Zero-carbon park full-life-cycle carbon footprint tracking accounting method and system

By constructing an energy network topology map and using graph neural networks to calculate power distribution relationships, the problem of tracking power flow and distribution ratios within the zero-carbon park is solved, and high-precision accounting and dynamic traceability of end-user carbon footprints are achieved, ensuring the accuracy of carbon footprint tracking.

CN120634590AActive Publication Date: 2025-09-12SINO SINGAPORE TIANJIN ECO CITY ENVIRONMENT & GREEN BUILDING EXPERIMENTAL CENT CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202511128172.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-13
Publication Date
2025-09-12
Estimated Expiration
2045-08-13

AI Technical Summary

Technical Problem

Existing technologies are unable to accurately track the flow and distribution ratio of electricity in modern zero-carbon parks where multiple energy sources are deeply coupled with the public power grid, resulting in insufficient accuracy in the carbon footprint accounting results of end users and the inability to implement differentiated carbon management and incentive strategies.

Method used

By constructing a weighted energy network topology diagram, combining real-time power data to generate a dynamic energy flow digital model, and using graph neural networks to solve the power distribution relationship between nodes, an energy flow matrix is ​​generated, and the power distribution ratio from energy supply units to energy consumption units is accurately quantified. Combined with the grid synchronized phasor data for physical verification, high-precision tracking of carbon footprints can be achieved.

Benefits of technology

In the complex power grid scenario of the zero-carbon park, high-precision dynamic traceability and accounting of terminal-level carbon footprints are achieved, which solves the problem of carbon footprint accounting distortion and improves the accuracy of carbon footprint tracking.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120634590A_ABST
    Figure CN120634590A_ABST
Patent Text Reader

Abstract

The invention discloses a zero-carbon park full-life-cycle carbon footprint tracking accounting method and system, and belongs to the field of carbon emission. The method is suitable for a zero-carbon park with photovoltaic, energy storage and commercial power multi-energy coupling power supply, and an energy network topological graph with energy-related units defined as nodes and physical lines as weighted directed edges is constructed by obtaining spatial topological data and real-time power data of the zero-carbon park and carbon intensity factors of all energy supply units; and a dynamic energy flow digital model is generated by combining real-time power data. Then, inputting the model into a graph neural network, and calculating an energy flow direction matrix representing the power distribution proportion from each energy supply unit to each energy consumption unit; and finally, converting the carbon intensity factor of each energy supply unit into a source end carbon intensity vector based on the matrix, distributing the source end carbon intensity vector to each energy consumption unit, and calculating a carbon footprint value in combination with real-time power data of the source end carbon intensity vector, so that accurate tracking and accounting of the carbon footprint of the zero-carbon park terminal user can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application belongs to the field of carbon emissions, and in particular relates to a method and system for tracking and calculating the carbon footprint of a zero-carbon park throughout its entire life cycle. Background Art

[0002] As a key vehicle for achieving energy conservation and carbon reduction, tracking and calculating the carbon footprint of zero-carbon parks is crucial. Accurate carbon footprint calculation methods not only provide a scientific basis for assessing a park's green and low-carbon status and managing its carbon assets, but also offer key technical support for promoting green electricity trading within the park, guiding users toward energy conservation and carbon reduction, and optimizing energy system scheduling. These methods hold broad application prospects.

[0003] In the existing technology, the carbon footprint accounting method for zero-carbon parks usually adopts a macro-measurement method based on total energy consumption. The total electricity purchase amount of the park provided by the power grid company and the average carbon emission factor of the regional power grid are obtained to calculate the carbon emissions of electricity consumption of the entire park.

[0004] However, when applied to modern zero-carbon parks, where multiple energy sources, such as photovoltaics and energy storage, are deeply integrated with the public grid, existing technologies are unable to track the specific flow and distribution ratio of mixed electricity along various transmission and distribution paths within the park's internal grid. This results in inaccurate carbon footprint calculations for end users. Therefore, existing methods suffer from the technical problem of being unable to accurately track and calculate the carbon footprint of end users in zero-carbon parks. Summary of the Invention

[0005] This application actually provides a method, system, device and computer storage medium for tracking and calculating the carbon footprint of a zero-carbon park throughout its entire life cycle, which can accurately track and calculate the carbon footprint of end users in the zero-carbon park.

[0006] In a first aspect, the present application provides a method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle, which is applicable to a zero-carbon park powered by multi-energy coupling. The method comprises:

[0007] Obtain spatial topological data of energy-related units within the zero-carbon park, real-time power data of energy-related units, and the carbon intensity factor of each energy supply unit. Energy-related units include at least one energy supply unit and at least one energy consumption unit. The spatial topological data includes the physical parameters of the physical lines between energy-related units.

[0008] Based on spatial topological data, energy-related units are defined as nodes, physical lines connecting nodes are defined as directed edges, and physical parameters of physical lines are defined as weights of directed edges to construct an energy network topology graph.

[0009] Mapping real-time power data to the node attributes of the corresponding nodes in the energy network topology diagram to generate a digital energy flow model that represents the energy flow status of the zero-carbon park;

[0010] The energy flow digital model is input into the trained graph neural network. By calculating the power distribution relationship between nodes, the energy flow matrix is ​​obtained. The row dimension of the energy flow matrix corresponds to the number of energy supply units, the column dimension corresponds to the number of energy consumption units, and the matrix elements represent the power distribution ratio coefficient.

[0011] The carbon intensity factor of each energy supply unit is converted into a source-end carbon intensity vector. Each source-end carbon intensity vector is assigned to the energy-consuming unit through the energy flow matrix, and the carbon footprint value of the energy-consuming unit is calculated based on the real-time power data of the energy-consuming unit.

[0012] In one feasible embodiment, the energy supply unit includes a photovoltaic power generation unit, an energy storage unit, and a public grid unit.

[0013] In one possible implementation, the method further includes:

[0014] When the charge and discharge state corresponding to the real-time power data of the energy storage unit is a charging state, the energy storage unit is determined as an energy consuming unit;

[0015] Based on the energy flow matrix, the source-end carbon intensity vector assigned to the energy storage unit is calculated. Based on the real-time power data of the energy storage unit, the charging capacity of the energy storage unit and the corresponding carbon attribute data block are calculated.

[0016] A first-in-first-out carbon accounting queue is established for the energy storage unit, and the carbon attribute data blocks of the energy storage unit are stored at the end of the carbon accounting queue in chronological order. When the energy storage unit serves as an energy supply unit, the carbon attribute data block corresponding to the target discharge power of the energy storage unit is extracted from the head of the carbon accounting queue according to the target discharge power of the energy storage unit to generate the carbon intensity factor of the energy storage unit.

[0017] In one possible implementation, the method further includes:

[0018] Obtain grid synchronized phasor data of target energy-related units within the zero-carbon park;

[0019] The grid synchronized phasor data is mapped to the node attributes of the corresponding nodes in the energy network topology diagram, and the energy flow digital model is updated.

[0020] In one feasible implementation, the energy flow digital model is input into a trained graph neural network, and the power distribution relationship between nodes is calculated to obtain an energy flow matrix, including:

[0021] The digital model of energy flow is input into the trained graph neural network to calculate the initial power distribution relationship between nodes. The initial power distribution relationship is corrected using the grid synchronized phasor data as physical constraints to obtain the energy flow matrix.

[0022] In one feasible implementation, the digital energy flow model is input into a trained graph neural network to calculate the initial power distribution relationship between nodes. The initial power distribution relationship is then corrected using the grid synchronized phasor data as a physical constraint to obtain an energy flow matrix, including:

[0023] Based on the node attributes of each node in the energy flow digital model and the weights of the directed edges connecting the nodes, the trained graph neural network is used to determine the initial power distribution relationship between each node;

[0024] Based on the grid synchronized phasor data of the target energy-related units, the voltage amplitude and phase angle difference between the two target nodes corresponding to the two target energy-related units are calculated. Combined with the weight of the edge between the two target nodes, the verification power distribution relationship including the power size and flow direction between the two target nodes is determined;

[0025] By comparing the target initial power distribution relationship between the two target nodes with the verification power distribution relationship, a distribution relationship correction amount for adjusting the target initial power distribution relationship between the target nodes is determined;

[0026] The target initial power distribution relationship between the two target nodes is corrected by using the distribution relationship correction amount, and all initial power distribution relationships are updated with the corrected target initial power distribution relationship to obtain the energy flow matrix.

