A power distribution network station area user portrait generation method, device, equipment and medium

Abstract

The present application mainly relates to the field of artificial intelligence technology. The present application discloses a power distribution network area user portrait generation method, device, equipment and medium, the method comprises: obtaining power data in the target area, and generating power consumption behavior feature set based on the power data; clustering the feature data of the power consumption behavior feature set to obtain a plurality of first data sets; the plurality of first data sets are combined into a second data set, and the second data set comprises a plurality of data layer nodes; based on the target data layer node in the plurality of data layer nodes, the second data set is divided into a plurality of data subsets; determine the user characteristics corresponding to each data subset and display to obtain a power distribution network area user portrait including each user characteristic. The present application can generate accurate power distribution network area user portrait, which is beneficial to optimizing the distribution of power resources in the power system according to the power distribution network area user portrait, thereby improving the operation efficiency of the power distribution network.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a method, apparatus, equipment, and medium for generating user profiles for power distribution network areas. Background Technology

[0002] With the continuous growth of electricity demand and the acceleration of urbanization, the planning and optimization of power distribution networks have become increasingly important. As a crucial component of the power system, the power distribution network is primarily responsible for receiving electricity from the transmission network or regional power plants and then distributing it locally or tiered according to voltage to various users through distribution facilities. A distribution area is the final stage of the distribution network and the part that directly interacts with users. It typically refers to an area within the distribution network powered by a single transformer, where all users are connected to the network through the same transformer. By analyzing the electricity consumption data of users within a distribution area, power companies can gain a detailed understanding of the electricity consumption characteristics and behavioral patterns of different users. However, traditional electricity consumption data analysis methods rely on experience and simple statistics, lacking in-depth analysis of user characteristics and making it difficult to identify different types of user groups. This results in low accuracy and insufficient effectiveness in distribution network planning. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, and medium for generating user profiles of distribution network areas. It can generate accurate user profiles of distribution network areas, which is beneficial for optimizing the allocation of power resources in the power system based on the user profiles of distribution network areas, thereby improving the operating efficiency of the distribution network.

[0004] This invention provides a method for generating user profiles for distribution network areas, the method comprising:

[0005] Acquire power data within the target transformer area and generate a set of electricity consumption behavior features based on the power data;

[0006] Cluster the feature data of the electricity consumption behavior feature set to obtain multiple first datasets;

[0007] The multiple first datasets are merged into a second dataset, which includes multiple data layer nodes;

[0008] Based on the target data layer node among the multiple data layer nodes, the second dataset is divided into multiple data subsets;

[0009] The user characteristics corresponding to each subset of data are determined and displayed to obtain a user profile of the distribution network area including each user characteristic.

[0010] Furthermore, the step of acquiring power data within the target transformer area and generating a power consumption behavior feature set based on the power data includes:

[0011] The power data is divided into multiple feature parameters;

[0012] Based on the correlation between each of the aforementioned feature parameters, the plurality of feature parameters are filtered, and the electricity consumption behavior feature set is generated according to the filtered feature parameters.

[0013] Furthermore, each of the aforementioned feature parameters includes multiple parameter values;

[0014] The method for generating user profiles for distribution network areas also includes a step of determining the degree of relevance.

[0015] Determining the degree of relevance includes:

[0016] Obtain sample values ​​from multiple parameter values ​​in the first feature parameter, and determine the average value of multiple parameter values ​​in the first feature parameter;

[0017] Sample values ​​are obtained from multiple parameter values ​​in the second feature parameter, and the average value of multiple parameter values ​​in the second feature parameter is determined;

[0018] Based on the correlation between the sample values ​​and average values ​​corresponding to the first feature parameter and the sample values ​​and average values ​​corresponding to the second feature parameter, the correlation value between the first feature parameter and the second feature parameter is determined, so as to determine the degree of correlation between the first feature parameter and the second feature parameter.

[0019] Furthermore, the method for generating user profiles for distribution network areas also includes a step of determining the number of clusters when clustering the feature data of the electricity consumption behavior feature set;

[0020] Determining the number of clusters when clustering the feature data of the electricity consumption behavior feature set includes:

[0021] When clustering the feature data of the electricity consumption behavior feature set, the electricity consumption behavior feature set is divided into multiple data clusters;

[0022] Determine the sum of squared errors within each data cluster, where the sum of squared errors is the sum of squared distances between each sample data point within the data cluster and the center point of the data cluster.

