Carbon flow tracking and simulation evaluation system for power distribution network

Abstract

The application discloses a carbon flow tracking and simulation evaluation system for a power distribution network, and belongs to the technical field of power distribution network energy management and carbon emission reduction, and specifically relates to a carbon flow tracking and simulation evaluation system for a power distribution network, which comprises a carbon flow data acquisition module, is used for deploying edge terminals and sensor sampling data at feeder lines, transformers, user electricity meters and distributed new energy stations, and performs encrypted transmission through a 5G / edge gateway to ensure data real-time performance; and a hierarchical carbon flow tracking module is used for constructing a four-layer model of a power distribution network master station, a feeder line, a power distribution transformer and a user side, each layer is superimposed with a differentiated calculation factor, and each node real-time carbon flow is calculated through a weighted algorithm of upper layer carbon flow x node power proportion x loss correction coefficient. The carbon flow data acquisition module is arranged, all key nodes associated with carbon flow can be covered, fragmented data originally scattered in multiple links is integrated into a unified acquisition link, and the problem that data is scattered in different scenes and needs to be found across links is completely solved.

Description

Technical Field

[0001] This invention relates to the field of power distribution network energy management and carbon emission reduction technology, specifically a power distribution network carbon flow tracking and simulation evaluation system. Background Technology

[0002] As the core link connecting distributed energy (photovoltaics, energy storage) and users, the carbon flow path of the distribution network is becoming increasingly complex: on the one hand, the randomness of distributed photovoltaic output and the peak-valley fluctuations of user load lead to dynamic changes in carbon flow; on the other hand, carbon flow management requires the linkage of multiple entities such as power grid companies, new energy power plants, users, and carbon trading institutions, and it is necessary to break down cross-entity data barriers.

[0003] Existing carbon flow management technologies for distribution networks have three major limitations: First, the granularity of carbon flow tracking is coarse, only enabling regional or overall distribution network carbon emission statistics, and failing to accurately pinpoint specific nodes such as feeders, transformers, and user sides. Second, simulation evaluations are based on static historical data, which cannot adapt to dynamic operating conditions of the distribution network (such as sudden increases in photovoltaic output or sudden drops in load), resulting in large discrepancies between simulation results and actual conditions. Third, data from multiple entities is stored in independent systems (such as grid SCADA and user electricity consumption data acquisition platforms), leading to inconsistent data standards and low sharing efficiency, which affects the timeliness and accuracy of carbon flow calculations. These limitations are detailed below:

[0004] 1. The granularity of carbon flow tracking is coarse, and the responsibility for emission reduction cannot be accurately assigned: Existing methods can only count the carbon emissions of the distribution network as a whole or at the regional level, but cannot pinpoint the specific nodes such as feeders and users, resulting in a lack of targeted carbon emission reduction measures.

[0005] 2. Static simulation evaluation cannot adapt to dynamic operating conditions of distribution networks: Existing simulation systems calculate carbon flow based on historical average data (such as fixed load curves and renewable energy output coefficients), which cannot respond to changes in distribution network operating conditions in real time. This results in a large deviation between simulation results and actual carbon flow, making it impossible to guide real-time control.

[0006] 3. High data barriers among multiple entities lead to low efficiency and reliability in carbon flow calculation: Data from power grid companies, renewable energy plants, and users are stored in separate systems with inconsistent data formats and a lack of sharing mechanisms, resulting in time-consuming and error-prone data acquisition, which affects the accuracy of carbon flow calculation.

[0007] Based on the above, a carbon flow tracking and simulation evaluation system for power distribution networks is invented. Summary of the Invention

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] A distribution network carbon flow tracing and simulation evaluation system, comprising:

[0010] The carbon flow data acquisition module is used to deploy edge terminals and sensors to collect data in feeders, transformers, user meters, and distributed new energy power stations, and transmits the data in encrypted form via 5G / edge gateway to ensure real-time data transmission.

[0011] The hierarchical carbon flow tracking module is used to construct a four-layer model of distribution network master station → feeder → distribution transformer → user side. Each layer is superimposed with differentiated calculation factors, and the real-time carbon flow of each node is calculated by a weighted algorithm of upper-layer carbon flow × node power ratio × loss correction coefficient.

[0012] The dynamic carbon flow simulation module is used to build a digital twin model based on the distribution network topology, access real-time data and predict future operating conditions through LSTM neural networks, and supports multi-scenario simulation, outputting carbon flow deviation analysis and emission reduction potential prediction.

