Analysis Methods for Regional Resource Distribution Characteristics of Power Grid Power Supply Structure and Load

Abstract

This invention discloses a method for analyzing the regional resource distribution characteristics of power grid power structure and load, belonging to the field of feature analysis technology. The method includes the following steps: based on a regional resource distribution model, extracting the changing data of power output and load demand to form power-load time-series feature pairs; based on these power-load time-series feature pairs, analyzing the spatial mismatch between power output and load demand to construct a spatial distribution difference pattern between power and load; based on this spatial distribution difference pattern, and combined with power grid topology and transmission constraints, calculating the accessibility and matching degree of power and load to obtain an achievable distribution pattern; and based on this distribution pattern, extracting the coupling characteristics of power structure and load distribution to output the regional distribution feature analysis results. This invention solves the problem of difficulty in quantifying and dynamically evaluating regional power-load mismatch by extracting the time-series coupling characteristics of power and load and combining them with power grid topology constraint analysis to achieve an achievable distribution pattern.

Description

Technical Field

[0001] This invention relates to the field of feature analysis technology, and more specifically, to a method for analyzing the regional resource distribution characteristics of power grid power structure and load. Background Technology

[0002] With the continuous expansion of new energy access and the rapid development of distributed power sources, the power structure and load distribution of modern power grids exhibit highly unbalanced and dynamically changing characteristics. Traditional power grid planning and operation analysis methods mainly rely on overall capacity statistics, single-node load forecasting, or static topology analysis, typically ignoring the spatial distribution differences, temporal characteristics, and coupling relationships between adjacent regions of power sources and loads. This makes it difficult for existing methods to comprehensively quantify the matching degree and potential mismatch risks between regional power sources and loads, and also makes it impossible to accurately assess the actual effects of energy storage deployment, renewable energy absorption capacity, and load regulation strategies. Furthermore, existing methods lack effective comprehensive analysis tools when dealing with power output fluctuations, peak-valley load demand misalignment, and dynamic trends, making it difficult to form a reliable indicator system reflecting the power-load coupling characteristics at the regional level. Therefore, there is an urgent need for a method that can systematically analyze the resource distribution characteristics of regional power grids by combining power structure, load distribution, and their spatiotemporal dynamic characteristics, providing a scientific basis for power grid planning, operation optimization, and regulation strategies, and achieving accurate assessment of regional power grid supply-demand matching, resource optimization potential, and operational safety.

[0003] The above-disclosed technical solutions have at least the following technical problems: existing power grid planning and operation analysis methods usually only focus on the total capacity distribution of power sources and loads, lacking quantitative analysis of the spatial differences and dynamic coupling characteristics of power sources and loads within the region. This makes it difficult to identify local supply and demand mismatches, assess the potential for resource optimization, and limit the scientific formulation of optimization strategies such as energy storage regulation, distributed power source dispatching, and load migration.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a method for analyzing the regional resource distribution characteristics of power grid power structure and load. By extracting the temporal coupling characteristics of power sources and loads and combining them with power grid topology constraint analysis, the distribution pattern can be realized, thereby solving the problem of difficulty in quantifying and dynamically evaluating regional power source-load mismatch.

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

[0007] The method for analyzing the regional resource distribution characteristics of power grid power structure and load includes the following steps: Based on the regional resource distribution model, extract the changing data of power output and load demand to form power-load time-series characteristic pairs; based on the power-load time-series characteristic pairs, analyze the spatial mismatch between power output and load demand to construct a spatial distribution difference pattern of power and load; based on the spatial distribution difference pattern, combined with the power grid topology and transmission constraints, calculate the accessibility and matching degree of power and load to obtain the feasible distribution pattern; based on the distribution pattern, extract the coupling characteristics of power structure and load distribution, and output the regional distribution characteristic analysis results.