[0023] A relationship curve is generated based on the number of data clusters and the sum of squared errors for each data cluster. The relationship curve includes a horizontal axis and a vertical axis, where the horizontal axis represents the number of data clusters and the vertical axis represents the sum of squared errors.

[0024] The target curve inflection point is determined in the relationship curve graph, and the horizontal coordinate value corresponding to the target curve inflection point is taken as the optimal number of clusters.

[0025] Furthermore, the merging of the multiple first datasets into a second dataset, the second dataset comprising multiple data layer nodes, including:

[0026] Based on the distance between each data point in the first dataset, a merging operation is performed on each data point until all data points in the first dataset are merged into the same cluster, resulting in the second dataset, which includes multiple data layer nodes.

[0027] Furthermore, the specific method for performing the merging operation on each of the data points is as follows:

[0028] A distance matrix is ​​generated based on each link distance, wherein the distance matrix includes multiple clusters, each cluster includes at least one data point, and the link distance is the distance between two clusters;

[0029] Merge the two clusters with the smallest link distance in the distance matrix into a new cluster;

[0030] The distance matrix is ​​updated based on the distance between the new cluster and other clusters;

[0031] Based on the updated distance matrix, the step of merging the two clusters with the smallest link distance in the distance matrix into a new cluster is performed until all data points are merged into the same cluster, resulting in a hierarchical clustering tree structure. The hierarchical clustering tree structure is used to divide the data layer nodes into multiple clusters.

[0032] Furthermore, the method for generating user profiles for distribution network areas also includes:

[0033] Identify abnormal data, including outliers, within the power data;

[0034] The abnormal data is deleted based on the abnormal values, and the power data after deleting the abnormal data is used as the preprocessed power data.

[0035] The present invention also provides a device for generating user profiles for distribution network areas, the device comprising:

[0036] The acquisition module is used to acquire power data within the target transformer area and generate a set of electricity consumption behavior features based on the power data.

[0037] The first clustering module is used to cluster the feature data of the electricity consumption behavior feature set to obtain multiple first datasets;

[0038] The second clustering module is used to merge the multiple first datasets into a second dataset, the second dataset including multiple data layer nodes;

[0039] The hierarchical partitioning module is used to divide the second dataset into multiple data subsets based on the target data layer node among the multiple data layer nodes;

[0040] The display module is used to determine and display the user characteristics corresponding to each subset of data to obtain a user profile of the distribution network area including each user characteristic.

[0041] The present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the distribution network area user profile generation method as described in any of the preceding claims.

[0042] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the distribution network area user profile generation method as described in any of the preceding claims.

[0043] The present invention has at least the following beneficial effects:

[0044] This application's technical solution can generate accurate user profiles for distribution network areas. First, by collecting power data within the target area, it automatically generates a set of electricity consumption behavior features, avoiding the subjectivity of human feature selection. Next, it uses a clustering algorithm to group the feature data; this method is unaffected by personal experience and can objectively identify natural groups of electricity consumption behavior. Then, by merging and dividing the dataset, it further refines the user groups; this method is more in-depth than simple statistical analysis and can identify different types of user groups. Finally, it displays the user characteristics corresponding to each data subset, constructing an accurate user profile for the distribution network area. This application's technical solution reduces reliance on expert experience, improves the accuracy and effectiveness of user profiles, and enables in-depth analysis of user characteristics. This facilitates the optimization of power resource allocation in the power system based on the distribution network area user profile, thereby improving the operational efficiency of the distribution network. Attached Figure Description

[0045] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0046] Figure 1 This is a flowchart of the steps involved in generating user profiles for distribution network areas.

[0047] Figure 2 This is a flowchart of the steps for determining the degree of relevance in the method for generating user profiles for distribution network areas;

[0048] Figure 3This is a flowchart of the steps for determining the number of clusters in the method for generating user profiles for distribution network areas;

[0049] Figure 4 This is a flowchart of the steps involved in merging each data point in the method for generating user profiles for distribution network areas.

