A regional power grid new energy consumption capacity calculation method and system

Abstract

The present application relates to the technical field of new energy consumption, especially relates to a regional power grid new energy consumption capacity calculation method and equipment. Including: the power grid node data and environmental influence factors are processed through the graph neural network to obtain the electrical distance dynamic index; the transmission capacity limit and the load distribution are determined according to the index, the preliminary consumption capacity boundary is obtained, and the boundary is adjusted based on the environmental factors to obtain the optimized consumption capacity boundary; the supply-demand matching deviation is calculated by combining the current actual supply-demand data of the power grid, and the real-time adjustment scheme is formulated by fusing historical data and grid connection requirements; through the real-time adjustment scheme, the power flow calculation and stability evaluation are integrated, and finally the optimized consumption capacity boundary is obtained; the stability of the power grid is judged based on the final consumption capacity boundary, and the optimal power distribution path of the power grid is determined by combining the supply-demand matching model. The present application can effectively improve the new energy consumption capacity and equipment stability of the power grid, and adapt to changing environmental conditions.

Description

Technical Field

[0001] This invention relates to the field of new energy consumption technology, and in particular to a method and system for calculating the new energy consumption capacity of a regional power grid. Background Technology

[0002] With the rapid development of renewable energy, especially wind and solar power, the energy structure of the power system has undergone significant changes. Traditional power grid design and operation methods are no longer effective in coping with the uncertainties and volatility brought about by the large-scale integration of renewable energy. Therefore, improving the power grid's capacity for renewable energy absorption and ensuring grid stability has become a major challenge facing the current power system. Traditional power grid operation methods often cannot adjust power distribution in real time to adapt to environmental changes, such as fluctuations in wind speed and solar radiation intensity, leading to uneven grid load, resource waste, and stability problems.

[0003] To address these challenges, employing modern technologies for dynamic regulation of the power grid is crucial. Graph Neural Networks (GNNs), as an advanced deep learning technique, have achieved significant results in complex system modeling. By processing power grid topology and environmental factors through GNNs, the dynamic efficiency of power grid operation can be reflected in real time, providing accurate calculation methods for power grid load allocation and renewable energy consumption. Furthermore, by combining optimization algorithms with environmental factors, the capacity boundary can be dynamically adjusted to ensure the maximum power absorption capacity of the power grid under different conditions, optimizing power grid scheduling based on real-time supply and demand data.

[0004] This invention proposes a method for calculating the renewable energy absorption capacity of a regional power grid. By combining graph neural networks and optimization algorithms, it aims to provide an efficient and reliable method for optimizing power grid capacity, which can not only improve the renewable energy absorption capacity of the power grid, but also effectively enhance the stability and flexibility of the power grid. Summary of the Invention

[0005] This invention provides a method and system for calculating the renewable energy absorption capacity of a regional power grid, which is used to optimize the renewable energy absorption capacity of the regional power grid and improve the stability and adaptability of the power grid.

[0006] In a first aspect, the present invention provides a method for calculating the renewable energy absorption capacity of a regional power grid, mainly comprising:

[0007] Step S1: Obtain power grid node data and environmental influencing factors, use graph neural network to process the power grid topology, and obtain the dynamic index of electrical distance characterizing the dynamic efficiency of power transmission between power grid nodes;

[0008] Step S2: Based on the electrical distance dynamic index, determine the transmission capacity limit between nodes and the load distribution of the power grid to obtain the preliminary absorption capacity boundary; based on the environmental factors, adjust the preliminary absorption capacity boundary through an optimization algorithm to obtain the adjusted absorption capacity boundary;

[0009] Step S3: Based on the adjusted absorption capacity boundary, obtain the current actual supply and demand data of the power grid, calculate the supply and demand matching deviation based on the actual supply and demand data; based on the supply and demand matching deviation, integrate historical data and grid connection requirements to determine a real-time adjustment scheme for dynamically balancing the power grid supply and demand;

[0010] Step S4: Through the real-time adjustment scheme, integrate power flow calculation and stability assessment to obtain the final absorption capacity boundary; based on the final absorption capacity boundary, determine the grid stability, and determine the supply and demand matching path based on the grid stability and the supply and demand matching model.

[0011] As a preferred embodiment of the present invention, step S1 includes:

[0012] By collecting real-time voltage, current, and power data of power grid nodes, as well as wind speed and solar radiation intensity data in the environment, a dynamic representation of the power grid topology is constructed. The dynamic representation is then input into a pre-trained graph neural network, which includes a node feature extraction layer and an edge weight update layer. The electrical characteristics of each node are extracted through the node feature extraction layer to generate node feature vectors.

[0013] The edge weight update layer updates the edge weights in the topology based on the impedance changes between nodes and real-time voltage fluctuations; and calculates the dynamic index of electrical distance between nodes based on the node feature vectors and the updated edge weights.

[0014] As a preferred embodiment of the present invention, step S2, determining the inter-node transmission limits and load distribution based on the electrical distance dynamic index, and obtaining the preliminary absorption capacity boundary, includes:

[0015] Based on the aforementioned dynamic electrical distance index, the transmission line capacity limit of each node in the power grid is obtained. Based on the transmission line capacity limit, the degree of uneven load distribution of each node is calculated. By integrating random wind speed variations and solar radiation intensity data in the environment, the power generation output fluctuation range of each node is determined.

[0016] Based on the uneven load distribution and the fluctuation range of power generation output, a power transmission constraint model between nodes is constructed. Through the power transmission constraint model, the preliminary absorption capacity boundary of the power grid under the current state is calculated, wherein the preliminary absorption capacity boundary represents the maximum power absorption capacity of the power grid under dynamic environment.

[0017] As a preferred embodiment of the present invention, step S2, obtaining the adjusted absorption capacity boundary, includes:

[0018] Determine whether the initial absorption capacity boundary exceeds a preset threshold. If the initial absorption capacity boundary exceeds the preset threshold, then use a linear programming algorithm to adjust the load distribution of each node, integrate the influence of day and night cycles and seasonal output differences, and update the constraints of the linear programming algorithm.

[0019] The optimized load distribution scheme is calculated using the linear programming algorithm. Based on the optimized load distribution scheme, the grid absorption capacity boundary is redefined to obtain the adjusted absorption capacity boundary. The optimized absorption capacity boundary represents the maximum stable absorption capacity of the grid under dynamic conditions.

[0020] As a preferred embodiment of the present invention, step S3 involves calculating the supply-demand matching deviation based on the adjusted absorption capacity boundary and the current actual supply and demand data of the power grid, including:

[0021] Obtain current power grid supply and demand data, including power generation and load demand at each node, and calculate the supply and demand matching deviation at each node based on the adjusted absorption capacity boundary; for sudden weather events, obtain data on the impact of weather on the efficiency of power generation equipment.