[0008] In a preferred embodiment, the regional resource distribution model is established based on the power supply data and load operation data of the target power grid. Specifically, the model involves: collecting the operation parameters of the target power grid, including power supply data and load operation data; dividing the region into grids according to the spatial structure and grid node layout of the target power grid; constructing a quantitative feature vector reflecting the power supply and load status within each grid cell based on the operation parameters; and integrating the quantitative feature vectors to generate a regional resource distribution model covering the target power grid.

[0009] In a preferred embodiment, the power supply-load timing characteristic pair is formed by the following steps:

[0010] Based on the regional resource distribution model, the power output and load demand time series data of each grid cell are obtained and the data is preprocessed. Through multi-scale decomposition and nonlinear time alignment, the dynamic coupling characteristics of power supply and load in each grid cell are extracted from the preprocessed time series data. The dynamic coupling characteristics of power supply and load are paired according to the time correspondence to form power supply-load time series feature pairs.

[0011] In a preferred embodiment, the step of extracting the dynamic coupling characteristics of power supply and load within each grid cell from the preprocessed time-series data through multi-scale decomposition and nonlinear time alignment specifically involves: calculating the spatial weight of each grid cell based on the power capacity density and load intensity in the regional resource distribution model; performing multi-scale decomposition on the time-series signals of power output and load demand based on the spatial weights; dynamically adjusting the weights of feature extraction according to the distribution differences of adjacent grid cells during the decomposition process to extract initial features; aligning the initial features to fuse the spatiotemporal correlation of neighboring cells; and extracting dynamic coupling characteristics representing the coupling relationship between power supply and load from the aligned sequence.

[0012] In a preferred embodiment, the step of analyzing the spatial mismatch between power output and load demand based on power-time sequence feature pairs specifically involves: calculating the cell-level mismatch index vector within each grid cell based on the power-load time sequence feature pairs; and performing a difference operation on the mismatch index vectors of adjacent cells based on spatial proximity to generate an inter-grid coupling deviation matrix.

[0013] In a preferred embodiment, the construction of the spatial distribution difference pattern between power supply and load specifically involves: constructing a weighted graph model with topological constraints based on the coupling deviation matrix; performing dynamic spatial clustering on the weighted graph model within a sliding time window to obtain the temporally evolving spatial cluster partitioning results; weighted fusion of the cell-level mismatch indices of all grid cells within each spatial cluster to generate representative feature vectors for each spatial cluster; and aggregating the representative feature vectors of the dynamic clusters to form a spatiotemporal coupling difference pattern characterizing power supply and load.

[0014] In a preferred embodiment, the step of performing dynamic spatial clustering on the weighted graph model within a sliding time window to obtain a temporally evolved spatial cluster partitioning result specifically involves: performing initial clustering of grid cells based on the weighted graph edge weights of the current time window; merging adjacent cells according to a preset intra-cluster consistency condition to form an optimized spatial cluster partition; applying temporal stability constraints to the spatial cluster partitioning results of adjacent time windows to minimize changes in cluster structure over time; based on the spatial cluster partitioning of the current time window, fusing the mismatch indices of each cell within the cluster to update the representative feature vector of the cluster; and outputting the spatial cluster partitioning and its representative feature vector under each time window to form a temporally evolved spatial cluster partitioning result.

[0015] In a preferred embodiment, the step of combining the power grid topology and transmission constraints to calculate the accessibility and matching degree of power sources and loads to obtain an achievable distribution pattern specifically involves: determining the accessibility matrix between power source nodes and load nodes that take into account transmission constraints based on the spatial distribution difference pattern and the power grid topology; calculating the matching degree of connected power source-load nodes in the accessibility matrix based on the spatial distribution difference pattern to generate a matching degree matrix; and selecting power source-load combinations that meet the preset matching degree requirements based on the accessibility matrix and the matching degree matrix to form an achievable distribution pattern.

