Power grid scene region division method based on clustering analysis, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of power distribution network planning target network frame construction, and relates to a power grid scene region division method based on clustering analysis, electronic equipment and a storage medium, and the method comprises the steps: obtaining power grid scene information which comprises source side information, load side information, reliability information and load density information; performing data preprocessing on the power grid scene information to obtain normalized data; based on a clustering analysis method, performing simulation calculation on the normalized data to obtain a scene category; grading the source-side low-carbon resources, the load-side low-carbon resources, the reliability analysis and the load density of each scene category, and dividing grades; and performing classification arrangement based on the scene category and the grade to obtain a scene region division result, the scene region division result comprising the scene category and a corresponding grade division result. Through the data driving mode of the clustering algorithm, the influence of human factors can be reduced, and the scientificity and objectivity of planning are improved.

Description

Technical Field

[0001] This invention belongs to the technical field of distribution network planning target network structure construction, specifically involving a method for dividing power grid scene areas based on cluster analysis, electronic equipment, and storage medium. Background Technology

[0002] As power system construction progresses, massive amounts of new energy are being integrated into the distribution network on the source side, while diverse loads on the load side are also changing. Traditional target grid structures can no longer meet the evolving needs of the power grid under the new circumstances. When faced with massive, high-dimensional scenarios, relying on the planner's personal experience and judgment may lead to a lack of objectivity in the planning scheme. Summary of the Invention

[0003] In view of the above-mentioned defects or deficiencies in the prior art, the present invention proposes a method for dividing power grid scene regions based on cluster analysis, an electronic device, and a storage medium.

[0004] Firstly, a method for dividing power grid scenarios into regions based on cluster analysis is provided, comprising: acquiring power grid scenario information, including source-side information, load-side information, reliability information, and load density information; performing data preprocessing on the power grid scenario information to obtain normalized data; performing simulation calculations on the normalized data based on cluster analysis to obtain scenario categories; classifying the source-side low-carbon resources, load-side low-carbon resources, reliability analysis, and load density of each scenario category to determine a level; and classifying and organizing the scenario categories and levels to obtain scenario region division results, wherein the scenario region division results include the scenario categories and the corresponding level division results.

[0005] The beneficial effects of this invention are as follows: Using clustering algorithms in a data-driven approach can reduce the influence of human factors and improve the scientific rigor and objectivity of planning. Dividing regions into different levels based on the low-carbon resource characteristics of the source and load sides, as well as factors such as reliability, economy, and load density, can effectively reduce the complexity of power grid planning. Furthermore, by standardizing the number of samples and dimensions, the adaptability of planning schemes can be improved. Attached Figure Description

[0006] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart of a power grid scenario region division method based on cluster analysis provided in an embodiment of the present invention. Detailed Implementation

[0007] The following is in conjunction with the appendix Figure 1The present application will be further described in detail with reference to the embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0008] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0009] Please refer to Figure 1 The flowchart below provides a method for dividing a power grid scene region based on cluster analysis, according to an embodiment of the present invention. The method for dividing a power grid scene region based on cluster analysis includes the following steps: Step S101: Obtain power grid scenario information, which includes source-side information, load-side information, reliability information, and load density information.

[0010] Step S103: Perform data preprocessing on the power grid scenario information to obtain normalized data.

[0011] Step S105: Based on cluster analysis, simulate and calculate the normalized data to obtain the scene category.

[0012] Step S107: Classify and categorize the source-side low-carbon resources, load-side low-carbon resources, reliability analysis, and load density for each scenario category.

[0013] Step S109: Classify and organize the scenes based on their categories and levels to obtain the scene area division results. The scene area division results include scene categories and level division results corresponding to the scene categories.

[0014] In this embodiment, a clustering algorithm is used to divide the region into different levels based on source-side low-carbon resources, load-side low-carbon resources, reliability, and load density. The clustering algorithm can effectively reduce the complexity of power grid planning by dividing the region into different levels based on the characteristics of low-carbon resources on the source and load sides, as well as factors such as reliability and load density. Furthermore, by standardizing the number of samples and dimensions, the adaptability of the planning scheme is improved.