[0013] The carbon flow anomaly early warning and intelligent emission reduction strategy generation module is used to set three-level early warnings based on real-time carbon flow, simulation deviation, and equipment status, and push accurate early warning reports after triggering; and combine anomaly type + subject role + operating condition to generate differentiated strategies through reinforcement learning, and optimize them after technical feasibility verification and economic evaluation.

[0014] A multi-entity collaborative carbon flow data platform is used for evidence storage using a consortium blockchain and supports multi-entity authorized access based on the IEC61850 standard for unified data format and interface.

[0015] As a preferred embodiment of the distribution network carbon flow tracing and simulation evaluation system of the present invention, the carbon flow data acquisition module includes:

[0016] The data acquisition module is used to collect real-time data on the operation of the power distribution network.

[0017] The data transmission module is used to encrypt and transmit the collected data to the multi-entity collaborative carbon flow data platform via a 5G private network or edge computing gateway, ensuring data real-time performance.

[0018] As a preferred embodiment of the distribution network carbon flow tracing and simulation evaluation system of the present invention, the hierarchical carbon flow tracing module includes:

[0019] The four-layer tracking model module is used to construct four layers of carbon flow nodes: distribution network master station → feeder → distribution transformer → user side, and each layer defines a differentiated calculation factor; the distribution network master station layer introduces the carbon factor of electricity purchased from the grid; the feeder layer superimposes the carbon footprint of line loss; the distribution transformer layer includes the carbon contribution of transformer loss; and the user side considers the local consumption rate of new energy.

[0020] The weighted allocation module is used to allocate carbon flow based on the upper layer carbon flow and the power ratio of each node in the lower layer. The formula is as follows: Carbon flow of a node = upper layer allocated carbon flow × (actual power of the node / total power of the upper layer) × (1 + loss correction coefficient).

[0021] As a preferred embodiment of the power distribution network carbon flow tracing and simulation evaluation system of the present invention, the dynamic carbon flow simulation module includes:

[0022] The digital twin modeling module is used to build a virtual simulation model based on the distribution network topology and equipment parameters, and map it to the physical distribution network in real time.

[0023] The dynamic parameter input module is used to access real-time data from the multi-entity collaborative carbon flow data platform and predict the changes in operating conditions within the next hour through an LSTM neural network.

[0024] The multi-scenario simulation module supports carbon flow simulation in multiple scenarios, updates simulation results every 5 minutes, and outputs carbon flow deviation analysis and emission reduction potential prediction.

[0025] As a preferred embodiment of the distribution network carbon flow tracking and simulation evaluation system of the present invention, the carbon flow anomaly early warning and intelligent emission reduction strategy generation module includes:

[0026] The carbon flow anomaly identification and graded early warning module is used to first build a multi-dimensional anomaly judgment model and set three-level early warning thresholds, and then generate an early warning report through the early warning triggering mechanism.

[0027] The multi-entity differentiated emission reduction strategy generation module is used to generate appropriate strategies by calling historical data and dynamic simulation prediction results from the multi-entity collaborative carbon flow data platform based on three dimensions: anomaly type, entity role, and distribution network operating conditions, and by using reinforcement learning algorithms.

[0028] The strategy feasibility assessment and dynamic optimization module is used to first verify the technical feasibility, then conduct an economic assessment, and finally perform dynamic optimization.

[0029] As a preferred embodiment of the distribution network carbon flow tracing and simulation evaluation system of the present invention, the carbon flow anomaly identification and graded early warning module includes:

[0030] A multi-dimensional anomaly detection model unit is constructed to set three-level early warning thresholds based on real-time carbon flow from hierarchical tracking, deviation values ​​from dynamic simulation, and equipment operating status.

[0031] The early warning triggering mechanism unit is used to compare module data with thresholds in real time. After triggering an early warning, it automatically generates an early warning report and pushes it to the corresponding entity via 5G message.

[0032] As a preferred embodiment of the distribution network carbon flow tracing and simulation evaluation system of the present invention, the strategy feasibility evaluation and dynamic optimization module includes:

[0033] The technical feasibility verification unit is used to combine distribution network topology constraints and equipment parameters to verify whether the strategy will cause distribution network security problems. If there are risks, the parameters will be automatically adjusted.

[0034] The economic assessment unit is used to calculate the cost of implementing the strategy and the emission reduction benefits, and outputs the cost-benefit ratio;

[0035] The dynamic optimization unit is used to collect real-time data on changes in carbon flow in the distribution network after the strategy is executed. If the actual emission reduction effect is lower than expected, the strategy will be automatically adjusted retrospectively.

