Power distribution network low-voltage user power supply reliability analysis method and system

Abstract

The invention discloses a power distribution network low-voltage user power supply reliability analysis method and system, and relates to the technical field of power distribution network analysis, and the method comprises the steps: collecting user power consumption data for preprocessing, and carrying out the low-voltage user recognition according to the user power consumption data; analyzing power supply reliability according to the power consumption data of the low-voltage users, and predicting the power grid state of the low-voltage users according to the power consumption data of the low-voltage users and the power supply reliability for early warning; and visually displaying the power utilization data and the power supply reliability of the low-voltage users, and storing the power utilization data and the power supply reliability in a database. According to the method, low-voltage user identification is carried out by collecting the power consumption data of the users, the efficiency and pertinence of reliability analysis are improved, the power supply reliability of the users is analyzed more effectively, meanwhile, the power supply reliability is analyzed by constructing the local feature function through the power consumption data of the low-voltage users, the accuracy and flexibility of power supply reliability analysis are improved, and the user experience is improved. The power utilization safety of users is improved, and power grid faults of the users are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network analysis, and in particular to a method and system for analyzing the reliability of power supply to low-voltage users of a power distribution network. Background Art

[0002] With the intelligence of modern power systems and the popularization of distributed energy, the power consumption patterns of low-voltage users in power grids have become more complex and diversified, resulting in the increasing importance of distribution network power supply reliability analysis. Traditional distribution network power supply analysis is mostly concentrated on the high-voltage main grid side, and the power supply reliability is predicted and guaranteed by analyzing the overall operation data of the power grid. However, with the increase in the number of low-voltage users, especially in the context of the gradual popularization of distributed generation and energy storage equipment, traditional main grid monitoring alone can no longer meet the demand for accurate and reliable power supply. In recent years, with the rapid development of smart meters, the Internet of Things, and artificial intelligence technologies, the power consumption data of low-voltage users can be collected and transmitted to cloud data platforms in real time, forming a large amount of user power consumption data. Personalized power supply reliability analysis for low-voltage users has gradually become a research hotspot. Related technologies have begun to try to combine multi-dimensional data and machine learning algorithms to more deeply identify and analyze the power supply characteristics of low-voltage users, but there are still deficiencies. Existing technologies usually rely on traditional load classification algorithms in terms of user identification, which makes it difficult to accurately identify different types of low-voltage users, and it is difficult to accurately analyze user power reliability under complex load changes, and it is difficult to meet the managers' refined control needs for the power supply status of low-voltage users. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing power supply reliability analysis method and system for low-voltage users in distribution network, the purpose of the present invention is to provide a power supply reliability analysis method for low-voltage users in distribution network. The existing technology usually relies on traditional load classification algorithms in user identification, which makes it difficult to accurately identify different types of low-voltage users, and it is difficult to accurately analyze the power reliability of users under complex load changes.

[0004] The technical solution of the present invention is: a method for analyzing the power supply reliability of low-voltage users in a distribution network, which includes collecting user power consumption data for preprocessing, identifying low-voltage users based on the user power consumption data; analyzing power supply reliability based on the low-voltage user power consumption data, and predicting the low-voltage user power grid status based on the low-voltage user power consumption data and power supply reliability for early warning; visually displaying the low-voltage user power consumption data and power supply reliability, and storing them in a database.

[0005] As a preferred solution of the method for analyzing the reliability of power supply to low-voltage users in the distribution network described in the present invention, the pre-processing of the collection of user electricity consumption data refers to installing a smart meter at the user's meter terminal to collect the user's electricity consumption data, removing noise and filling missing values ​​from the electricity consumption data, the smart meter is connected to the monitoring center via a wireless network and transmits the collected user electricity consumption data to the monitoring center, the monitoring center synchronizes the user's electricity consumption data in time and performs standardized processing.