[0027] In one feasible implementation, the carbon intensity factor of each energy supply unit is converted into a source carbon intensity vector. Each source carbon intensity vector is assigned to an energy consumption unit through an energy flow matrix. The carbon footprint value of the energy consumption unit is calculated based on the real-time power data of the energy consumption unit, including:

[0028] Arrange the carbon intensity factor of each energy supply unit according to the order of the row dimension in the energy flow matrix to form the source-end carbon intensity vector;

[0029] Perform matrix multiplication on the source-end carbon intensity vector and the energy flow matrix to obtain the energy-consuming unit carbon attribute vector. Each element of the energy-consuming unit carbon attribute vector represents the unit power carbon attribute value obtained by allocating the corresponding energy-consuming unit in the energy flow digital model.

[0030] The carbon footprint value of the energy consuming unit is obtained by performing a scalar multiplication operation on the active power component in the real-time power data of the energy consuming unit and the value of the corresponding element in the carbon attribute vector of the energy consuming unit.

[0031] In a second aspect, the present application provides a zero-carbon park full life cycle carbon footprint tracking and accounting system, which is applicable to zero-carbon parks powered by multi-energy coupling. The system includes:

[0032] An acquisition module is used to obtain spatial topological data of energy-related units in the zero-carbon park, real-time power data of energy-related units, and the carbon intensity factor of each energy supply unit. Energy-related units include at least one energy supply unit and at least one energy consumption unit. The spatial topological data includes physical parameters of physical lines between energy-related units.

[0033] A construction module is used to define energy-related units as nodes, physical lines connecting nodes as directed edges, and physical parameters of physical lines as weights of directed edges based on spatial topological data to construct an energy network topology graph;

[0034] A generation module is used to map the real-time power data to the node attributes of the corresponding nodes in the energy network topology diagram, and generate an energy flow digital model that represents the energy flow status of the zero-carbon park;

[0035] The generation module is also used to input the digital energy flow model into the trained graph neural network. By calculating the power distribution relationship between nodes, the energy flow matrix is ​​obtained. The row dimension of the energy flow matrix corresponds to the number of energy supply units, the column dimension corresponds to the number of energy application units, and the matrix elements represent the power distribution ratio coefficient.

[0036] The calculation module is used to convert the carbon intensity factor of each energy supply unit into a source-end carbon intensity vector, distribute each source-end carbon intensity vector to the energy-consuming unit through the energy flow matrix, and calculate the carbon footprint value of the energy-consuming unit based on the real-time power data of the energy-consuming unit.

[0037] In a third aspect, the present application provides an electronic device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement a method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle as in any one of the embodiments of the first aspect.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, a method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle is implemented as in any one of the embodiments of the first aspect.

[0039] The present application implements a method, system, device and computer storage medium for tracking and calculating the carbon footprint of a zero-carbon park throughout its entire life cycle. By constructing a weighted energy network topology diagram, the physical connection relationship of a multi-energy coupled power grid is accurately modeled, and a dynamic energy flow digital model is generated in combination with real-time power data to accurately simulate the energy transmission path in a deep hybrid scenario of photovoltaic, energy storage and city power. The graph neural network is further used to solve the nonlinear power distribution relationship between nodes to generate an energy flow matrix, and the dynamic power distribution ratio from the energy supply unit to the energy consumption unit is accurately quantified. Based on this ratio, the real-time carbon intensity factor is losslessly transmitted to the terminal through matrix operations, solving the problem of carbon footprint accounting distortion caused by the inability of existing technologies to track hybrid power transmission and distribution paths, and realizing high-precision dynamic traceability and accounting of terminal-level carbon footprint in the complex power grid scenario of a zero-carbon park.

[0040] Furthermore, by acquiring high-precision physical measurements from the grid's synchronized phasor data, a definitive physical verification benchmark is provided for model calculations. This physical measurement is first used to calculate the actual power flow and magnitude along the critical path. This is then used as a basis for quantitative correction of the initial distribution relationships derived from the graph neural network, ensuring that the resulting energy flow matrix is ​​consistent with the physical operating state of the grid. Therefore, by introducing strong physical constraints, the accuracy of end-user carbon footprint tracking and accounting is further enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 This is a flow chart of a method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle, provided by one embodiment of the present application;

[0043] Figure 2 1 is a flow chart of a method for determining the carbon intensity factor of an energy storage unit provided by one embodiment of the present application;

[0044] Figure 3 This is a flow chart of a method for generating an energy flow matrix provided by one embodiment of the present application;

[0045] Figure 4 This is a schematic diagram of the structure of a zero-carbon park full life cycle carbon footprint tracking and accounting system provided by an embodiment of the present application;

[0046] Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0047] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0048] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0049] However, when existing technologies are applied to modern zero-carbon parks where multiple energy sources such as photovoltaics and energy storage are deeply coupled with the public power grid, the inability to track the specific flow and distribution ratio of the mixed electricity on each transmission and distribution path within the park's internal power grid leads to insufficient accuracy in the carbon footprint accounting results for end users. In particular, it is impossible to distinguish the differences in the proportion of low-carbon electricity consumed by different electricity terminals, resulting in insufficient fairness and accuracy in the accounting results, which in turn makes it difficult to implement differentiated carbon management and incentive strategies. Therefore, the existing technical methods have the technical problem of being unable to accurately track and calculate the carbon footprint of end users in zero-carbon parks.

[0050] In order to solve the problems of the prior art, the embodiments of the present application provide a method, system, device and computer storage medium for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle. The following first introduces the method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle provided by the embodiments of the present application.

[0051] Figure 1 The flowchart of the carbon footprint tracking and accounting method for the zero-carbon park throughout its life cycle provided by one embodiment of the present application is shown. This method is applicable to zero-carbon parks powered by multi-energy coupling, such as Figure 1 As shown, the method includes steps S110 to S150.

[0052] S110: Obtain spatial topology data of energy-related units in the zero-carbon park, real-time power data of energy-related units, and carbon intensity factors of each energy supply unit. The energy-related units include at least one energy supply unit and at least one energy consumption unit. The spatial topology data includes physical parameters of physical lines between energy-related units.

[0053] A zero-carbon park powered by multi-energy coupling refers to a specific functional area within a specific geographic area that integrates multiple energy supply methods and coordinates power supply through an internal power grid, aiming to achieve net-zero carbon emissions. Energy units are the collective term for all physical entities within the park related to energy generation, transmission, conversion, storage, and consumption. They are the fundamental elements of the energy network and can include photovoltaic arrays, energy storage power stations, park substations, distribution boxes at all levels, electric vehicle charging stations, and buildings. Energy supply units and energy consumption units dynamically divide the functional roles of energy units at specific moments. Energy supply units are energy units that serve as energy sources and output power to the network. These can be photovoltaic power generation units, energy storage units in a discharged state, or public grid units. Energy consumption units are energy units that are the final link in energy consumption. These can be buildings, production equipment, charging stations, and energy storage units in a charged state.

[0054] Spatial topology data refers to a data set that describes the position of each energy-related unit in three-dimensional space and its physical connection relationship. The physical parameters it contains refer to the inherent physical properties of the connecting line, which can be the material, length, wire diameter and theoretical impedance value of the cable. Real-time power data refers to the electric energy operation status data collected in real time by sensors at each energy-related unit, which can be active power, reactive power, voltage, current and the charge and discharge status identification for the energy storage unit. The carbon intensity factor is a quantitative indicator used to characterize the carbon emissions contained in a unit of electric energy. For photovoltaic power generation units, the carbon intensity factor is a fixed value of zero or close to zero. For public grid units, the carbon intensity factor changes in real time. For energy storage units, the carbon intensity factor when it is an energy supply unit is dynamically determined by the source of its historical charging power.

[0055] Spatial topology data can be acquired by analyzing Building Information Model (BIM) data or Geographic Information System (GIS) data from the park's construction period, combined with on-site surveys and engineering drawings. Data processing extracts the precise coordinates of all energy-related units and the physical parameters of their connecting cables. Real-time power data acquisition relies on smart meters, power sensors, or microgrid energy management systems deployed at each energy-related unit within the park. These devices continuously upload collected power operation data streams to a data processing platform via Industrial Internet of Things (IIoT) communication protocols at a preset frequency, such as once per minute. Carbon intensity factors can be obtained in a variety of ways. The carbon intensity factor for public grid units is obtained by calling a real-time application programming interface (API) published by an external authority or power grid company, while the carbon intensity factor for energy supply units within the park, such as photovoltaic power generation units, is preset in the system based on their technology type. In some specific implementations, to achieve higher-precision power allocation relationship correction, synchronized phasor data from the grid deployed at key target energy-related units can also be acquired simultaneously. Ultimately, these three types of data are integrated as input for subsequent steps, laying the foundation for building a dynamic and accurate energy network model.

