Intelligent submission method and system for power grid information

Through intelligent reporting methods, different monitoring equipment are used to fully cover the power grid information, conduct in-depth analysis and automated processing, solving the accuracy and lag problems in the collection and processing of power grid information, and achieving efficient and accurate data transmission and report generation, satisfying the satisfaction of Diversified information needs.

CN119003625AInactive Publication Date: 2024-11-22XINXIANG POWER SUPPLY COMPANY STATE GRID HENAN ELECTRIC POWER
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411467895.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-21
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing technology lacks more accurate data collection and data analysis in the collection and processing of power grid information, resulting in inaccurate data forecasting and inaccurate abnormal data and key data being discovered. The obtained power grid information has not been submitted and generated, resulting in information. Get lag.

Method used

Using intelligent reporting methods, the power grid information is fully covered through different monitoring equipment, data preprocessing and in-depth analysis, key information and abnormal information are extracted, and reports are automatically generated and transmitted, supporting multiple reporting forms, and automatically generated according to preset time periods. And select the optimal transmission channel to send.

Benefits of technology

It improves data quality and accuracy, reduces manual intervention and error rates, provides a comprehensive understanding of power grid operation status and potential problems, improves the efficiency and accuracy of the reporting process, and meets the information needs of different management departments and personnel.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119003625A_ABST
    Figure CN119003625A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent submission method and system for power grid information, relates to the technical field of power grid information, and aims to solve the problems of inaccurate power grid information acquisition and inconvenient submission. By automatically generating and submitting the report, the complexity and error rate of manual operation are greatly reduced, the report is automatically generated according to the preset time period, and the optimal transmission channel is automatically selected for transmission, so that the efficiency and accuracy of the whole submission process are improved, and the user experience is improved. The system supports the generation of various forms of image reports, text reports, curve reports, pie chart reports and the like, can meet the diversified information requirements of different management departments and personnel, achieves the intelligent processing of the power grid information through automatically extracting key information and comparing the key information with standard data, reduces the risk of human errors, and improves the efficiency. The analysis methods of different dimensions provide a comprehensive view angle for different types of power grid data, and are helpful to more accurately understand the operation state and potential problems of the power grid.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of power grid information technology, and in particular to an intelligent reporting method and system for power grid information. Background Art

[0002] Grid information refers to data and information related to the operation, management, maintenance and planning of power systems.

[0003] The patent application with publication number CN116317151A discloses a signal labeling method and system based on feature extraction of multi-source heterogeneous power grid information. It mainly builds an abnormal data intelligent identification rule base through key technologies such as abnormal data feature extraction and intelligent identification of power grid data, labels the accessed multi-source heterogeneous information, intelligently identifies data anomalies, annotates abnormal data, and forms an effective data set of power grid operation information. The patent application with publication number CN118035710A discloses a method for extracting power generation characteristics of a typical scenario. The method mainly fills missing values, corrects outliers and deletes duplicate values ​​of the collected relevant power generation data, so as to make the data more standardized and neat, improve the readability of the data, and make the data analysis easier to understand. The method standardizes the data differential deviation by using a preset data steady-state factor, so as to make the processing process more stable, improve stability and reliability. The method analyzes the target characteristic data by a time series analysis method, so as to better reveal the internal connection and law between the data. The method analyzes the target characteristic data by a statistical analysis method, so as to quantitatively describe and analyze the data. The method trains the power generation characteristic index data by a neural network model, so as to greatly improve the calculation efficiency of the power generation characteristic index data, and can quickly train and learn on a large-scale data set. Although the above patents solve the problem of obtaining grid information and power data, the following problems still exist in actual operation: 1. Failure to locate power grid information for more accurate data collection and processing results in inaccurate subsequent data forecasts.

[0004] 2. The acquired power grid data is not further analyzed, resulting in the inability to accurately detect abnormal data and key data in the data.

[0005] 3. After obtaining the power grid information, the acquired data is not submitted for report generation, and no corresponding report is submitted according to the type of report, which leads to a delay in obtaining power grid information. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for intelligent reporting of power grid information. By automatically generating and submitting reports, the complexity and error rate of manual operations are greatly reduced. Reports are automatically generated according to a preset time period, and the optimal transmission channel is automatically selected for sending, thereby improving the efficiency and accuracy of the entire reporting process. The system supports the generation of various forms of reports such as image reports, text reports, curve reports, and pie chart reports, and can meet the diversified information needs of different management departments and personnel. By automatically extracting key information and comparing it with standard data, intelligent processing of power grid information is achieved, and the risk of human error is reduced. Analysis methods in different dimensions provide a comprehensive perspective for different types of power grid data, which helps to more accurately understand the operating status and potential problems of the power grid and can solve the problems in the prior art.

