Intelligent electric energy meter containing metering performance anomaly detection module

Abstract

The invention relates to the technical field of power monitoring, in particular to an intelligent electric energy meter with a metering performance anomaly detection module, which comprises a power reading acquisition module, a power utilization mode identification module, a power data detection module, an electric energy meter fault identification module, a power utilization data comparison module and an automatic charging module. According to the invention, various electric power parameters such as current, voltage and electricity consumption are measured and analyzed, and the metering problem of the electricity meter is identified and detected, so that rapid response and correction of abnormal problems are realized, energy waste and economic loss caused by metering errors are reduced, and continuous stability and safety of power supply are ensured; by accurately comparing the total electricity consumption of a community with the reading of an individual electricity meter, non-technical loss is effectively identified, electricity stealing users are effectively marked, the economic benefit of power grid operation is guaranteed, the accuracy and response speed of a power monitoring system are ensured, and the management and operation efficiency of a power grid is optimized by combining automatic electricity consumption charging.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and particularly to an intelligent electricity meter with a metering performance anomaly detection module. Background Art

[0002] The technical field of power monitoring focuses on the real-time monitoring, management, and optimization of electric energy, including power consumption monitoring, load management, and fault prediction. Through intelligent sensing technology, big data analysis, and cloud computing, it improves the efficiency and reliability of the power grid, reduces energy waste, ensures power supply safety. By collecting various key parameters of the power grid such as current, voltage, frequency, and power in real time, combined with data analysis and artificial intelligence, it comprehensively evaluates the operating state of the power grid, detects power grid faults and abnormal conditions in real time, maintains the stable operation of the power system, and optimizes power distribution and consumption.

[0003] Among them, intelligent electricity meters focus on measuring and recording electricity consumption information, and support remote reading and management functions. By providing energy consumption data, they help consumers and power companies understand and control power usage, and realize multiple functions such as fault detection, demand response, and time-of-use electricity price response, improving the flexibility and economy of power supply, promoting energy efficiency improvement, including enhancing the load management ability of the power grid, promoting energy conservation, and supporting the integration of renewable energy, helping users and power providers achieve effective power management and cost control, and supporting sustainable development goals.

[0004] Traditional intelligent electricity meters are limited to traditional monitoring methods in metering performance anomaly detection, relying on periodic system detection or preset threshold triggering, making it difficult to perform real-time and accurate anomaly identification. As a result, when sudden power problems or metering errors occur, the response time is delayed, and fault diagnosis and processing cannot be carried out in real time. The efficiency in processing large-scale data is low, making it difficult to meet the requirements of real-time and accuracy in the big data era. There is a lack of effective analysis tools to distinguish and identify electricity theft behavior, increasing the economic burden on power companies, affecting the reasonable distribution and fair use of energy, and restricting energy management efficiency. Summary of the Invention

[0005] In order to solve the technical problems of metering errors and identification of electricity theft behavior existing in the prior art, an embodiment of the present invention provides an intelligent electricity meter with a metering performance anomaly detection module. The technical solution is as follows:

[0006] On the one hand, an intelligent electricity meter with a metering performance anomaly detection module is provided, including:

[0007] The power reading acquisition module, based on the electricity meter position information, collects the current, voltage, and electricity consumption data of the electricity meter in real time, records the time information, and generates a real-time power dataset in combination with data formatting;

[0008] The power consumption pattern recognition module, based on the real-time power dataset, evaluates the power consumption pattern of the target user and the group power consumption behavior by analyzing the power consumption information at multiple time points, and generates a power consumption behavior model;

[0009] The power data detection module, based on the power consumption behavior model, detects abnormal power consumption behavior by real-time monitoring of the user's power behavior, and generates abnormal power detection data;

[0010] The electricity meter fault identification module, based on the abnormal power detection data, analyzes the abnormal data, identifies abnormal current and voltage readings, detects electricity meter faults and analyzes the causes of the faults, and generates a fault cause analysis result;

[0011] The power consumption data comparison module uses the fault cause analysis result, uses the transformer measurement equipment to collect the power consumption data of the community, and compares it with the electricity meter measurement data, identifies non-technical losses and marks electricity theft behavior, and generates an electricity theft behavior detection result;

[0012] The automatic billing module calculates payment bills for multiple users according to the electricity theft behavior detection result, and sends notification information to the users, and generates a bill sending record.