[0056] First, the location information of all energy-related units, such as photovoltaic arrays, energy storage plants, and buildings, is extracted from the zero-carbon park's building information model. The physical parameters of the physical lines connecting these units, such as cable material, length, and theoretical impedance, are also extracted. This information together constitutes the spatial topology data of the zero-carbon park. Smart meters and power sensors deployed at each energy-related unit upload their collected operating status information every minute via the Industrial Internet of Things communication protocol. This information includes active and reactive power information for each energy-related unit. For energy-related units that serve as energy storage units, the charge and discharge status indicators are also required. These uploaded data streams together form real-time power data. Simultaneously, the carbon intensity factor of the public grid unit serving as the energy supply unit is obtained from relevant agencies. For power supply units such as photovoltaic power generation units, their carbon intensity factors are pre-set based on their zero-emission technology type. For an energy storage unit, its carbon intensity factor when acting as an energy supply unit is dynamically determined by the composition of its historical charging power sources and the corresponding carbon intensity factor. For example, based on the proportion of electricity absorbed from the photovoltaic power generation unit and the public grid unit during the charging period of the energy storage unit, the carbon intensity factors of these two energy supply units are weighted averaged and calculated. The result is the carbon intensity factor of the energy storage unit during this discharge.

[0057] For example, a zero-carbon smart industrial park features a 5MW rooftop photovoltaic power generation system and a 2MW / 4MWh containerized lithium-ion battery energy storage power station, connected to the municipal public grid via a dedicated 10kV line. Key energy-related components within the park include the photovoltaic power generation system's grid-connected inverter, the energy storage station's bidirectional converter (PCS), the park's 10kV main substation, the power distribution room in Building A, the power distribution cabinet in the production workshop in Building B, and three 120kW DC fast chargers in the parking lot.

[0058] First, by parsing and calling the pre-imported completed BIM 3D model of the park, the geographical coordinates of all the above-mentioned energy-related units in the park and the models of all power cables connecting them were obtained. Based on the cable model and laying length, the theoretical impedance value was calculated to obtain a complete set of spatial topology data.

[0059] At the same time, multifunctional smart energy meters and sensor arrays deployed at key measurement points in each of the aforementioned energy-related units transmit real-time power data measured by each meter to the data server of the park's energy management system via the Modbus-TCP industrial Ethernet protocol once per minute. The data server receives data indicating that the active power output of the photovoltaic grid-connected inverter is 2.0 MW; the active power of the bidirectional converter PCS of the energy storage station is 0.5 MW, with its status indicated as discharged; the metering gateway at the park's main substation indicates that the active power purchased from the public grid is 1.1 MW; the active power of the main incoming line to Office Building A is 1.5 MW; the active power of the main incoming line to the production workshop in Building B is 2 MW; and the total active power of the three charging stations is 0.1 MW. The server requests and obtains the real-time carbon intensity factor of the regional power grid from the power grid data service platform, which is 0.58 kg CO2 per kilowatt-hour. Based on these real-time data, the photovoltaic power generation unit, public grid unit and energy storage power station now act as energy supply units, while the office building A, production workshop Building B and charging piles all act as energy consumption units.

[0060] S120: Based on the spatial topology data, energy-related units are defined as nodes, physical lines connecting the nodes are defined as directed edges, and physical parameters of the physical lines are defined as weights of the directed edges to construct an energy network topology map.

[0061] An energy network topology is a data model that uses graph theory to represent the physical connections of an energy system. It consists of three core elements: nodes, directed edges, and weights. A node represents an independent energy-related unit, such as a photovoltaic array or a building. A directed edge represents the physical path that connects two nodes, such as a cable running from a substation to a distribution box. Its direction indicates the primary flow of electrical energy in the design. A weight is a numerical value or set of numerical values ​​assigned to a directed edge to quantify the physical parameters of the path, such as the theoretical impedance of a cable. The weight directly reflects the physical impact on energy passing through this path.

[0062] First, for each energy-related unit in the spatial topology data, such as photovoltaic arrays, energy storage power stations, and buildings, a corresponding node is created in the data structure. Then, based on the physical line connection relationship recorded in the spatial topology data, a directed edge is established between the corresponding two nodes. The direction of the edge is determined according to the normal power flow design direction of the power grid or the master-slave relationship, for example, from the park's main substation node to the office building's power distribution room node. Finally, the physical parameters of each physical line in the spatial topology data, such as the theoretical impedance value calculated by the cable material, length, and wire diameter, are assigned as numerical values ​​to the weight attributes of the corresponding directed edges. After completing the processing of all energy-related units and physical lines, the energy network topology map reflecting the static physical characteristics of the park's energy network is constructed.

[0063] For example, each energy-related unit identified in the spatial topology data, such as the grid-connected inverter of the photovoltaic power generation system, the bidirectional converter PCS of the energy storage power station, the 10 kV main substation in the park, the power distribution room of the office building A, the power distribution cabinet of the production workshop of the building B, and the three charging piles, is first created in the data structure. A corresponding node is then created. Afterwards, a directed edge is established between the corresponding two nodes based on the physical line connection relationship recorded in the spatial topology data. For example, based on the wiring diagram information, a directed edge is established between the node of the 10 kV main substation in the park and the node of the power distribution room of the office building A. The direction of the edge is determined to be from the main substation to the power distribution room of the office building based on the design principle that electric energy flows from the main station to the substation. Similarly, a directed edge is also established between the node of the power distribution room of the office building A and one of the charging pile nodes.

[0064] Finally, the physical parameters of each physical line in the spatial topology data are assigned as numerical values ​​to the weight attributes of the corresponding directed edges. For example, the theoretical impedance of the cable between the main substation and the power distribution room in Office Building A, which is 0.05 + 0.02 ohms, is used as the weight of the directed edge connecting these two nodes. After processing all energy-related units and physical lines, the energy network topology map is constructed.

[0065] S130: Mapping the real-time power data to the node attributes of the corresponding nodes in the energy network topology diagram to generate an energy flow digital model representing the energy flow status of the zero-carbon park.

[0066] The digital energy flow model builds on the static skeleton of the energy network topology by attaching current, real-time power data to each node as a node attribute. This model not only encompasses the physical connections and line parameters of the campus energy network, but also reflects the generation, consumption, and transmission status of each energy-related unit, dynamically characterizing the true energy flow of the entire zero-carbon campus.

[0067] First, a data mapping relationship is established, establishing a one-to-one association between each data source in the acquired real-time power data stream, such as the unique identifier of a smart meter, and a specific node in the energy network topology, such as the node representing the energy-related unit where the smart meter is located. Based on this mapping relationship, the latest values ​​of each node, such as active power, reactive power, and charge / discharge status, are updated in the corresponding node's node attributes.

[0068] For example, based on the established mapping relationship, the active power value of 2.0 MW at the output of the photovoltaic grid-connected inverter is updated to the node attributes of the node representing the photovoltaic power generation system grid-connected inverter in the energy network topology diagram. The active power value of 0.5 MW and the discharge status indicator are updated to the node attributes of the node representing the energy storage power station; the active power value of 1.1 MW is updated to the node attributes of the node representing the park's main substation; and the power values ​​of 1.5 MW, 2.0 MW, and 0.1 MW are updated to the node attributes of the nodes representing Office Building A, Production Workshop Building B, and three charging stations, respectively. Ultimately, a digital energy flow model is constructed that includes the current power state of each node.

[0069] S140: Input the digital model of energy flow into the trained graph neural network, and obtain the energy flow matrix by calculating the power distribution relationship between nodes. The row dimension of the energy flow matrix corresponds to the number of energy supply units, and the column dimension corresponds to the number of energy application units. The matrix elements represent the power distribution ratio coefficient.

[0070] Graph neural networks are artificial intelligence models designed to process graph-structured data. They can learn node representations in a graph by aggregating information from neighboring nodes, effectively capturing the graph's topological structure and the complex dependencies between node features. The power allocation relationship between nodes refers to the power exchange between any two directly connected nodes, determined by the weight of their connecting edges and their respective node attributes. For example, a distribution box node, acting as an intermediate transmission node, distributes the total power it receives from the upstream main substation node according to a certain proportion based on the different line impedances connecting the downstream office building node A and the production workshop node B. All these local power exchange interactions together constitute the end-to-end power distribution relationship from all energy supply units to all energy consumption units in the entire energy network. The energy flow matrix is ​​a two-dimensional data structure that quantitatively represents power allocation relationships. The rows of the matrix correspond to all energy supply units in the park, and the columns correspond to all energy consumption units. Each element in the matrix, known as the power allocation coefficient, represents the proportion of the power generated by a specific energy supply unit that flows to a specific energy consumption unit. The coefficient ranges from 0 to 1.