[0007] To achieve the above object, the present invention provides the following technical solutions: A method for intelligently reporting power grid information comprises the following steps: S1: Grid information collection: Grid information is collected using different monitoring devices, and after collection, it is saved and marked as target grid information data; S2: Data collection and processing: The target power grid information data is processed according to the data type, and the data is marked as standard collection data after the data processing is completed; S3: Processing data analysis: Conduct in-depth analysis on standard collected data, extract key information and abnormal information after in-depth analysis, and mark them as grid reporting information; S4: Analyze data transmission and reporting: Generate a report based on the power grid reporting information, and transmit the generated report to the corresponding department through a preset reporting channel; In-depth analysis is performed on the standard collected data in S3 to extract key information and abnormal information, including: Use standard collected data for model building and training; Among them, the standard collected data is divided into training set, validation set and test set; After the division is completed, the deep learning model is trained using the training set; Use the validation set to adjust the model parameters of the deep learning model; Use the test set to evaluate the performance of deep learning models; Conduct in-depth analysis of the deep learning models in the test set; After the analysis is completed, the power grid information analysis data is obtained; Extract key information and detect abnormal information from power grid information analysis data; First, extract key information from the power grid information analysis data; After the key information is extracted, the key data of the power grid is obtained; Compare key grid data with standard grid information data; According to the comparison result, the key data of the power grid whose data value is not within the numerical range of the standard power grid information data is marked as abnormal power grid data; And the key data and abnormal data of the power grid are uniformly marked as power grid reporting information.

[0008] Preferably, the grid information is collected separately using different monitoring devices in S1, and after the collection is completed, they are saved separately, including; The collected power grid information includes basic data, operation data, status monitoring data, power quality data, power market data, environmental and meteorological data, and safety management data; Basic data include grid structure data and equipment parameter data; operation data include real-time data and historical data; status monitoring data include equipment status monitoring data and fault recording data; power quality data include voltage fluctuation, flicker and harmonic content data; power market data include electricity price data and market transaction data; environmental and meteorological data include ambient temperature, humidity and wind speed data; safety management data include safety event record data and safety inspection data.

[0009] Preferably, the power grid information is collected respectively by using different monitoring devices in S1, and is saved respectively after the collection is completed, and further includes: Basic data is collected through geographic information systems and asset management information systems; operational data is collected through monitoring and electronic equipment; condition monitoring data is collected using sensors and fault recorders; power quality data is collected through power quality analyzers; power market data is collected through operating systems; environmental and meteorological data is collected through meteorological stations and environmental monitors; and safety management data is collected through safety reporting systems. The collected power grid information is stored separately and marked as target power grid information data.

[0010] Preferably, in S2, the target power grid information data is processed according to the data type, including: Preprocess basic data, operation data, status monitoring data, power quality data, power market data, environment and meteorological data, and safety management data respectively; The data preprocessing process of basic data is data cleaning, data verification and data standardization; The data preprocessing process of the operational data is time synchronization, data calibration, outlier processing and data normalization; The data preprocessing process of condition monitoring data is signal processing, data compression and feature extraction; The data preprocessing process of power quality data is data sampling, frequency analysis and index calculation; The data preprocessing process of power market data is data integration, missing value processing and data alignment; The data preprocessing process of environmental and meteorological data is data cleaning and data conversion; The data preprocessing process of security management data is data coding, data structuring and data integration; After the data preprocessing is completed, it is marked as standard collection data.

[0011] Preferably, the missing value processing of the power market data includes: extracting missing values ​​corresponding to the electricity market data; Extracting the number of data collection intervals between every two adjacent missing values ​​from all the missing values ​​of the power market data as a data group; Obtaining a missing value data abnormality evaluation coefficient according to the number of data collected between each two adjacent missing values; The missing value data abnormality evaluation coefficient is obtained by the following formula: ; Among them, S represents the missing value data abnormal evaluation coefficient; M min Indicates the minimum number of data collected between each two adjacent missing values; M c represents the preset reference value; n represents the number of data groups; M i Indicates the number of data collected corresponding to the i-th data group; zi represents the average value of the data weight corresponding to the i-th data group; qi represents the missing value weight reference value corresponding to the i-th data group, and the missing value weight reference value is obtained by the following formula: ; Among them, λ q represents the missing value weight reference value corresponding to the data group; M represents the number of data collected corresponding to the data group; λ max Indicates the maximum value of the weight of the corresponding data in the data group; 01 and λ 02 Indicates the weight value of the two missing value data corresponding to the data group; m 01 represents the number of data between the missing value data before the missing value data collection time and the data corresponding to the maximum weight value in the data group; m 02 Indicates the number of data between the missing value data after the missing value data collection time and the data corresponding to the maximum value of the weight value in the data group; Comparing the missing value data abnormality evaluation coefficient with a preset evaluation coefficient threshold; When the abnormal evaluation coefficient of the missing value data does not exceed the preset evaluation coefficient threshold, there is no need to perform numerical filling on the missing value; When the missing value data abnormality evaluation coefficient exceeds a preset evaluation coefficient threshold, the missing value is numerically filled.