[0022] By integrating the data on the impact of power generation equipment efficiency and the supply-demand matching deviation, a supply-demand deviation analysis model is constructed. Through the supply-demand deviation analysis model, the supply-demand matching deviation value of the power grid under the current state is determined, wherein the supply-demand matching deviation value characterizes the degree of balance between power supply and demand during power grid operation.

[0023] As a preferred embodiment of the present invention, step S3, determining the real-time adjustment scheme for power grid supply and demand, includes:

[0024] Acquire historical supply and demand data sequences, including power generation, load demand, and environmental data from past periods. Based on the supply and demand matching deviation, analyze the patterns in the historical supply and demand data sequences, integrate grid connection synchronization requirements, and determine the real-time constraints for grid operation.

[0025] Based on the real-time constraints and the response characteristics of the energy storage system, a real-time adjustment model is constructed; through the real-time adjustment model, a real-time adjustment scheme is generated, wherein the real-time adjustment scheme includes power allocation adjustment between nodes and energy storage system scheduling strategy.

[0026] As a preferred embodiment of the present invention, step S4, obtaining the final absorption capacity boundary, includes:

[0027] According to the real-time adjustment scheme, the power flow calculation model of the power grid is updated, and the voltage, current and power distribution of each node are obtained through the power flow calculation model. According to the power distribution, the stability assessment parameters of the power grid, including voltage stability and frequency stability, are calculated. The stability assessment parameters and the real-time adjustment scheme are fused to determine the final absorption capacity boundary of the power grid under the current operating state, wherein the final absorption capacity boundary represents the maximum power absorption capacity of the power grid after dynamic adjustment.

[0028] As a preferred embodiment of the present invention, step S4, determining the grid stability based on the final absorption capacity boundary, includes:

[0029] The system acquires operational status data of multiple nodes, including the voltage, power, and frequency of each node. Based on the final absorption capacity boundary, it analyzes the power transmission stability between multiple nodes and determines the impact of environmental factors on grid stability, taking into account random wind speed variations and solar radiation intensity.

[0030] The overall stability index of the power grid is calculated using a stability analysis model. Based on the overall stability index, it is determined whether the power grid is in a stable operating state. The overall stability index characterizes the operational reliability of the power grid under dynamic conditions.

[0031] As a preferred embodiment of the present invention, step S4, determining the supply-demand matching path based on the power grid stability and supply-demand matching model, includes:

[0032] Based on the grid stability, configuration data of backup power sources are obtained, including backup power source capacity and response time; data on diurnal cycle impact and sudden weather events are integrated to construct a supply-demand matching path model; the power dispatch path for each node is calculated using the supply-demand matching path model; and the precise supply-demand matching path is determined based on the power dispatch path, wherein the precise supply-demand matching path represents the optimal power allocation scheme of the grid under dynamic environment and backup power support.

[0033] Secondly, the present invention also provides a regional power grid renewable energy absorption capacity calculation system for implementing the above-mentioned method, the system comprising:

[0034] The data acquisition unit is used to acquire power grid node data and environmental influencing factors. It uses a graph neural network to process the power grid topology and obtains a dynamic index of electrical distance that characterizes the dynamic efficiency of power transmission between power grid nodes.

[0035] The capacity calculation unit is used to determine the transmission capacity limit between nodes and the load distribution of the power grid based on the electrical distance dynamic index, and obtain the preliminary absorption capacity boundary; based on the environmental factors, the preliminary absorption capacity boundary is adjusted by an optimization algorithm to obtain the adjusted absorption capacity boundary;

[0036] The supply and demand assessment unit is used to obtain the current actual supply and demand data of the power grid based on the adjusted absorption capacity boundary, calculate the supply and demand matching deviation based on the actual supply and demand data, and determine the real-time adjustment scheme for dynamically balancing the power grid supply and demand based on the supply and demand matching deviation and by integrating historical data and grid connection requirements.

[0037] The stability assessment unit is used to integrate power flow calculation and stability assessment through the real-time adjustment scheme to obtain the final absorption capacity boundary; to determine the grid stability based on the final absorption capacity boundary; and to determine the supply and demand matching path based on the grid stability and the supply and demand matching model.

[0038] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0039] This invention utilizes graph neural networks to process power grid node data and environmental influencing factors, thereby obtaining dynamic electrical distance indicators. These indicators provide fundamental support for subsequent capacity calculations and load allocation. Furthermore, it combines the power grid topology to determine transmission capacity limitations between nodes, calculates preliminary absorption capacity boundaries, and adjusts these boundaries using optimization algorithms based on environmental factors, ensuring the power grid can adapt to different external conditions. Based on the adjusted absorption capacity boundaries, actual power grid supply and demand data are used to calculate supply and demand matching deviations. By integrating historical data and grid connection requirements, a real-time adjustment scheme for dynamically balancing power grid supply and demand is formulated to effectively balance the power grid's supply and demand status. This adjustment scheme not only considers existing load distribution and generation capacity but also incorporates real-time weather changes. The impact on power generation equipment efficiency is addressed to better adapt to environmental fluctuations. In further optimization, power flow calculation and stability assessment are integrated into the real-time adjustment scheme to obtain the final absorption capacity boundary. This boundary is determined based on the current stability of the power grid. By analyzing load distribution and power transmission paths among grid nodes, an optimal power distribution scheme is ultimately formed to ensure efficient and stable grid operation and avoid overload and power waste. Through the synergy of these technical solutions, the grid's absorption capacity in dynamic environments can be effectively improved, and resource utilization optimized, thereby significantly enhancing grid stability and the capacity to accept new energy sources. This is particularly beneficial under conditions of fluctuating environmental factors such as wind speed and solar radiation intensity, effectively reducing the risks associated with supply-demand imbalances. Attached Figure Description

[0040] Figure 1 This is a flowchart of a method for calculating the renewable energy absorption capacity of a regional power grid according to the present invention.

[0041] Figure 2 This is a structural diagram of a regional power grid renewable energy absorption capacity calculation system according to the present invention. Detailed Implementation

[0042] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0043] like Figure 1 This embodiment of a method for determining grid absorption capacity may specifically include:

[0044] Step S1: Obtain power grid node data and environmental influencing factors, and use a graph neural network to process the power grid topology to obtain a dynamic index of electrical distance characterizing the dynamic efficiency of power transmission between power grid nodes; specifically including:

[0045] By collecting real-time voltage, current, and power data of power grid nodes, as well as wind speed and solar radiation intensity data in the environment, a dynamic representation of the power grid topology is constructed. The dynamic representation is then input into a pre-trained graph neural network, which includes a node feature extraction layer and an edge weight update layer. The electrical characteristics of each node are extracted through the node feature extraction layer to generate node feature vectors.