[0071] A pre-built graph neural network model is trained using a large amount of historical digital energy flow model data as training samples. During training, the graph neural network learns to map the input digital energy flow model—a graph structure containing node power attributes and edge weights—to a baseline end-to-end power distribution relationship, which can be pre-calculated using power grid power flow simulation software. The trained graph neural network is then capable of inferring power distribution relationships. The latest digital energy flow model is fed into the trained graph neural network as input. Through its internal multi-layer graph convolution operations, the graph neural network iteratively calculates the local power exchange between any two directly connected nodes based on the edge weights and node attributes. Through the stacking of these multiple layers of computation, this local information is propagated and aggregated throughout the network, enabling the graph neural network to ultimately understand and calculate the end-to-end power distribution relationship between all energy supply units and all energy consumption units. This relationship is ultimately output as an energy flow matrix.

[0072] S150: Convert the carbon intensity factor of each energy supply unit into a source-end carbon intensity vector, distribute each source-end carbon intensity vector to the energy-consuming unit through the energy flow matrix, and calculate the carbon footprint value of the energy-consuming unit based on the real-time power data of the energy-consuming unit.

[0073] The source carbon intensity vector is constructed by arranging the carbon intensity factors of all energy supply units within the park at the current moment in the same order as the row dimension of the energy flow matrix. This vector collectively represents the source carbon attributes of all electricity entering the park's energy network. The carbon footprint value is a quantitative value that represents the total amount of greenhouse gas emissions directly or indirectly generated by the consumption of electricity by a specific energy-consuming unit over a specific time period. Its unit is usually kilograms of carbon dioxide equivalent.

[0074] First, the carbon intensity factor of each energy supply unit is organized into a source-end carbon intensity vector based on its corresponding row order in the energy flow matrix. This source-end carbon intensity vector is then multiplied by the energy flow matrix through a matrix multiplication operation. This weighted summation of the carbon intensities of each source is performed based on the power allocation ratio coefficient, resulting in an energy-consuming unit carbon attribute vector. Each element in this vector represents the comprehensive carbon attribute of the unit power consumed by the corresponding energy-consuming unit. Finally, each element in this energy-consuming unit carbon attribute vector is multiplied by the active power component in the corresponding energy-consuming unit's real-time power data and the accounting time period to calculate the carbon footprint value of the energy-consuming unit during that time period.

[0075] This embodiment constructs a weighted energy network topology diagram to accurately model the physical connection relationship of the multi-energy coupled power grid, combines real-time power data to generate a dynamic energy flow digital model, and accurately simulates the energy transmission path in the deep hybrid scenario of photovoltaic, energy storage and city power; further uses the graph neural network to solve the nonlinear power distribution relationship between nodes to generate an energy flow matrix, and accurately quantify the dynamic power distribution ratio from the energy supply unit to the energy consumption unit; based on this ratio, the real-time carbon intensity factor is losslessly transmitted to the terminal through matrix operation, solving the problem of carbon footprint accounting distortion caused by the inability to track the hybrid power transmission and distribution path in the existing technology, and realizing high-precision dynamic traceability and accounting of terminal-level carbon footprint in the complex power grid scenario of the zero-carbon park.

[0076] In one feasible embodiment, the energy supply unit includes a photovoltaic power generation unit, an energy storage unit, and a public grid unit.

[0077] Photovoltaic power generation units refer to power generation facilities that directly convert solar energy into electricity. Within the park, these can be rooftop photovoltaic arrays or photovoltaic carports, and the electricity they output is generally considered zero-carbon or low-carbon energy. Energy storage units refer to devices or systems that can store electrical energy and release it again when needed. Within the park, these can be containerized lithium battery energy storage power stations, which can serve as both energy consumption units during charging and energy supply units during discharge. Public grid units refer to the gateway points where the park connects to the external large power grid. The park can purchase electricity from the external grid to supplement the shortfall in local power generation. The carbon intensity factor of this electricity is determined by the overall power generation structure of the regional power grid.

[0078] Figure 2 FIG1 shows a flow chart of a method for determining the carbon intensity factor of an energy storage unit provided by an embodiment of the present application. Figure 2 As shown, the method includes steps S210 to S230.

[0079] In one possible implementation, the method further includes:

[0080] S210: When the charge and discharge state corresponding to the real-time power data of the energy storage unit is a charging state, the energy storage unit is determined as an energy-consuming unit.

[0081] Detect the real-time power data of the energy storage unit and check the charge and discharge status flag contained in the data. If the flag clearly indicates that the current state is charging, the energy storage unit is determined to be an energy-consuming unit in the current calculation cycle.

[0082] S220: Calculate the source-end carbon intensity vector assigned to the energy storage unit based on the energy flow matrix, and calculate the charging capacity of the energy storage unit and the corresponding carbon attribute data block based on the real-time power data of the energy storage unit.

[0083] The carbon attribute data block is a structured data unit used to record the amount of charging power in a batch and its corresponding calculated comprehensive carbon intensity value. The comprehensive carbon intensity value reflects the mixed ratio of different energy supply units in the batch of power.

[0084] From this matrix, a column vector corresponding to the energy storage unit is extracted. Each element in this column vector, known as the power allocation coefficient, represents the proportion of the power charged to the energy storage unit that comes from each energy supply unit. This column vector is dot-producted with the constructed source-end carbon intensity vector, performing a weighted summation of the carbon intensity factors of each energy supply unit to obtain a carbon intensity value representing the comprehensive attributes of the batch of charging power. Simultaneously, the charging capacity for that cycle is calculated based on the active power component in the energy storage unit's real-time power data and the calculated time period. Ultimately, the calculated charging capacity and the comprehensive carbon intensity value are combined to form a new carbon attribute data block.

[0085] S230: Establish a carbon accounting queue based on the first-in-first-out principle for the energy storage unit, and store the carbon attribute data block of the energy storage unit at the end of the carbon accounting queue in chronological order, so that when the energy storage unit serves as an energy supply unit, the carbon attribute data block corresponding to the target discharge power of the energy storage unit is extracted from the head of the carbon accounting queue to generate the carbon intensity factor of the energy storage unit.

[0086] A carbon accounting queue is a digital data queue established for each energy storage unit, following a first-in, first-out principle. It stores a series of carbon attribute data blocks in chronological order, acting like a digital ledger, recording the history of every charge of the energy storage unit. The target discharge capacity refers to the total amount of electricity that the energy storage unit plans to or actually releases to the grid during the current calculation cycle.

[0087] A dedicated carbon accounting queue is created for each energy storage unit in the zero-carbon park. Whenever a new carbon attribute data block is generated, the data block is added to the end of the carbon accounting queue of the corresponding energy storage unit. This storage process is ongoing, and the queue will grow as the energy storage unit is continuously charged. When it is necessary to determine the carbon intensity factor of an energy storage unit in a discharging state, it will extract one or more carbon attribute data blocks in sequence from the head of its carbon accounting queue based on the target discharge power of the energy storage unit until the total power contained in the extracted carbon attribute data blocks meets or exceeds the target discharge power. Subsequently, the carbon intensity of these extracted data blocks is weighted averaged according to the proportion of their respective power to the target discharge power, and finally a carbon intensity factor of the energy storage unit is generated that can accurately reflect the true carbon attributes of the discharged power.

[0088] For example, at a certain point in the construction of a zero-carbon smart industrial park, photovoltaic power generation is sufficient, and the energy storage station begins charging at a charging capacity of 1 MW. By monitoring the energy storage station's real-time power data, it is found that its charge and discharge status is marked as charging. Therefore, for the current calculation cycle, the energy storage unit is assigned the role of energy consumer. The latest energy flow matrix is ​​retrieved, and the column vector corresponding to the energy storage unit is extracted. This vector shows that 80% of the electricity charging the energy storage station comes from zero-carbon photovoltaic units and 20% from the public grid with a carbon intensity factor of 0.58. The calculated carbon intensity of this charging power is 0.116 kg of CO2 per kilowatt-hour. Furthermore, based on the energy storage unit's active power of 1000 kW and a calculation period of 0.1 hours, the charging capacity for this period is calculated to be 100 kilowatt-hours. Finally, the calculated charging capacity and the comprehensive carbon intensity value are combined to form a new carbon attribute data block.

[0089] At the same time, a dedicated carbon accounting queue is created for the energy storage power station, and the new carbon attribute data block generated in the previous step is added to the end of the queue. During the evening peak, assume that the target discharge power of the energy storage power station is 50 kWh to support the park load. Data is extracted from the head of its carbon accounting queue, and a carbon attribute data block with a power of 100 kWh and a carbon intensity of 0.116 is stored at 2 pm. Because the power of this data block is greater than the target discharge power, 0.116 is directly used as the carbon intensity factor of the energy storage unit for this discharge, and the data block is updated, changing its remaining power to 50 kWh for use in the next discharge. This carbon intensity factor of 0.116 will be used as the carbon intensity input value of the energy storage unit when constructing the source-end carbon intensity vector.