[0050] Figure 5 This is a flowchart illustrating the steps involved in implementing the user profile generation method for distribution network areas in an application scenario.

[0051] Figure 6 This is a schematic diagram of the user profile generation device for a distribution network area;

[0052] Figure 7 This is a schematic diagram of the structure of an electronic device. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0054] In related technical fields, user profiling of distribution areas is a crucial aspect of distribution network management and optimization, and its accuracy directly impacts the economy, stability, and security of the power system. Traditional cluster analysis is a commonly used method in user profiling, identifying different types of user groups through the analysis of historical electricity consumption data. However, traditional cluster analysis has some shortcomings. For example, many existing methods rely on expert experience for feature selection, which has low reliability and is easily influenced by subjective factors, leading to insufficient accuracy and stability of the profiling results.

[0055] Please refer to Figure 1 , Figure 1 This is a flowchart of the steps involved in generating user profiles for distribution network areas.

[0056] This embodiment provides a method for generating user profiles for distribution network areas, including:

[0057] S101. Obtain power data within the target transformer area and generate a power consumption behavior feature set based on the power data.

[0058] S102. Cluster the feature data of the electricity consumption behavior feature set to obtain multiple first datasets.

[0059] S103. Merge multiple first datasets into a second dataset, which includes multiple data layer nodes.

[0060] S104. Based on the target data layer node among multiple data layer nodes, divide the second dataset into multiple data subsets.

[0061] S105. Determine and display the user characteristics corresponding to each data subset to obtain a user profile of the distribution network area including each user characteristic.

[0062] In step S101 of some embodiments, the user's electricity consumption data, including electricity consumption, electricity consumption time and frequency, is collected in real time by a smart meter. Historical electricity consumption records are used, combined with seasonal factors and weather changes, to analyze electricity consumption behavior patterns. Alternatively, user feedback and survey data are combined to supplement the electricity consumption behavior feature set, thereby increasing dimensions such as user satisfaction and electricity consumption habits.

[0063] In step S102 of some embodiments, the K-means clustering algorithm can be used to divide users into different groups based on the similarity of electricity consumption characteristics. In addition to the K-means algorithm, there are many other clustering algorithms available, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise), Gaussian Mixture Models (GMM), Spectral Clustering, etc.

[0064] In step S103 of some embodiments, dimensionality reduction techniques such as principal component analysis (PCA) are used to merge multiple first datasets and reduce the data dimensionality to form a second dataset.

[0065] Optionally, multiple first datasets can be merged into a second dataset using a multi-level clustering algorithm. Multi-level clustering is a technique that combines multiple clustering algorithms to perform clustering analysis on data at different levels, in order to more meticulously identify and classify patterns and features in the data. It can more comprehensively capture the hierarchical structure and complexity of the data by progressively refining the clustering results. Hierarchical clustering can be divided into two types: agglomerative hierarchical clustering (bottom-up) and splitting hierarchical clustering (top-down). Agglomerative hierarchical clustering starts from each data point, merging the two nearest clusters, progressively building larger clusters until all data points are merged into a single cluster.

[0066] It's understandable that the second dataset isn't a single large cluster, but rather a hierarchical structure of clusters. This structure includes multiple data hierarchy nodes, which can be segmented at different levels to obtain clusters of varying numbers and sizes. Each of these clusters represents a group of similar users. For each cluster, by analyzing the common characteristics of its members, these characteristics can be used to construct user profiles. For example, we can calculate the average age, average spending, and most common purchase categories for each cluster. Based on the feature analysis of the clusters, a user profile can be built for each cluster. User profiles can include demographic information, behavioral patterns, preferences, and more.

[0067] Alternatively, in addition to traditional clustering algorithms, deep learning models can be used to create user profiles. For example, convolutional neural networks (CNNs) can be used to extract spatial features from user electricity consumption data, or recurrent neural networks (RNNs) can be used to capture time-series features of user electricity consumption behavior. These deep learning models can more comprehensively capture the complex patterns of user electricity consumption behavior and improve the accuracy of user profiles.