[0015] The power grid scenario includes resources on both the generation and load sides, reflecting the power supply capacity and structure of the grid, and helping to understand the grid's electricity demand and load characteristics. Reliability information includes grid reliability indicators, reflecting the grid's stability and reliability level. Load density information refers to the load size per unit area, used to measure the degree of load concentration in the grid. Load density information helps identify load hotspots in the grid.

[0016] The collected power grid scenario information typically has different dimensions and numerical ranges, which may lead to biases if used directly for analysis. Therefore, it is necessary to normalize this data, that is, scale the data to the range of 0 to 1. Normalization can eliminate the influence of different dimensions between indicators, make the data comparable, and provide a standardized data foundation for subsequent cluster analysis.

[0017] Cluster analysis was used to perform simulation calculations on normalized data. Cluster analysis is an unsupervised learning method that can classify data into different categories based on their inherent similarity. Through cluster analysis, power grid scenarios can be divided into several scenario categories with similar characteristics. Each scenario category is similar in terms of source side, load side, reliability, and load density, thus providing a basis for subsequent regional division.

[0018] Based on the scenario categories and the ranking of indicators within each scenario category, power grid scenarios are categorized and organized. Regions with similar scenario categories and rankings are grouped into the same scenario region. The final scenario region division results include not only scenario categories but also the corresponding ranking results. This division method can more comprehensively reflect the operation and planning characteristics of the power grid, providing support for differentiated planning and management of the power grid.

[0019] By systematically collecting multi-dimensional information on power grid scenarios and combining it with cluster analysis and classification, a scientific division of power grid scenario regions has been achieved. This approach comprehensively considers factors such as the power grid's source side, load side, reliability, and load density, avoiding the one-sidedness of single-indicator division and improving the scientific rigor and systematic nature of the division results. By dividing the power grid into different scenario regions, targeted planning strategies can be formulated based on the characteristics of each region. For example, for regions rich in low-carbon resources, priority can be given to developing renewable energy access and distributed energy utilization; for regions with high load density, the focus can be on strengthening the power supply capacity and reliability of the power grid. This precise planning method can improve the efficiency and effectiveness of power grid planning, avoiding resource waste and irrational allocation. The scenario region division results can provide clear reference for power grid operation and management, adapting to the dynamic changes in power grid development. Through real-time updates and re-division of power grid scenario information, new characteristics and demands of the power grid can be reflected in a timely manner, providing strong support for the sustainable development of the power grid.

[0020] Further, based on step S101, obtaining power grid scenario information specifically includes the following steps: Step S1011: Obtain source-side information, which includes coal-to-electricity conversion data, wind speed, wind resources, and solar resources.

[0021] Step S1013: Obtain load-side information, which includes the number of charging piles.

[0022] Step S1015: Obtain reliability information and load density information.

[0023] Among these, data on coal-to-electricity conversion reflects the progress of clean energy replacing traditional energy in the power grid, which is of great significance for optimizing the power grid's energy structure and reducing carbon emissions. By acquiring wind speed data, the power generation efficiency and available hours of wind farms can be assessed, providing a scientific basis for the development and integration of wind power resources. Wind resource data includes information such as wind energy distribution, wind direction, and wind energy density, which helps determine the optimal site selection and layout of wind farms, thereby maximizing wind power utilization efficiency. Solar resource data mainly involves the distribution of solar energy resources, including sunshine duration and solar radiation intensity, which is crucial for planning the layout and scale of solar power plants and can effectively improve the efficiency and reliability of photovoltaic power generation.

[0024] The number and distribution of charging stations not only affect the charging convenience for electric vehicle users, but also have a significant impact on the load characteristics of the power grid. By obtaining information on the number of charging stations, it is possible to better plan the load allocation and demand-side management strategies of the power grid.

[0025] By accurately assessing the potential of renewable energy, the site selection and scale of new energy power generation projects can be optimized, and the grid's capacity to absorb renewable energy can be improved.