[0090] In one possible implementation, the method further includes:

[0091] Obtain grid synchronized phasor data of target energy-related units within the zero-carbon park.

[0092] Target energy-related units are those that serve as important power grid hubs within the park or have a significant impact on grid stability. These can include the park's main substation, a large energy storage power station connection point, or a major feeder outlet. Grid synchronized phasor data refers to grid operation data with GPS timestamps. It contains voltage and current amplitudes and corresponding phase angles. By comparing phase angles at different locations, the direction and magnitude of power flow can be determined.

[0093] Power grid synchronized phasor data is collected using phasor measurement units (PMUs) deployed at target energy-related units. The PMUs sample voltage and current waveforms at high speed and timestamp each measurement using an integrated GPS module. The collected data streams, including voltage amplitude, voltage phase angle, current amplitude, and current phase angle, constitute the synchronized power grid data.

[0094] The grid synchronized phasor data is mapped to the node attributes of the corresponding nodes in the energy network topology diagram, and the energy flow digital model is updated.

[0095] Based on the established mapping relationship, the latest grid synchronized phasor data, such as voltage amplitude and voltage phase angle, is obtained as a new set of values ​​and updated to the node attributes of the corresponding target node, generating a digital energy flow model that not only includes the power size of each node, but also phase angle information at key nodes.

[0096] For example, phasor measurement units (PMUs) were installed at two target energy-related nodes: the 10kV main substation node and the power distribution room node of Office Building A, both key hubs in the park. While acquiring regular real-time power data, the PMUs deployed at the main substation and the power distribution room of Office Building A simultaneously collected synchronized phasor data for the power grid at that moment. For example, the voltage amplitude at the main substation node was 10.1kV and the phase angle was 0 degrees, while the voltage amplitude at the power distribution room node of Office Building A was 10.05kV and the phase angle was negative 0.5 degrees. Subsequently, based on the established mapping relationship, these synchronized phasor data, including voltage amplitude and phase angle, were used as new node attributes and updated to the corresponding target nodes in the digital energy flow model, thereby generating a physically constrained digital energy flow model.

[0097] In one feasible implementation, in step S140, the energy flow digital model is input into a trained graph neural network, and the power distribution relationship between nodes is calculated to obtain an energy flow matrix, including:

[0098] The digital model of energy flow is input into the trained graph neural network to calculate the initial power distribution relationship between nodes. The initial power distribution relationship is corrected using the grid synchronized phasor data as physical constraints to obtain the energy flow matrix.

[0099] The initial power distribution relationship refers to the preliminary power distribution relationship network of all nodes directly deduced from the trained graph neural network. It includes the end-to-end power distribution relationship from the energy supply unit to the energy consumption unit, as well as the detailed power distribution relationship when the energy flows through each intermediate transmission node, such as substations and distribution boxes. Physical constraints refer to a set of deterministic relationships extracted from the grid's synchronized phasor data that can represent the physical laws of real grid operation. For example, the magnitude and direction of the power flow between two target nodes equipped with PMUs can be calculated as a strong physical constraint condition using the basic physical formulas of grid power flow, based on the voltage amplitude and phase angle difference between the two nodes and the impedance value of the line between them.

[0100] The system extracts synchronized phasor data from the target energy-related units deployed with PMUs. Based on the physical formulas for power flow calculation, it calculates the actual power flow values ​​between these key nodes and uses these values ​​as physical constraints. The portion of the initial power allocation relationship corresponding to these key nodes is compared with the calculated physical constraints. Based on the comparison results, the entire initial power allocation relationship network is adjusted to ensure that the adjusted network complies with the physical constraints at the key nodes.

[0101] Figure 3 FIG. 1 shows a flow chart of a method for generating an energy flow matrix according to an embodiment of the present application. Figure 3As shown, the method includes steps S310 to S340.

[0102] In one feasible implementation, the digital energy flow model is input into a trained graph neural network to calculate the initial power distribution relationship between nodes. The initial power distribution relationship is then corrected using the grid synchronized phasor data as a physical constraint to obtain an energy flow matrix, including:

[0103] S310: Based on the node attributes of each node in the energy flow digital model and the weights of the directed edges connecting the nodes, the trained graph neural network is used to determine the initial power distribution relationship between each node.

[0104] A pre-built and trained graph neural network can be an encoder consisting of multiple graph convolutional layers and a decoder for predicting relationships. Graph convolutional layers, such as graph convolutional networks (GCNs) or graph attention networks (GATs), aggregate information about neighboring nodes to update the feature representation of the central node. The generated digital model of energy flow, a graph structure containing the real-time power attributes of all nodes and the weights of the connecting edges, is input into the encoder of the graph neural network. Through its multi-layer graph convolution operations, the encoder iteratively transfers and aggregates information between connected nodes, learning layer by layer and generating a high-dimensional feature vector for each node. This vector encodes the node's state, its location in the network topology, and its surroundings. The decoder then receives the high-dimensional feature vectors of all nodes and processes any pair of nodes, ultimately outputting an initial power allocation relationship that describes the power exchange between any two nodes in the network.

[0105] For example, the digital energy flow model is input into a trained graph neural network whose encoder consists of a three-layer graph attention network (GAT) layer and whose decoder is a simple multi-layer perceptron. At the beginning of inference, the initial feature vector of each node in the digital energy flow model, such as the node of Office Building A, consists of information such as its own real-time power value of 1.5 megawatts. In the first layer of GAT operation, the node of Office Building A selectively aggregates information from its direct upstream, the 10 kV main substation node of the park, based on the attention weight. After three layers of information aggregation and updating, the node of Office Building A generates a new high-dimensional feature vector. This vector not only contains its own power information, but also integrates the influence of global sources such as photovoltaics, energy storage, and the public power grid, as well as the network topology.

[0106] Finally, the decoder receives the high-dimensional feature vectors of all nodes, including the node in Office Building A, and calculates the power exchange relationships between them, forming a complete initial power allocation relationship. This relationship contains detailed information about the power flow between all nodes in the network. For example, the allocation result may be that of the total power flowing from the grid-connected inverter node of the photovoltaic power generation system, 1.2 MW flows to the 10 kV main substation node of the park; of the total power flowing from the 10 kV main substation node of the park, 0.75 MW flows to the power distribution room node of Office Building A, and 1.5 MW flows to the power distribution cabinet node of the production workshop of Building B; and of the total power flowing from the power distribution room node of Office Building A, 0.08 MW flows to a connected charging station node.

[0107] In one embodiment, before inputting the digital energy flow model into the trained graph neural network in step S140 to determine the initial power distribution relationship between each node, the method further includes: obtaining a training sample set containing a large amount of historical data, wherein each training sample in the training sample set includes a digital energy flow model at a historical moment and the corresponding end-to-end power distribution relationship as a true label. The end-to-end power distribution relationship as a true label is pre-calculated using power grid flow simulation software based on the park operation data at that historical moment. In each training iteration, the digital energy flow model in a training sample is input into the graph neural network to obtain a predicted power distribution relationship derived from the model. Subsequently, by comparing this predicted power distribution relationship with the actual upgrade configuration information label corresponding to the sample, a loss function value is calculated to measure the difference between the two. If the loss function value does not meet the preset training termination conditions, such as reaching a minimum threshold or completing a specified number of iterations, the model parameters within the graph neural network, such as the weight coefficients of the graph convolution layer, are adjusted through a backpropagation algorithm to reduce the loss function value. This process will be repeated until the prediction results of the graph neural network are highly consistent with the true labels, the training stop conditions are met, and finally a trained graph neural network is obtained.

[0108] S320: Calculate the voltage amplitude and phase angle difference between the two target nodes corresponding to the two target energy-related units based on the grid synchronized phasor data of the target energy-related units, and determine the verification power distribution relationship including the power size and flow direction between the two target nodes in combination with the weight of the edge between the two target nodes.

[0109] Verifying the power allocation relationship is a power allocation relationship directly calculated through physical formulas. It refers to the specific information of the power flow size and direction between two target nodes equipped with PMUs. It is used as a benchmark to verify and correct the power allocation relationship deduced by the model.

[0110] From the digital energy flow model, the grid synchronized phasor data for the nodes of the target energy-related unit is extracted. This includes the voltage amplitude and phase angle of the head node, as well as the voltage amplitude and phase angle of the tail node. First, the voltage amplitude and phase angle differences between the two target nodes are calculated. Then, the weights of the directed edges connecting the two target nodes are combined, representing the theoretical impedance of the line. These parameters are substituted into the power transmission equation commonly used in power systems. This calculation yields a verified power distribution relationship between the two target nodes, reflecting both the power magnitude and flow direction.