[0068] Optionally, power data refers to data such as transformer substation name, transformer rated capacity, and annual maximum and minimum load rate of the substation. Furthermore, by incorporating the annual cumulative number of power outages and three-phase imbalance rate of the substation into the analysis dimensions, the aim is to generate user profiles through more precise cluster analysis of substation characteristics, thereby better reflecting user needs and facilitating distribution network planning and optimization.

[0069] In some embodiments, power data within a target distribution area is acquired, and a set of electricity consumption behavior features is generated based on the power data, including:

[0070] The power data is divided into multiple feature parameters; based on the correlation between each feature parameter, the multiple feature parameters are filtered, and a power consumption behavior feature set is generated based on the filtered feature parameters.

[0071] In some embodiments, each feature parameter includes multiple parameter values.

[0072] Please refer to Figure 2 , Figure 2 This is a flowchart of the steps for determining the degree of relevance in the method for generating user profiles for distribution network areas.

[0073] The method for generating user profiles for distribution network areas also includes a step of determining the degree of relevance, the specific implementation of which includes:

[0074] S201. Obtain sample values ​​from multiple parameter values ​​in the first feature parameter, and determine the average value of multiple parameter values ​​in the first feature parameter.

[0075] S202. Obtain sample values ​​from multiple parameter values ​​in the second feature parameter, and determine the average value of multiple parameter values ​​in the second feature parameter.

[0076] S203. Based on the correlation between the sample values ​​and average values ​​corresponding to the first feature parameter and the sample values ​​and average values ​​corresponding to the second feature parameter, determine the correlation value between the first feature parameter and the second feature parameter, so as to determine the degree of correlation between the first feature parameter and the second feature parameter.

[0077] Alternatively, in addition to using correlation analysis, other feature selection and dimensionality reduction methods can be combined to optimize the selection of user electricity consumption features, such as principal component analysis (PCA), linear discriminant analysis (LDA), and mutual information methods. These methods can extract and select features more effectively under specific circumstances, improving the accuracy and reliability of user profiles.

[0078] It is understood that this embodiment introduces a correlation analysis method to reduce the dimensionality and optimize the selection of user electricity consumption characteristics. By comprehensively considering the correlation between features, it selects the feature set that is most closely related to the user category and is the most concise, thereby improving the accuracy and reliability of user profiles, effectively reducing redundant features, and improving data processing efficiency and the accuracy of analysis results.

[0079] Please refer to Figure 3 , Figure 3 This is a flowchart of the steps for determining the number of clusters in the method for generating user profiles for distribution network areas.

[0080] In some embodiments, the method for generating user profiles for distribution network areas further includes a step of determining the number of clusters when clustering feature data of an electricity consumption behavior feature set. Specific implementations of this step include:

[0081] S301. When clustering the feature data of the electricity consumption behavior feature set, the electricity consumption behavior feature set is divided into multiple data clusters.

[0082] S302. Determine the sum of squared errors within each data cluster. The sum of squared errors is the sum of the squared distances between each sample data point within the data cluster and the center point of the data cluster.

[0083] S303. Based on the number of data clusters and the sum of squared errors for each cluster, generate a relationship curve. The relationship curve includes a horizontal axis and a vertical axis. The horizontal axis represents the number of data clusters, and the vertical axis represents the sum of squared errors.

[0084] S304. Determine the inflection point of the target curve in the relationship curve diagram, and take the horizontal coordinate value corresponding to the inflection point of the target curve as the optimal number of clusters.

[0085] It should be noted that traditional clustering algorithms often struggle to determine the optimal number of clusters when dealing with large-scale data, and the clustering results are easily affected by noisy data, impacting their accuracy. For example, while the K-means clustering algorithm is widely used, it is sensitive to the selection of initial cluster centers and is prone to getting trapped in local optima. Furthermore, the presence of noisy data and outliers can significantly affect the accuracy and stability of the clustering results.