[0016] In a preferred embodiment, the step of extracting the coupling characteristics of power supply structure and load distribution based on the distribution pattern and outputting regional distribution characteristic analysis results specifically involves: obtaining effective supply-demand pairs formed by power supply nodes and corresponding load nodes under transmission constraints based on the feasible distribution pattern; calculating the time-series coupling index for each effective supply-demand pair based on its time-series characteristics, and generating the spatial coupling degree of the supply-demand pair by combining the matching degree; aggregating and calculating the regional-level time-series complementarity and local power absorption potential based on the spatial coupling degree of each effective supply-demand pair; and outputting regional distribution characteristic analysis results including the spatial coupling degree, time-series complementarity, and local absorption potential.

[0017] The technical effects and advantages of the method for analyzing the regional resource distribution characteristics of power grid power structure and load in this invention are as follows:

[0018] 1. This invention constructs a spatial coupling analysis system based on the temporal characteristics of power output and load demand, which can quantify the dynamic matching of regional power sources and loads in terms of peak-valley synchronization, fluctuation complementarity, and rate of change. It can accurately identify the regional power-load mismatch characteristics and evolution patterns, and provide reliable data support for power grid planning, energy storage layout, and load regulation.

[0019] 2. This invention selects feasible power source-load distribution patterns by combining power grid topology and transmission constraints, and on this basis extracts spatial coupling degree, temporal complementarity degree and local power source absorption potential, so as to achieve a comprehensive evaluation of regional power source structure and load distribution characteristics, and provide a scientific basis for the analysis of new energy absorption capacity and operation optimization. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating the method for analyzing the regional resource distribution characteristics of power grid power structure and load according to the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1, Figure 1 This invention presents a method for analyzing the regional resource distribution characteristics of power grid power structure and load, comprising the following steps:

[0023] S1, based on the regional resource distribution model, extracts the change data of power output and load demand to form power-load time series feature pairs;

[0024] The regional resource distribution model is established based on the power supply data and load operation data of the target power grid;

[0025] The power data includes the installed capacity, output curves, and geographical location of distributed and centralized power sources, and the load operation data includes the capacity, power consumption curves, and power supply range of zoned loads.

[0026] The regional resource distribution model is as follows:

[0027] Collect power supply data and load operation data of the target power grid, and divide the area into grids according to the spatial structure and grid node layout of the target power grid;

[0028] Within each grid cell, the assigned power supply capacity, load capacity, and their time-series characteristics are statistically analyzed, and a quantized feature vector for that cell is constructed.

[0029] By integrating the quantized feature vectors of all grid cells, a regional resource distribution model covering the entire target area is formed.

[0030] In this embodiment, the step of extracting the changing data of power output and load demand based on the regional resource distribution model to form power-load time-series feature pairs is as follows:

[0031] Based on the regional resource distribution model, the corresponding power output and load demand time series data are obtained in each grid cell, and outlier correction and missing data are performed on the data.

[0032] By using multi-scale decomposition (such as intraday, intraweek, and intramonth) and nonlinear time alignment, the dynamic coupling characteristics of power supply and load within each grid cell are extracted, including peak-valley synchronicity, rate of change difference, and fluctuation complementarity.

[0033] The power source feature vector and load feature vector of each grid cell are paired according to the time correspondence to form a power source-load time series feature pair that can characterize the spatiotemporal coupling relationship between regional power output and load demand.

[0034] The dynamic coupling characteristics of power sources and loads within each grid cell are extracted through multi-scale decomposition and nonlinear time alignment, specifically as follows:

[0035] The spatial weight of each grid cell is calculated based on the power capacity density and load intensity of each grid cell in the regional resource distribution model.

[0036] Based on spatial weights, the time-series signals of power output and load demand are decomposed into multiple scales. At each time scale (such as hour, day, week), the feature extraction weights are dynamically adjusted in combination with the power-load distribution differences of adjacent grid cells to extract initial features, including peak and valley values, fluctuation amplitude, and rate of change, so that the obtained feature vector can simultaneously reflect the dynamic changes within the cell and the spatial mismatch potential at the regional level.