[0026] Furthermore, power grid scenario information typically includes a large amount of sensor data, equipment operating status information, load data, etc. During the collection process, these data may be affected by environmental interference, equipment failure or human factors, thus requiring data preprocessing of power grid scenario information.

[0027] Based on step S103, the power grid scenario information is preprocessed to obtain normalized data, specifically including the following steps: Step S1031: Perform data cleaning on the power grid scenario information to obtain information with missing values ​​removed; Step S1033: Perform linear correlation analysis between reliability information and load density information on the information after removing missing values, modify outliers, and obtain normalized data.

[0028] By investigating the current status of charging piles, coal-to-electricity conversion data, wind speed, wind resources, solar resources, reliability analysis, load density, and other information, data needs to be collected from various sources. This data may include time-series data, geographic location information, etc. Integrating this data into a unified data framework ensures consistency in data format and time series.

[0029] Missing values ​​can interfere with subsequent data analysis and model training, thus requiring handling. To address missing values ​​in a dataset, for time-series data, imputation can be done using data from the previous or next day, or a time-series prediction model can be used to estimate the missing values. For non-time-series data, the decision to delete or impute missing values ​​may depend on the specific circumstances.

[0030] Linear correlation analysis of reliability and load density information is performed on the data after removing missing values. If some data points are found to deviate significantly from the overall trend, they are considered outliers, and statistical methods can be used to identify them. For outliers, appropriate modification measures are taken according to their degree of deviation and data distribution. For example, outliers with large deviations can be replaced with the average of adjacent data points; outliers with small deviations can be corrected through interpolation or smoothing. Outliers can also be deleted or replaced, with the replacement value being the average of nearby time points or other statistical measures. Data consistency checks ensure that the data is logically consistent. For example, whether the load level matches historical data and expected patterns. This process yields corrected normalized data. Normalized data ensures the comparability between different indicators.

[0031] Removing missing values ​​ensures data integrity, allowing subsequent analyses to be based on the complete dataset. Correcting outliers improves data quality and reliability. Both removing missing values ​​and correcting outliers reduce data noise, making subsequent analysis more efficient and the results more accurate.

[0032] For example, cleaning data and removing outliers and missing values ​​is shown in the table below.

[0033]

[0034] The reliability analysis and load density results are related to the regional level, so the reliability analysis and load density are linearly related. However, there is an anomaly in one set of data. According to the relevant regional level classification documents, there is a problem with the load density result. Therefore, the load density 4 corresponding to the reliability analysis of 0.999650 is changed to 10.

[0035] A suitable clustering algorithm can be chosen. K-means is a commonly used clustering algorithm suitable for numerical data. Different classification results can be obtained by adjusting the number of clusters. Normalized data is input into the clustering algorithm model to obtain the classified data results. Based on the clustering results, the different characteristics of each cluster are interpreted, and they are classified into different levels.

[0036] Cluster analysis process: K-means clustering is an unsupervised learning algorithm that groups data points into several clusters, such that data points within the same cluster are similar to each other, while data points in different clusters are dissimilar to each other.

[0037] Data preprocessing: Load the dataset into memory, clean it, and handle missing values, outliers, etc. Perform normalization or standardization to ensure consistent scale across different features.

[0038] Determining the number of clusters: For some clustering algorithms, the number of clusters needs to be determined in advance. The optimal number of clusters can be estimated using methods such as the elbow rule and silhouette coefficient.

[0039] Perform a clustering algorithm: Cluster the data using the selected clustering algorithm. The execution process of a clustering algorithm may include the following steps: Initialization: Select initial cluster centers or construct an initial hierarchical structure. Continuously update the cluster centers and clustering results according to the rules of the clustering algorithm until the stopping condition is met.

[0040] The goal of K-means is to minimize the sum of squared errors within a cluster, which is the sum of the squared distances from each point to the center of its cluster, as shown in the following formula: ; In the formula, K represents the number of clusters. Indicates the first The point set of a cluster, Indicates belonging to Data points, Indicates the first The center of each cluster, Representing data points With cluster center The square of the Euclidean distance between them.