[0012] Preferably, when the missing value data abnormal evaluation coefficient exceeds a preset evaluation coefficient threshold, the missing value is numerically filled, including: When the missing value data abnormal evaluation coefficient exceeds a preset evaluation coefficient threshold, extracting the data values ​​of the normal data adjacent to and before each missing value data; The number of sampling interval data is obtained according to the number of data collected for the interval between the missing values ​​between each two adjacent missing value data; wherein the number of sampling interval data is obtained by the following formula: ; Where K represents the number of sampling interval data; M min Indicates the minimum number of data collected between each two adjacent missing values; M c represents the preset reference value; n represents the number of data groups; M i Indicates the number of data collection corresponding to the i-th data group; Taking the data positions of the normal data adjacent to and before each missing value data as the starting point, extracting the data values ​​corresponding to the number of sampling interval data forward and backward respectively as the data set corresponding to each missing value data; Obtaining the filling data corresponding to each missing value data by using each data in the data set in combination with the data values ​​of the normal data adjacent to and before each missing value data; The filling data is obtained by the following formula: ; Where X represents the filling data corresponding to each missing value data; X 01 and X 02 They represent the data values ​​corresponding to the normal data before and after each missing value data; K represents the number of sampling interval data; X pi represents the data value corresponding to the i-th sampling interval data corresponding to the normal data before and after each missing value data; X qi Indicates the data value corresponding to the i-th sampling interval data corresponding to the normal data at the later moment in the normal data adjacent to and before each missing value data; The missing value data is filled using the filling data.

[0013] Preferably, the standard collected data is deeply analyzed in S3, and key information and abnormal information are extracted after the deep analysis, which also includes: The operational data from the deep learning models in the test set were analyzed using time series analysis and pattern recognition methods; The condition monitoring data from the deep learning model in the test set is analyzed using fault diagnosis and remaining useful life prediction techniques; The power quality data from the deep learning model in the test set is analyzed using the power quality assessment method; The power market data in the deep learning model in the test set was analyzed using the market trend analysis method; The environmental and meteorological data in the deep learning model in the test set were analyzed using environmental impact and disaster warning technology; Analyze the security management data in the deep learning model in the test set using risk assessment and security incident prediction methods; Finally, the power grid information analysis data is obtained after the analysis is completed.

[0014] Preferably, the standard collected data is deeply analyzed in S3, and key information and abnormal information are extracted after the deep analysis, which also includes: Among them, the grid topology, equipment parameters and geographic location data in the basic data are obtained; the load curve, power generation and line flow data in the operation data are obtained; the equipment temperature, vibration and insulation status data in the status monitoring data are obtained; the voltage fluctuation, harmonic content and frequency deviation data in the power quality data are obtained; the market price, transaction volume and supply and demand relationship data in the power market data are obtained; the temperature, humidity, wind speed and precipitation data in the environment and meteorological data are obtained; the accident report, safety hazard and maintenance record data in the safety management data are obtained; Finally, complete key data of the power grid is obtained.

[0015] An intelligent reporting system for power grid information, comprising: Submission report generation module, used to: Generate reports using report generation software for key grid data and abnormal grid data in grid reporting information; Among them, the generated reports include image reports, text reports, curve reports and pie chart reports; At the same time, before the report is generated, the time period for automatic generation and automatic reporting is set according to the sending needs.

[0016] Preferably, including: Submission report transmission display module, used for: After the report is generated, it is sent to the corresponding management department according to the type of report; At the same time, the report automatically selects the fastest transmission channel when sending; Among them, the report transmission volume of each type of report is first confirmed; The report shall be sent to the management department for no less than three transmission channels, and the remaining capacity of each transmission channel shall be monitored in real time; A transmission channel whose reported transmission volume is less than the remaining capacity of the channel is selected as the transmission channel for the report, and the generated report is transmitted to the display terminal.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention provides an intelligent reporting method and system for power grid information, which comprehensively covers various types of information required for power grid operation through different types of monitoring equipment, comprehensively ensures the complete presentation of the power grid operation status, and facilitates more accurate analysis and decision-making. Each type of data adopts different preprocessing steps according to its characteristics and uses, which can effectively remove noise, correct errors, fill missing values, calibrate deviations, etc., thereby significantly improving the quality and accuracy of the data.

[0018] 2. The present invention provides a method and system for intelligently reporting power grid information, which realizes intelligent processing of power grid information by automatically extracting key information and comparing it with standard data. This greatly reduces manual intervention, improves processing efficiency, and reduces the risk of human error. Analysis methods in different dimensions provide a comprehensive perspective for different types of power grid data, which helps to more accurately understand the operating status and potential problems of the power grid.

[0019] 3. The present invention provides an intelligent reporting method and system for power grid information, which greatly reduces the complexity and error rate of manual operations by automatically generating and submitting reports. It automatically generates reports according to a preset time period and automatically selects the optimal transmission channel for sending, thereby improving the efficiency and accuracy of the entire reporting process. It supports the generation of multiple forms of reports such as image reports, text reports, curve reports, and pie chart reports, and can meet the diversified information needs of different management departments and personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the steps for intelligently reporting power grid information according to the present invention;

[0021] Figure 2 The figure is a schematic diagram of the intelligent reporting process of the power grid information of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] A method for intelligently reporting power grid information comprises the following steps: S1: Grid information collection: Grid information is collected using different monitoring devices, and after collection, it is saved and marked as target grid information data; Among them, various types of monitoring equipment are used to comprehensively cover all kinds of information required for power grid operation, ensuring the complete presentation of the power grid operation status; S2: Data collection and processing: The target power grid information data is processed according to the data type, and the data is marked as standard collection data after the data processing is completed; Among them, the preprocessed data is more standardized and can better meet the needs of intelligent algorithms and models; S3: Processing data analysis: Conduct in-depth analysis on standard collected data, extract key information and abnormal information after in-depth analysis, and mark them as grid reporting information; Among them, intelligent processing of power grid information is achieved by automatically extracting key information and comparing it with standard data; S4: Analyze data transmission and reporting: Generate a report based on the power grid reporting information, and transmit the generated report to the corresponding department through a preset reporting channel; Among them, the complexity and error rate of manual operations are greatly reduced through automated generation and submission of reports.