[0006] As a preferred solution of the power supply reliability analysis method for low-voltage users in the distribution network of the present invention, the low-voltage user identification based on the user's power consumption data refers to obtaining the pre-processed user power consumption data, setting a load fluctuation threshold, defining the time when the load in the user's power consumption data is higher than the load fluctuation threshold as a load fluctuation state, and the rest as a load stable state, and using the Brownian motion probability density function to calculate the probability of the user being in a load fluctuation state and a load stable state:

[0007]

[0008] Where P(t|0) is the probability of the user being in a certain state, M is the maximum load change amplitude of the user in a certain state, D is the diffusion coefficient of the load change, t m is the time when the user reaches the maximum load in a certain state, and t is the total time when the user is in a certain state;

[0009] The probability P(t|0) of user load fluctuation state is solved by Brownian motion probability density function. - ) and the probability of load stability P(t|0 + ), according to P(t|0 - ) and P(t|0 + ) Calculate the probability flow J(t|0) of the user between two states:

[0010] J(t|0)=κ[P(t|0 - )-P(t|0 + )];

[0011] Where κ is the user load mutation frequency parameter;

[0012] The Brownian motion diffusion equation is constructed based on the probability flow J(t|0) of the user between two states and the probability P(t|0) of the user being in a certain state:

[0013]

[0014] Where δ is the diffusion coefficient;

[0015] By solving the Brownian motion diffusion equation, we can get the probability P of the final user being in a certain state. *(t|0) and extract the probability P of the end user being in a load fluctuation state * (t|0 - ) and the probability of load stability P * (t|0 + ), according to P * (t|0 - ) and P * (t|0 + ) Recalculate the user’s probability flow J between two states * (t|0);

[0016] Set the probability threshold. If the user has a probability flow J between two states * If (t|0) is lower than the probability threshold, the user is marked as a low-voltage user, otherwise it is marked as the remaining user.

[0017] As a preferred solution of the method for analyzing the reliability of power supply to low-voltage users in the distribution network of the present invention, wherein: the analyzing the reliability of power supply according to the power consumption data of low-voltage users refers to extracting the power consumption data of low-voltage users according to the low-voltage user tags, and extracting the features of the power consumption data of low-voltage users to construct the feature vector X of low-voltage users;

[0018] The distribution network is divided into grid units T, each grid unit T is further divided into sub-grids, the number of low-voltage users in each sub-grid is counted, and the weight of the sub-grid in the grid unit T is calculated:

[0019]

[0020] where c K is the weight of subgrid K in grid unit T, N is the number of low-voltage users in subgrid K, X i is the feature vector of the i-th low-voltage user;

[0021] In each grid cell T, construct the local feature function g T :

[0022]

[0023] Among them l K is the indicator function, which is 1 in the area of ​​subgrid K and 0 otherwise;

[0024] According to the local characteristic function g T And the low-voltage user characteristic vector is used to calculate the power supply reliability R of the low-voltage user:

[0025]

[0026] Where β0 is the intercept, β j is the regression coefficient, X jis the jth eigenvalue in the low-voltage user feature vector, and n is the number of feature items in the low-voltage user feature vector;

[0027] By using the least squares method, β0 and β j Optimize and recalculate the power supply reliability R of low-voltage users * .

[0028] As a preferred solution of the power supply reliability analysis method for low-voltage users in the distribution network of the present invention, wherein: the prediction of the low-voltage user power grid state based on the power consumption data and power supply reliability of the low-voltage user for early warning refers to constructing a convolutional neural network model, setting the input to be the power consumption data and power supply reliability of the low-voltage user, and the output to be the low-voltage user power grid state, including normal and abnormal, and training the convolutional neural network through a training data set;

[0029] The low-voltage user electricity consumption data and power supply reliability are input into the trained convolutional neural network to obtain the low-voltage user's power grid status. If it is abnormal, the low-voltage user is notified to issue a power grid risk warning and arrange staff to perform advance maintenance.

[0030] As a preferred solution of the method for analyzing the power supply reliability of low-voltage users in the distribution network described in the present invention, the visual display of the power consumption data and power supply reliability of the low-voltage users refers to marking the low-voltage users on a digital map, synchronously associating the power consumption data and power supply reliability of the low-voltage users with the low-voltage user marks on the digital map, and marking the low-voltage users with visual colors according to the power supply reliability.

[0031] As a preferred solution of the method for analyzing the power supply reliability of low-voltage users in the distribution network described in the present invention, the storage in the database refers to storing the identified low-voltage user tags, user power consumption data and power supply reliability analysis results in the database, and the database regularly uploads the stored data to the cloud for backup, and simultaneously performs integrity checks on the stored data.