[0036] As a preferred embodiment of the distribution network carbon flow tracking and simulation evaluation system described in this invention, the multi-entity collaborative carbon flow data platform includes:

[0037] The blockchain data storage module is designed to use a consortium blockchain architecture, enabling power grid companies, photovoltaic power plants, users, and carbon trading institutions to connect as nodes. When data is uploaded, a timestamp and encrypted identifier are automatically generated to ensure that the data cannot be tampered with.

[0038] The Unified Data Standards Module is used to extend the carbon flow data model according to the IEC61850 standard, unify the data format and interaction interface, and support authorized access by various entities.

[0039] The data intelligence processing module is used to preprocess data based on built-in data cleaning and fusion algorithms.

[0040] Compared with existing technologies:

[0041] 1. By first constructing a hierarchical carbon flow tracking model through a hierarchical carbon flow tracking module, and then accurately calculating the carbon flow of each node through a weighted allocation algorithm, it can achieve a refined positioning of carbon emission responsibility and provide a quantitative basis for the formulation of emission reduction measures.

[0042] 2. A digital twin model is first constructed through the dynamic carbon flow simulation module, and then the LSTM neural network is combined to predict changes in operating conditions. It supports dynamic simulation in multiple scenarios and enables the simulation results to be adjusted in real time according to the distribution network operation status, effectively reducing the deviation from the actual carbon flow and ensuring the accuracy and effectiveness of the control strategy.

[0043] 3. Through the multi-entity collaborative carbon flow data platform, a unified data standard and consortium blockchain architecture are established, enabling unified data formats and authorized sharing among multiple entities such as power grids, users, and new energy power plants. Furthermore, with the addition of a data intelligent processing module, data preprocessing time is significantly reduced, data accuracy and reliability are improved, and carbon flow calculation is ensured to be efficient and reliable. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the overall framework of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0046] This invention provides a carbon flow tracing and simulation evaluation system for power distribution networks. Please refer to [link / reference]. Figure 1 ,include:

[0047] The carbon flow data acquisition module is used to deploy edge terminals and sensors to collect data in feeders, transformers, user meters, and distributed new energy power stations, and transmits the data in encrypted form via 5G / edge gateway to ensure real-time data transmission.

[0048] The hierarchical carbon flow tracking module is used to construct a four-layer model of distribution network master station → feeder → distribution transformer → user side. Each layer is superimposed with differentiated calculation factors, and the real-time carbon flow of each node is calculated by a weighted algorithm of upper-layer carbon flow × node power ratio × loss correction coefficient.

[0049] The dynamic carbon flow simulation module is used to build a digital twin model based on the distribution network topology, access real-time data and predict future operating conditions through LSTM neural networks, and supports multi-scenario simulation, outputting carbon flow deviation analysis and emission reduction potential prediction.

[0050] The carbon flow anomaly early warning and intelligent emission reduction strategy generation module is used to set three-level early warnings based on real-time carbon flow, simulation deviation, and equipment status, and push accurate early warning reports after triggering; and combine anomaly type + subject role + operating condition to generate differentiated strategies through reinforcement learning, and optimize them after technical feasibility verification and economic evaluation.

[0051] A multi-entity collaborative carbon flow data platform is used for evidence storage using a consortium blockchain and supports multi-entity authorized access based on the IEC61850 standard for unified data format and interface.

[0052] The carbon flow data acquisition module includes:

[0053] The data acquisition module is used to collect distribution network operation data in real time (sampling frequency 1 minute / time), including: feeder power, transformer loss, user electricity consumption, photovoltaic output, and energy storage charging and discharging power;

[0054] The data transmission module is used to encrypt and transmit the collected data to the multi-entity collaborative carbon flow data platform via a 5G private network or edge computing gateway, ensuring data real-time performance.

[0055] The hierarchical carbon flow tracking module includes:

[0056] The four-layer tracking model module is used to construct four layers of carbon flow nodes: distribution network master station → feeder → distribution transformer → user side, and each layer defines a differentiated calculation factor. The distribution network master station layer introduces the carbon factor of electricity purchased from the grid; the feeder layer superimposes the carbon footprint of line loss (line loss rate × master station carbon flow); the distribution transformer layer includes the carbon contribution of transformer loss (transformer loss power × operating time × carbon factor); and the user side considers the local consumption rate of new energy (local photovoltaic consumption × 0 + purchased electricity × carbon factor).