[0013] As a further solution of the present invention, the real-time power dataset includes current and voltage measurement values, power consumption data, and timestamp information. The power consumption behavior model includes user power consumption patterns, group power consumption behavior analysis results, and power consumption prediction data for multiple time periods. The abnormal power detection data includes identified abnormal power consumption, abnormal power consumption time, and abnormal current and voltage readings. The fault cause analysis result includes similarity calculation results, fault type identification results, and abnormal data feature information. The electricity theft behavior detection result includes marked data deviation calculation results, abnormal point time information, and abnormal user location information. The bill sending record includes the calculated total electricity bill, the user's bill sending record, and the notification information matching result.

[0014] As a further solution of the present invention, the power reading acquisition module includes:

[0015] The user grouping sub-module, based on the electricity meter location information, groups the user groups according to the community scope through the location coordinate information of multiple electricity meters, and generates user group information;

[0016] The power consumption data recording sub-module, based on the user group information, real-time collects the current, voltage, power consumption, and collection time information of multiple electricity meters, and generates real-time monitoring data;

[0017] The data preprocessing sub-module, based on the real-time monitoring data, formats the collected data, optimizes the consistency and accuracy of the data, and generates a real-time power dataset.

[0018] As a further solution of the present invention, the power consumption pattern recognition module includes:

[0019] The user behavior analysis sub-module analyzes the power consumption information of the target user at multiple time points based on the real-time power data set, identifies the change trend and behavior characteristics of the power consumption, evaluates the power consumption pattern of the target user, and generates power consumption behavior analysis data;

[0020] The group pattern evaluation sub-module analyzes the power consumption data of multiple users based on the power consumption behavior analysis data, identifies the power consumption behavior of the group, identifies periodic fluctuations and seasonal changes, and generates group power consumption pattern information;

[0021] The power consumption prediction sub-module calculates the predicted power consumption values of the user at multiple time points based on the group power consumption pattern information and generates a power consumption behavior model.

[0022] As a further solution of the present invention, the power data detection module includes:

[0023] The power consumption data extraction sub-module extracts the power usage data of multiple users based on the power consumption behavior model, including current, voltage, and power consumption data at multiple time points, and generates user power consumption data;

[0024] The abnormal data identification sub-module analyzes the power consumption data and detects abnormal power consumption behaviors based on the user power consumption data, including abnormal power consumption, abnormal power consumption time, and abnormal current and voltage, and generates an abnormal detection result;

[0025] The abnormal event recording sub-module records the identified abnormal events based on the abnormal detection result, including the time of event occurrence, abnormal data type, and abnormal reading, and generates abnormal power detection data.

[0026] As a further solution of the present invention, the electricity meter fault identification module includes:

[0027] The data feature extraction sub-module extracts the data features of the abnormal points based on the abnormal power detection data, including the fluctuation amplitude of the power voltage, current and voltage values, and abnormal duration, and generates abnormal point data features;

[0028] The fault cause analysis sub-module calculates the similarity by comparing the data features of the known fault modes based on the abnormal point data features, identifies the fault cause, and generates a fault diagnosis record;

[0029] The fault response sub-module matches the notification information according to the position of the faulty electricity meter, the time point of the abnormal data, and the fault cause based on the fault diagnosis record and sends it to the management personnel, and generates a fault cause analysis result.

[0030] As a further solution of the present invention, the specific formula for calculating the similarity is as follows:

[0031]

[0032] Wherein, S represents the similarity value, reflecting the similarity degree between the abnormal point data and the known fault mode, A i represents the current and voltage values of the abnormal point data, B i represents the current and voltage values of the known fault mode, i is the index of the data point, and n represents the total number of data points.

[0033] As a further solution of the present invention, the electricity consumption data comparison module includes:

[0034] The group electricity consumption measurement sub-module uses the fault cause analysis result, and uses the transformer measurement equipment to collect the electricity consumption data of the community, and generates the community electricity consumption data;

[0035] The measurement data comparison sub-module compares the community electricity consumption data with the community electricity consumption data measured by the electricity meter, identifies and marks the non-technical losses, and generates the non-technical loss detection result;

[0036] The abnormal user judgment sub-module identifies the electricity stealing users based on the non-technical loss detection result, records the household number and location information of the target users, and generates the abnormal electricity consumption judgment result.

[0037] As a further solution of the present invention, the automatic billing module includes:

[0038] The user fee calculation sub-module calculates the payment bills of multiple users based on the electricity stealing behavior detection result, according to the electricity consumption data of multiple users, combined with the real-time electricity price, and generates the user billing data;

[0039] The notification information matching sub-module matches the notification information for multiple users based on the user billing data, including the payable amount, overdue time, and electricity consumption, and generates the user notification data;

[0040] The bill status monitoring sub-module sends the notification information to multiple users based on the user notification data, and monitors the credit status of the bill in real time, and generates the bill sending record.