[0041] K-means typically uses Euclidean distance to measure the distance from a point to the cluster center, and its formula is: ; In the formula, Indicates the dimension of the data.

[0042] Evaluate clustering results: Use clustering evaluation metrics to assess the quality of the clustering results. Common clustering evaluation metrics include the silhouette coefficient, Davies-Bouldin index, and Calinski-Harabasz index. Based on the evaluation results, the parameters of the clustering algorithm can be adjusted or different clustering algorithms can be selected. Understand the characteristics of each cluster and the data type it represents. Use visualization tools (such as scatter plots, heatmaps, etc.) to display the clustering results to help understand the data distribution and cluster structure.

[0043] Further, in step S105, based on cluster analysis, the normalized data is simulated and calculated to obtain the scene categories, specifically including the following steps: Step S1051: Based on cluster analysis, the normalized data is classified according to source-side quality, load-side quality, reliability level and load density level to obtain a normalized table; Step S1053: Analyze the normalized table to obtain the different level classification results corresponding to different categories, and obtain the scene category.

[0044] In this embodiment, cluster analysis is used to classify normalized data based on source-side quality, load-side quality, reliability, and load density, enabling the power grid scenarios to be divided into categories with different characteristics. This refined scenario classification helps to more accurately identify the operating status and potential problems of the power grid. Data-driven classification methods can provide a scientific basis for power grid planning, operation management, and fault early warning, avoiding the subjectivity and uncertainty of traditional experience-based decision-making. By identifying and analyzing scenario categories, targeted power grid operation strategies and optimization measures can be formulated, improving the power grid's adaptability to different load demands and operating environments. Scenario categorization allows power grid managers to quickly identify the power grid's operating status, promptly discover potential problems, and take corresponding measures. This efficient management model helps reduce the occurrence of power grid faults, improves the power grid's operating efficiency and reliability, and avoids the subjectivity and uncertainty of traditional experience-based decision-making.

[0045] Furthermore, the source-side mass and load-side mass are respectively divided into high, medium, and low quality, and the reliability level and load density level are respectively divided into high, medium, and low. The source-side mass, load-side mass, reliability level, and load density level are each divided into four levels.

[0046] The scene area division results include eight scene categories.

[0047] The scenario categories include: high source low load medium reliability load density space frame, medium source low load low reliability load density space frame, medium source medium load low reliability load density space frame, medium source low load low reliability load density space frame, low source medium load low reliability load density space frame, medium source high load low reliability load density space frame, medium source medium load medium reliability load density space frame, and medium source medium load high reliability load density space frame.

[0048] Example: Current annual data information is as follows:

[0049]

[0050]

[0051]

[0052]

[0053]

[0054] Cluster analysis was performed on the data, and the following results were obtained as normalized data:

[0055]

[0056]

[0057]

[0058]

[0059] The clustering results were analyzed to obtain different level classifications for different categories:

[0060] The method for dividing power grid scenarios based on cluster analysis also includes the following steps: analyzing the scenario region division results to obtain the analysis results.

[0061] The eight types of scenarios are named and analyzed as follows.

[0062] Category 1 is "High-Source, Low-Load, Medium-Reliability Load-Density Grid (HSLR-MD)". Low-carbon resources on the source side refer to clean energy from the power generation side, such as wind and solar power. A grade A indicates that these resources have excellent low-carbon performance and make a significant contribution to reducing carbon emissions. Low-carbon resources on the load side refer to low-carbon technologies or measures from the consumption side, such as electric vehicles and heat pumps. A grade D indicates that the low-carbon performance of these resources is relatively low, possibly due to low technological maturity or limited application. A reliability analysis grade C indicates that the power grid's supply reliability is at a medium level, with a potential risk of power outages, requiring improvement through technological advancements and optimized management. A load density grade C indicates that the grid's load distribution is relatively uniform, but there is still room for optimization. H represents high-quality source, L represents low-quality load, R represents medium reliability, and MD represents medium load density.