[0086] In this embodiment, firstly, the large-scale data is preliminarily clustered by dividing the electricity consumption behavior feature set into multiple data clusters. Next, the sum of squared errors for each data cluster is calculated; this step quantifies the quality of the clustering, making the evaluation of the clustering results more objective. Then, a relationship curve is generated to visualize the relationship between the number of data clusters and the sum of squared errors, helping to identify the changing trend between the number of clusters and clustering quality. Finally, the inflection point of the target curve is determined in the relationship curve; this inflection point represents the optimal solution for the number of clusters, meaning that at this point, increasing the number of clusters no longer significantly improves the clustering quality. This method reduces reliance on expert experience, mitigates the impact of noisy data, and improves the accuracy and reliability of the clustering results.

[0087] In some embodiments, multiple first datasets are merged into a second dataset, the second dataset comprising multiple data layer nodes, including:

[0088] Based on the distance between each data point in the first dataset, a merging operation is performed on each data point until all data points in the first dataset are merged into the same cluster, resulting in the second dataset, which includes multiple data layer nodes.

[0089] In some embodiments, K-means clustering is used to generate the first dataset, and hierarchical clustering is used to generate the second dataset. Combining K-means and hierarchical clustering allows for multi-level clustering analysis of the user data. Through preliminary clustering and further refinement, different types of user groups are identified. This method can more comprehensively capture the multi-level characteristics of user electricity consumption behavior, improving the accuracy and stability of the clustering results.

[0090] Please refer to Figure 4 , Figure 4 This is a flowchart of the steps involved in merging each data point in the method for generating user profiles for distribution network areas.

[0091] In some embodiments, the specific method for merging each data point is as follows:

[0092] S401. Generate a distance matrix based on each link distance, wherein the distance matrix includes multiple clusters, each cluster includes at least one data point, and the link distance is the distance between two clusters.

[0093] S402. Merge the two clusters with the smallest link distance in the distance matrix into a new cluster.

[0094] S403. Update the distance matrix based on the distance between the new cluster and other clusters.

[0095] S404. Return to step S402 based on the updated distance matrix until each data point is merged into the same cluster, resulting in a hierarchical clustering tree structure. The hierarchical clustering tree structure is used to divide the data into multiple clusters through data layer nodes.

[0096] It should be noted that existing user profiling methods typically focus only on single-level cluster analysis, making it difficult to comprehensively capture the multi-level characteristics of user electricity consumption behavior. Single-level cluster analysis cannot fully reflect the complexity and diversity of user electricity consumption behavior, resulting in insufficient detail and accuracy in the profiling results.

[0097] This embodiment addresses the limitations of existing user profiling methods when processing multi-dimensional data by employing a hierarchical clustering approach. First, by generating a distance matrix, the similarity between clusters can be quantified, which helps to comprehensively capture the multi-level characteristics of user electricity consumption behavior. Next, the two clusters with the smallest link distance are merged. This step gradually integrates information, reduces feature redundancy, and preserves the correlation between features. After updating the distance matrix, the merging process is repeated until all data points are merged into the same cluster, forming a hierarchical clustering tree structure. This tree structure not only reveals the hierarchy of user electricity consumption behavior but also allows for partitioning at different data layer nodes, resulting in multiple clusters, each representing a group of users with similar electricity consumption behaviors. This method effectively processes multi-dimensional data, improves the effectiveness and conciseness of feature selection, and makes user profiles more comprehensive and accurate.

[0098] In some embodiments, the method for generating user profiles for distribution network areas further includes:

[0099] Identify outlier data in the power data; delete outlier data based on the outlier values, and use the power data after deleting outlier data as the preprocessed power data.

[0100] It is understood that this embodiment preprocesses the original dataset to remove noisy data and outliers, ensuring data quality and consistency. Outliers are used to identify and process abnormal points in the data, reducing their impact on clustering results. This helps ensure the accuracy of multi-level clustering and provides a reliable data foundation for the subsequent generation of user profiles.

[0101] In some embodiments, when displaying user characteristics and user profiles for distribution network areas, visualization tools such as radar charts and bar charts can be used to intuitively display user electricity consumption characteristics and behavioral patterns, helping power companies better understand and manage user needs. Visualized user profiles not only improve the intuitiveness of data analysis but also provide a scientific basis for the optimization and management of the power system.