[0041] As a further solution of the present invention, the specific formula for calculating the payment bills of multiple users is as follows:

[0042] C k =∑(E kj ×P j )-B k

[0043] Wherein, C kRepresents the total billing amount for the k-th user, E kj Represents the electricity consumption of the k-th user in the j-th electricity price range, P j Represents the unit price of the j-th electricity price range, B k Represents the remaining balance of the k-th user.

[0044] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0045] By measuring and analyzing various power parameters such as current, voltage, and electricity consumption, identifying and detecting electricity meter measurement problems, realizing rapid response and correction of abnormal problems, reducing energy waste and economic losses caused by measurement errors, ensuring the continuous stability and safety of power supply, effectively identifying non-technical losses and marking electricity theft users by accurately comparing the total electricity consumption of the community with individual electricity meter readings, safeguarding the economic benefits of power grid operation, ensuring the accuracy and response speed of the power monitoring system, and combining automated electricity billing to optimize the management and operation efficiency of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0047] Figure 1 Is the system flow chart of the present invention;

[0048] Figure 2 Is the schematic diagram of the system framework of the present invention;

[0049] Figure 3 Is the flow chart of the power reading acquisition module of the present invention;

[0050] Figure 4 Is the flow chart of the electricity consumption pattern recognition module of the present invention;

[0051] Figure 5 Is the flow chart of the power data detection module of the present invention;

[0052] Figure 6 Is the flow chart of the electricity meter fault recognition module of the present invention;

[0053] Figure 7 Is the flow chart of the electricity consumption data comparison module of the present invention;

[0054] Figure 8 Is the flow chart of the automatic billing module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The technical solutions in the present invention will be described below with reference to the accompanying drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0057] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "Of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W 1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0059] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0060] The embodiments of the present invention provide an intelligent electricity meter with a metering performance anomaly detection module. Please refer to Figures 1 to 2 An intelligent electricity meter with a metering performance anomaly detection module includes:

[0061] The power reading acquisition module, based on the electricity meter position information, collects the current, voltage, and electricity consumption data of the electricity meter in real time, records the time information, and generates a real-time power data set by combining data formatting.

[0062] The electricity consumption pattern recognition module, based on the real-time power data set, evaluates the electricity consumption pattern of the target user and the group electricity consumption behavior by analyzing the electricity consumption information at multiple time points, and generates an electricity consumption behavior model.

[0063] The power data detection module, based on the electricity consumption behavior model, detects abnormal electricity consumption behavior by monitoring the user's power behavior in real time, and generates abnormal power detection data.

[0064] The electricity meter fault identification module, based on the abnormal power detection data, identifies abnormal current and voltage readings by analyzing the abnormal data, detects the electricity meter fault and analyzes the fault cause, and generates a fault cause analysis result.

[0065] The electricity consumption data comparison module uses the analysis results of the fault causes, utilizes the transformer measurement equipment to collect the electricity consumption data of the community, compares it with the electricity meter measurement data, identifies non-technical losses and marks the electricity theft behavior, and generates the electricity theft behavior detection result;

[0066] The automatic billing module calculates the payment bills for multiple users according to the electricity theft behavior detection result, sends notification information to the users, and generates the bill sending record.

[0067] The real-time power data set includes current and voltage measurement values, electricity consumption data, and timestamp information. The electricity consumption behavior model includes user electricity consumption patterns, analysis results of group electricity consumption behavior, and electricity consumption prediction data for multiple time periods. The abnormal power detection data includes identified abnormal electricity consumption, abnormal electricity consumption time, and abnormal current and voltage readings. The analysis results of the fault causes include similarity calculation results, fault type identification results, and abnormal data feature information. The electricity theft behavior detection result includes marked calculation results of data deviation, abnormal point time information, and abnormal user location information. The bill sending record includes the calculated total electricity bill, the bill sending record of the user, and the notification information matching result.

[0068] Please refer to Figure 2 and Figure 3 , the power reading acquisition module includes:

[0069] The user grouping sub-module groups the user groups according to the community scope based on the electricity meter location information and through the location coordinate information of multiple electricity meters, and generates the user group information;

[0070] Extract all the location coordinate information of the electricity meters from the database, including longitude and latitude, and the information is stored in floating-point format. Group the user groups according to the geographical boundary of the community. The community boundary is obtained through government data services or defined using GIS map services. Determine which community each electricity meter belongs to using the nearest neighbor algorithm for the location of each electricity meter. Call the geographic information processing library, such as GeoPandas or ArcGIS API, to achieve grouping by calculating the distance between each electricity meter and the community boundary. The grouped results are stored in list form, and each list item contains the community identifier and the ID of the electricity meters within that community. This process ensures the geographical accuracy of the data and promotes the efficiency of subsequent data management.