[0111] For example, it is necessary to calculate the verification power distribution relationship between the main substation node (head end, marked as i) and the power distribution room node of office building A (end end, marked as j). First, the active power value is calculated using the line active power transmission equation shown in formula (1):

[0112] (1)

[0113] in, represents the active power flowing from node i to node j, and denote the voltage amplitudes at nodes i and j, respectively. and denote the voltage phase angles at nodes i and j, respectively. Represents the reactance value of the line connecting node i and node j.

[0114] The following parameters are extracted from the energy flow digital model: the voltage amplitude at the head end is 10.1 kV, and the phase angle of the voltage at the first end is is 0 degrees; terminal voltage amplitude is 10.05 kV, and the terminal voltage phase angle is minus 0.5 degrees; the reactance value in the line impedance connecting the two nodes Substituting these values ​​into the above formula, we can get the active power flowing from the main substation node to the office building A node. The value is approximately 0.8 MW. Since the phase angle at the head end is 0 degrees ahead of the phase angle at the tail end by -0.5 degrees, the power flow is determined to be from the main substation to Office Building A. Therefore, the final verification power distribution relationship is that the active power flowing from the main substation node to the Office Building A node is 0.8 MW.

[0115] S330: Determine a distribution relationship correction value for adjusting the target initial power distribution relationship between the target nodes by comparing the target initial power distribution relationship between the two target nodes with the verification power distribution relationship.

[0116] The target initial power allocation relationship refers to the initial power allocation relationship between the two target nodes in the generated initial power allocation relationship, i.e., the model's preliminary prediction of the power exchange between these two nodes. The allocation relationship correction value represents the difference between the target initial power allocation relationship and the verification power allocation relationship. The correction value includes the size and direction of the adjustment to the initial allocation relationship to make the model prediction consistent with physical reality.

[0117] A target initial power allocation relationship corresponding to the two target nodes is extracted from the initial power allocation relationship. This target initial power allocation relationship is numerically compared with a verification power allocation relationship used as a physical check. For example, the value of the target initial power allocation relationship can be subtracted from the value of the verification power allocation relationship. The result of this operation, i.e., the difference between the two, is used as an allocation relationship correction value for adjusting the target initial power allocation relationship between the target nodes.

[0118] First, from the generated initial power distribution relationship containing the power flow between all nodes, the target initial power distribution relationship corresponding to the main substation node and the office building A node is extracted, that is, the active power flowing from the main substation node to the office building A node predicted by the model, which has a value of 0.75 MW. Subsequently, this target initial power distribution relationship is numerically compared with the verification power distribution relationship calculated as a physical verification, the value of which is 0.8 MW. Specifically, the value of the target initial power distribution relationship is subtracted from the value of the verification power distribution relationship, that is, a subtraction operation of 0.8 MW minus 0.75 MW is performed. The result of the operation, 0.05 MW, is determined as the distribution relationship correction value for this calculation. This distribution relationship correction value clearly indicates that the initially predicted power distribution value needs to be increased by 0.05 MW, which will be used to guide the global correction of the entire power distribution network.

[0119] In one embodiment, the model may incorrectly predict the reverse flow of power. For example, the model predicts that the active power flowing from the office building node to the main substation node is 0.1 MW, that is, the value of the target initial power distribution relationship is negative 0.1 MW. However, the verification power distribution relationship calculated based on the PMU data is 0.1 MW, indicating that the actual flow direction of power is from the main substation node to the office building node in the positive direction. At this time, the value of the verification power distribution relationship is also subtracted from the value of the target initial power distribution relationship, that is, the subtraction operation of 0.1 MW minus negative 0.1 MW is performed, and the distribution relationship correction amount is 0.2 MW. The correction amount not only indicates the adjustment of the numerical value, but its positive sign more critically indicates that the initially predicted power flow direction needs to be reversed. The calculated distribution relationship correction amount will be used to guide the global correction of the entire power distribution network.

[0120] S340: Using the distribution relationship correction amount, correcting the target initial power distribution relationship between the two target nodes, and using the corrected target initial power distribution relationship to update all initial power distribution relationships, thereby obtaining an energy flow matrix.

[0121] First, a distribution correction is applied to the target initial power distribution relationship. For example, through addition, the power distribution relationship between the two target nodes is directly corrected to be identical to the verified power distribution relationship. Next, this locally accurately corrected power distribution relationship serves as a new anchor point or hard constraint, and a global update of the initial power distribution relationship network is performed using the Constrained Least Squares (CLS) algorithm. The algorithm aims to minimize the overall deviation between the updated distribution relationship and the initial distribution relationship while satisfying two core constraints: the first constraint is that the updated relationship must be strictly equal to the corrected value between the target nodes; the second constraint is that the sum of the power inputs of all nodes in the network must equal the sum of their outputs, thus satisfying the power balance law. After the entire initial power distribution relationship network is optimized and updated, the end-to-end relationships from all energy supply units to all energy consumption units are extracted and organized into the final output energy flow matrix.

[0122] For example, the distribution relationship correction value is 0.05 MW. The distribution relationship correction value is applied to the target initial power distribution relationship. Through the addition operation, the power distribution relationship predicted by the model from the main substation node to the office building node of Building A is directly corrected from the initial 0.75 MW to 0.8 MW, making it completely consistent with the verification power distribution relationship.

[0123] Next, the initial power allocation network is globally updated using a constrained least squares algorithm, using the hard constraint that the active power flowing from the main substation to Office Building A must be 0.8 MW. This method's optimization objective is to minimize deviations from the initial allocation while satisfying two core constraints. The first constraint is that the power flowing from the main substation to Office Building A must be 0.8 MW; the second constraint is that the total input power of all nodes in the network, such as the main substation, must equal the total output power. To meet these constraints, the method may reduce the initial 1.5 MW of power flowing from the main substation to the power distribution cabinet in Building B by 0.05 MW, adjusting it to 1.45 MW. After optimizing and updating the entire initial power allocation network, the end-to-end allocation ratios between the three energy supply units—PV, energy storage, and the grid—and the three energy consumption units—Building A, Workshop B, and charging stations—are extracted, and an energy flow matrix is ​​constructed.

[0124] For example, the energy flow matrix is ​​shown in Table 1. The rows of the matrix correspond to three energy supply units: a photovoltaic power generation unit, an energy storage power station, and a public grid unit; the columns correspond to three energy consumption units: Office Building A, Production Workshop Building B, and three charging stations. Each element in the matrix, or the power allocation coefficient, represents the proportion of the output power of the corresponding energy supply unit that flows to the corresponding energy consumption unit. Taking the element in the first row and first column as an example, the proportional coefficient of 0.5333 indicates that of the total 1.5 MW of electricity consumed by Office Building A, 53.33%, or 0.8 MW, comes from the clean photovoltaic power generation unit.

[0125]

[0126] Table 1

[0127] This embodiment uses high-precision physical measurements of grid synchronized phasor data to provide a definitive physical calibration benchmark for model calculations. This physical measurement is first used to calculate the actual power flow and magnitude along the critical path. This is then used as a basis for quantitative correction of the initial distribution relationships derived by the graph neural network, ensuring that the resulting energy flow matrix is ​​consistent with the physical operating state of the grid. Therefore, by introducing strong physical constraints, the accuracy of end-user carbon footprint tracking and accounting is further enhanced.

[0128] In one possible implementation, step S150: converting the carbon intensity factor of each energy supply unit into a source-end carbon intensity vector, assigning each source-end carbon intensity vector to an energy consumption unit through an energy flow matrix, and calculating the carbon footprint value of the energy consumption unit based on the real-time power data of the energy consumption unit, including:

[0129] Arrange the carbon intensity factor of each energy supply unit according to the order of the row dimension in the energy flow matrix to form the source-end carbon intensity vector.

[0130] First, determine the order of the energy supply units corresponding to the row dimension of the energy flow matrix. For example, the first row is photovoltaic power generation units, the second row is energy storage units, and the third row is public grid units. Next, arrange the carbon intensity factors of each energy supply unit at the current moment in this order to form a source-end carbon intensity vector. For example, if the carbon intensity factors of photovoltaic power generation, energy storage, and the grid are 0, 0.232, and 0.58, respectively, the resulting source-end carbon intensity vector is [0, 0.232, 0.58].

[0131] Perform matrix multiplication on the source-end carbon intensity vector and the energy flow matrix to obtain the energy-consuming unit carbon attribute vector. Each element of the energy-consuming unit carbon attribute vector represents the unit power carbon attribute value obtained by allocating the corresponding energy-consuming unit in the energy flow digital model.