[0057] The weighted allocation module is used to allocate carbon flow based on the upper layer carbon flow and the power ratio of each node in the lower layer (combined with the loss correction coefficient). The formula is as follows: Carbon flow of a node = upper layer allocated carbon flow × (actual power of the node / total power of the upper layer) × (1 + loss correction coefficient).

[0058] The dynamic carbon flow simulation module includes:

[0059] The digital twin modeling module is used to build a virtual simulation model based on the distribution network topology and equipment parameters (such as transformer capacity and line resistance), and map it to the physical distribution network in real time.

[0060] The dynamic parameter input module is used to access real-time data (load, photovoltaic output) from the multi-entity collaborative carbon flow data platform and predict the operating condition changes in the next hour through an LSTM neural network.

[0061] The multi-scenario simulation module supports carbon flow simulation for various scenarios such as load fluctuations, changes in new energy output, and adjustments to energy storage charging and discharging strategies. The simulation results are updated every 5 minutes, and the module outputs carbon flow deviation analysis (comparison of actual and simulated values) and emission reduction potential prediction (e.g., users can reduce carbon emissions by 10% by using electricity during off-peak hours).

[0062] The carbon flow anomaly early warning and intelligent emission reduction strategy generation module includes:

[0063] The carbon flow anomaly identification and graded early warning module is used to first build a multi-dimensional anomaly judgment model and set three-level early warning thresholds, and then generate an early warning report through the early warning triggering mechanism.

[0064] The multi-entity differentiated emission reduction strategy generation module is used to generate appropriate strategies based on three dimensions: anomaly type, entity role, and distribution network operating conditions. It calls historical data (such as the user's past emission reduction response rate and the regulation capacity of new energy power plants) from the multi-entity collaborative carbon flow data platform and the operating condition prediction results of dynamic simulation, and generates appropriate strategies through reinforcement learning algorithms.

[0065] For the power grid company: If the feeder carbon flow exceeds the red alert level (due to the high proportion of purchased high-carbon electricity), a control strategy will be generated to increase local photovoltaic consumption and supplement the load with energy storage discharge, with specific execution parameters (such as energy storage discharge power of 2MW and a duration of 1 hour).

[0066] For industrial users: If a user's carbon emissions exceed the yellow alert level (due to high-energy-consuming equipment operating at full load), a combined strategy of "off-peak production (shifting the load from the high-carbon period of 10:00-12:00 to the peak photovoltaic power generation period of 14:00-16:00) + equipment energy efficiency optimization (such as motor frequency conversion modification)" will be generated, and the estimated emission reduction (such as off-peak production can reduce carbon emissions by 5 tons / day).

[0067] For photovoltaic power plants: If the simulation predicts a sharp drop in photovoltaic output the next day (leading to an increase in external power purchases and carbon flow in the distribution network), a contingency plan strategy of "pre-emptively storing energy (charging to 80% capacity) + coordinating with neighboring power plants for energy replenishment" will be generated.

[0068] The strategy feasibility assessment and dynamic optimization module is used to first verify the technical feasibility, then conduct an economic assessment, and finally perform dynamic optimization.

[0069] The carbon flow anomaly identification and graded early warning module includes:

[0070] A multi-dimensional anomaly detection model unit is constructed to set three-level warning thresholds (blue warning: potential risk; yellow warning: slight exceedance; red warning: serious exceedance) based on real-time carbon flow tracking (e.g., a sudden increase of 20% in feeder carbon flow, or a user's carbon emissions exceeding the monthly quota by 10%), deviation values ​​from dynamic simulation (the actual carbon flow deviation from the simulated carbon flow exceeds 8%), and equipment operating status (e.g., abnormal transformer losses causing an additional 5% increase in carbon flow).

[0071] The early warning triggering mechanism unit is used to compare module data with thresholds in real time. After triggering an early warning, it automatically generates an early warning report (including abnormal node location, preliminary analysis of the cause of exceeding the standard, and assessment of the scope of impact) and pushes it to the corresponding subject via 5G message (e.g., red warning pushes to the power grid control center and high carbon emission users, yellow warning pushes to user operation and maintenance personnel).

[0072] The strategy feasibility assessment and dynamic optimization module includes:

[0073] The technical feasibility verification unit is used to combine distribution network topology constraints (such as line capacity and voltage limits) with equipment parameters (such as maximum charging and discharging power of energy storage) to verify whether the strategy will cause distribution network safety problems (such as overload and voltage exceeding limits). If there is a risk, the parameters will be automatically adjusted (such as reducing the energy storage discharge power from 2MW to 1.5MW).