[0071] The electricity consumption data recording sub-module, based on the user group information, real-time collects the current, voltage, electricity consumption, and collection time information of multiple electricity meters, and generates the real-time monitoring data;

[0072] Monitor the current, voltage, and power consumption of each electricity meter in real time. Each data point includes the current value, voltage value, power consumption, and collection time. Data collection is automatically performed by sensors, and the collection frequency can be set to once per minute. The collected data is initially stored in a temporary data cache, and timestamps are used to mark to ensure the accuracy of the data order. Batch processing technology is used to periodically write the data in the cache to the main database in batches. SQL database transactions are used to ensure the atomicity and consistency of data writing, reduce the number of requests to the database, optimize the system's response time, and reduce the server burden. The real-time monitoring data generated after each processing is further passed to the data preprocessing sub-module.

[0073] Based on the real-time monitoring data, the data preprocessing sub-module formats the collected data, optimizes the consistency and accuracy of the data, and generates a real-time power dataset.

[0074] Perform data formatting to standardize all data fields into a unified format. For example, the data units of current and voltage are unified into standard international units, and the timestamp format is unified into the ISO 8601 standard. Perform data cleaning to delete any abnormal or corrupted data points. Anomaly detection is achieved by setting threshold methods. For example, the current and voltage values must not exceed the preset maximum and minimum safety ranges. For any data points outside the range, a deletion operation is performed. Perform data consistency checks to ensure the continuity and integrity of all data in the time series. Use a data alignment algorithm to check the coherence of timestamps. The processed dataset becomes a real-time power dataset, which is used for further data analysis and training of power consumption prediction models, ensuring the quality and usability of the dataset.

[0075] Please refer to Figure 2 and Figure 4 , the electricity consumption pattern recognition module includes:

[0076] Based on the real-time power dataset, the user behavior analysis sub-module analyzes the power consumption information of the target user at multiple time points, identifies the changing trends and behavioral characteristics of power consumption, evaluates the electricity consumption pattern of the target user, and generates electricity consumption behavior analysis data.

[0077] Extract the power consumption data of the target user at different time points. The data types include timestamps and power consumption, which are stored in floating-point format. Use time series analysis techniques and the autoregressive integrated moving average model to perform trend analysis on the power consumption data. Predict the future power consumption pattern through historical power consumption data. Use the Statsmodels library in Python for calculation. The peak, trough, and occurrence time points of power consumption will be identified and recorded in the results. Evaluate the target user's daily electricity consumption habits and abnormal electricity consumption behaviors through the target data. The generated electricity consumption behavior analysis data includes the user's peak electricity consumption period, trough electricity consumption period, and abnormal consumption patterns. The target data is crucial for further user behavior evaluation.

[0078] Based on the electricity consumption behavior analysis data, the group pattern evaluation sub-module analyzes the electricity consumption data of multiple users, identifies the electricity consumption behavior of the group, identifies periodic fluctuations and seasonal changes, and generates group electricity consumption pattern information;

[0079] Through the K-means clustering algorithm, classify the electricity consumption behavior of users, set the value of K to 5, divide users into five categories according to the similarity of electricity consumption behavior, implement through the Scikit-learn library, analyze the electricity consumption data of users in each category, pay attention to the periodic fluctuations and seasonal changes of users within each group, use Fourier transform for periodic analysis to identify the main frequencies, and implement seasonal analysis by comparing the average electricity consumption differences in different months. The results help understand the electricity consumption patterns of different user groups, such as the electricity consumption differences between weekdays and weekends, and the electricity consumption behaviors in summer and winter. The generated group electricity consumption pattern information is used for further strategy formulation and demand prediction.

[0080] Based on the group electricity consumption pattern information, the electricity consumption prediction sub-module calculates the predicted electricity consumption values of users at multiple time points and generates an electricity consumption behavior model;

[0081] Define the parameters of the electricity consumption behavior model, including the time window and the length of historical data. Use the random forest algorithm in the machine learning model for prediction. Model training involves selecting appropriate features, such as time points, historical electricity consumption in the same period, weather conditions, etc. The model is trained with historical data and cross-validation is used to ensure prediction accuracy. The prediction process uses the Pandas library in Python to process time series data, and the Sklearn library is used to implement the random forest model training. The model will output the predicted electricity consumption of each user at the target time point. The target prediction values are stored in the form of an array, and each array contains the time point and the corresponding predicted electricity consumption. The generation of the electricity consumption behavior model provides data support for the scheduling and optimization of the energy management system, ensuring the balance between energy supply and demand.