[0024] In S1, different monitoring devices are used to collect the power grid information respectively, and the information is saved respectively after the collection is completed, including; The collected power grid information includes basic data, operation data, status monitoring data, power quality data, power market data, environmental and meteorological data, and safety management data; Basic data include grid structure data and equipment parameter data; operation data include real-time data and historical data; status monitoring data include equipment status monitoring data and fault recording data; power quality data include voltage fluctuation, flicker and harmonic content data; power market data include electricity price data and market transaction data; environmental and meteorological data include ambient temperature, humidity and wind speed data; safety management data include safety event record data and safety inspection data.

[0025] Among them, basic data is collected through geographic information systems and asset management information systems; operation data is collected through monitoring and electronic equipment; condition monitoring data is collected using sensors and fault recorders; power quality data is collected through power quality analyzers; power market data is collected through operating systems; environmental and meteorological data are collected through meteorological stations and environmental monitors; safety management data is collected through safety reporting systems; The collected power grid information is stored separately and marked as target power grid information data.

[0026] Specifically, through different types of monitoring equipment, all kinds of information required for power grid operation are fully covered, including basic data, operating data, status monitoring data, power quality data, power market data, environmental and meteorological data, and safety management data. This comprehensiveness ensures the complete presentation of the power grid operation status, which helps to make more accurate analysis and decision-making. Special equipment and systems are used to collect various types of data, such as geographic information systems and asset management information systems for basic data, monitoring and electronic equipment for operating data, sensors and fault recorders for status monitoring data, etc., to ensure the accuracy and reliability of the data. This is crucial for the safe and stable operation of the power grid. Various types of data are collected and stored independently to avoid mutual interference and confusion between data. This independence is helpful for subsequent data processing and analysis, and can more clearly identify the root causes and influencing factors of the problem. Combined with big data analysis and artificial intelligence technology, the collected power grid information can be deeply mined and intelligently analyzed to discover potential problems and trends, providing strong support for the intelligent management of the power grid.

[0027] In S2, the target power grid information data is processed according to the data type, including: Preprocess basic data, operation data, status monitoring data, power quality data, power market data, environment and meteorological data, and safety management data respectively; The data preprocessing process of basic data is data cleaning, data verification and data standardization; The data preprocessing process of the operational data is time synchronization, data calibration, outlier processing and data normalization; The data preprocessing process of condition monitoring data is signal processing, data compression and feature extraction; The data preprocessing process of power quality data is data sampling, frequency analysis and index calculation; The data preprocessing process of power market data is data integration, missing value processing and data alignment; The data preprocessing process of environmental and meteorological data is data cleaning and data conversion; The data preprocessing process of security management data is data coding, data structuring and data integration; After the data preprocessing is completed, it is marked as standard collection data.

[0028] Specifically, each type of data adopts different preprocessing steps according to its characteristics and uses, which can effectively remove noise, correct errors, fill missing values, calibrate deviations, etc., thereby significantly improving the quality and accuracy of the data. The preprocessed data is more standardized and standardized, and can better meet the needs of intelligent algorithms and models, providing strong data support for intelligent monitoring, fault diagnosis, predictive analysis, market strategy formulation, etc. of the power grid, and promoting intelligent decision-making. The preprocessing process design is flexible and scalable, and the processing steps can be adjusted and optimized according to actual needs to adapt to different scenarios and the requirements of future power grid informatization development. Through unified preprocessing standards and processes, data from different sources and in different formats can be more easily shared and exchanged, which promotes the integration and comprehensive utilization of power grid information.

[0029] Specifically, the missing value processing of the power market data includes: extracting missing values ​​corresponding to the electricity market data; Extracting the number of data collection intervals between every two adjacent missing values ​​from all the missing values ​​of the power market data as a data group; Obtaining the missing value data abnormality evaluation coefficient according to the number of data collection intervals between each two adjacent missing values; The missing value data abnormality evaluation coefficient is obtained by the following formula: ; Among them, S represents the missing value data abnormal evaluation coefficient; M min Indicates the minimum number of data collected between each two adjacent missing values; M c represents the preset reference value; n represents the number of data groups; M i Indicates the number of data collected corresponding to the i-th data group; zi represents the average value of the data weight corresponding to the i-th data group; qi represents the missing value weight reference value corresponding to the i-th data group, and the missing value weight reference value is obtained by the following formula: ; Among them, λ q represents the missing value weight reference value corresponding to the data group; M represents the number of data collected corresponding to the data group; λ max Indicates the maximum value of the weight of the corresponding data in the data group; 01 and λ 02Indicates the weight value of the two missing value data corresponding to the data group; m 01 represents the number of data between the missing value data before the missing value data collection time and the data corresponding to the maximum weight value in the data group; m 02 Indicates the number of data between the missing value data after the missing value data collection time and the data corresponding to the maximum value of the weight value in the data group; Comparing the missing value data abnormality evaluation coefficient with a preset evaluation coefficient threshold; When the abnormal evaluation coefficient of the missing value data does not exceed the preset evaluation coefficient threshold, there is no need to perform numerical filling on the missing value; When the missing value data abnormality evaluation coefficient exceeds a preset evaluation coefficient threshold, the missing value is numerically filled.