[0046] The edge weight update layer updates the edge weights in the topology based on the impedance changes between nodes and real-time voltage fluctuations; and calculates the dynamic index of electrical distance between nodes based on the node feature vectors and the updated edge weights.

[0047] Specifically, in this embodiment, a dynamic representation of the power grid topology is constructed by first collecting real-time voltage, current, and power data of the power grid nodes, as well as wind speed and solar radiation intensity data in the environment. Voltage data reflects the instantaneous power transmission status between the nodes of the power grid, current data indicates the load flow, and power data quantifies the energy distribution of each node. In addition, wind speed and solar radiation intensity data are used as environmental variables to take into account the output fluctuations of renewable energy sources, so that the dynamic representation of the power grid can more comprehensively reflect its actual operating status. After fusing the above multi-dimensional data, a graph structure containing power grid nodes and transmission lines (edges) is constructed, where node features describe the electrical attributes of the power grid nodes, and edges describe the power transmission relationships between nodes.

[0048] The constructed dynamic representation is input into a pre-trained graph neural network, which includes a node feature extraction layer and an edge weight update layer. The graph neural network adopts a graph convolutional network architecture and simulates the topological dynamics of the power grid and changes in environmental factors through the pre-trained network. In the node feature extraction layer, the voltage, current, and power data of each node are nonlinearly transformed by a multilayer perceptron to generate a feature vector for each node. The feature vector contains the electrical characteristics of the node, such as impedance, phase angle, and power factor. In the edge weight update layer, the edge weights in the topology are dynamically updated by considering the impedance changes between nodes and real-time voltage fluctuations to ensure that the edge weights reflect the real-time transmission resistance of the power grid. The updated edge weights are weighted through an attention mechanism to ensure that the edge weights can accurately respond to changes in the power grid when voltage fluctuations are large.

[0049] Based on this, the dynamic electrical distance index between nodes is calculated according to the node feature vectors and the updated edge weights. The dynamic electrical distance index is calculated using the weighted shortest path algorithm. In this algorithm, the node feature vectors represent the characteristics of the nodes themselves, and the edge weights represent the dynamic efficiency of power transmission. By constructing an adjacency matrix and using Dijkstra's algorithm to calculate the path distance between any two nodes, and multiplying it by the norm of the node feature vectors, the dynamic electrical distance index is finally obtained. The smaller the value of this index, the higher the power transmission efficiency between nodes, and vice versa.

[0050] The above-mentioned technical solution, based on the graph neural network-based power grid dynamic modeling method, can reflect the operating status of the regional power grid under different environmental conditions in real time. Through continuous iterative optimization, the power grid can dynamically adjust the load distribution and power transmission path when facing complex environmental factors such as wind speed changes and solar radiation intensity fluctuations, thereby improving the overall efficiency and robustness of the power grid. It can also adapt to the operation of the power grid under extreme weather conditions. When environmental variables such as wind speed and solar radiation intensity change, it can accurately capture the dynamic characteristics of power transmission, ensure the stability and load balance of the power grid under unstable conditions, and provide accurate data support for the optimized scheduling of the power system.

[0051] Step S2: Based on the electrical distance dynamic index, determine the transmission capacity limit between nodes and the load distribution of the power grid to obtain the preliminary absorption capacity boundary; based on the environmental factors, adjust the preliminary absorption capacity boundary through an optimization algorithm to obtain the adjusted absorption capacity boundary;

[0052] In step S2, based on the electrical distance dynamic index, the transmission limitations and load distribution between nodes are determined to obtain the preliminary absorption capacity boundary, including:

[0053] Based on the aforementioned dynamic electrical distance index, the transmission line capacity limit of each node in the power grid is obtained. Based on the transmission line capacity limit, the degree of uneven load distribution of each node is calculated. By integrating random wind speed variations and solar radiation intensity data in the environment, the power generation output fluctuation range of each node is determined.

[0054] Based on the uneven load distribution and the fluctuation range of power generation output, a power transmission constraint model between nodes is constructed. Through the power transmission constraint model, the preliminary absorption capacity boundary of the power grid under the current state is calculated, wherein the preliminary absorption capacity boundary represents the maximum power absorption capacity of the power grid under dynamic environment.

[0055] Specifically, based on the aforementioned dynamic electrical distance index, the transmission line capacity limits of each node in the power grid are first obtained. This involves processing real-time data from the power grid nodes using a graph neural network, integrating environmental factors such as wind speed and solar radiation intensity, and combining this with impedance changes and voltage fluctuations between nodes to calculate the dynamic electrical distance index. This index uses a graph neural network to map changes in the power grid topology and fluctuations in external environmental factors to electrical transmission efficiency between nodes, thereby determining the transmission line capacity limits. Based on this, the degree of load unevenness at each node is calculated using the dynamic electrical distance index. This unevenness is measured using statistical methods such as standard deviation to measure the load deviation between nodes, reflecting the differences in load carrying capacity at different nodes of the power grid. By using data on random wind speed variations and solar radiation intensity, the power generation output fluctuation range of each node is determined. Specifically, through Monte Carlo simulation and historical data fitting, scenario samples with different wind speeds and solar radiation intensities are generated, thereby deriving the upper and lower limits of power generation output fluctuation for each node. This ensures that the grid's absorption capacity can be adjusted and optimized in real time under extreme weather or environmental changes. For the aforementioned power generation output fluctuation range, a power transmission constraint model between nodes is constructed in conjunction with the degree of load unevenness. This power transmission constraint model is based on a linear programming algorithm, incorporating the unevenness of load distribution and the volatility of power generation output. The goal is to minimize power transmission losses while satisfying capacity constraints and power generation fluctuation constraints, thereby optimizing the grid's resource utilization efficiency.

[0056] The aforementioned power transmission constraint model calculates the initial absorption capacity boundary of the power grid under the current state. This initial absorption capacity boundary defines the maximum power absorption capacity of the power grid in a dynamic environment, ensuring that the power grid can effectively handle the challenges brought about by uneven load distribution and environmental fluctuations in actual operation, thereby achieving efficient power transmission and stable operation. The above technical solution, by combining real-time power grid data and environmental data, constitutes an accurate power grid absorption capacity assessment mechanism, providing a scientific basis for the optimized scheduling and dynamic balance of the power grid.