[0032] Another object of the present invention is to provide a power supply reliability analysis system for low-voltage users in a distribution network, which comprises:

[0033] An acquisition identification module is used to collect user electricity consumption data and identify low-voltage users based on the user electricity consumption data;

[0034] A reliability analysis module, used to analyze the power supply reliability of low-voltage users based on their power consumption data;

[0035] The risk prediction module is used to predict the power grid status of low-voltage users based on their power consumption data and power supply reliability, and to perform predictive maintenance;

[0036] The display storage module is used to mark and display low-voltage users and store them in the database.

[0037] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned method for analyzing the reliability of power supply to low-voltage users in a distribution network when executing the computer program.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for analyzing the reliability of power supply to low-voltage users in a distribution network.

[0039] The beneficial effects of the present invention are as follows: the present invention collects user electricity consumption data to identify low-voltage users, thereby improving the efficiency and pertinence of reliability analysis, thereby more effectively analyzing the power supply reliability of users; at the same time, local characteristic functions are constructed through the electricity consumption data of low-voltage users to analyze power supply reliability, thereby improving the accuracy and flexibility of power supply reliability analysis; finally, the power consumption data of low-voltage users and the power supply reliability analysis of users are used to analyze the status of the user's power grid for early warning, thereby improving the safety of user electricity use and avoiding user power grid failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0041] Figure 1 A flow chart of the power supply reliability analysis method for low-voltage users in the distribution network.

[0042] Figure 2 This is a structural diagram of the power supply reliability analysis system for low-voltage users in the distribution network. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0044] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0045] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0046] Example 1

[0047] Reference Figure 1 , which is the first embodiment of the present invention, and which provides a method for analyzing the reliability of power supply to low-voltage users of a distribution network. The method for analyzing the reliability of power supply to low-voltage users of a distribution network comprises:

[0048] S1. Collect user electricity consumption data for preprocessing, and identify low-voltage users based on the user electricity consumption data;

[0049] Specifically, collecting user electricity usage data for preprocessing means installing a smart meter on the user's meter terminal to collect the user's electricity usage data, removing noise and filling missing values ​​in the electricity usage data. The smart meter is connected to the monitoring center through a wireless network and transmits the collected user electricity usage data to the monitoring center. The monitoring center synchronizes the user's electricity usage data and performs standardized processing.

[0050] Smart meters are installed at user terminals, and user electricity consumption data is transmitted to the monitoring center in real time through wireless networks, providing the system with high-precision real-time data. Smart meters can not only accurately collect user electricity consumption information, but also transmit data to the monitoring center in the first place, so that the monitoring center can monitor the user's electricity consumption status in real time. This data transmission method can reduce data latency, ensure the real-time and accuracy of the data obtained by the monitoring center, and lay a solid foundation for subsequent power supply reliability analysis. At the same time, remote data transmission reduces errors in manual reading and data recording, and improves data collection efficiency. During data transmission, network fluctuations, equipment failures or signal interference may cause data loss or noise. The noise removal and missing value filling steps in the preprocessing can effectively improve the stability and continuity of the data, ensuring that the data basis for power supply reliability analysis is more reliable. Noise removal can effectively eliminate mutations or outliers to avoid misleading the analysis model; missing value filling ensures the integrity of the data and avoids calculation deviations caused by missing data. Through this series of data preprocessing, the system can obtain more accurate and coherent user electricity consumption data, which will provide a solid foundation for subsequent users. Identification and power supply reliability analysis provide high-quality data support. When conducting power supply reliability analysis, there may be large differences in the magnitude of power consumption data of different users. These differences may cause large deviations to the analysis model. Through standardization, the user's power consumption data is unified into the same range, which can not only improve the comparability of the data, but also avoid the impact of data magnitude differences on the analysis process, and ensure the accuracy of the power supply reliability analysis model. This standardization provides clearer and more consistent input data for subsequent data mining and pattern recognition, so that the model can more accurately capture the user's power consumption characteristics. The collection of user power consumption data involves multiple smart meter devices, and these devices may have errors in collection time due to regional or device differences. Time synchronization plays a particularly important role in this process. Through a unified time base for data alignment, the consistency of power consumption data in different time periods or different devices can be guaranteed. Time synchronization not only ensures the basic correctness of data analysis, but also avoids the deviation of power supply reliability analysis results caused by time errors. Based on the consistent time data, the monitoring center can better identify the user's power consumption pattern and accurately predict and analyze the power supply status.