[0030] The technical effect of the above technical solution is: by calculating the number of data collections between each two adjacent missing values, and combining the preset number reference value, the abnormal situation of the missing value data is evaluated. This method can more accurately identify whether the missing data is an abnormal situation, thereby avoiding blindly filling all missing values, and improving the accuracy and reliability of data processing. Traditional data missing processing often adopts a simple filling strategy (such as mean filling, mode filling, etc.), without considering the specific situation of the missing value. However, this technical solution reduces the blindness of data filling by calculating the missing value data abnormality evaluation coefficient and deciding whether to perform numerical filling according to the coefficient, so that the processed data is closer to the actual situation of the original data. When judging whether the missing value needs to be filled, the concepts of data weight numerical average value and missing value weight reference value are introduced. The weights of each data point in the data group and the location information of the missing value are comprehensively considered through complex calculation formulas, making the judgment process more scientific and reasonable. This can not only improve the accuracy of the judgment, but also improve the overall efficiency of data processing to a certain extent. This technical solution controls whether to fill the missing value through a preset evaluation coefficient threshold. This design makes the data processing process more flexible. Users can adjust the evaluation coefficient threshold according to specific data characteristics and needs to achieve the best data processing effect. By scientifically and reasonably processing the missing values ​​in the power market data, this technical solution helps to improve data quality and provide more reliable data support for subsequent data analysis, prediction and decision-making. This is of great significance for improving the operational efficiency of the power market and optimizing resource allocation.

[0031] Specifically, when the missing value data abnormal evaluation coefficient exceeds a preset evaluation coefficient threshold, the missing value is numerically filled, including: When the missing value data abnormal evaluation coefficient exceeds a preset evaluation coefficient threshold, extracting the data values ​​of the normal data adjacent to and before each missing value data; The number of sampling interval data is obtained according to the number of data collected for the interval between the missing values ​​between each two adjacent missing value data; wherein the number of sampling interval data is obtained by the following formula: ; Where K represents the number of sampling interval data; M min Indicates the minimum number of data collected between each two adjacent missing values; M c represents the preset reference value; n represents the number of data groups; M i Indicates the number of data collection corresponding to the i-th data group; Taking the data positions of the normal data adjacent to and before each missing value data as the starting point, extracting the data values ​​corresponding to the number of sampling interval data forward and backward respectively as the data set corresponding to each missing value data; Obtaining the filling data corresponding to each missing value data by using each data in the data set in combination with the data values ​​of the normal data adjacent to and before each missing value data; The filling data is obtained by the following formula: ; Where X represents the filling data corresponding to each missing value data; X 01 and X 02 They represent the data values ​​corresponding to the normal data before and after each missing value data; K represents the number of sampling interval data; X pi represents the data value corresponding to the i-th sampling interval data corresponding to the normal data before and after each missing value data; X qi Indicates the data value corresponding to the i-th sampling interval data corresponding to the normal data at the later moment in the normal data adjacent to and before each missing value data; The missing value data is filled using the filling data.

[0032] The technical effect of the above technical solution is: by extracting the normal data before and after each missing value data and constructing a data set based on these normal data, a richer data basis is provided for filling the missing values. At the same time, the number of sampling interval data is used to determine the data range extracted from the normal data, making the filling process more scientific and reasonable, and helping to improve the accuracy of the filled data. By considering the normal data before and after the missing value data and the sampling interval data between them, the solution can more comprehensively reflect the changing trends and characteristics of the data, so that the filled data is more representative and can better reflect the true situation of the original data.

[0033] Different from the simple mean or mode filling method, this solution uses a more complex calculation formula to determine the filling data, which fully considers the position of the missing value data in the data sequence, the value of the adjacent normal data, and the data change relationship between them. This refined processing method can better preserve the original characteristics of the data and reduce the data distortion caused by filling. By adjusting the calculation formula of the number of sampling interval data and the parameters in the calculation formula of the filling data (such as the preset number reference value Mc), users can optimize the filling process according to the specific data characteristics and needs, making data processing more flexible and changeable. By using the above technical solution to fill in the missing values, the quality of the power market data can be significantly improved. High-quality data plays a vital role in subsequent data analysis, prediction and decision-making, and helps to improve the operational efficiency and management level of the power market.

[0034] In summary, this technical solution improves the accuracy and reliability of missing value processing in power market data through refined data processing and filling methods, providing a more solid data foundation for data analysis and decision-making.