[0057] Further, in step S2, the adjusted absorption capacity boundary is obtained, including:

[0058] Determine whether the initial absorption capacity boundary exceeds a preset threshold. If the initial absorption capacity boundary exceeds the preset threshold, then use a linear programming algorithm to adjust the load distribution of each node, integrate the influence of day and night cycles and seasonal output differences, and update the constraints of the linear programming algorithm.

[0059] The optimized load distribution scheme is calculated using the linear programming algorithm. Based on the optimized load distribution scheme, the grid absorption capacity boundary is redefined to obtain the adjusted absorption capacity boundary. The adjusted absorption capacity boundary represents the maximum stable absorption capacity of the grid under dynamic conditions.

[0060] Specifically, based on the aforementioned dynamic electrical distance index, it is determined whether the preliminary absorption capacity boundary exceeds a preset threshold. If the preliminary absorption capacity boundary exceeds the set threshold, a linear programming algorithm is used to adjust the load distribution of each node, thereby optimizing the overall load balance of the power grid. The constraints of the linear programming consider the influence of the diurnal cycle and seasonal output differences. The aforementioned environmental factors, such as the changes in solar radiation during the day and night, and the differences in wind speed between summer and winter, are quantified and integrated into the constraints of the linear programming model to reflect the dynamic characteristics of the power transmission process. Among them, the diurnal cycle influence refers to the peak solar radiation during the day and the low solar radiation during the night, while the seasonal output difference reflects the trend of higher wind speed and increased wind power output in summer, and lower wind speed and weakened solar radiation intensity in winter. Through the weighted processing of the aforementioned periodic changes, the updated linear programming algorithm constraints are more in line with the actual operation requirements of the power grid, thereby enabling the adjusted load distribution scheme to optimize the load balance of each node in the power grid, ensuring that the load distribution between nodes does not exceed the capacity limit of the nodes, and can also effectively cope with the load fluctuations caused by environmental changes.

[0061] The optimized linear programming scheme yields a load distribution plan that redefines the grid's absorption capacity boundary, resulting in an adjusted absorption capacity boundary. This boundary represents the grid's maximum stable absorption capacity under dynamic conditions. The adjusted boundary not only considers load distribution optimization and reasonable capacity allocation but also ensures efficient grid operation under extreme weather and seasonal fluctuations through stability and resource utilization analysis. In some embodiments, combining wind speed and solar radiation data, the adjusted absorption capacity boundary characterizes the grid's maximum absorption capacity at a first wind speed and first radiation intensity, effectively enhancing the grid's ability to absorb renewable energy and reducing energy waste. In other embodiments, from the perspective of grid stability, calculating the adjusted boundary enhances the grid's resilience to sudden weather events and ensures supply-demand matching, ultimately leading to efficient utilization of grid resources and improved overall grid performance. These technical solutions enable the adjusted absorption capacity boundary to comprehensively characterize the grid's maximum stable absorption capacity under different environmental conditions and provide a scientific basis for grid optimization scheduling and dynamic balancing.

[0062] Step S3: Based on the adjusted absorption capacity boundary, obtain the current actual supply and demand data of the power grid, calculate the supply and demand matching deviation based on the actual supply and demand data; based on the supply and demand matching deviation, integrate historical data and grid connection requirements to determine a real-time adjustment scheme for dynamically balancing the power grid supply and demand;

[0063] In step S3, the supply-demand matching deviation is calculated based on the adjusted absorption capacity boundary and the current actual supply and demand data of the power grid, including:

[0064] Obtain the actual supply and demand data of the current power grid, including the power generation and load demand of each node, and calculate the supply and demand matching deviation of each node based on the optimized absorption capacity boundary; for sudden weather events, obtain data on the impact of weather on the efficiency of power generation equipment.

[0065] By integrating the data on the impact of power generation equipment efficiency and the supply-demand matching deviation, a supply-demand deviation analysis model is constructed. Through the supply-demand deviation analysis model, the supply-demand matching deviation value of the power grid under the current state is determined, wherein the supply-demand matching deviation value characterizes the degree of balance between power supply and demand during power grid operation.

[0066] Specifically, based on the adjusted absorption capacity boundary and the current actual supply and demand data of the power grid, the actual supply and demand data of the current power grid are first obtained, including the power generation and load demand of each power grid node. For example, the power generation data of wind farm nodes is collected through a real-time monitoring system, recording the output power of wind turbine generators as 500MW and the load demand as 450MW. Combined with the adjusted absorption capacity boundary, the supply and demand matching deviation of each node is calculated. The method for calculating the supply and demand matching deviation is to first use the adjusted boundary value, such as 480MW, as a benchmark, then calculate the deviation as power generation minus load demand, and then compare it with the boundary value to obtain a deviation of 20MW. This process helps to quantify the degree of power supply and demand balance of the power grid under the current state.

[0067] To address sudden weather events, such as storms and other extreme weather conditions, it is necessary to obtain data on the impact of weather on the efficiency of power generation equipment. This involves first collecting data on sudden weather events using meteorological sensors, such as wind speeds reaching preset levels and rainfall amounts set at a predetermined level. Based on the collected weather data, the percentage reduction in power generation equipment efficiency is calculated. For example, the efficiency of wind turbines may decrease under high wind speeds, and the efficiency of solar panels may decrease during rainfall. This impact data is integrated into an impact data table for subsequent supply-demand matching deviation analysis. After obtaining the data on the impact of weather on power generation equipment, this efficiency impact data is weighted and fused with the supply-demand matching deviation to construct a supply-demand deviation analysis model. The model construction process includes fusing efficiency impact data, such as the percentage reduction in efficiency, with the deviation amount. Specifically, a linear regression method can be used, employing least squares to fit the relationship between efficiency reduction values ​​(such as efficiency reduction due to wind speed changes) and the deviation amount, thereby calculating regression coefficients. This constructs the deviation model equation. The model takes efficiency data and deviation data as input and outputs a comprehensive deviation index to further verify the model's accuracy.

[0068] To address the random fluctuations in wind speed, Support Vector Regression (SVR) is used instead of traditional linear regression. SVR maps data to a high-dimensional space using kernel functions such as radial basis functions, minimizing prediction errors. Especially in power grids with significant seasonal output variations, SVR provides a more robust deviation model. To address the impact of diurnal cycles, nighttime efficiency data is weighted during model construction to reflect the amplified effect of nighttime deviations. Through time series analysis, such as autoregressive integral moving average, the model effectively captures periodic fluctuations, supporting the optimized response of energy storage systems. A supply-demand deviation analysis model is used to determine the supply-demand matching deviation of the power grid under current conditions. This deviation value characterizes the degree of balance between power supply and demand during grid operation, further helping to adjust the grid's absorption capacity boundary. When the deviation value exceeds a set threshold, it indicates an imbalance between power supply and demand, requiring adjustment through boundary optimization to ensure stable operation and efficient absorption capacity of the power grid in dynamic environments.