[0037] The initial features are aligned using a nonlinear alignment algorithm based on mutual information, thereby synchronizing the peak-valley misalignment and fluctuations of each grid cell and its neighboring cells.

[0038] Dynamic coupling features are extracted from the aligned weighted multiscale sequences, including peak-valley synchronicity, rate of change deviation, fluctuation complementarity, and cross-grid complementarity potential.

[0039] The power source feature vector and load feature vector of each grid cell are paired according to the time correspondence to form a power source-load time series feature pair that can characterize the spatiotemporal coupling relationship between regional power output and load demand.

[0040] The power capacity density is the total installed power capacity within each grid cell divided by the grid area. ,in, For power capacity density, This represents the total installed capacity of all power sources within grid k. The actual spatial area of ​​grid k;

[0041] The load intensity is the average load demand within each grid cell. ,in, For load strength, For the statistical period, The instantaneous load function of grid k at continuous time t (obtained based on discrete instantaneous load operation data). This represents the start time of the statistical period.

[0042] Power capacity density and load intensity can be used as the weighting criteria for spatially weighted multi-scale decomposition.

[0043] High grid power supply capacity density and low load intensity → Feature extraction can increase the weight of power supply fluctuations;

[0044] High grid load intensity and low capacity density → Feature extraction can increase load response weights.

[0045] S2, based on the power supply-load time sequence characteristics, analyzes the spatial mismatch between power supply output and load demand, and constructs a spatial distribution difference pattern of power supply and load.

[0046] The analysis of spatial mismatch between power supply output and load demand based on power supply-load time sequence characteristics specifically includes:

[0047] Based on the power supply-load time sequence characteristics, the peak-valley synchronicity, fluctuation complementarity, and rate of change difference between power supply output and load demand are calculated in each grid cell to obtain a cell-level mismatch index vector.

[0048] Based on the spatial proximity relationship between each grid cell, the mismatch index vectors of adjacent cells are subjected to difference calculation to form a coupling deviation matrix between grid cells, which quantifies the degree of mismatch between adjacent cells.

[0049] The step of performing difference calculation on the mismatch index vectors of adjacent units is specifically as follows:

[0050]

[0051]

[0052] in, This is the inter-grid coupling deviation matrix. Let be the Euclidean distance between element i and element j. , These are the mismatch index vectors of neighboring units. Spatial weights based on geographical proximity Let be the distance between the geographic centers of unit i and unit j.

[0053] The peak-valley synchronicity is used to characterize the synchronicity between the power supply and the load at the times when peak and valley values ​​occur, specifically:

[0054]

[0055] The fluctuation complementarity is used to measure whether there is a complementary relationship between the fluctuations of power output and load demand over a short time scale, specifically:

[0056]

[0057] The difference in the rate of change is used to measure the difference in the changing trends of power output and load demand, specifically:

[0058]

[0059] in, For peak-valley synchronization, The number of peaks and valleys to be aligned. , These represent the times when the k-th peak / valley occurs in terms of power output and load demand, respectively. Total sampling time For wave complementarity, , Let be the power output and load demand at time t within the i-th grid cell, respectively. , These are the average values ​​of power output and load demand, respectively. Due to differences in the rate of change, The sampling interval is denoted as .

[0060] The spatial distribution difference pattern of power supply and load is specifically constructed as follows:

[0061] The coupling deviation matrix is ​​constructed as a weighted graph with topological constraints, where the edge weights not only include the coupling deviation values ​​between units, but also combine the similarity of unit resource structure and spatial proximity to form a comprehensive edge weight.

[0062] Within a sliding time window, the weighted graph is dynamically partitioned. By optimizing the consistency of edge weights within clusters and temporal continuity, the spatial cluster partitioning results of temporal evolution are obtained.