[0035] In order to solve the problem in the prior art that the acquired power grid data is not further analyzed, which leads to the inability to accurately find abnormal data and key data in the data, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions: In-depth analysis is performed on the standard collected data in S3 to extract key information and abnormal information, including: Use standard collected data for model building and training; Among them, the standard collected data is divided into training set, validation set and test set; After the division is completed, the deep learning model is trained using the training set; Use the validation set to adjust the model parameters of the deep learning model; Use the test set to evaluate the performance of deep learning models; Conduct in-depth analysis of the deep learning models in the test set; Among them, the basic data from the deep learning model in the test set was analyzed using network analysis and device performance evaluation methods; The operational data from the deep learning models in the test set were analyzed using time series analysis and pattern recognition methods; The condition monitoring data from the deep learning model in the test set is analyzed using fault diagnosis and remaining useful life prediction techniques; The power quality data from the deep learning model in the test set is analyzed using the power quality assessment method; The power market data in the deep learning model in the test set was analyzed using the market trend analysis method; The environmental and meteorological data in the deep learning model in the test set were analyzed using environmental impact and disaster warning technology; Analyze the security management data in the deep learning model in the test set using risk assessment and security incident prediction methods; After all the analysis is completed, the power grid information analysis data is obtained.

[0036] Specifically, by dividing the standard collected data into training sets, validation sets, and test sets, it is possible to ensure that the deep learning model performs well on different data sets, improve the model's ability to predict and classify unknown data, that is, generalization ability, and use the validation set to adjust the model parameters. This process is a key step in model optimization. By continuously adjusting the model parameters and finding the optimal configuration, the performance of the model on the test set can be significantly improved, including key indicators such as accuracy and recall. The test set is used to perform unbiased performance evaluation of the trained model to ensure that the model's effect in actual application meets expectations. Through rigorous testing, problems with the model can be discovered and corrected in a timely manner, and in-depth analysis of the deep learning model in the test set can deeply explore the inherent laws and characteristics of power grid data. Analysis methods in different dimensions (such as network analysis, time series analysis, pattern recognition, etc.) provide a comprehensive perspective for different types of power grid data, which helps to more accurately understand the operating status and potential problems of the power grid. Through in-depth analysis of status monitoring data, power quality data, environmental and meteorological data, etc., it is possible to promptly detect abnormal conditions in the power grid, predict possible failures or disasters, and provide strong support for the safe and stable operation of the power grid. By continuously optimizing and improving deep learning models, the intelligence level of the power grid can be further improved, and more accurate and efficient power grid management and operation can be achieved.

[0037] Extract key information and detect abnormal information from power grid information analysis data; First, extract key information from the power grid information analysis data; Among them, the grid topology, equipment parameters and geographic location data in the basic data are obtained; the load curve, power generation and line flow data in the operation data are obtained; the equipment temperature, vibration and insulation status data in the status monitoring data are obtained; the voltage fluctuation, harmonic content and frequency deviation data in the power quality data are obtained; the market price, transaction volume and supply and demand relationship data in the power market data are obtained; the temperature, humidity, wind speed and precipitation data in the environment and meteorological data are obtained; the accident report, safety hazard and maintenance record data in the safety management data are obtained; After all acquisitions are completed, the key data of the power grid are obtained; Compare key grid data with standard grid information data; According to the comparison result, the key data of the power grid whose data value is not within the numerical range of the standard power grid information data is marked as abnormal power grid data; And the key data and abnormal data of the power grid are uniformly marked as power grid reporting information.

[0038] Specifically, by automatically extracting key information and comparing it with standard data, intelligent processing of power grid information is achieved. This greatly reduces manual intervention, improves processing efficiency, and reduces the risk of human error. It covers multiple dimensions of power grid information analysis, including basic data, operating data, status monitoring data, power quality data, power market data, environmental and meteorological data, and safety management data, ensuring the comprehensiveness and accuracy of information. Comprehensive data collection helps to understand the operation status of the power grid more comprehensively and improve the accuracy of analysis. By comparing with standard data, abnormal data in the power grid can be quickly identified, and abnormal detection and early warning can be achieved. This helps the power grid management department to take timely measures to prevent the further expansion of the problem and ensure the normal operation of the power grid. By realizing the intelligent reporting of power grid information, it promotes the intelligent development of the power grid, improves the automation and information level of the power grid, and lays a solid foundation for the construction of smart grids.

[0039] In order to solve the problem in the prior art that after obtaining the power grid information, the obtained data is not submitted for report generation, and no corresponding report is submitted according to the type of report, which leads to the problem of delayed acquisition of power grid information, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions: An intelligent reporting system for power grid information, comprising: Submission report generation module, used to: Generate reports using report generation software for key grid data and abnormal grid data in grid reporting information; Among them, the generated reports include image reports, text reports, curve reports and pie chart reports; At the same time, before the report is generated, the time period for automatic generation and automatic reporting is set according to the sending needs.

[0040] include: Submission report transmission display module, used for: After the report is generated, it is sent to the corresponding management department according to the type of report; At the same time, the report automatically selects the fastest transmission channel when sending; Among them, the report transmission volume of each type of report is first confirmed; The report shall be sent to the management department for no less than three transmission channels, and the remaining capacity of each transmission channel shall be monitored in real time; A transmission channel whose reported transmission volume is less than the remaining capacity of the channel is selected as the transmission channel for the report, and the generated report is transmitted to the display terminal.