[0132] The dimension of the energy-consuming unit carbon attribute vector is the same as the column dimension of the energy flow matrix, corresponding to the number of energy-consuming units. Each element in this vector represents the weighted average of the carbon emissions from all energy-supplying units per unit of power consumed by the corresponding energy-consuming unit. This value can also be considered the unit's carbon attribute value per unit of power.

[0133] Multiply the source carbon intensity vector by the energy flow matrix. For each energy-consuming unit (each column of the matrix), perform a dot product of the corresponding power allocation coefficient set (column vector) with the source carbon intensity vector. For example, perform a dot product of the vector [0, 0.232, 0.58] with the column vector [0.5333, 0.2000, 0.2667] representing Office Building A. This weighted sum of the carbon intensities of each source yields the unit power carbon attribute value for Office Building A. After the calculation is complete for all energy-consuming units, these unit power carbon attribute values ​​together constitute an energy unit carbon attribute vector.

[0134] The carbon footprint value of the energy consuming unit is obtained by performing a scalar multiplication operation on the active power component in the real-time power data of the energy consuming unit and the value of the corresponding element in the carbon attribute vector of the energy consuming unit.

[0135] Each element in the generated energy unit carbon attribute vector is traversed. For each element, the corresponding energy unit is found. The active power component of the energy unit during the current accounting period is extracted from the real-time power data. This active power component is then multiplied by the accounting time period to obtain the total electricity consumption. This total electricity consumption is then multiplied by the corresponding unit power carbon attribute value. For example, if the unit power carbon attribute value of Office Building A is 0.201086, its active power is 1500 kilowatts, and the accounting period is 1 hour, the final carbon footprint value is 1500 times 1 times 0.201086. The result of this calculation is the final carbon footprint value of the energy unit during this time period. After completing the calculation for all energy units, a dynamically updated end-user carbon footprint list is obtained.

[0136] For example, first, based on the row order of the energy flow matrix (photovoltaic power generation units in the first row, energy storage power stations in the second row, and public grid units in the third row), the corresponding carbon intensity factors are arranged into a source carbon intensity vector with the value [0, 0.232, 0.58]. Next, this source carbon intensity vector is matrix multiplied with the energy flow matrix. Taking Office Building A as an example, the dot product of its corresponding column vector [0.5333, 0.2000, 0.2667] with the source carbon intensity vector yields a carbon attribute value per unit power of 0.201086 kg CO2 per kilowatt-hour for Office Building A. Similarly, the carbon attribute values ​​per unit power are calculated for the production workshop in Building B and the three charging stations, forming a single energy unit carbon attribute vector.

[0137] Afterwards, the final carbon footprint value is calculated based on the carbon attribute vector of this energy unit. For office building A, its active power is extracted from the real-time power data as 1500 kilowatts, and the calculation period is set to 1 hour, and its total electricity consumption is 1500 kWh. By multiplying the total electricity consumption by the unit power carbon attribute value of office building A, 0.201086, the carbon footprint value of office building A in that hour is 301.629 kg of carbon dioxide. For the three charging piles, their unit power carbon attribute value is 0, so regardless of their electricity consumption, their carbon footprint value is 0. By performing the same calculation on all energy units, the accurate tracking and accounting of the carbon footprint of all end users in the park within that hour is completed, and a complete list is obtained.

[0138] Based on the same concept, the present application embodiment provides a zero-carbon park full life cycle carbon footprint tracking and accounting system. Figure 4 The zero-carbon park full life cycle carbon footprint tracking and accounting system provided in the embodiment of the present application is described in detail.

[0139] Figure 4 This is a structural block diagram of a zero-carbon park full life cycle carbon footprint tracking and accounting system shown in an embodiment of the present application.

[0140] like Figure 4 As shown, the zero-carbon park full life cycle carbon footprint tracking and accounting system is applicable to zero-carbon parks powered by multi-energy coupling. The system can include:

[0141] Acquisition module 410 is used to obtain spatial topology data of energy-related units in the zero-carbon park, real-time power data of energy-related units, and carbon intensity factors of each energy supply unit. Energy-related units include at least one energy supply unit and at least one energy consumption unit. The spatial topology data includes physical parameters of physical lines between energy-related units.

[0142] A construction module 420 is configured to construct an energy network topology map based on the spatial topology data by defining energy-related units as nodes, defining physical lines connecting the nodes as directed edges, and defining physical parameters of the physical lines as weights of the directed edges;

[0143] A generation module 430 is configured to map the real-time power data to node attributes of corresponding nodes in the energy network topology diagram, and generate an energy flow digital model representing the energy flow state of the zero-carbon park;

[0144] The generation module 430 is further configured to input the digital energy flow model into the trained graph neural network and obtain an energy flow matrix by calculating the power distribution relationship between nodes. The row dimension of the energy flow matrix corresponds to the number of energy supply units, the column dimension corresponds to the number of energy consumption units, and the matrix elements represent the power distribution ratio coefficients.

[0145] The calculation module 440 is used to convert the carbon intensity factor of each energy supply unit into a source-end carbon intensity vector, distribute each source-end carbon intensity vector to the energy-consuming unit through the energy flow matrix, and calculate the carbon footprint value of the energy-consuming unit based on the real-time power data of the energy-consuming unit.

[0146] In one embodiment, the energy supply unit includes a photovoltaic power generation unit, an energy storage unit, and a public grid unit.

[0147] In one embodiment, the generation module 430 is also used to determine the energy storage unit as an energy-consuming unit when the charge and discharge state corresponding to the real-time power data of the energy storage unit is a charging state; calculate the source-end carbon intensity vector assigned to the energy storage unit according to the energy flow matrix, and calculate the charging power of the energy storage unit and the corresponding carbon attribute data block according to the real-time power data of the energy storage unit; establish a carbon accounting queue based on the first-in-first-out principle for the energy storage unit, and store the carbon attribute data block of the energy storage unit at the end of the carbon accounting queue in chronological order, so that when the energy storage unit is an energy supply unit, the carbon attribute data block corresponding to the target discharge power of the energy storage unit is extracted at the head of the carbon accounting queue according to the target discharge power of the energy storage unit to generate the carbon intensity factor of the energy storage unit.

[0148] In one embodiment, the acquisition module 410 is also used to obtain the grid synchronized phasor data of the target energy-related units in the zero-carbon park; map the grid synchronized phasor data to the node attributes of the corresponding nodes in the energy network topology diagram, and update the energy flow digital model.

[0149] In one feasible implementation, the energy flow digital model is input into a trained graph neural network, and the power distribution relationship between nodes is calculated to obtain an energy flow matrix, including:

[0150] The digital model of energy flow is input into the trained graph neural network to calculate the initial power distribution relationship between nodes. The initial power distribution relationship is corrected using the grid synchronized phasor data as physical constraints to obtain the energy flow matrix.

[0151] In one embodiment, the generation module 430 is specifically used to determine the initial power distribution relationship between each node based on the node attributes of each node in the energy flow digital model and the weight of the directed edge connecting the nodes, using a trained graph neural network; calculate the voltage amplitude and phase angle difference between the two target nodes corresponding to the two target energy-related units according to the grid synchronous phasor data of the target energy-related units, and determine the verification power distribution relationship including the power size and flow direction between the two target nodes in combination with the weight of the edge between the two target nodes; determine a distribution relationship correction amount for adjusting the target initial power distribution relationship between the target nodes by comparing the target initial power distribution relationship between the two target nodes with the verification power distribution relationship; use the distribution relationship correction amount to correct the target initial power distribution relationship between the two target nodes, and use the corrected target initial power distribution relationship to update all initial power distribution relationships to obtain an energy flow matrix.

[0152] In one embodiment, the calculation module 440 is also used to arrange the carbon intensity factor of each energy supply unit according to the arrangement order of the row dimension in the energy flow matrix to form a source-end carbon intensity vector; perform matrix multiplication operation on the source-end carbon intensity vector and the energy flow matrix to obtain the energy-consuming unit carbon attribute vector, and each element of the energy-consuming unit carbon attribute vector represents the unit power carbon attribute value obtained by allocating the corresponding energy-consuming unit in the energy flow digital model; perform scalar multiplication operation on the active power component in the real-time power data of the energy-consuming unit and the value of the corresponding element in the energy-consuming unit carbon attribute vector to obtain the carbon footprint value of the energy-consuming unit.

[0153] Figure 4 Each module in the system shown has the function of implementing Figures 1 to 3 The functions of each step in the embodiment can achieve the corresponding technical effects, which will not be described in detail here for the sake of brevity.

[0154] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present application is shown.

[0155] The electronic device may include a processor 510 and a memory 520 storing computer program instructions.

[0156] Specifically, the processor 510 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0157] The memory 520 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 520 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 520 may include removable or non-removable (or fixed) media. Where appropriate, the memory 520 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 520 is a non-volatile solid-state memory.