[0063] The unit-level mismatch index vectors within each dynamic cluster are weighted and fused. The weights are dynamically adjusted based on the unit's power supply capacity, load scale, and the strength of mutual coupling within the cluster to obtain a representative feature vector of the cluster. The weights of the unit-level mismatch index vectors are dynamically determined based on the power supply contribution of the units within the dynamic cluster (the proportion of the unit's total installed power capacity to the total installed power capacity of the cluster), the load demand influence (the proportion of the unit's average load to the total average load of the cluster), and the degree of cooperative coupling within the cluster (the normalized value of the average mutual information between the unit and other units within the cluster). The larger the value of each dimension index, the higher the corresponding weight. At the same time, the grid operation status within the sliding time window (such as peak electricity consumption, power shortage, and flat operation) is combined with the adjustment coefficient to balance the importance of each dimension. The final weights must satisfy the requirement that the sum of the weights of all units within the cluster is 1, so as to accurately match the comprehensive influence of the unit on the power-load mismatch characteristics within the cluster.

[0064] The representative feature vectors of each dynamic cluster are combined to form the final spatiotemporal coupling difference pattern of power supply and load, reflecting the power supply-load mismatch characteristics and evolution law at the regional level.

[0065] Within the sliding time window, the weighted graph is dynamically partitioned. By optimizing the consistency of edge weights within clusters and temporal continuity, a temporally evolving spatial cluster partitioning result is obtained, specifically:

[0066] Within each time window, grid cells are initially clustered based on the weighted graph edge weights, and adjacent cells with edge weights higher than a preset threshold are merged to optimize intra-cluster consistency.

[0067] The cluster labels of adjacent time windows are adjusted with temporal continuity constraints to minimize cluster label changes and maintain temporal stability;

[0068] Within each cluster, the unit-level mismatch index vectors are weighted and fused to update the cluster representative feature vectors for cluster partitioning in the next time window;

[0069] Output the dynamic evolution clusters and their representative characteristics under each time window to form the spatial cluster partitioning results of temporal evolution.

[0070] The comprehensive edge weights are specifically as follows:

[0071]

[0072]

[0073]

[0074] in, In order to integrate border rights, The value of the inter-grid coupling deviation matrix. For unit resource structure similarity, For spatial proximity, , , These are the proportional coefficients (set based on historical data). is the scale parameter of the Gaussian kernel.

[0075] S3, based on the spatial distribution difference pattern, combined with the power grid topology and transmission constraints, calculates the accessibility and matching degree of the power source-load, and obtains the feasible distribution pattern;

[0076] In this embodiment, the calculation of power supply-load accessibility and matching degree to obtain an achievable distribution pattern specifically includes:

[0077] Based on the spatial distribution difference pattern and power grid topology, the reachability from each power source node to the load node is determined, and the reachability matrix is ​​obtained by considering the transmission line capacity constraints.

[0078] For each pair of power-load nodes in the reachability matrix, the matching degree is calculated by combining the spatial distribution difference pattern characteristics;

[0079] Based on the accessibility matrix and matching degree matrix, power source-load combinations that meet transmission constraints and have high matching degree are selected to form the final feasible distribution pattern.

[0080] The determination of the reachability from each power node to the load node specifically involves:

[0081] For each power source unit i and load unit j, determine whether there exists a power grid topology path through which the remaining capacity of all passing lines exceeds the load demand. If the condition is met, then set the reachability. ,otherwise .

[0082] The matching degree is specifically:

[0083]

[0084]

[0085] in, For matching degree, This is a weighting coefficient, ranging from 0 to 1 (set according to power grid planning standards). For power supply capacity, To meet load demand, For spatial matching degree, , Each cluster represents a feature vector. , These are the cluster representative feature vectors for grid k and grid l, respectively.