[0082] Please refer to Figure 2 and Figure 5 , the power data detection module includes:

[0083] Based on the electricity consumption behavior model, the electricity consumption data extraction sub-module extracts the electricity usage data of multiple users, including current, voltage, and electricity consumption data at multiple time points, and generates user electricity consumption data;

[0084] Extract the electricity usage data of multiple user groups, including current, voltage, and electricity consumption. Call the electricity usage records of specific users from the database. The process is implemented through SQL queries. The parameter types involved are mainly timestamps and user IDs, which are used to determine the data range and target user group for the query. Perform data cleaning operations on the extracted data to eliminate any invalid data caused by reading errors or transmission problems. Use the Pandas library for data preprocessing, including filling missing values, removing duplicate records, etc. The cleaned data is stored in a structured format to provide an accurate input source for the next step of abnormal data analysis. The generated user electricity usage data is saved in CSV file format. Each file contains time-series current, voltage, and electricity consumption data. The files are updated and backed up regularly through an automated script to ensure the availability and security of the data.

[0085] The abnormal data identification sub-module analyzes the electricity usage data and detects abnormal electricity usage behaviors based on the user electricity usage data, including abnormal electricity consumption, abnormal electricity usage time, and abnormal current and voltage, and generates abnormal detection results.

[0086] Use the user electricity usage data obtained from the electricity usage data extraction module to conduct abnormal behavior analysis. Define the criteria for abnormal detection, including the normal operation ranges of electricity consumption, current, and voltage. Adopt statistical methods such as standard deviation analysis and IQR method to identify outliers in the data, including calculating the deviation of each data point from the average value. If it exceeds the set standard deviation range, it is marked as abnormal. Also, monitor the sudden changes in current and voltage in real-time. Use the sliding window technique with a window size set to 5 minutes to analyze the maximum and minimum values within the window and identify sudden peaks or troughs. The identified abnormal points are summarized to generate abnormal detection results. The target results record the type, time, and affected electricity parameters of the abnormal event, providing key information for fault diagnosis.

[0087] The abnormal event recording sub-module records the identified abnormal events based on the abnormal detection results, including the time of event occurrence, abnormal data type, and abnormal readings, and generates abnormal electricity detection data.

[0088] According to the identified abnormal detection results, record the detailed information of each abnormal event, including the specific time of the event, the data type involved, and the specific abnormal value. The process involves data marking and classification. Analyze the abnormal detection results through an automated script to identify the occurrence time and parameters of each type of abnormality. Use the database management system for data entry. Each abnormal event is stored as a record in a specific database table. Sort the priorities according to the severity of the abnormality to ensure that critical abnormal events can be processed in a timely manner. The generated abnormal electricity detection data includes a comprehensive list of abnormal events. Each record describes the nature and impact of the abnormality. The target information is of great value for the maintenance team to conduct fault response and system optimization.

[0089] Please refer to Figure 2 and Figure 6 , the electricity meter fault identification module includes:

[0090] Based on the abnormal power detection data, the data feature extraction sub-module extracts the data features of the abnormal points, including the fluctuation amplitude of the power voltage, the current voltage value, and the abnormal duration, and generates the data features of the abnormal points;

[0091] Based on the abnormal power detection data, key performance indicators are extracted from the data, such as the fluctuation amplitude of the power voltage, the current voltage value, and the abnormal duration. The process involves time series analysis techniques, such as autoregressive models. The abnormal duration is calculated by the time when the continuously monitored abnormal readings exceed the normal range. The extracted data features are stored in the central database in a standardized form for further analysis. This step ensures the accuracy and response speed of subsequent fault analysis. The generated data features of the abnormal points provide the necessary input data for the subsequent modules.

[0092] Based on the data features of the abnormal points, the fault cause analysis sub-module calculates the similarity by comparing the data features of the known fault modes, identifies the fault cause, and generates a fault diagnosis record;

[0093] The specific formula for calculating the similarity is:

[0094]

[0095] where S represents the similarity value, which reflects the similarity between the abnormal point data and the known fault mode. A i represents the current voltage value of the abnormal point data, B i represents the current voltage value of the known fault mode, i is the index of the data point, and n represents the total number of data points.