[0102] Understandably, in-depth analysis of user profiles within the distribution network identifies user groups with potential for regulation, supporting power companies in effectively controlling power demand during peak periods, balancing supply and demand, and ensuring stable grid operation. Simultaneously, it provides personalized services and solutions to different types of users, improving user satisfaction and loyalty.

[0103] Please refer to Figure 5 , Figure 5 This is a flowchart illustrating the steps involved in implementing the user profile generation method for distribution network areas in an application scenario.

[0104] like Figure 5 As shown in the figure, this embodiment provides a method for generating user profiles of distribution network areas in an application scenario.

[0105] First, extract the power data for the target distribution area used for analysis, including the following characteristic parameters: distribution area name, transformer GISID, transformer rated capacity (kVA), number of low-voltage users in the distribution area, rated current (A), 10 over-limit days, load evaluation, time of the distribution area's annual maximum load rate, annual maximum load rate (%), three-phase imbalance rate at maximum load rate, time of the distribution area's annual minimum load rate, annual minimum load rate, three-phase imbalance rate at minimum load rate, annual cumulative power outage duration (hours), annual cumulative number of power outages, transformer operating years, topology change indicators, monthly line loss (%) in the distribution area, power supply radius, and 10 distribution area 2.0.

[0106] Secondly, the aforementioned power data is preprocessed, including data cleaning and outlier detection.

[0107] Next, correlation analysis was used to identify and quantify the relationships between the features, thereby reducing the dimensionality of the original data. In the correlation analysis, the Pearson correlation coefficient was used to measure the linear correlation between two variables. The formula for the Pearson correlation coefficient is:

[0108]

[0109] in, and They are variables and The sample values, and They are and The mean of the values ​​is used. The Pearson correlation coefficient ranges from [-1, 1], where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation. The Pearson correlation coefficient between each feature and the user category is calculated, and features are selected based on the magnitude of the correlation coefficient. The selected feature parameters are added to the electricity consumption behavior feature set.

[0110] After selection, a multi-level clustering analysis is performed on the feature parameters using a combination of K-means clustering and hierarchical clustering methods. First, the K-means clustering algorithm is used to perform preliminary clustering, dividing the data into several initial cluster groups. To determine the optimal number of clusters for K-means clustering, the Elbow Method is employed. The Elbow Method calculates the sum of squared errors (SSE) for different numbers of clusters and plots the relationship between the number of clusters and SSE. The inflection point where SSE significantly decreases is selected as the inflection point of the target curve, and the x-coordinate value corresponding to the inflection point is taken as the optimal number of clusters. The goal of the K-means clustering algorithm is to minimize the distance from each data point within a cluster to the cluster center; its objective function is:

[0111]

[0112] in, It is the number of clusters. It is the first One cluster, It is the first The center of each cluster, These are data points.

[0113] After the initial clustering is completed, hierarchical clustering algorithms are used to refine the results. Agglomerative hierarchical clustering starts with each data point, merging the two nearest clusters and gradually building larger clusters until all data points are merged into a single cluster. Its main steps and formulas are as follows:

[0114] 1. Calculate the distance matrix. Calculate the distances between all data points to form a distance matrix. Commonly used distance metrics include Euclidean distance and Manhattan distance. The formula for Euclidean distance is:

[0115]

[0116] in, and There are two data points. It is the dimension of the feature.

[0117] 2. Merge the two closest clusters. Find the two clusters with the smallest distance in the distance matrix and merge them into a new cluster. Update the distance matrix and calculate the distance between the new cluster and all other clusters. Common distance update methods include minimum distance (single-linked), maximum distance (fully-linked), and average distance (evenly-linked). The formula for single-linked clusters is:

[0118]

[0119] in, and There are two clusters. and These are data points in a cluster.

[0120] 3. Repeat step 2 until all data points are merged into one cluster.

[0121] The goal of hierarchical clustering is to identify the hierarchical structure and complexity of data by progressively refining the clustering results. Through multi-level clustering methods, different types of user groups within a given area can be identified, such as high-load users, low-load users, users with stable electricity consumption behavior, and users with highly fluctuating electricity consumption behavior.