[0051] Furthermore, low-voltage user identification based on user power consumption data refers to obtaining pre-processed user power consumption data, setting a load fluctuation threshold, defining the time when the load in the user power consumption data is higher than the load fluctuation threshold as a load fluctuation state, and the rest as a load stable state, and using the Brownian motion probability density function to calculate the probability of the user being in a load fluctuation state and a load stable state:

[0052]

[0053] Where P(t|0) is the probability of the user being in a certain state, M is the maximum load change amplitude of the user in a certain state, D is the diffusion coefficient of the load change, t m is the time when the user reaches the maximum load in a certain state, and t is the total time when the user is in a certain state;

[0054] The probability P(t|0) of user load fluctuation state is solved by Brownian motion probability density function. - ) and the probability of load stability P(t|0 + ), according to P(t|0 - ) and P(t|0 + ) Calculate the probability flow J(t|0) of the user between two states:

[0055] J(t|0)=κ[P(t|0 - )-P(t|0 + )];

[0056] Where κ is the user load mutation frequency parameter;

[0057] The Brownian motion diffusion equation is constructed based on the probability flow J(t|0) of the user between two states and the probability P(t|0) of the user being in a certain state:

[0058]

[0059] Where δ is the diffusion coefficient, which is set empirically;

[0060] By solving the Brownian motion diffusion equation, we can get the probability P of the final user being in a certain state. * (t|0) and extract the probability P of the end user being in a load fluctuation state * (t|0 - ) and the probability of load stability P * (t|0 + ), according to P * (t|0 - ) and P * (t|0 + ) Recalculate the user’s probability flow J between two states * (t|0);

[0061] Set the probability threshold. If the user has a probability flow J between two states * If (t|0) is lower than the probability threshold, the user is marked as a low-voltage user, otherwise it is marked as the remaining user.

[0062] By setting the load fluctuation threshold, the user's power load state is divided into "load fluctuation state" and "load stability state". This method realizes the accurate identification of the user's power consumption behavior. The load fluctuation state indicates that the user's power load has changed significantly in a short period of time, while the load stability state indicates that the user's power load remains at a relatively stable level. Through this state division, the system can intuitively and accurately understand the user's load characteristics, which provides a basis for the subsequent power supply reliability analysis. At the same time, this identification method can significantly improve the adaptability to different types of user behaviors, ensure the accuracy and stability of power supply services, and introduce Brownian motion probability density. The probability function is used to calculate the probability of users in different load states, thereby more scientifically reflecting the changing characteristics of user loads. The Brownian motion probability model can effectively describe the characteristics of random fluctuations, so that the identification of user load fluctuations and stable states is not only based on threshold division, but also takes into account the randomness of load fluctuations. This probability model improves the scientific nature of the system's identification of user load states, ensures the accuracy of low-voltage user classification, and facilitates subsequent power resource scheduling and load management. By solving the Brownian motion probability model, the system can calculate the probability flow of users between load fluctuation states and load stable states. This probability flow parameter directly quantifies the user's load fluctuation frequency, which is reflected in the The changing characteristics of the user's power consumption state are revealed. In practical applications, the calculation of probability flow parameters helps to identify which users' power consumption patterns fluctuate frequently, thereby providing early warning of possible changes in power supply demand. The design of this step can enhance the system's responsiveness and effectively reduce the risk of instability caused by excessive load fluctuations during power supply management. The Brownian motion diffusion equation is used to construct a diffusion model of users between load fluctuations and load stability. This equation can be used to predict the conversion trend of user load states. The introduction of the Brownian motion diffusion equation can not only provide mathematical support for the power supply state, but also reveal the long-term change trend of user load characteristics. Through the solution of this diffusion equation, The solution can obtain the user's final state probability, provide a basis for the load regulation of the power supply system, help optimize the allocation efficiency of power supply resources, and improve power supply reliability. After obtaining the preliminary user load state probability, the system is further optimized by solving the Brownian motion diffusion equation, and the probability flow of the user between load fluctuation and load stability is recalculated. This recalculation process can gradually approach the user's real power consumption characteristics in multi-level state analysis, and improve the dynamic analysis capability of state transfer. Recalculating the probability flow can realize in-depth analysis of the user's power consumption state, identify users with large load changes, and realize more flexible load management and power grid regulation strategies.