[0096] Formula:

[0097]

[0098] Detailed explanation of the formula and the derivation process of the formula calculation:

[0099] The formula is used to calculate the similarity between the abnormal data and the known fault mode, and the result is used to identify the fault cause.

[0100] Meaning of parameters and set values:

[0101] n is the total number of data points, assumed to be 3;

[0102] A i is the voltage value of the abnormal point at the i-th time, assumed to be [100, 102, 109], which reflects the voltage at different time points during the monitoring period;

[0103] B i is the voltage value of the known fault mode at the i-th time, assumed to be [90, 105, 115], which reflects the voltage mode under a specific fault state;

[0104] Substitute the parameters into the formula for calculation:

[0105]

[0106]

[0107] The result S≈0.965 indicates that the abnormal data has a high similarity with the known fault mode, suggesting that the current detected abnormality may be caused by the same fault reason.

[0108] Based on the fault diagnosis record, the fault response sub-module matches the notification information according to the position of the faulty electricity meter, the time point of the abnormal data, and the fault reason, and sends it to the management personnel, generating the fault cause analysis result;

[0109] Execute the notification sending process. This process involves the application of information matching and communication technologies. The system locates the specific location where the fault occurs using geographic information system technology according to the position of the faulty electricity meter, the time point of the abnormal data, and the diagnosed fault reason. Through the internally developed notification system, combined with email and SMS communication services, the fault information is formatted and sent to the relevant management and technical personnel. During the process, the notification information template is used to prioritize according to the severity and urgency of the fault to ensure the timely transmission of key information, reducing the potential risks and losses brought by the fault. The generated fault cause analysis result provides decision-making support for the management.

[0110] Please refer to Figure 2 and Figure 7 , the electricity consumption data comparison module includes:

[0111] The group electricity consumption measurement sub-module uses the fault cause analysis result and uses the transformer measurement equipment to collect the electricity consumption data of the community, generating the community electricity consumption data;

[0112] In the group electricity consumption measurement sub-step, the system uses the transformer measurement equipment to monitor the overall electricity consumption of the community in real time. Connect the output of the transformer to the data acquisition system, which is configured with multi-channel acquisition interfaces and can process multiple data streams simultaneously. During the acquisition process, each transformer regularly sends readings of current and voltage. The target readings are processed through Fourier transform analysis to obtain the electricity consumption. The collected data is transmitted to the central monitoring system in real time through a wireless network. The central monitoring system uses data smoothing and error correction algorithms to further ensure the accuracy of the data. The generated community electricity consumption data provides a reliable basis for subsequent data comparison and analysis.

[0113] The measurement data comparison sub-module compares the community electricity consumption data with the community electricity consumption data measured by the electricity meters, identifies and marks non-technical losses, and generates non-technical loss detection results;

[0114] Through data analysis software, the collected community electricity consumption data and the recorded data of each household's electricity meter are compared and analyzed. The data normalization process is used to eliminate the reading deviation between devices. Statistical test methods, such as the T-test, are applied to determine the significant differences between the two sets of data. The clustering analysis process is used to identify abnormal patterns in the data, such as significant increases or decreases in electricity consumption. The target abnormal patterns usually indicate the possibility of non-technical losses, such as electricity theft and other behaviors. Potential non-technical losses are automatically marked, and non-technical loss detection results are generated, listing the accounts and relevant data of suspected abnormal consumption.

[0115] The abnormal user judgment sub-module identifies electricity theft users based on the non-technical loss detection results, records the household numbers and location information of the target users, and generates abnormal electricity consumption judgment results;

[0116] The decision tree algorithm is used to identify electricity theft users. The algorithm constructs a decision tree based on factors such as the user's historical electricity consumption behavior and typical characteristics of electricity theft behavior, such as sudden increases in electricity consumption or electricity consumption at abnormal times. Through logical analysis, the user data that matches the known electricity theft behavior pattern is identified, and the detailed information of the user is automatically recorded, including the household number, location information, and the time and characteristics of the electricity theft behavior. The target information is used to generate abnormal electricity consumption judgment results, and the results are used for immediate anti-electricity theft actions, electricity consumption behavior analysis, and pattern establishment, reducing power losses and improving the overall operation efficiency of the power grid.

[0117] Please refer to Figure 2 and Figure 8 , the automatic billing module includes:

[0118] The user fee calculation sub-module calculates the payment bills of multiple users based on the electricity theft behavior detection results, combines the electricity consumption data of multiple users with the real-time electricity price, and generates user billing data;

[0119] The specific formula for calculating the payment bills of multiple users is:

[0120] C k =∑(E kj ×P j )-B k

[0121] Among them, C k represents the total billing amount of the k-th user, E kj represents the electricity consumption of the k-th user in the j-th electricity price interval, P j represents the unit price of the j-th electricity price interval, B kRepresents the remaining balance of the k-th user.