[0122] Finally, by using visualization tools such as radar charts and bar charts, user characteristics are displayed to obtain a user profile of the distribution network area that includes the characteristics of each user.

[0123] It is understood that any of the above embodiments can generate accurate user profiles for distribution network areas. First, by collecting power data within the target area, a set of electricity consumption behavior features is automatically generated, avoiding the subjectivity of human feature selection. Next, clustering algorithms are used to group the feature data; this method is unaffected by personal experience and can objectively identify natural groups of electricity consumption behavior. Then, by merging and dividing the datasets, user groups are further refined; this method is more in-depth than simple statistical analysis and can identify different types of user groups. Finally, the user characteristics corresponding to each data subset are displayed, constructing an accurate user profile for the distribution network area. The technical solution of this application reduces reliance on expert experience, improves the accuracy and effectiveness of user profiles, and achieves in-depth analysis of user characteristics. This is beneficial for optimizing the allocation of power resources in the power system based on the user profiles of distribution network areas, thereby improving the operating efficiency of the distribution network.

[0124] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the device for generating user profiles in a power distribution network area.

[0125] This embodiment provides a distribution network area user profile generation device, which includes:

[0126] The acquisition module 601 is used to acquire power data within the target transformer area and generate a set of electricity consumption behavior features based on the power data.

[0127] The first clustering module 602 is used to cluster the feature data of the electricity consumption behavior feature set to obtain multiple first datasets.

[0128] The second clustering module 603 is used to merge multiple first datasets into a second dataset, which includes multiple data layer nodes.

[0129] The hierarchical partitioning module 604 is used to divide the second dataset into multiple data subsets based on the target data layer node among multiple data layer nodes.

[0130] The display module 605 is used to determine and display the user characteristics corresponding to each data subset in order to obtain a user profile of the distribution network area including each user characteristic.

[0131] It will be understood by those skilled in the art that all or some of the steps and apparatuses in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. As is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0132] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0133] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above-mentioned methods for generating user profiles of distribution network areas.

[0134] refer to Figure 7 , Figure 7 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0135] The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0136] The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store operating devices and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 to execute the distribution network area user profile generation method of the embodiments of this application.

[0137] The input / output interface 703 is used to implement information input and output;

[0138] The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0139] Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704);

[0140] The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0141] It is understood that the content of the above method embodiments is applicable to the embodiments of this electronic device. The specific functions implemented by the embodiments of this electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0142] This application also provides a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the distribution network area user profile generation method as described in any of the above specific embodiments.

[0143] This application also discloses a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, causing the computer device to perform the distribution network area user profile generation method as described in any of the preceding embodiments.

[0144] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0145] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. It should be understood that in this application, “at least one” means one or more, and “more than one” means two or more.

[0146] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0147] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0148] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0149] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0150] Although the description of this application has been quite detailed and particularly focused on several of the described embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiment. Rather, it should be considered as effectively covering the intended scope of this application by referring to the appended claims and taking into account the prior art, which provides for a broad possible interpretation of these claims. Furthermore, the foregoing description of this application with respect to embodiments foreseeable by the inventors is intended to provide a useful description, and non-substantial modifications to this application that have not yet been foreseen may still represent equivalent modifications.

Claims

1. A method for generating user profiles for a distribution network area, characterized in that, The method includes: Acquire power data within the target transformer area and generate a set of electricity consumption behavior features based on the power data; Cluster the feature data of the electricity consumption behavior feature set to obtain multiple first datasets; Based on the distance between each data point in the first dataset, a merging operation is performed on each data point until all data points in the first dataset are merged into the same cluster, resulting in a second dataset, which includes multiple data layer nodes. The specific method for performing the merging operation on each of the data points is as follows: A distance matrix is ​​generated based on each link distance, wherein the distance matrix includes multiple clusters, each cluster includes at least one data point, and the link distance is the distance between two clusters; Merge the two clusters with the smallest link distance in the distance matrix into a new cluster; The distance matrix is ​​updated based on the distance between the new cluster and other clusters; Based on the updated distance matrix, the step of merging the two clusters with the smallest link distance in the distance matrix into a new cluster is performed until each data point is merged into the same cluster, resulting in a hierarchical clustering tree structure. The hierarchical clustering tree structure is used to divide the data layer nodes into multiple clusters. Based on the target data layer node among the multiple data layer nodes, the second dataset is divided into multiple data subsets; The user characteristics corresponding to each subset of data are determined and displayed to obtain a user profile of the distribution network area including each user characteristic.

