) differ in cross-modal association capture accuracy and computational cost). Decision variables in the carbon source calculation stage include: model simplification coefficients (e.g., whether to ignore secondary carbon source terms; for example, retaining the proportion of green electricity). With no green electricity share (There are differences in computational error and computational efficiency). Using the carbon footprint real-time monitoring reward function as the particle's fitness, the overall performance of each monitoring strategy in terms of "accuracy-real-time performance" is evaluated (the higher the value, the better the strategy). The monitoring strategy parameters corresponding to the particles are input into the carbon footprint digital twin of the convention center. Based on the input strategy, the carbon footprint digital twin simulates the entire process of data acquisition, preprocessing, fusion, and carbon source calculation; the target carbon footprint monitoring accuracy under this strategy is output. and real-time objectives The process involves calculating a reward function value based on the output results, which serves as the "fitness" of each particle. An improved Particle Swarm Optimization (PSO) algorithm is used to search for the optimal strategy, randomly generating multiple sets of monitoring strategy parameters to form an initial particle swarm. The digital twin of the carbon footprint of the convention center is then invoked to calculate the fitness of each particle (each strategy). Optimal position update: Based on the fitness, the individual optimal position (its own historical optimal strategy) and the global optimal position of the population (the overall population's historical optimal strategy) are updated. Particle position update: Combining improved mechanisms (such as adaptive inertia weights, dynamically balancing "exploring new strategies" and "converging to a better strategy"; or mutation operations to avoid getting trapped in local optima), the velocity and position of the particles are updated to generate new monitoring strategies. Termination condition: When the number of iterations reaches a preset value, or the fitness no longer significantly improves, iteration stops. After iteration terminates, the monitoring strategy corresponding to the global optimal position (including the parameter combination for data acquisition, preprocessing, fusion, and carbon source calculation) is output, which is the carbon footprint real-time monitoring strategy with the optimal balance between "accuracy" and "real-time performance".

[0047] The above formulas are all dimensionless calculations, and the preset parameters in the formulas should be set by those skilled in the art according to the actual situation.

[0048] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0049] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0050] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0051] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0052] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0053] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0054] The above description is merely a specific 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 scope of the technology 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 real-time carbon footprint monitoring platform for convention and exhibition centers based on digital twins, characterized in that: include The carbon footprint digital twin module is used to construct a digital twin of the convention center's carbon footprint. The carbon footprint vector fusion module is used to collect energy modal data, personnel modal data, vehicle modal data, and equipment modal data in real time. It preprocesses each modal data and then fuses the preprocessed modal data to generate a carbon footprint fusion vector in real time. ; The carbon footprint real-time monitoring strategy update module defines the carbon footprint monitoring accuracy target. Real-time objectives A reward function for real-time carbon footprint monitoring is constructed based on the accuracy and real-time performance targets of carbon footprint monitoring. ; Multi-objective strategy optimization and deduction were performed on the carbon footprint digital twin at the convention center, and the real-time carbon footprint monitoring strategy was updated based on the improved particle swarm optimization algorithm.

2. The real-time carbon footprint monitoring platform for convention centers based on digital twins as described in claim 1, characterized in that, The specific steps for constructing a digital twin of the carbon footprint of a convention and exhibition center are as follows: Step 1: Collect static basic data about the convention center, and standardize the collected static basic data to construct a carbon source coding system; Step 2: Construct a physical space geometric model of the convention center based on static basic data; establish carbon source models for energy consumption, personnel, vehicles, and equipment operation; define time-dimensional and scenario-dimensional behavioral rules; and finally define a data mapping mechanism to construct a digital twin of the convention center's carbon footprint.

3. The real-time carbon footprint monitoring platform for convention centers based on digital twins according to claim 2, characterized in that, Energy consumption carbon source models include electricity carbon emission models and gas carbon emission models. Electricity carbon emission model: ; Let be the carbon emission coefficient of electricity at time t. The regional benchmark coefficient is the average carbon emission coefficient of the regional power grid. For the proportion of green electricity; The real-time power at time t is the actual active power consumed in the convention center at time t, which is collected through the power system. The time interval is the time unit for carbon emission calculation; Gas emission model: ; The carbon emission coefficient per unit calorific value of natural gas; Let be the amount of gas consumed at time t; For combustion efficiency.

4. The real-time carbon footprint monitoring platform for convention centers based on digital twins according to claim 2, characterized in that, The personnel-related carbon source model includes an on-site air conditioning load carbon emission model and a personnel respiratory carbon emission model; the air conditioning load carbon emission model ; The average energy consumption per unit of time induced by air conditioning; The total number of people participating in activities at the convention center at time t; personnel respiratory carbon emission model. ; This represents the carbon emission coefficient per capita per unit of time emitted by breathing.

5. The real-time carbon footprint monitoring platform for convention centers based on digital twins according to claim 2, characterized in that, Vehicle carbon source model ; This represents the total number of gasoline-powered vehicles. Carbon emissions per 100 kilometers for the kth vehicle; Let represent the mileage traveled by the kth fuel-powered vehicle within the "target statistical period".

6. The real-time carbon footprint monitoring platform for convention centers based on digital twins according to claim 2, characterized in that, The equipment operation carbon source model includes an air conditioning operation carbon source model and a lighting operation carbon source model; the air conditioning operation carbon source model ; Let be the active power of the compressor in the air conditioning system at time t; The total active power of all fans in the air conditioning system at time t; the carbon source model for lighting operation. m represents the total number of all lighting fixtures categorized within the convention center. The rated power of the i-th type of luminaire; Let t represent the on / off state of the i-th type of lamp at time t, with a value of "1" or "0". "1" indicates that the lamp is on and "0" indicates that it is off.

7. The real-time carbon footprint monitoring platform for convention centers based on digital twins according to claim 1, characterized in that, Carbon footprint monitoring accuracy target S=4, The contribution weight of the s-th type of carbon source. ,, Let be the calculated carbon emission value of the s-th type of carbon source at time t; Let be the actual carbon emissions of the s-th type of carbon source at time t.

8. The real-time carbon footprint monitoring platform for convention centers based on digital twins according to claim 1, characterized in that, Real-time target D=4; The importance weight of the d-th stage; This represents the actual delay of the d-th stage at time t.

Images