[0063] S2. Analyze the power supply reliability based on the power consumption data of low-voltage users, and predict the power grid status of low-voltage users based on the power consumption data and power supply reliability of low-voltage users to provide early warning;

[0064] Specifically, analyzing power supply reliability based on low-voltage user power consumption data refers to extracting low-voltage user power consumption data based on low-voltage user tags, and extracting low-voltage user power consumption data features to construct a low-voltage user feature vector X, including load fluctuation frequency, average daily power consumption, equipment status, etc.;

[0065] The distribution network is divided into grid units T, each grid unit T is further divided into sub-grids, the number of low-voltage users in each sub-grid is counted, and the weight of the sub-grid in the grid unit T is calculated:

[0066]

[0067] where c K is the weight of subgrid K in grid unit T, N is the number of low-voltage users in subgrid K, X i is the feature vector of the i-th low-voltage user;

[0068] In each grid cell T, construct the local feature function g T :

[0069]

[0070] Among them l K is the indicator function, which is 1 in the area of ​​subgrid K and 0 otherwise;

[0071] According to the local characteristic function g T And the low-voltage user characteristic vector is used to calculate the power supply reliability R of the low-voltage user:

[0072]

[0073] Where β0 is the intercept, β j is the regression coefficient, X j is the jth eigenvalue in the low-voltage user feature vector, and n is the number of feature items in the low-voltage user feature vector;

[0074] By using the least squares method, β0 and β j Optimize and recalculate the power supply reliability R of low-voltage users * .

[0075] By constructing low-voltage user feature vectors, we systematically extract and analyze key features of users such as load fluctuation frequency, average daily power consumption, and equipment status. Compared with traditional methods, this multi-dimensional feature extraction method makes power supply reliability analysis more detailed and comprehensive. Feature vectors can not only quantify the individual power consumption characteristics of users, but also reflect the differences in equipment and power consumption habits, which helps to identify users with frequent load changes or high power demand, and ensure the scientific nature of power supply reliability prediction for low-voltage users. The distribution network is divided into grid units and further divided into sub-grids. The number of low-voltage users in each sub-grid can effectively represent the load density of the area. The division of grid units and sub-grids makes power supply reliability analysis It can focus on the characteristics of local areas and avoid the information loss caused by averaging the characteristics of users in a large area. This hierarchical division method can refine the power supply reliability analysis and accurately monitor and manage the power supply status according to the differences in user needs in different regions, thereby improving the efficiency of power resource allocation. By calculating the weight of each sub-grid in the grid unit, the impact of the power consumption characteristics of low-voltage users in different sub-grids on the overall power supply reliability can be accurately expressed. This weight calculation method reflects the distribution density and demand characteristics of low-voltage users in the region, making the power supply reliability analysis have a high regional adaptability. At the same time, weight-based calculations can help identify high-density load areas. , providing a scientific basis for the power supply system to warn of possible changes in power supply demand in advance. The local characteristic function is not only constructed through weights and sub-grid characteristics, but also combined with the characteristic vector of low-voltage users to accurately calculate the power supply reliability of users in each grid unit. The introduction of local characteristic functions allows the power supply reliability analysis to be adjusted in real time according to the dynamic changes of regional loads, thereby improving the accuracy of power supply analysis. The local characteristic function accurately describes the distribution characteristics of low-voltage users, which helps to identify power supply reliability risks in the region and provides the power sector with efficient power supply monitoring and optimization basis. Compared with traditional power supply reliability analysis methods, the regression model can be used to analyze the correlation between features and states. Prediction and inference can be performed to make the power supply reliability score more scientific and reasonable. This scoring model can reflect the stability and reliability of users' electricity demand, and provide a clear quantitative reference for power supply management departments in resource allocation and power supply regulation. The least squares method is used to optimize the regression coefficient and intercept of the regression model, which reduces the error of power supply reliability prediction. This optimization step ensures the adaptability of the model to actual user data and improves the accuracy of power supply reliability analysis. Least squares optimization can help the regression model better reflect the user's load fluctuation characteristics and electricity consumption behavior, so as to be more in line with the actual power supply reliability needs. This process provides more data-supported guidance for the management and scheduling of the power supply system.