[0086] The function of achieving the aforementioned distribution pattern is reflected in:

[0087] Operability guarantee under constraints: By considering the power grid topology and transmission line capacity constraints, the selected power source-load combination is a truly feasible distribution pattern, ensuring that it will not exceed the line capacity or cause power supply unavailability when operating in the actual power grid. This ensures that subsequent analysis is based on feasible realities rather than theoretically ideal distributions, thus avoiding planning deviations.

[0088] Quantifying the potential for spatial mismatch and resource optimization: Based on the achievable distribution pattern, it is possible to analyze which areas have insufficient power supply-load matching or redundancy, quantify the degree of spatial mismatch, and provide a basis for power grid operation optimization, load regulation or resource allocation, such as adjusting energy storage, renewable energy utilization or load migration strategies.

[0089] S4, based on the distribution pattern, extracts the coupling characteristics between the power supply structure and the load distribution, and outputs the regional distribution characteristic analysis results.

[0090] Based on the distribution pattern, the coupling characteristics between the power supply structure and load distribution are extracted, and the regional distribution characteristic analysis results are output, specifically as follows:

[0091] Based on the feasible distribution pattern, the connection relationship between each power node and the corresponding load node and the effective supply-demand pair under transmission constraints are obtained.

[0092] Within the effective supply and demand pair, a time-series coupling index is constructed by combining peak-valley synchronicity, fluctuation complementarity, and difference in rate of change.

[0093] By combining the temporal coupling index with the matching degree, the spatial coupling degree of the power supply-load pair is obtained;

[0094] Calculate the temporal complementarity of the region and the local power consumption potential based on the spatial coupling degree of the power supply-load pair;

[0095] The spatial coupling degree, temporal complementarity degree, and local absorption potential are output as the regional distribution characteristic analysis results.

[0096] The spatial coupling degree is specifically as follows:

[0097]

[0098]

[0099] The temporal complementarity is specifically as follows:

[0100]

[0101] The potential for local power consumption is specifically as follows:

[0102]

[0103] in, For spatial coupling degree, , These are the preset coupling coefficients. For matching degree, As a time-series coupling index, , , These are weighting factors (set according to the entropy weighting method, calculating the entropy value for the distribution of each indicator on different grids; the smaller the entropy value (the greater the difference), the higher the weight, used for normalization). , For peak-valley synchronization, For wave complementarity, Due to differences in the rate of change, To effectively balance supply and demand Quantity, For temporal complementarity, The power supply capacity of power supply unit i. For the requirements of load unit j, This demonstrates the potential for local power consumption.

[0104] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0105] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0106] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0107] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0108] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0109] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing the regional resource distribution characteristics of power grid power supply structure and load, characterized in that, The method comprises the following steps: Based on the regional resource distribution model, the variation data of power output and load demand are extracted to form a power-load time sequence feature pair; Based on the power-load time sequence feature pair, the spatial mismatch of power output and load demand is analyzed, and a spatial distribution difference mode of power and load is constructed, specifically: according to the power-load time sequence feature pair, the peak-valley synchronization degree, fluctuation complementarity and variation rate difference of power output and load demand in each regional grid cell are calculated to obtain a mismatch index vector; based on the spatial proximity relationship between each grid cell, the mismatch index vectors of adjacent cells are operated to form a coupling deviation matrix; based on the coupling deviation matrix, a weighted graph model with topological constraints is constructed; In the sliding time window, the weighted graph model is dynamically spatially clustered to obtain a spatial cluster division result of time evolution; The unit-level mismatch indexes of all grid cells in each spatial cluster are weighted and fused to generate a representative feature vector of each spatial cluster; The representative feature vectors of the dynamic clusters are aggregated to form a spatial-temporal coupling difference mode representing power and load; Based on the spatial distribution difference mode, the reachability and matching degree of power and load are calculated in combination with the power grid topology and transmission constraints to obtain an achievable distribution pattern; Based on the distribution pattern, the coupling features of power structure and load distribution are extracted, and the regional distribution feature analysis result is output.