2. The method for generating user profiles for a distribution network area according to claim 1, characterized in that, The step of acquiring power data within the target transformer area and generating a power consumption behavior feature set based on the power data includes: The power data is divided into multiple feature parameters; Based on the correlation between each of the aforementioned feature parameters, the plurality of feature parameters are filtered, and the electricity consumption behavior feature set is generated according to the filtered feature parameters.

3. The method for generating user profiles for a distribution network area according to claim 2, characterized in that, Each of the aforementioned feature parameters includes multiple parameter values; The method further includes the step of determining the degree of correlation; Determining the degree of relevance includes: Obtain sample values ​​from multiple parameter values ​​in the first feature parameter, and determine the average value of multiple parameter values ​​in the first feature parameter; Sample values ​​are obtained from multiple parameter values ​​in the second feature parameter, and the average value of multiple parameter values ​​in the second feature parameter is determined; Based on the correlation between the sample values ​​and average values ​​corresponding to the first feature parameter and the sample values ​​and average values ​​corresponding to the second feature parameter, the correlation value between the first feature parameter and the second feature parameter is determined, so as to determine the degree of correlation between the first feature parameter and the second feature parameter.

4. The method for generating user profiles for a distribution network area according to claim 1, characterized in that, The method further includes a step of determining the number of clusters when clustering the feature data of the electricity consumption behavior feature set; Determining the number of clusters when clustering the feature data of the electricity consumption behavior feature set includes: When clustering the feature data of the electricity consumption behavior feature set, the electricity consumption behavior feature set is divided into multiple data clusters; Determine the sum of squared errors within each data cluster, where the sum of squared errors is the sum of squared distances between each sample data point within the data cluster and the center point of the data cluster. A relationship curve is generated based on the number of data clusters and the sum of squared errors for each data cluster. The relationship curve includes a horizontal axis and a vertical axis, where the horizontal axis represents the number of data clusters and the vertical axis represents the sum of squared errors. The target curve inflection point is determined in the relationship curve graph, and the horizontal coordinate value corresponding to the target curve inflection point is taken as the optimal number of clusters.

5. The method for generating user profiles for a distribution network area according to claim 1, characterized in that, The method further includes: Identify abnormal data, including outliers, within the power data; The abnormal data is deleted based on the abnormal values, and the power data after deleting the abnormal data is used as the preprocessed power data.

6. A device for generating user profiles for a distribution network area, characterized in that, The device includes: The acquisition module is used to acquire power data within the target transformer area and generate a set of electricity consumption behavior features based on the power data. The first clustering module is used to cluster the feature data of the electricity consumption behavior feature set to obtain multiple first datasets; The second clustering module is used to merge each data point based on the distance between each data point in the first dataset until all data points in the first dataset are merged into the same cluster to obtain the second dataset, which includes multiple data layer nodes. The specific method for performing the merging operation on each of the data points is as follows: A distance matrix is ​​generated based on each link distance, wherein the distance matrix includes multiple clusters, each cluster includes at least one data point, and the link distance is the distance between two clusters; Merge the two clusters with the smallest link distance in the distance matrix into a new cluster; The distance matrix is ​​updated based on the distance between the new cluster and other clusters; Based on the updated distance matrix, the step of merging the two clusters with the smallest link distance in the distance matrix into a new cluster is performed until each data point is merged into the same cluster, resulting in a hierarchical clustering tree structure. The hierarchical clustering tree structure is used to divide the data layer nodes into multiple clusters. The hierarchical partitioning module is used to divide the second dataset into multiple data subsets based on the target data layer node among the multiple data layer nodes; The display module is used to determine and display the user characteristics corresponding to each subset of data to obtain a user profile of the distribution network area including each user characteristic.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the method for generating user profiles of distribution network areas as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for generating user profiles of distribution network areas as described in any one of claims 1 to 5.

Images