[0063] Category 2 is "Medium-quality source, low-load, low-reliability, and low-density grid-1 (MSLR-LD)". A B rating indicates that the clean energy generated has good low-carbon performance, but may be slightly inferior to resources in the A rating due to factors such as technology, cost, or supply stability. A D rating indicates that the low-carbon technology on the consumption side is relatively weak, possibly due to low technological maturity or limited application. Grid reliability refers to the grid's ability to supply power continuously and stably over a certain period. A reliability analysis rating of D indicates low grid reliability, potentially with a high risk of power outages, requiring improvement through technological advancements and optimized management. A D rating indicates low load density, possibly indicating uneven load distribution within the grid or relatively low electricity demand in the grid's service area. M represents Medium-quality source, S represents Low-quality load, L represents Low reliability, and LD represents Low load density.

[0064] Category 3 is "Medium-Quality Source, Medium-Load, Low-Reliability Load-Density Grid (MMLR-LD)". Category C indicates that the clean energy generation side has good low-carbon performance, but may be slightly inferior to Category A and B resources due to factors such as technology, cost, or supply stability. Category C also indicates that the low-carbon technology on the consumption side is good, but there is still room for improvement. Category D indicates low grid reliability, with a potentially high risk of power outages. Category D also indicates low load density, which may indicate uneven load distribution within the grid or relatively low electricity demand within the grid's service area. M represents Medium-quality source, M represents Medium-quality load, L represents Low reliability, and LD represents Low load density.

[0065] Category 4 is "Medium-quality source, low-load, low-reliability, and low-density grid-2 (MSLR-LD)". Category C indicates that the clean energy generated has good low-carbon performance, but may be slightly inferior to Category A and B resources due to factors such as technology, cost, or supply stability. Category D indicates good low-carbon technology on the consumption side, but may be due to low technological maturity or limited application. Category D indicates low grid reliability, potentially with a higher risk of power outages. Category D indicates low load density, possibly indicating uneven load distribution within the grid or relatively low electricity demand in the grid's service area. M represents Medium-quality source, S represents Low-quality load, L represents Low reliability, and LD represents Low load density.

[0066] Category 5 is "Low-quality source, medium-quality load, low-reliability load-density grid (LSLR-LD)". A D rating indicates relatively low low-carbon performance of clean energy on the generation side, possibly due to low technological maturity or limited application. A B rating indicates good low-carbon technologies on the consumption side, but with room for improvement. A D rating indicates low grid reliability, potentially with a higher risk of power outages. A D rating also indicates low load density, possibly indicating uneven load distribution within the grid or relatively low electricity demand in the grid's service area. L represents low-quality source, S represents medium-quality load, L represents low reliability, and LD represents low load density.

[0067] Category 6 is "Medium-quality source, high-load, low-reliability load-density grid (MHLR-LD)". Category C indicates that the clean energy generated has good low-carbon performance, but may be slightly inferior to Category A and B resources due to factors such as technology, cost, or supply stability. Category A indicates that the low-carbon technologies on the consumption side are excellent, making a significant contribution to reducing carbon emissions. Category D indicates low grid reliability, with a potentially high risk of power outages. Category D also indicates low load density, which may indicate uneven load distribution within the grid or relatively low electricity demand in the grid's service area. M represents Medium-quality source, H represents High-quality load, L represents Low reliability, and LD represents Low load density.

[0068] Category 7 is "Medium-Quality Source, Medium-Load, Medium-Reliability Load-Dense Grid (MMCR-MD)". Category C indicates that the clean energy generation side has good low-carbon performance, but may be slightly inferior to Category A and B resources due to factors such as technology, cost, or supply stability. Category C also indicates that the consumption side has good low-carbon technologies, but there is still room for improvement. Category B indicates that the power grid has good supply reliability, but there is still room for improvement. Category B also indicates good load density, which may indicate that the load distribution of the grid is relatively uniform, or that the electricity demand in the grid service area is at a moderate level. M represents Medium-quality source, M represents Medium-quality load, C represents Medium reliability, and MD represents Medium load density.