[0041] Specifically, the complexity and error rate of manual operations are greatly reduced through the automatic generation and submission of reports. The system can automatically generate reports according to the preset time period and automatically select the optimal transmission channel for transmission, which improves the efficiency and accuracy of the entire reporting process. It supports the generation of multiple forms such as image reports, text reports, curve reports and pie chart reports, and can meet the diversified information needs of different management departments and personnel. The form of images and charts can intuitively display the key data and abnormal data of the power grid, which is convenient for quick understanding and analysis. When sending reports, the system can automatically select the fastest transmission channel and perform intelligent scheduling based on the remaining capacity of the channel to ensure that the report can be delivered to the destination quickly and accurately. This helps to avoid channel congestion and transmission delays, improve the real-time and reliability of report transmission, monitor the remaining capacity of each transmission channel in real time, and dynamically adjust the transmission strategy according to real-time data. This real-time monitoring and dynamic adjustment capabilities enable the system to adapt to the ever-changing network environment and maintain efficient and stable operation.

[0042] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0043] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for intelligently reporting power grid information. It is characterized in that The steps include: S1: Grid information collection: Grid information is collected using different monitoring devices, and after collection, it is saved and marked as target grid information data; S2: Data collection and processing: The target power grid information data is processed according to the data type, and the data is marked as standard collection data after the data processing is completed; S3: Processing data analysis: Conduct in-depth analysis on standard collected data, extract key information and abnormal information after in-depth analysis, and mark them as grid reporting information; S4: Analyze data transmission and reporting: Generate a report based on the power grid reporting information, and transmit the generated report to the corresponding department through a preset reporting channel; In-depth analysis is performed on the standard collected data in S3. After in-depth analysis, key information and abnormal information are extracted, including: Use standard collected data for model building and training; Among them, the standard collected data is divided into training set, validation set and test set; After the division is completed, the deep learning model is trained using the training set; Use the validation set to adjust the model parameters of the deep learning model; Use the test set to evaluate the performance of deep learning models; Conduct in-depth analysis of the deep learning models in the test set; After the analysis is completed, the power grid information analysis data is obtained; Extract key information and detect abnormal information from power grid information analysis data; First, extract key information from the power grid information analysis data; After the key information is extracted, the key data of the power grid is obtained; Compare key grid data with standard grid information data; According to the comparison result, the key data of the power grid whose data value is not within the numerical range of the standard power grid information data is marked as abnormal power grid data; And the key data and abnormal data of the power grid are uniformly marked as power grid reporting information.

2. According to claim 1, a method for intelligently reporting power grid information, It is characterized in that In S1, different monitoring devices are used to collect the power grid information respectively, and the information is saved respectively after the collection is completed, including; The collected power grid information includes basic data, operation data, status monitoring data, power quality data, power market data, environmental and meteorological data, and safety management data; Basic data include grid structure data and equipment parameter data; operation data include real-time data and historical data; status monitoring data include equipment status monitoring data and fault recording data; power quality data include voltage fluctuation, flicker and harmonic content data; power market data include electricity price data and market transaction data; environmental and meteorological data include ambient temperature, humidity and wind speed data; safety management data include safety event record data and safety inspection data.

3. The method for intelligently reporting power grid information according to claim 2, It is characterized in that In S1, different monitoring devices are used to collect power grid information respectively, and the collected information is saved respectively after the collection is completed, which also includes: Basic data is collected through geographic information systems and asset management information systems; operational data is collected through monitoring and electronic equipment; condition monitoring data is collected using sensors and fault recorders; power quality data is collected through power quality analyzers; power market data is collected through operating systems; environmental and meteorological data is collected through meteorological stations and environmental monitors; and safety management data is collected through safety reporting systems. The collected power grid information is stored separately and marked as target power grid information data.

4. The method for intelligently reporting power grid information according to claim 3, It is characterized in that In S2, the target power grid information data is processed according to the data type, including: Preprocess basic data, operation data, status monitoring data, power quality data, power market data, environment and meteorological data, and safety management data respectively; The data preprocessing process of basic data is data cleaning, data verification and data standardization; The data preprocessing process of the operational data is time synchronization, data calibration, outlier processing and data normalization; The data preprocessing process of condition monitoring data is signal processing, data compression and feature extraction; The data preprocessing process of power quality data is data sampling, frequency analysis and index calculation; The data preprocessing process of power market data is data integration, missing value processing and data alignment; The data preprocessing process of environmental and meteorological data is data cleaning and data conversion; The data preprocessing process of security management data is data coding, data structuring and data integration; After the data preprocessing is completed, it is marked as standard collection data.

5. A method for intelligently reporting power grid information according to claim 4, It is characterized in that The missing value processing of the power market data includes: extracting missing values ​​corresponding to the electricity market data; Extracting the number of data collection intervals between every two adjacent missing values ​​from all the missing values ​​of the power market data as a data group; Obtaining a missing value data abnormality evaluation coefficient according to the number of data collected between each two adjacent missing values; The missing value data abnormality evaluation coefficient is obtained by the following formula: ; Among them, S represents the missing value data abnormal evaluation coefficient; M min Indicates the minimum number of data collected between each two adjacent missing values; M c represents the preset reference value; n represents the number of data groups; M i Indicates the number of data collected corresponding to the i-th data group; zi represents the average value of the data weight corresponding to the i-th data group; qi represents the missing value weight reference value corresponding to the i-th data group, and the missing value weight reference value is obtained by the following formula: ; Among them, λ q represents the missing value weight reference value corresponding to the data group; M represents the number of data collected corresponding to the data group; λ max Indicates the maximum value of the weight of the corresponding data in the data group; 01 and λ 02 Indicates the weight value of the two missing value data corresponding to the data group; m 01 represents the number of data between the missing value data before the missing value data collection time and the data corresponding to the maximum weight value in the data group; m 02 Indicates the number of data between the missing value data after the missing value data collection time and the data corresponding to the maximum value of the weight value in the data group; Comparing the missing value data abnormality evaluation coefficient with a preset evaluation coefficient threshold; When the abnormal evaluation coefficient of the missing value data does not exceed the preset evaluation coefficient threshold, there is no need to perform numerical filling on the missing value; When the missing value data abnormality evaluation coefficient exceeds a preset evaluation coefficient threshold, the missing value is numerically filled.