[0158] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present disclosure.

[0159] The processor 510 reads and executes the computer program instructions stored in the memory 520 to implement any one of the zero-carbon park full life cycle carbon footprint tracking and accounting methods in the above embodiments.

[0160] In one example, the electronic device may further include a communication interface 530 and a bus 540. Figure 5 As shown, the processor 510 , the memory 520 , and the communication interface 530 are connected via a bus 540 and communicate with each other.

[0161] The communication interface 530 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0162] Bus 540 includes hardware, software, or both, and couples the components of the online data traffic metering device to each other. By way of example, and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Area Network (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 540 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0163] The electronic device can execute the zero-carbon park full life cycle carbon footprint tracking and accounting method in the embodiment of the present application, thereby realizing the combination Figures 1 to 3 Describes the carbon footprint tracking and accounting method for the entire life cycle of a zero-carbon park.

[0164] In addition, in conjunction with the zero-carbon park full life cycle carbon footprint tracking and accounting method in the above embodiments, the present application embodiments may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the zero-carbon park full life cycle carbon footprint tracking and accounting methods in the above embodiments is implemented.

[0165] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0166] The functional blocks shown in the block diagrams described above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they may be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments may be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave over a transmission medium or communication link. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memory, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. Code segments may be downloaded via a computer network such as the Internet or an intranet.

[0167] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0168] Aspects of the present application have been described above with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each block in the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, 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, or other programmable data processing device to produce a machine such that execution of these instructions by the processor of the computer or other programmable data processing device enables the implementation of the functions / actions specified in one or more blocks in the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagrams and / or flowcharts, as well as combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0169] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle, applicable to zero-carbon parks powered by multi-energy coupling, characterized in that: include: Obtaining spatial topological data of energy-related units in a zero-carbon park, real-time power data of the energy-related units, and a carbon intensity factor of each energy supply unit, wherein the energy-related units include at least one energy supply unit and at least one energy consumption unit, and the spatial topological data includes physical parameters of physical lines between the energy-related units; Based on the spatial topology data, the energy-related units are defined as nodes, the physical lines connecting the nodes are defined as directed edges, and the physical parameters of the physical lines are defined as weights of the directed edges, to construct an energy network topology graph; Mapping the real-time power data to the node attributes of the corresponding nodes in the energy network topology diagram to generate an energy flow digital model representing the energy flow state of the zero-carbon park; Input the energy flow digital model into the trained graph neural network, and obtain an energy flow matrix by calculating the power distribution relationship between the nodes. The row dimension of the energy flow matrix corresponds to the number of the energy supply units, the column dimension corresponds to the number of the energy consumption units, and the matrix elements represent the power distribution ratio coefficients; The carbon intensity factor of each energy supply unit is converted into a source-end carbon intensity vector, each source-end carbon intensity vector is allocated to the energy-consuming unit through the energy flow matrix, and the carbon footprint value of the energy-consuming unit is calculated based on the real-time power data of the energy-consuming unit.

2. The method according to claim 1, characterized in that The energy supply unit includes a photovoltaic power generation unit, an energy storage unit and a public power grid unit.

3. The method according to claim 2, characterized in that The method further comprises: When the charge and discharge state corresponding to the real-time power data of the energy storage unit is a charging state, determining the energy storage unit as the energy consuming unit; Calculating the source-end carbon intensity vector allocated to the energy storage unit according to the energy flow matrix, and calculating the charging capacity of the energy storage unit and the corresponding carbon attribute data block according to the real-time power data of the energy storage unit; A carbon accounting queue based on the first-in-first-out principle is established for the energy storage unit, and the carbon attribute data block of the energy storage unit is stored at the end of the carbon accounting queue in chronological order, so that when the energy storage unit serves as the energy supply unit, the carbon attribute data block corresponding to the target discharge power of the energy storage unit is extracted at the head of the carbon accounting queue to generate the carbon intensity factor of the energy storage unit.

4. The method according to claim 1, wherein The method further comprises: Obtaining grid synchronized phasor data of target energy-related units within the zero-carbon park; The grid synchronized phasor data is mapped to node attributes of the corresponding nodes in the energy network topology diagram, and the energy flow digital model is updated.

5. The method according to claim 4, characterized in that The energy flow digital model is input into the trained graph neural network, and the energy flow matrix is ​​obtained by calculating the power distribution relationship between the nodes, including: The energy flow digital model is input into the trained graph neural network, the initial power distribution relationship between the nodes is calculated, and the initial power distribution relationship is corrected using the grid synchronized phasor data as a physical constraint condition to obtain the energy flow matrix.

6. The method according to claim 5, characterized in that The energy flow digital model is input into a trained graph neural network, the initial power distribution relationship between the nodes is calculated, and the initial power distribution relationship is corrected using the grid synchronized phasor data as a physical constraint condition to obtain the energy flow matrix, including: Based on the node attributes of each node in the energy flow digital model and the weights of the directed edges connecting the nodes, using the trained graph neural network, determining the initial power distribution relationship between each of the nodes; Calculating, based on the grid synchronized phasor data of the target energy-related unit, a voltage amplitude and a phase angle difference between two target nodes corresponding to the two target energy-related units, and determining, in combination with the weight of the edge between the two target nodes, a verification power distribution relationship including the power size and flow direction between the two target nodes; Determining a distribution relationship correction amount for adjusting the target initial power distribution relationship between the two target nodes by comparing the target initial power distribution relationship between the two target nodes with the verification power distribution relationship; The energy flow matrix is ​​obtained by correcting the target initial power distribution relationship between the two target nodes using the distribution relationship correction amount and updating all the initial power distribution relationships using the corrected target initial power distribution relationship.

7. The method according to claim 1, characterized in that The converting of the carbon intensity factor of each energy supply unit into a source-end carbon intensity vector, allocating each source-end carbon intensity vector to the energy consumption unit through the energy flow matrix, and calculating the carbon footprint value of the energy consumption unit based on the real-time power data of the energy consumption unit includes: Arrange the carbon intensity factor of each energy supply unit according to the arrangement order of the row dimension in the energy flow matrix to form the source-end carbon intensity vector; Performing a matrix multiplication operation on the source-end carbon intensity vector and the energy flow matrix to obtain an energy consumption unit carbon attribute vector, wherein each element of the energy consumption unit carbon attribute vector represents a unit power carbon attribute value obtained by allocating the corresponding energy consumption unit in the energy flow digital model; A scalar multiplication operation is performed on the active power component in the real-time power data of the energy consuming unit and the value of the corresponding element in the carbon attribute vector of the energy consuming unit to obtain the carbon footprint value of the energy consuming unit.

8. A zero-carbon park full life cycle carbon footprint tracking and accounting system, suitable for zero-carbon parks powered by multi-energy coupling, characterized by: The system comprises: An acquisition module is configured to acquire spatial topological data of energy-related units within a zero-carbon park, real-time power data of the energy-related units, and a carbon intensity factor of each energy supply unit, wherein the energy-related units include at least one energy supply unit and at least one energy consumption unit, and the spatial topological data includes physical parameters of physical lines between the energy-related units; A construction module is configured to define the energy-related units as nodes, define the physical lines connecting the nodes as directed edges, and define the physical parameters of the physical lines as weights of the directed edges based on the spatial topology data, so as to construct an energy network topology graph; A generation module, configured to map the real-time power data to node attributes of the corresponding nodes in the energy network topology diagram, and generate an energy flow digital model representing the energy flow state of the zero-carbon park; The generation module is further configured to input the energy flow digital model into a trained graph neural network, and obtain an energy flow matrix by calculating the power distribution relationship between the nodes, wherein the row dimension of the energy flow matrix corresponds to the number of the energy supply units, the column dimension corresponds to the number of the energy consumption units, and the matrix elements represent the power distribution ratio coefficients; A calculation module is used to convert the carbon intensity factor of each of the energy supply units into a source-end carbon intensity vector, distribute each of the source-end carbon intensity vectors to the energy-consuming unit through the energy flow matrix, and calculate the carbon footprint value of the energy-consuming unit based on the real-time power data of the energy-consuming unit.

9. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the zero-carbon park full life cycle carbon footprint tracking and accounting method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the method for tracking and calculating the carbon footprint of a zero-carbon park throughout its life cycle as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Carbon emission flow tracking method based on graph neural network

    CN114741956A

  • Power grid carbon footprint tracking method based on source grid load incidence matrix

    CN116054124A

  • Electric carbon tracking method based on electric power flow topological grid modeling

    CN119691947A

  • Power system carbon footprint accounting method and device

    CN120069292A

  • Hybrid battery management system

    US11130422B1