[0069] Furthermore, in step S3, the real-time adjustment scheme for power grid supply and demand is determined, including:

[0070] Acquire historical supply and demand data sequences, including power generation, load demand, and environmental data from past periods. Based on the supply and demand matching deviation, analyze the patterns in the historical supply and demand data sequences, integrate grid connection synchronization requirements, and determine the real-time constraints for grid operation.

[0071] Based on the real-time constraints and the response characteristics of the energy storage system, a real-time adjustment model is constructed; through the real-time adjustment model, a real-time adjustment scheme is generated, wherein the real-time adjustment scheme includes power allocation adjustment between nodes and energy storage system scheduling strategy.

[0072] Specifically, the process begins by acquiring historical supply and demand data sequences, including power generation, load demand, and environmental data from past periods, to construct the foundation of the power grid's supply and demand data. This involves collecting real-time output data of wind and solar power generation over a defined time period (e.g., 24 hours) from various nodes of the power grid, along with load demand curves and relevant environmental data such as wind speed and solar radiation intensity. This data is then compiled into a time series to ensure coverage of diurnal variations, facilitating pattern extraction and trend identification in subsequent analysis. Furthermore, based on supply and demand mismatches, patterns in the historical supply and demand data sequences are analyzed. This is achieved using time series analysis methods, such as the Autoregressive Integral Moving Average (ARIMA) model, to extract patterns from historical data and identify periodic fluctuations and characteristics of supply and demand mismatches, such as power generation fluctuations caused by wind speed variations. The model eliminates trend components in the data through differencing and calculates the autocorrelation function to identify recurring supply and demand mismatch patterns, forming a pattern feature vector for further integration with grid synchronization requirements and other real-time constraints.

[0073] The model also combines grid synchronization requirements with historical patterns to determine real-time constraints for grid operation. These constraints include voltage and frequency synchronization standards, ensuring impedance changes between nodes do not exceed predetermined thresholds, and that generation equipment matches the phase and frequency of the grid. For handling sudden weather events, real-time constraints also include impedance changes caused by storms. These factors are integrated into the model through the collection and analysis of real-time meteorological data to ensure stable grid operation under dynamic conditions. After determining the real-time constraints, a real-time adjustment model is constructed based on the response characteristics of the energy storage system. This model uses linear programming, minimizing the supply-demand deviation as the objective function, and incorporates real-time constraints such as the energy storage system's discharge rate, maximum and minimum limits for node power allocation, and energy storage response delays such as battery discharge response time. This allows the model to capture the characteristics of the energy storage system, including the time delay between receiving dispatch commands and actual power output. Furthermore, the model considers weather factors such as fluctuations in solar radiation intensity and incorporates random variable simulations for wind speed variations to calculate expected values ​​and improve the model's robustness, ensuring that the real-time adjustment scheme can adapt to complex environmental changes.

[0074] By constructing the aforementioned real-time adjustment model, a real-time adjustment scheme is generated. This scheme includes power allocation adjustment between nodes and energy storage system scheduling strategies. The current supply-demand matching deviation is input into the real-time adjustment model to obtain the optimal power allocation scheme for each node. For example, excess wind power is transferred from nodes with lower loads to nodes with higher loads. Furthermore, the energy storage system scheduling strategy is optimized based on the magnitude of the deviation. For instance, when the deviation exceeds a set threshold, the energy storage system's discharge process is activated, thereby balancing the grid's supply-demand deviation. Through this technical solution, the grid can maintain efficient and stable operation in a dynamic environment, ensuring the optimal utilization of power resources and improving system robustness. It also forms an efficient supply-demand matching adjustment scheme capable of coping with various sudden and periodic changes, improving the grid's adaptability and stability.

[0075] Step S4: Through the real-time adjustment scheme, integrate power flow calculation and stability assessment to obtain the final absorption capacity boundary; based on the final absorption capacity boundary, determine the grid stability, and determine the supply and demand matching path based on the grid stability and the supply and demand matching model.

[0076] In step S4, the final absorption capacity boundary is obtained, including:

[0077] According to the real-time adjustment scheme, the power flow calculation model of the power grid is updated, and the voltage, current and power distribution of each node are obtained through the power flow calculation model. According to the power distribution, the stability assessment parameters of the power grid, including voltage stability and frequency stability, are calculated. The stability assessment parameters and the real-time adjustment scheme are fused to determine the final absorption capacity boundary of the power grid under the current operating state, wherein the final absorption capacity boundary represents the maximum power absorption capacity of the power grid after dynamic adjustment.

[0078] Specifically, according to the above real-time adjustment scheme, the power flow calculation model of the power grid is first updated. This involves collecting real-time data from power grid nodes and weather-related factors, processing the dynamic changes in the power grid topology using a graph neural network, and integrating impedance changes and real-time voltage fluctuations between nodes to obtain dynamic electrical distance indicators. Based on these dynamic electrical distance indicators, the input parameters in the power flow calculation model are adjusted. In particular, by incorporating the influence of random wind speed variations, the model is ensured to adapt to the current state of the power grid and accurately reflect uneven load distribution and transmission line capacity limitations.

[0079] After updating the power flow calculation model, the updated model is used to calculate the power flow, obtaining the voltage, current, and power distribution of each node. Specifically, the Newton-Raphson iterative method is used to solve for the voltage amplitude, phase angle, and power value of each node in the power grid, thereby obtaining the power flow direction between nodes and serving as the power distribution of the nodes in the power grid. This data provides a basis for subsequent stability assessment. Based on the calculated power distribution, the stability of the power grid is further evaluated, mainly including voltage stability and frequency stability. Voltage stability is assessed by calculating the voltage deviation and load margin of each node. Voltage stability is typically assessed by using the continuous power flow method to track the voltage collapse point, or the instability critical point. In this state, the grid voltage is on the verge of instability, and any small load increase or system disturbance, such as generator tripping or line fault, can cause a sharp and uncontrollable drop in voltage, eventually leading to partial or complete system failure. Frequency stability is assessed by evaluating the imbalance of active power in the power distribution to calculate the frequency deviation rate, i.e., the frequency change rate of active power. In order to comprehensively reflect the stability of the power grid, the effects of day and night cycles and seasonal power output differences are also taken into account. A weighted average of voltage and frequency stability is then used to obtain a comprehensive stability assessment index.