[0074] The economic evaluation unit is used to calculate the strategy implementation costs (such as compensation for capacity loss due to user peak shifting and the difference in electricity costs for energy storage charging and discharging) and emission reduction benefits (such as carbon trading revenue and policy subsidies), and outputs the cost-benefit ratio (e.g., if the strategy implementation cost is 2,000 yuan / day and the emission reduction benefit is 5,000 yuan / day, the benefit ratio is 2.5:1).

[0075] The dynamic optimization unit is used to collect real-time data on changes in carbon flow in the distribution network after the strategy is executed. If the actual emission reduction effect is lower than expected (e.g., the estimated emission reduction is 5 tons / day, but the actual reduction is only 3 tons / day), the strategy will be automatically adjusted back (e.g., the user's staggered peak time period will be extended from 2 hours to 3 hours).

[0076] The multi-entity collaborative carbon flow data platform includes:

[0077] The blockchain data storage module is designed to use a consortium blockchain architecture, enabling power grid companies, photovoltaic power plants, users, and carbon trading institutions to connect as nodes. When data is uploaded, a timestamp and encrypted identifier are automatically generated to ensure that the data cannot be tampered with.

[0078] The Unified Data Standards Module is used to extend the carbon flow data model according to the IEC61850 standard, unify the data format and interaction interface, and support authorized access by various entities (such as users can only query their own carbon data, while power grid companies can obtain data from the entire distribution network).

[0079] The data intelligent processing module is used to preprocess data based on the built-in data cleaning algorithm (removing outliers, such as invalid data where photovoltaic output suddenly drops to 0) and fusion algorithm (unifying multi-source data to the same time scale). The data preprocessing time is ≤10 minutes.

[0080] In practical use, the specific steps are as follows:

[0081] S1: The carbon flow data acquisition module collects real-time data from the distribution network through the edge terminal and transmits it to the multi-entity collaborative carbon flow data platform with encryption.

[0082] S2: After cleaning and standardizing the data, the multi-entity collaborative carbon flow data platform stores the data on the blockchain and opens authorized data access to each entity;

[0083] S3: The hierarchical carbon flow tracing module calls the data from the middle platform, calculates the real-time carbon flow of each node based on the four-layer model and weighted algorithm, and generates the "Carbon Flow Tracing Report".

[0084] S4: The dynamic carbon flow simulation module combines real-time data and operating condition prediction to drive digital twin model simulation and output the "Carbon Flow Dynamic Simulation Evaluation Report".

[0085] S5: The carbon flow anomaly early warning and intelligent emission reduction strategy generation module sets three levels of early warning based on real-time carbon flow, simulation deviation, and equipment status, and pushes an accurate early warning report after triggering; and combines anomaly type + subject role + operating condition to generate differentiated strategies through reinforcement learning, and optimizes them after technical feasibility verification and economic evaluation.

[0086] S6: Push the two reports to various main terminals (such as the power grid control center's large screen and user APP) to support emission reduction decisions (such as power grid optimizing feeder operation mode and users adjusting electricity consumption periods).