[0076] Further, predicting the low-voltage user power grid status for early warning based on the low-voltage user's power consumption data and power supply reliability refers to constructing a convolutional neural network model, setting the input as the low-voltage user's power consumption data and power supply reliability, and the output as the low-voltage user power grid status, including normal and abnormal, and training the convolutional neural network through the training data set;

[0077] The low-voltage user electricity consumption data and power supply reliability are input into the trained convolutional neural network to obtain the low-voltage user's power grid status. If it is abnormal, the low-voltage user is notified to issue a power grid risk warning and arrange staff to perform advance maintenance.

[0078] By constructing a convolutional neural network (CNN) model, accurate prediction of the power grid status of low-voltage users can be achieved. Unlike traditional rule-setting or statistical models, CNN can automatically learn the potential patterns and characteristics of power grid status changes from a large amount of historical data. The multi-layer structure of CNN enables it to capture complex nonlinear relationships, so the recognition ability of fluctuations in low-voltage user electricity consumption data and power supply reliability is significantly improved, thereby providing effective support for the accurate prediction of power grid status. This high-precision prediction method can not only reduce the false alarm rate, but also effectively improve the reliability of early warning. By inputting the low-voltage user electricity consumption data and power supply reliability data into the trained convolutional neural network, the present invention can realize automatic power grid status recognition. Compared with the method that relies on manual judgment or traditional monitoring systems, the CNN model can It can process large amounts of data in real time and automatically output grid status results with higher efficiency and accuracy. The automated grid status identification function reduces errors caused by human intervention, allowing the power system to maintain efficient status monitoring in actual operation, thereby improving the power supply safety of low-voltage users. Once the convolutional neural network detects that the grid status of a low-voltage user is abnormal, the present invention will trigger an intelligent early warning mechanism, quickly notify the user and arrange for operation and maintenance personnel to conduct inspections and maintenance. This early warning mechanism can effectively reduce the risk of power supply interruptions caused by emergencies in the power system by discovering potential grid anomalies in advance. The intelligent early warning mechanism can not only allow power management personnel to take measures before a fault occurs to avoid large-scale power outages, but also significantly improve the response speed of operation and maintenance, ensuring the power safety of low-voltage users and the stable operation of the power grid.

[0079] S3, visualize the power consumption data and power supply reliability of low-voltage users and store them in the database;

[0080] Specifically, visually displaying the electricity consumption data and power supply reliability of low-voltage users means marking the low-voltage users on a digital map, synchronously associating the electricity consumption data and power supply reliability of low-voltage users with the low-voltage user marks on the digital map, and marking the low-voltage users with visual colors according to the power supply reliability. The higher the power supply reliability, the brighter the color.

[0081] By marking and visually displaying the power consumption data and power supply reliability of low-voltage users on digital maps, power management personnel can intuitively understand the power supply reliability of low-voltage users in various regions from the map. This visual display method directly links the location of low-voltage users with their power supply reliability, and no longer needs to manually consult complex power data or cumbersome text records. Through an intuitive digital map, managers can easily obtain the overall power consumption status distribution map, thereby quickly identifying key areas and high-demand areas. This not only greatly improves the power department's management efficiency of low-voltage users, but also improves the response speed to potential power problems. By using the characteristics of the geographical location to combine the power supply reliability with the characteristics of the user's area, this geographical location-based visual display not only makes the power supply reliability analysis more detailed, but also reveals the power supply stability of different regions. Characteristics, for example, managers can clearly identify areas with low power supply reliability, and by further analyzing the load distribution characteristics and user density in the area, take targeted power capacity expansion or transformation measures to enhance power supply security, and display the power supply reliability of low-voltage users through markings of different colors. The present invention realizes a hierarchical display of power supply status. Users with different power supply reliability status will be marked with different colors by using color marking. The lower the reliability of the user, the darker the marking color. This method can intuitively reflect potential power supply problem areas. Power management personnel can quickly identify dim color areas, identify potential power supply failure risks in advance and take preventive maintenance measures. The color marking method improves the visual effect of power supply reliability monitoring, thereby effectively reducing possible power failures and improving the power supply stability and user satisfaction of the power grid.