[0080] By combining the aforementioned stability assessment parameters with the load optimization values ​​in the real-time adjustment scheme, a weighted summation method is used to fuse voltage stability and frequency stability. Voltage stability is assigned a weight of 0.6, and frequency stability is assigned another weight of 0.4. This allows for the calculation of comprehensive stability assessment parameters. Based on these assessment results, a preliminary absorption capacity boundary is determined. This boundary is further modified according to seasonal power output differences to ensure stable grid operation under different seasonal conditions. Based on the modified absorption capacity boundary, the final absorption capacity boundary of the grid is determined. This final boundary represents the grid's maximum power absorption capacity under the current dynamic environment. By weightedly fusing multiple factors, including multi-node information, random wind speed variations, and voltage and frequency stability, the final determined absorption capacity boundary effectively addresses sudden weather events and environmental changes, improving grid stability and the absorption capacity of renewable energy. For example, the absorption capacity boundary can be increased for daytime scenarios with high solar radiation intensity, while the boundary may be adjusted to a conservative value when wind speed fluctuates significantly at night to ensure that the grid is not overloaded. In addition, backup power configuration is also taken into consideration. For example, when the backup power response time is long, the absorption capacity boundary may be appropriately expanded to achieve precise matching of supply and demand.

[0081] The aforementioned technical solution generates a final absorption capacity boundary that represents the maximum absorption capacity of the power grid after dynamic adjustment. It can operate efficiently and safely under different environmental conditions, maximize the utilization rate of renewable energy, reduce energy waste, and improve the adaptability and stability of the power grid under extreme conditions.

[0082] Further, in step S4, determining grid stability based on the final absorption capacity boundary includes:

[0083] The system acquires operational status data of multiple nodes, including the voltage, power, and frequency of each node. Based on the final absorption capacity boundary, it analyzes the power transmission stability between multiple nodes and determines the impact of environmental factors on grid stability, taking into account random wind speed variations and solar radiation intensity.

[0084] The overall stability index of the power grid is calculated using a stability analysis model. Based on the overall stability index, it is determined whether the power grid is in a stable operating state. The overall stability index characterizes the operational reliability of the power grid under dynamic conditions.

[0085] Specifically, based on the aforementioned final absorption capacity boundary, the operating status data of multiple nodes is obtained. This operating status data includes the voltage, power, and frequency of each node. Data is collected in real time from sensors and monitoring equipment in the power grid. Voltage data reflects the potential level of the nodes, power data represents active and reactive power values, and frequency data shows the synchronization status of the node data. With the support of this basic data, combined with the final absorption capacity boundary, the stability of power transmission between multiple nodes is analyzed. Specifically, the final absorption capacity boundary is first used as a reference threshold, and it is combined with the collected voltage and power data to calculate the transmission path between each node. The load factor, obtained by dividing the power value by the boundary capacity, is used to assess whether transmission is nearing saturation. When the load factor exceeds a set value, such as 0.8, the path is marked as a high-risk path, which helps to identify potential transmission instability areas early, thereby improving the efficiency of preventive adjustments to the power grid and ensuring timely intervention when facing high load conditions to avoid transmission bottlenecks. Furthermore, the impact of environmental factors such as random wind speed variations and solar radiation intensity on power grid stability is determined by collecting real-time monitoring data of wind speed and solar radiation. Wind speed variations are measured every minute using an anemometer. The changes in solar radiation intensity are recorded hourly averages using radiometers. This data is used to calculate environmental impact coefficients, such as the wind power output deviation caused by wind speed changes, quantified using historical statistical models. The impact of solar radiation intensity on photovoltaic power generation is expressed as the product of output, radiation intensity, and conversion efficiency. When wind speed varies, the power injection into the wind farm may fluctuate; the impact coefficient of this fluctuation effectively reflects the disturbance to the power grid caused by sudden wind speed changes. Furthermore, changes in solar radiation intensity also affect the output of photovoltaic power plants, especially in scenarios with significant seasonal variations such as summer and winter. The changes in the impact coefficient can... This helps the power grid optimize energy storage configuration to meet stability requirements. By combining the aforementioned environmental impact data with node power fluctuation data, it further simulates the disturbances of the environment on power transmission stability. In particular, when wind speed changes suddenly, uneven power injection may lead to frequency shifts. This can help identify situations where local node power increases in windy summer scenarios. For example, when the wind speed increases from 5 m / s to 15 m / s, the impact coefficient can reach 1.5, resulting in a 20% increase in local node power, thereby increasing the risk of transmission instability. This allows the power grid to improve its adaptability to renewable energy fluctuations and reduce power transmission risks caused by environmental changes.

[0086] Subsequently, based on the acquired data and analysis, a stability analysis model was established to calculate the overall stability index of the power grid. This model employs a small-signal stability analysis method, evaluating the response after a disturbance by linearizing the system equations. First, a state matrix is ​​constructed, and eigenvalues ​​are extracted from the collected power grid data. The negative real part of the eigenvalue indicates the convergence of the system. By inputting environmental influence coefficients and transmitted stability data into the model, the stability index is calculated. A commonly used index is the reciprocal of the modulus of the eigenvalue; a larger value indicates higher power grid stability, ensuring that the power grid can respond to disturbances in real time and maintain stable operation.

[0087] The system also determines whether the power grid is in a stable operating state based on the calculated overall stability index. When the stability index exceeds a preset threshold, such as 0.9, the power grid is considered to be in a stable operating state. If the stability index is lower than the threshold, an alarm mechanism is triggered, indicating that the power grid is in an unstable state and requires further adjustments. This ensures that the stability of the final absorption capacity boundary is effectively verified, thereby ensuring that the power grid can operate safely and reliably in a dynamic environment and achieve maximum absorption capacity for renewable energy.

[0088] Further, in step S4, determining the supply-demand matching path based on the power grid stability and supply-demand matching model includes:

[0089] Based on the grid stability, configuration data of backup power sources are obtained, including backup power source capacity and response time; data on diurnal cycle impact and sudden weather events are integrated to construct a supply-demand matching path model; the power dispatch path for each node is calculated using the supply-demand matching path model; and the precise supply-demand matching path is determined based on the power dispatch path, wherein the precise supply-demand matching path represents the optimal power allocation scheme of the grid under dynamic environment and backup power support.