[0069] Category 8 is "Medium-Quality Source, Medium-Load, High-Reliability Load-Dense Grid (MHCR-HD)". Category C indicates that the clean energy generated has good low-carbon performance, but may be slightly inferior to Category A and B resources due to factors such as technology, cost, or supply stability. Category C also indicates that the low-carbon technology on the consumption side is good, but there is still room for improvement. Category A indicates very high grid reliability. Category A also indicates high load density, relatively uniform load distribution on the grid, or high electricity demand within the grid's service area. M represents medium-quality source, H represents medium-quality load, C represents high reliability, and HD represents high load density.

[0070] The present invention also proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute a power grid scene area division method based on cluster analysis.

[0071] The present invention also proposes a storage medium storing a computer program, which, when executed by a processor, implements any one of the following methods for dividing power grid scene regions based on cluster analysis.

[0072] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Dual Data SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM). The various embodiments described in this specification are presented in a progressive manner, with reference allowed to each other for similar or identical parts. Each embodiment focuses on its differences from other embodiments. In particular, embodiments of apparatus, devices, and non-volatile computer storage media are described simply because they are substantially similar to method embodiments; relevant details can be found in the descriptions of the method embodiments.

[0073] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for dividing power grid scenarios into regions based on cluster analysis, characterized in that, include: Obtain power grid scenario information, which includes source-side information, load-side information, reliability information, and load density information; The power grid scenario information is preprocessed to obtain normalized data; Based on cluster analysis, the normalized data is simulated and calculated to obtain scene categories; The source-side low-carbon resources, load-side low-carbon resources, reliability analysis, and load density of each scenario category are classified and graded. Based on the scene category and the level, the scene area division results are obtained, which include the scene category and the corresponding level division results.

2. The method for dividing power grid scenarios based on cluster analysis according to claim 1, characterized in that, Obtaining power grid scenario information specifically includes: The source-side information is obtained, including coal-to-electricity conversion data, wind speed, wind resources, and solar resources; Obtain load-side information, including the number of charging piles; Obtain the reliability information and the load density information.

3. The method for dividing power grid scenarios based on cluster analysis according to claim 1, characterized in that, The power grid scenario information is preprocessed to obtain normalized data, specifically including: The power grid scenario information is cleaned to obtain information with missing values ​​removed; Linear correlation analysis between reliability information and load density information is performed on the information with missing values ​​removed, outliers are modified, and the normalized data is obtained.

4. The method for dividing power grid scenarios based on cluster analysis according to any one of claims 1 to 3, characterized in that, Based on cluster analysis, the normalized data is simulated and calculated to obtain scene categories, specifically including: Based on cluster analysis, the normalized data is classified according to source-side quality, load-side quality, reliability level, and load density level to obtain a normalized table; The normalized table is analyzed to obtain different level classification results corresponding to different categories, thus obtaining the scene category.

5. The method for dividing power grid scenarios based on cluster analysis according to claim 4, characterized in that, The source-side mass and the load-side mass are respectively classified as high, medium and low quality, the reliability level and the load density level are respectively classified as high, medium and low, and the source-side mass, the load-side mass, the reliability level and the load density level are respectively classified as four levels.

6. The method for dividing power grid scene regions based on cluster analysis according to claim 5, characterized in that, The scene area division results include eight scene categories.

7. The method for dividing power grid scenarios based on cluster analysis according to claim 5, characterized in that, The scenario categories include: high-source low-load medium-reliability load-density space frame, medium-source low-load low-reliability load-density space frame, medium-source medium-load low-reliability load-density space frame, medium-source low-load low-reliability load-density space frame, low-source medium-load low-reliability load-density space frame, medium-source high-load low-reliability load-density space frame, medium-source medium-load medium-reliability load-density space frame, and medium-source medium-load high-reliability load-density space frame.

8. The method for dividing power grid scenarios based on cluster analysis according to any one of claims 1 to 3, characterized in that, Also includes: The results of the scene region division were analyzed to obtain the analysis results.

9. An electronic device, characterized in that, include: At least one processor; A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the power grid scene area division method based on cluster analysis as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The device contains a computer program that, when executed by a processor, implements the power grid scene area division method based on cluster analysis as described in any one of claims 1 to 8.

Images