2. The method of claim 1, wherein, The regional resource distribution model is established based on power data and load operation data of the target power grid, specifically: Collect the operation parameters of the target power grid, including power data and load operation data; According to the spatial structure and grid node layout of the target power grid, regional grid division is performed; In each grid cell, a quantitative feature vector reflecting the state of power and load in the cell is constructed based on the operation parameters; Integrate the quantitative feature vectors to generate a regional resource distribution model covering the target power grid.

3. The method of claim 2, wherein, The power-load time sequence feature pair is specifically formed by the following steps: Based on the regional resource distribution model, the power output and load demand time sequence data of each grid cell are obtained, and the data are preprocessed; Through multi-scale decomposition and nonlinear time alignment, the power dynamic coupling features and load dynamic coupling features in each grid cell are extracted from the preprocessed time sequence data; The power dynamic coupling features and load dynamic coupling features are paired according to the time correspondence to form a power-load time sequence feature pair.

4. The method of claim 3, wherein, The power dynamic coupling features and load dynamic coupling features in each grid cell are extracted from the preprocessed time sequence data by multi-scale decomposition and nonlinear time alignment, specifically: According to the power capacity density and load intensity of each grid cell in the regional resource distribution model, the spatial weight of the cell is calculated; Based on the spatial weight, the power output and load demand time sequence signals are subjected to multi-scale decomposition, and in the decomposition process, the weight of feature extraction is dynamically adjusted according to the distribution difference of adjacent grid cells to extract initial features; Through a nonlinear alignment algorithm based on mutual information, the initial features are aligned to synchronize the peak-valley misalignment and fluctuation of each grid cell and its adjacent cells; On the sequence after alignment processing, dynamic coupling features representing the coupling relationship between power supply and load are extracted.

5. The method of claim 4, wherein, The dynamic spatial clustering is performed on the weighted graph model in the sliding time window to obtain the spatial cluster division result of time evolution, and specifically includes the following steps: initial clustering of the grid cells based on the edge weight of the weighted graph in the current time window; merging adjacent cells according to a preset intra-cluster consistency condition to form an optimized spatial cluster division; applying a temporal stability constraint to the spatial cluster division result of the adjacent time window to minimize the change of the cluster structure over time; based on the spatial cluster division of the current time window, fusing the mismatch indicators of each cell in the cluster to update the representative feature vector of the cluster; outputting the spatial cluster division and its representative feature vector in each time window to form the spatial cluster division result of time evolution.

6. The method of claim 5, wherein, The reachability and matching degree of the power supply-load are calculated based on the power grid topology and transmission constraints to obtain the achievable distribution pattern, and specifically includes the following steps: based on the spatial distribution difference mode and the power grid topology structure, determining the reachability matrix between the power supply nodes and the load nodes considering the transmission constraints; for the connected power supply-load nodes in the reachability matrix, calculating the matching degree thereof based on the spatial distribution difference mode to generate a matching degree matrix; based on the reachability matrix and the matching degree matrix, screening the power supply-load combinations that meet the preset matching degree requirement to form the achievable distribution pattern.

7. The method of claim 6, wherein the method further comprises: Based on the distribution pattern, the coupling features of the power supply structure and the load distribution are extracted, and the regional distribution feature analysis result is output, and specifically includes the following steps: based on the achievable distribution pattern, obtaining the effective supply-demand pairs formed by the power supply nodes and the corresponding load nodes under the transmission constraints; for each effective supply-demand pair, calculating the time sequence coupling index according to its time sequence characteristics, and generating the spatial coupling degree of the supply-demand pair in combination with the matching degree; based on the spatial coupling degree of each effective supply-demand pair, aggregating and calculating the time sequence complementarity and the local consumption potential of the regional level; outputting the regional distribution feature analysis result containing the spatial coupling degree, the time sequence complementarity and the local consumption potential.

Images