[0082] Furthermore, storing in a database means storing the identified low-voltage user tags, user power consumption data and power supply reliability analysis results in the database, and the database regularly uploads the stored data to the cloud for backup and simultaneously performs integrity checks on the stored data.

[0083] Example 2

[0084] Reference Figure 2 , which is a second embodiment of the present invention, provides a power supply reliability analysis system for low-voltage users in a distribution network, which includes:

[0085] An acquisition identification module is used to collect user electricity consumption data and identify low-voltage users based on the user electricity consumption data;

[0086] A reliability analysis module, used to analyze the power supply reliability of low-voltage users based on their power consumption data;

[0087] The risk prediction module is used to predict the power grid status of low-voltage users based on their power consumption data and power supply reliability, and to perform predictive maintenance;

[0088] The display storage module is used to mark and display low-voltage users and store them in the database.

[0089] The above modules are all constructed using existing technologies:

[0090] Specifically: the acquisition and recognition module collects user electricity consumption data through Schneider Electric ION7400 series smart meters. The meters have advanced power monitoring functions, can record user load data in real time and transmit it to the cloud through wireless networks, and preprocess the collected electricity consumption data through the MATLAB data preprocessing toolbox. Then, Python Pandas and Python SciPy libraries are used to analyze user load fluctuation data, and Scikit-learn is used to classify users using machine learning algorithms.

[0091] The reliability analysis module analyzes power supply reliability based on the collected low-voltage user power consumption data based on the Python scikit-learn regression analysis library. PowerFactory 2023 supports regional reliability assessment and has the ability to model the power supply status of large-scale users.

[0092] The risk prediction module uses the TensorFlow deep learning framework and convolutional neural networks to analyze and predict the status of low-voltage user power grids. TensorFlow 2.x has efficient model training and reasoning capabilities and can quickly process massive user data.

[0093] The display and storage module uses ESRI ArcGIS to provide digital map visualization functions and supports dynamic annotation and display of user data in geographic space. ArcGIS Pro 3.x can display the power supply reliability of different users through layer management functions, and use MySQL 8.0 database to efficiently store and manage users' electricity consumption data, power supply reliability and visualization results.

[0094] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0095] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0096] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0097] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0098] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for analyzing the reliability of power supply to low-voltage users in a distribution network, characterized by: include, Collect user electricity consumption data for pre-processing, and identify low-voltage users based on the user electricity consumption data; Analyze the power supply reliability based on the power consumption data of low-voltage users, and predict the power grid status of low-voltage users based on the power consumption data and power supply reliability of low-voltage users to provide early warning; The electricity consumption data and power supply reliability of low-voltage users are visualized and stored in the database.

2. The method for analyzing the reliability of power supply to low-voltage users in a distribution network according to claim 1, characterized in that: The collection of user electricity usage data for preprocessing refers to installing a smart meter on the user's meter terminal to collect the user's electricity usage data, removing noise and filling missing values ​​in the electricity usage data. The smart meter is connected to the monitoring center via a wireless network and transmits the collected user electricity usage data to the monitoring center. The monitoring center synchronizes the user's electricity usage data and performs standardized processing.