[0122] Formula:

[0123] C k = ∑(E kj × P j ) - B k ;

[0124] Detailed explanation of the formula and the derivation process of the formula calculation:

[0125] The formula is used to calculate the total electricity bill of multiple users, and the result provides basic data for the operation of the power grid.

[0126] Meaning of parameters and set values:

[0127] E kj Is the electricity consumption of the k-th user in the j-th electricity price interval. Assume that the electricity consumptions of the user in three electricity price intervals are 200 kWh, 150 kWh, and 100 kWh respectively;

[0128] P j Is the unit price of the j-th electricity price interval. Assume that the electricity prices in the 3 intervals are 1.5 yuan / kWh, 1.2 yuan / kWh, and 1.0 yuan / kWh respectively;

[0129] B k Is the remaining balance of the k-th user. Assume that the remaining balance of the user is 350 yuan;

[0130] Substitute the parameters into the formula for calculation:

[0131] C k = (200 × 1.5 + 150 × 1.2 + 100 × 1.0) - 350;

[0132] C k = (300 + 180 + 100) - 350;

[0133] C k = 580 - 350;

[0134] C k = 230;

[0135] The result of 230 yuan indicates the total electricity bill payable by the user calculated based on their electricity consumption in each period and the remaining balance. The value reflects the relationship between the user's actual electricity consumption cost and the prepaid balance. The calculation process provides a data basis for the operation of the electricity formula.

[0136] The notification information matching sub-module matches notification information for multiple users based on user billing data, including the amount payable, overdue time, and electricity consumption, and generates user notification data;

[0137] In the notification information matching sub-step, based on the generated user billing data, the mail management system automatically matches specific notification information for each user, including the amount due, overdue time, and electricity consumption. The system uses a database management system to process a large amount of user data, accesses the user's bill data through SQL query statements, extracts the necessary information, and formats it into a notification template. The target template is used by the mail server to automatically fill in the specific bill information, and conditional logic is applied to determine the priority of the notification. For example, overdue bills will be sent first. The generated user notification data is stored in a central database for auditing and customer service purposes.

[0138] Based on the user notification data, the bill status monitoring sub-module sends notification information to multiple users and monitors the credit status of the bills in real time, generating bill sending records.

[0139] In the bill status monitoring sub-step, using the generated user notification data, bills are sent to users through an integrated email and SMS sending platform. The process includes using automated communication tools configured with APIs to connect to the telecommunications service provider to ensure the instant delivery of information. The credit status of the bills is monitored in real time during the sending process, including the payment status and receipt confirmation, and the status of each transaction is tracked, such as paid, unpaid, or overdue. An event-driven programming model is applied to handle payment failures, such as network problems or payment gateway failures. The generated bill sending records include the sending time, status, and user feedback of each message. The target data provides valuable information for the power company regarding its collection efficiency and customer response.

[0140] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0141] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0142] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0143] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0144] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0145] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0146] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical, or other forms.

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

[0148] In addition, the functional units in the various embodiments of the present invention can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0149] When the above-mentioned 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, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0150] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A smart electric energy meter with a metering performance abnormality detection module, characterized in that: The system comprises: The power reading acquisition module collects the current, voltage, and power consumption data of the meter in real time based on the meter location information, records the time information, and combines data formatting to generate a real-time power data set; The power consumption pattern recognition module analyzes the power consumption information at multiple time points based on the real-time power data set, evaluates the power consumption pattern and group power consumption behavior of the target user, and generates a power consumption behavior model; The power data detection module detects abnormal power usage behavior based on the power usage behavior model and generates abnormal power detection data by real-time monitoring of the user's power usage behavior; The electric meter fault identification module is based on the abnormal power detection data, identifies abnormal current and voltage readings by analyzing the abnormal data, detects the electric meter fault and analyzes the fault cause, and generates a fault cause analysis result; The power consumption data comparison module uses the fault cause analysis results and transformer measurement equipment to collect the power consumption data of the community, and compares it with the meter measurement data to identify non-technical losses and mark power theft behaviors, and generate power theft behavior detection results; The automatic billing module calculates payment bills for multiple users according to the electricity theft detection results, sends notification information to the users, and generates bill sending records.

2. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The real-time power data set includes current and voltage measurement values, power consumption data, and timestamp information; the power consumption behavior model includes user power consumption patterns, group power consumption behavior analysis results, and power consumption forecast data for multiple time periods; the abnormal power detection data includes identified abnormal power consumption, abnormal power consumption time, and abnormal current and voltage readings; the fault cause analysis results include similarity calculation results, fault type identification results, and abnormal data feature information; the power theft behavior detection results include marked data deviation calculation results, abnormal point time information, and abnormal user location information; the bill sending record includes the calculated total electricity bill, the user's bill sending record, and notification information matching results.

3. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The power reading acquisition module includes: The user grouping submodule is based on the meter location information and the location coordinate information of multiple meters to group user groups according to the community range and generate user group information; The power consumption data recording submodule collects the current, voltage, power consumption and collection time information of multiple electric meters in real time based on the user group information to generate real-time monitoring data; The data preprocessing submodule formats the collected data based on the real-time monitoring data, optimizes the consistency and accuracy of the data, and generates a real-time power data set.

4. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The power usage mode recognition module includes: The user behavior analysis submodule analyzes the target user's power consumption information at multiple time points based on the real-time power data set, identifies the change trend and behavior characteristics of power consumption, evaluates the target user's power consumption pattern, and generates power consumption behavior analysis data; The group pattern evaluation submodule analyzes the power consumption data of multiple users based on the power consumption behavior analysis data, identifies the power consumption behavior of the group, identifies periodic fluctuations and seasonal changes, and generates group power consumption pattern information; The power consumption prediction submodule calculates the power consumption prediction values ​​of the users at multiple time points based on the group power consumption pattern information and generates a power consumption behavior model.

5. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The power data detection module includes: The power consumption data extraction submodule extracts power consumption data of multiple users based on the power consumption behavior model, including current, voltage and power consumption data at multiple time points, and generates user power consumption data; The abnormal data identification submodule analyzes the power consumption data and detects abnormal power consumption behavior based on the user's power consumption data, including abnormal power consumption, abnormal power consumption time, and abnormal current and voltage, and generates an abnormal detection result; The abnormal event recording submodule records the identified abnormal events based on the abnormal detection results, including the time when the event occurred, the abnormal data type, and the abnormal reading, and generates abnormal power detection data.

6. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The electric meter fault identification module comprises: The data feature extraction submodule extracts data features of abnormal points based on the abnormal power detection data, including the fluctuation amplitude of power voltage, current and voltage values, and duration of abnormality, and generates data features of abnormal points; The fault cause analysis submodule calculates similarity based on the abnormal point data features, compares the data features of known fault modes, identifies the fault causes, and generates fault diagnosis records; The fault response submodule matches the notification information based on the fault diagnosis record, the location of the faulty meter, the time point of the abnormal data, and the cause of the fault, and sends it to the management personnel to generate a fault cause analysis result.

7. The smart electric energy meter with a metering performance abnormality detection module according to claim 6, characterized in that: The specific formula for calculating the similarity is: Among them, S represents the similarity value, which reflects the similarity between the abnormal point data and the known fault mode, and A i The current and voltage values ​​representing the abnormal point data, B i The current and voltage values ​​representing known fault modes, i is the index of the data point, and n represents the total number of data points.

8. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The power consumption data comparison module includes: The group power consumption measurement submodule uses the fault cause analysis result and the transformer measurement device to collect the power consumption data of the community and generate the community power consumption data; The measurement data comparison submodule compares the community electricity consumption data with the community electricity consumption data measured by the electric meter, identifies and marks non-technical losses, and generates non-technical loss detection results; The abnormal user judgment submodule identifies the electricity theft user based on the non-technical loss detection result, records the household number and location information of the target user, and generates an abnormal electricity consumption judgment result.

9. The smart electric energy meter with a metering performance abnormality detection module according to claim 1, characterized in that: The automatic billing module comprises: The user fee calculation submodule calculates the payment bills of multiple users based on the electricity theft detection results, according to the electricity consumption data of multiple users and the real-time electricity price, and generates user billing data; The notification information matching submodule matches notification information for multiple users based on the user billing data, including the amount payable, overdue time, and power consumption, and generates user notification data; The bill status monitoring submodule sends notification information to multiple users based on the user notification data, monitors the credit status of the bill in real time, and generates a bill sending record.

10. The smart electric energy meter with a metering performance abnormality detection module according to claim 9, characterized in that: The specific formula for calculating the payment bills of multiple users is: C k =∑(E kj ×P j )-B k Among them, C k represents the total billing amount of the kth user, E kj represents the electricity consumption of the kth user in the jth electricity price interval, P j represents the unit price of the jth electricity price interval, B k Represents the remaining balance of the kth user.

Images