[0090] Specifically, based on grid stability, configuration data for backup power sources is obtained. This configuration data includes the capacity and response time of the backup power sources. Specifically, by querying backup power source records related to grid stability in the grid database, the capacity and response time of the backup power sources can be directly extracted. This data will provide fundamental support for subsequent power dispatch, ensuring that the grid can respond quickly under load fluctuations or emergencies and maintain system stability. Furthermore, the impact of diurnal cycles and sudden weather event data are integrated to construct a supply-demand matching path model. Due to diurnal cycle variations, especially fluctuations in solar radiation intensity, and the impact of sudden weather events such as wind speed changes on power generation, these are factors that cannot be ignored in grid supply-demand matching. By collecting and integrating the aforementioned environmental factor data, such as peak solar radiation intensity during the day and zero intensity at night, as well as random wind speed variations, the supply-demand matching model can reflect the actual power generation and load demand of the grid under different time periods and weather conditions. The power source configuration data, the data on diurnal cycle influences, and sudden weather event data are input into a graph neural network. Nodes represent grid nodes, and edges represent dynamic indicators of electrical distance. The model is trained to predict supply-demand deviations and optimizes the supply-demand matching path based on historical data sequences and real-time adjustment schemes.

[0091] The power dispatch path for each node is calculated using the constructed supply-demand matching path model. Specifically, the transmission line capacity limitations and uneven load distribution data of each node are first input into the supply-demand matching model. The model then applies a linear programming algorithm, using the minimization of supply-demand deviation as the objective function, and sets constraints, such as the backup power response time not exceeding a set duration, to optimize power flow. The power dispatch path generated by the above process ensures that the power grid can minimize supply-demand imbalance when the load changes or the environment fluctuates. For example, in the event of sudden weather events such as storms, the path calculation prioritizes stability assessment parameters to ensure that overloaded nodes are avoided during the dispatch process, further enhancing the stability of the power grid.

[0092] Finally, based on the power dispatch path, a precise supply-demand matching path is determined. This path represents the optimal power allocation scheme of the power grid under dynamic environments and with the support of backup power sources. Specifically, by aggregating the dispatch path results, the path with the smallest deviation is selected as the precise matching path. For example, calculations show that in the final scheme, the capacity utilization rate of the backup power source is not lower than a set threshold, such as 80%, and the response time is controlled within a set duration, thereby achieving optimal power allocation for the power grid. Under the influence of the day-night cycle, the above path ensures that nighttime loads can be supplemented by backup power sources, reducing fluctuations and improving the grid's absorption capacity and overall stability. This supply-demand matching model, through multi-node information integration, especially in handling scenarios of random wind speed changes and solar radiation intensity variations, ensures that the power grid can optimize power allocation under variable environmental conditions, maximizing resource utilization and improving grid stability and the absorption capacity of renewable energy.

[0093] This invention also provides a regional power grid renewable energy absorption capacity calculation system for implementing the above-mentioned method, such as... Figure 2 As shown, the system includes:

[0094] The data acquisition unit is used to acquire power grid node data and environmental influencing factors. It uses a graph neural network to process the power grid topology and obtains a dynamic index of electrical distance that characterizes the dynamic efficiency of power transmission between power grid nodes.

[0095] The capacity calculation unit is used to determine the transmission capacity limit between nodes and the load distribution of the power grid based on the electrical distance dynamic index, and obtain the preliminary absorption capacity boundary; based on the environmental factors, the preliminary absorption capacity boundary is adjusted by an optimization algorithm to obtain the adjusted absorption capacity boundary;

[0096] The supply and demand assessment unit is used to obtain the current actual supply and demand data of the power grid based on the adjusted absorption capacity boundary, calculate the supply and demand matching deviation based on the actual supply and demand data, and determine the real-time adjustment scheme for dynamically balancing the power grid supply and demand based on the supply and demand matching deviation and by integrating historical data and grid connection requirements.

[0097] The stability assessment unit is used to integrate power flow calculation and stability assessment through the real-time adjustment scheme to obtain the final absorption capacity boundary; to determine the grid stability based on the final absorption capacity boundary; and to determine the supply and demand matching path based on the grid stability and the supply and demand matching model.

[0098] In summary, this invention utilizes graph neural networks to process power grid node data and environmental influencing factors, thereby obtaining dynamic electrical distance indicators. These indicators provide fundamental support for subsequent capacity calculations and load allocation. Furthermore, by considering the power grid topology, it determines the transmission capacity limitations between nodes, calculates the initial absorption capacity boundary, and adjusts this boundary using optimization algorithms based on environmental factors, ensuring the power grid can adapt to different external conditions. Based on the adjusted absorption capacity boundary, the actual supply and demand data of the power grid are used to calculate the supply and demand matching deviation. By integrating historical data and grid connection requirements, a real-time adjustment scheme for dynamically balancing power grid supply and demand is formulated to effectively balance the power grid's supply and demand status. This adjustment scheme not only considers the existing load distribution and power generation capacity but also incorporates real-time weather changes. The optimization process aims to mitigate the impact of power generation equipment efficiency on environmental fluctuations. Power flow calculation and stability assessment are integrated into the real-time adjustment scheme to determine the final absorption capacity boundary. This boundary is determined based on the current stability of the power grid. By analyzing load distribution and power transmission paths among grid nodes, an optimal power allocation scheme is formed to ensure efficient and stable grid operation and avoid overload and power waste. Through the synergy of these technical solutions, the grid's absorption capacity in dynamic environments can be effectively improved, and resource utilization optimized. This significantly enhances grid stability and the capacity to accept new energy sources, particularly reducing the risks associated with supply-demand imbalances under fluctuating environmental factors such as wind speed and solar radiation intensity.

[0099] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit the scope of one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the protection scope of one or more embodiments of this specification.

Claims

1. A method for calculating the renewable energy absorption capacity of a regional power grid, characterized in that, include: Step S1: Obtain power grid node data and environmental influencing factors, use graph neural network to process the power grid topology, and obtain the dynamic index of electrical distance characterizing the dynamic efficiency of power transmission between power grid nodes; Step S2: Based on the electrical distance dynamic index, determine the transmission capacity limit between nodes and the load distribution of the power grid to obtain the preliminary absorption capacity boundary; adjust the preliminary absorption capacity boundary based on environmental factors using an optimization algorithm to obtain the adjusted absorption capacity boundary; Step S3: Based on the adjusted absorption capacity boundary, obtain the current actual supply and demand data of the power grid, and calculate the supply and demand matching deviation based on the actual supply and demand data; Based on the supply and demand mismatch, and by integrating historical data and grid connection requirements, a real-time adjustment scheme for dynamically balancing the power grid supply and demand is determined. Step S4: Through the real-time adjustment scheme, integrate power flow calculation and stability assessment to obtain the final absorption capacity boundary; based on the final absorption capacity boundary, determine the grid stability, and determine the supply and demand matching path based on the grid stability and the supply and demand matching model; Obtaining the initial absorption capacity boundary includes: Based on the aforementioned dynamic electrical distance index, the transmission line capacity limit of each node in the power grid is obtained. Based on the transmission line capacity limit, the degree of uneven load distribution of each node is calculated. By integrating random wind speed variation and solar radiation intensity data in the environment, the power generation output fluctuation range of each node is determined. Based on the uneven load distribution and the fluctuation range of power generation output, a power transmission constraint model between nodes is constructed. Through the power transmission constraint model, the preliminary absorption capacity boundary of the power grid under the current state is calculated, wherein the preliminary absorption capacity boundary represents the maximum power absorption capacity of the power grid under dynamic environment.