[0087] Although the present invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the disclosed embodiments can be combined with each other in any manner. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A carbon flow tracing and simulation evaluation system for power distribution networks, characterized in that, include: The carbon flow data acquisition module is used to deploy edge terminals and sensors to collect data in feeders, transformers, user meters, and distributed new energy power stations, and transmits the data in encrypted form via 5G / edge gateway to ensure real-time data transmission. The hierarchical carbon flow tracking module is used to construct a four-layer model of distribution network master station → feeder → distribution transformer → user side. Each layer is superimposed with a differentiated calculation factor, and the real-time carbon flow of each node is calculated by carbon flow of a certain node = carbon flow allocated by the upper layer × (actual power of the node / total power of the upper layer) × (1 + loss correction coefficient). The dynamic carbon flow simulation module is used to build a digital twin model based on the distribution network topology, access real-time data and predict future operating conditions through LSTM neural networks, and supports multi-scenario simulation, outputting carbon flow deviation analysis and emission reduction potential prediction. The carbon flow anomaly early warning and intelligent emission reduction strategy generation module is used to set three-level early warnings based on real-time carbon flow, simulation deviation, and equipment status, and push accurate early warning reports after triggering. Furthermore, by combining anomaly type, subject role, and working condition, a differentiated strategy is generated through reinforcement learning, and then optimized after technical feasibility verification and economic evaluation. A multi-entity collaborative carbon flow data platform is used for evidence storage using a consortium blockchain and supports multi-entity authorized access based on the IEC61850 standard for unified data format and interface. The carbon flow anomaly early warning and intelligent emission reduction strategy generation module includes: The carbon flow anomaly identification and graded early warning module is used to first build a multi-dimensional anomaly judgment model and set three-level early warning thresholds, and then generate an early warning report through the early warning triggering mechanism. The multi-entity differentiated emission reduction strategy generation module is used to generate appropriate strategies by calling historical data and dynamic simulation prediction results from the multi-entity collaborative carbon flow data platform based on three dimensions: anomaly type, entity role, and distribution network operating conditions, and by using reinforcement learning algorithms. The strategy feasibility assessment and dynamic optimization module is used to first verify the technical feasibility, then conduct an economic assessment, and finally perform dynamic optimization. The carbon flow anomaly identification and graded early warning module includes: A multi-dimensional anomaly detection model unit is constructed to set three-level early warning thresholds based on real-time carbon flow from hierarchical tracking, deviation values ​​from dynamic simulation, and equipment operating status. The early warning triggering mechanism unit is used to compare module data with thresholds in real time. After triggering an early warning, it automatically generates an early warning report and pushes it to the corresponding entity via 5G message.

2. The distribution network carbon flow tracing and simulation evaluation system according to claim 1, characterized in that, The carbon flow data acquisition module includes: The data acquisition module is used to collect real-time data on the operation of the power distribution network. The data transmission module is used to encrypt and transmit the collected data to the multi-entity collaborative carbon flow data platform via a 5G private network or edge computing gateway, ensuring data real-time performance.

3. The distribution network carbon flow tracing and simulation evaluation system according to claim 1, characterized in that, The hierarchical carbon flow tracking module includes: The four-layer tracking model module is used to construct four layers of carbon flow nodes: distribution network master station → feeder → distribution transformer → user side, and each layer defines a differentiated calculation factor; the distribution network master station layer introduces the carbon factor of electricity purchased from the grid; the feeder layer superimposes the carbon footprint of line loss; the distribution transformer layer includes the carbon contribution of transformer loss; and the user side considers the local consumption rate of new energy. The weighted allocation module is used to allocate carbon flow based on the upper layer carbon flow and the power ratio of each node in the lower layer. The formula is as follows: Carbon flow of a node = upper layer allocated carbon flow × (actual power of the node / total power of the upper layer) × (1 + loss correction coefficient).

4. The distribution network carbon flow tracking and simulation evaluation system according to claim 1, characterized in that, The dynamic carbon flow simulation module includes: The digital twin modeling module is used to build a virtual simulation model based on the distribution network topology and equipment parameters, and map it to the physical distribution network in real time. The dynamic parameter input module is used to access real-time data from the multi-entity collaborative carbon flow data platform and predict the changes in operating conditions within the next hour through an LSTM neural network. The multi-scenario simulation module supports carbon flow simulation in multiple scenarios, updates simulation results every 5 minutes, and outputs carbon flow deviation analysis and emission reduction potential prediction.

5. The distribution network carbon flow tracing and simulation evaluation system according to claim 1, characterized in that, The strategy feasibility assessment and dynamic optimization module includes: The technical feasibility verification unit is used to combine distribution network topology constraints and equipment parameters to verify whether the strategy will cause distribution network security problems. If there are risks, the parameters will be automatically adjusted. The economic assessment unit is used to calculate the cost of implementing the strategy and the emission reduction benefits, and outputs the cost-benefit ratio; The dynamic optimization unit is used to collect real-time data on changes in carbon flow in the distribution network after the strategy is executed. If the actual emission reduction effect is lower than expected, the strategy will be automatically adjusted retrospectively.

6. The distribution network carbon flow tracing and simulation evaluation system according to claim 1, characterized in that, The multi-entity collaborative carbon flow data platform includes: The blockchain data storage module is designed to use a consortium blockchain architecture, enabling power grid companies, photovoltaic power plants, users, and carbon trading institutions to connect as nodes. When data is uploaded, a timestamp and encrypted identifier are automatically generated to ensure that the data cannot be tampered with. The Unified Data Standards Module is used to extend the carbon flow data model according to the IEC61850 standard, unify the data format and interaction interface, and support authorized access by various entities. The data intelligence processing module is used to preprocess data based on built-in data cleaning and fusion algorithms.

Images