3. The method for analyzing the reliability of power supply to low-voltage users in a distribution network according to claim 1, characterized in that: The low-voltage user identification based on the user's power consumption data refers to obtaining the pre-processed user power consumption data, setting the load fluctuation threshold, defining the time when the load in the user's power consumption data is higher than the load fluctuation threshold as the load fluctuation state, and the rest as the load stable state, and using the Brownian motion probability density function to calculate the probability of the user being in the load fluctuation state and the load stable state: Where P(t|0) is the probability of the user being in a certain state, M is the maximum load change amplitude of the user in a certain state, D is the diffusion coefficient of the load change, t m is the time when the user reaches the maximum load in a certain state, and t is the total time when the user is in a certain state; The probability P(t|0) of user load fluctuation state is solved by Brownian motion probability density function. - ) and the probability of load stability P(t|0 + ), according to P(t|0 - ) and P(t|0 + ) Calculate the probability flow J(t|0) of the user between two states: J(t|0)=κ[P(t|0 - )-P(t|0 + )]; Where κ is the user load mutation frequency parameter; The Brownian motion diffusion equation is constructed based on the probability flow J(t|0) of the user between two states and the probability P(t|0) of the user being in a certain state: Where δ is the diffusion coefficient; By solving the Brownian motion diffusion equation, we can get the probability P of the final user being in a certain state. * (t|0) and extract the probability P of the end user being in a load fluctuation state * (t|0 - ) and the probability of load stability P * (t|0 + ), according to P * (t|0 - ) and P * (t|0 + ) Recalculate the user’s probability flow J between two states * (t|0); Set the probability threshold. If the user has a probability flow J between two states * If (t|0) is lower than the probability threshold, the user is marked as a low-voltage user, otherwise it is marked as the remaining user.

4. The method for analyzing the reliability of power supply to low-voltage users in a distribution network according to claim 1, characterized in that: Analyzing the power supply reliability according to the power consumption data of low-voltage users refers to extracting the power consumption data of low-voltage users according to the low-voltage user tags, and extracting the features of the power consumption data of low-voltage users to construct the feature vector X of low-voltage users; The distribution network is divided into grid units T, each grid unit T is further divided into sub-grids, the number of low-voltage users in each sub-grid is counted, and the weight of the sub-grid in the grid unit T is calculated: where c K is the weight of subgrid K in grid unit T, N is the number of low-voltage users in subgrid K, X i is the feature vector of the i-th low-voltage user; In each grid cell T, construct the local feature function g T : Among them l K is the indicator function, which is 1 in the area of ​​subgrid K and 0 otherwise; According to the local characteristic function g T And the low-voltage user characteristic vector is used to calculate the power supply reliability R of the low-voltage user: Where β0 is the intercept, β j is the regression coefficient, X j is the jth eigenvalue in the low-voltage user feature vector, and n is the number of feature items in the low-voltage user feature vector; By using the least squares method, β0 and β j Optimize and recalculate the power supply reliability R of low-voltage users * .

5. The method for analyzing the reliability of power supply to low-voltage users in a distribution network according to claim 1, characterized in that: The predicting of the low-voltage user power grid status according to the low-voltage user's power consumption data and power supply reliability for early warning refers to constructing a convolutional neural network model, setting the input to be the low-voltage user's power consumption data and power supply reliability, and the output to be the low-voltage user's power grid status, including normal and abnormal, and training the convolutional neural network through a training data set; The low-voltage user electricity consumption data and power supply reliability are input into the trained convolutional neural network to obtain the low-voltage user's power grid status. If it is abnormal, the low-voltage user is notified to issue a power grid risk warning and arrange staff to perform advance maintenance.

6. The method for analyzing the reliability of power supply to low-voltage users in a distribution network according to claim 1, characterized in that: The visual display of the power consumption data and power supply reliability of low-voltage users refers to marking the low-voltage users on a digital map, synchronously associating the power consumption data and power supply reliability of the low-voltage users with the low-voltage user marks on the digital map, and marking the low-voltage users with visual colors according to the power supply reliability.

7. The method for analyzing the reliability of power supply to low-voltage users in a distribution network according to claim 1, characterized in that: The storage in the database refers to storing the identified low-voltage user tags, user power consumption data and power supply reliability analysis results in the database. The database regularly uploads the stored data to the cloud for backup and simultaneously performs integrity checks on the stored data.

8. A power supply reliability analysis system for low-voltage users in a distribution network according to any one of claims 1 to 7, characterized in that: include, An acquisition identification module is used to collect user electricity consumption data and identify low-voltage users based on the user electricity consumption data; A reliability analysis module, used to analyze the power supply reliability of low-voltage users based on their power consumption data; The risk prediction module is used to predict the power grid status of low-voltage users based on their power consumption data and power supply reliability, and to perform predictive maintenance; The display storage module is used to mark and display low-voltage users and store them in the database.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method for analyzing the reliability of power supply to low-voltage users in a distribution network according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for analyzing the reliability of power supply to low-voltage users in a distribution network according to any one of claims 1 to 7 are implemented.

Images