6. A method for intelligently reporting power grid information according to claim 5, It is characterized in that When the missing value data abnormal evaluation coefficient exceeds the preset evaluation coefficient threshold, the missing value is numerically filled, including: When the missing value data abnormal evaluation coefficient exceeds a preset evaluation coefficient threshold, extracting the data values ​​of the normal data adjacent to and before each missing value data; The number of sampling interval data is obtained according to the number of data collected for the interval between the missing values ​​between each two adjacent missing value data; wherein the number of sampling interval data is obtained by the following formula: ; Where K represents the number of sampling interval data; M min Indicates the minimum number of data collected between each two adjacent missing values; M c represents the preset reference value; n represents the number of data groups; M i Indicates the number of data collection corresponding to the i-th data group; Taking the data positions of the normal data adjacent to and before each missing value data as the starting point, extracting the data values ​​corresponding to the number of sampling interval data forward and backward respectively as the data set corresponding to each missing value data; Obtaining the filling data corresponding to each missing value data by using each data in the data set in combination with the data values ​​of the normal data adjacent to and before each missing value data; The filling data is obtained by the following formula: ; Where X represents the filling data corresponding to each missing value data; X 01 and X 02 They represent the data values ​​corresponding to the normal data before and after each missing value data; K represents the number of sampling interval data; X pi represents the data value corresponding to the i-th sampling interval data corresponding to the normal data before and after each missing value data; X qi Indicates the data value corresponding to the i-th sampling interval data corresponding to the normal data at the later moment in the normal data adjacent to and before each missing value data; The missing value data is filled using the filling data.

7. A method for intelligently reporting power grid information according to claim 6, It is characterized in that In-depth analysis is performed on the standard collected data in S3. After in-depth analysis, key information and abnormal information are extracted, including: The operational data from the deep learning models in the test set were analyzed using time series analysis and pattern recognition methods; The condition monitoring data from the deep learning model in the test set is analyzed using fault diagnosis and remaining useful life prediction techniques; The power quality data from the deep learning model in the test set is analyzed using the power quality assessment method; The power market data in the deep learning model in the test set was analyzed using the market trend analysis method; The environmental and meteorological data in the deep learning model in the test set were analyzed using environmental impact and disaster warning technology; Analyze the security management data in the deep learning model in the test set using risk assessment and security incident prediction methods; Finally, the power grid information analysis data is obtained after the analysis is completed.

8. A method for intelligently reporting power grid information according to claim 7, It is characterized in that In-depth analysis is performed on the standard collected data in S3. After in-depth analysis, key information and abnormal information are extracted, including: Among them, the grid topology, equipment parameters and geographic location data in the basic data are obtained; the load curve, power generation and line flow data in the operation data are obtained; the equipment temperature, vibration and insulation status data in the status monitoring data are obtained; the voltage fluctuation, harmonic content and frequency deviation data in the power quality data are obtained; the market price, transaction volume and supply and demand relationship data in the power market data are obtained; the temperature, humidity, wind speed and precipitation data in the environment and meteorological data are obtained; the accident report, safety hazard and maintenance record data in the safety management data are obtained; Finally, complete key data of the power grid is obtained.

9. An intelligent reporting system for power grid information, used to implement the intelligent reporting method for power grid information according to claim 8, include: Submission report generation module, used to: Generate reports using report generation software for key grid data and abnormal grid data in grid reporting information; Among them, the generated reports include image reports, text reports, curve reports and pie chart reports; At the same time, before the report is generated, the time period for automatic generation and automatic reporting is set according to the sending needs.

10. The intelligent reporting system for power grid information according to claim 9, It is characterized in that include: Submission report transmission display module, used for: After the report is generated, it is sent to the corresponding management department according to the type of report; At the same time, the report automatically selects the fastest transmission channel when sending; Among them, the report transmission volume of each type of report is first confirmed; The report shall be sent to the management department for no less than three transmission channels, and the remaining capacity of each transmission channel shall be monitored in real time; A transmission channel whose reported transmission volume is less than the remaining capacity of the channel is selected as the transmission channel for the report, and the generated report is transmitted to the display terminal.

Citation Information

Patent Citations

  • Signal labeling method and system based on multi-source heterogeneous power grid information feature extraction

    CN116317151A

  • Typical scene power generation characteristic extraction method

    CN118035710A

  • Ensemble forecasting method, system and equipment for data missing and storage medium

    CN115409246A

  • Automatic troubleshooting method based on power dispatching system

    CN117674128A

  • Modularized electric energy metering system capable of controlling measurement

    CN117849700A