2. The method as described in claim 1, characterized in that, Step S1 includes: By collecting real-time voltage, current, and power data of power grid nodes, as well as wind speed and solar radiation intensity data in the environment, a dynamic representation of the power grid topology is constructed. The dynamic representation is then input into a pre-trained graph neural network, which includes a node feature extraction layer and an edge weight update layer. The electrical characteristics of each node are extracted through the node feature extraction layer to generate node feature vectors. The edge weight update layer updates the edge weights in the topology based on the impedance changes between nodes and real-time voltage fluctuations; and calculates the dynamic index of electrical distance between nodes based on the node feature vectors and the updated edge weights.

3. The method as described in claim 1, characterized in that, In step S2, the adjusted absorption capacity boundary is obtained, including: Determine whether the initial absorption capacity boundary exceeds a preset threshold. If the initial absorption capacity boundary exceeds the preset threshold, then use a linear programming algorithm to adjust the load distribution of each node, integrate the influence of day and night cycles and seasonal output differences, and update the constraints of the linear programming algorithm. The optimized load distribution scheme is calculated using the linear programming algorithm. Based on the optimized load distribution scheme, the power grid absorption capacity boundary is redefined to obtain the adjusted absorption capacity boundary. The adjusted absorption capacity boundary represents the maximum stable absorption capacity of the power grid under dynamic conditions.

4. The method as described in claim 1, characterized in that, In step S3, based on the adjusted absorption capacity boundary and the current actual supply and demand data of the power grid, the supply and demand matching deviation is calculated, including: Obtain current power grid supply and demand data, including power generation and load demand at each node, and calculate the supply and demand matching deviation at each node based on the adjusted absorption capacity boundary; for sudden weather events, obtain data on the impact of weather on the efficiency of power generation equipment. By integrating the data on the impact of power generation equipment efficiency and the supply-demand matching deviation, a supply-demand deviation analysis model is constructed. Through the supply-demand deviation analysis model, the supply-demand matching deviation value of the power grid under the current state is determined, wherein the supply-demand matching deviation value characterizes the degree of balance between power supply and demand during power grid operation.

5. The method as described in claim 4, characterized in that, In step S3, the real-time adjustment scheme for power grid supply and demand is determined, including: Acquire historical supply and demand data sequences, including power generation, load demand, and environmental data from past periods. Based on the supply and demand matching deviation, analyze the patterns in the historical supply and demand data sequences, integrate grid connection synchronization requirements, and determine the real-time constraints for grid operation. Based on the real-time constraints and the response characteristics of the energy storage system, a real-time adjustment model is constructed; through the real-time adjustment model, a real-time adjustment scheme is generated, wherein the real-time adjustment scheme includes power allocation adjustment between nodes and energy storage system scheduling strategy.

6. The method as described in claim 1, characterized in that, In step S4, the final absorption capacity boundary is obtained, including: According to the real-time adjustment scheme, the power flow calculation model of the power grid is updated, and the voltage, current and power distribution of each node are obtained through the power flow calculation model. According to the power distribution, the stability assessment parameters of the power grid, including voltage stability and frequency stability, are calculated. The stability assessment parameters and the real-time adjustment scheme are fused to determine the final absorption capacity boundary of the power grid under the current operating state, wherein the final absorption capacity boundary represents the maximum power absorption capacity of the power grid after dynamic adjustment.

7. The method as described in claim 6, characterized in that, In step S4, the grid stability is determined based on the final absorption capacity boundary, including: The system acquires operational status data of multiple nodes, including the voltage, power, and frequency of each node. Based on the final absorption capacity boundary, it analyzes the power transmission stability between multiple nodes and determines the impact of environmental factors on grid stability, taking into account random wind speed variations and solar radiation intensity. The overall stability index of the power grid is calculated using a stability analysis model. Based on the overall stability index, it is determined whether the power grid is in a stable operating state. The overall stability index characterizes the operational reliability of the power grid under dynamic conditions.

8. The method as described in claim 7, characterized in that, In step S4, the supply and demand matching path is determined based on the power grid stability and supply and demand matching model, including: Based on the grid stability, configuration data of backup power sources are obtained, including backup power source capacity and response time; data on diurnal cycle impact and sudden weather events are integrated to construct a supply-demand matching path model; the power dispatch path of each node is calculated through the supply-demand matching path model; and the precise supply-demand matching path is determined based on the power dispatch path, wherein the precise supply-demand matching path represents the optimal power allocation scheme of the grid under dynamic environment and backup power support.

9. A regional power grid renewable energy absorption capacity calculation system, used to implement the method as described in any one of claims 1-8, characterized in that, The system includes: The data acquisition unit is used to acquire power grid node data and environmental influencing factors. It uses a graph neural network to process the power grid topology and obtains a dynamic index of electrical distance that characterizes the dynamic efficiency of power transmission between power grid nodes. The capacity calculation unit is used to determine the transmission capacity limit between nodes and the load distribution of the power grid based on the electrical distance dynamic index, and obtain the preliminary absorption capacity boundary; based on the environmental factors, the preliminary absorption capacity boundary is adjusted by an optimization algorithm to obtain the adjusted absorption capacity boundary; The supply and demand assessment unit is used to obtain the current actual supply and demand data of the power grid based on the adjusted absorption capacity boundary, calculate the supply and demand matching deviation based on the actual supply and demand data, and determine the real-time adjustment scheme for dynamically balancing the power grid supply and demand based on the supply and demand matching deviation and by integrating historical data and grid connection requirements. The stability assessment unit is used to integrate power flow calculation and stability assessment through the real-time adjustment scheme to obtain the final absorption capacity boundary; to determine the grid stability based on the final absorption capacity boundary; and to determine the supply and demand matching path based on the grid stability and the supply and demand matching model.

Images