Power grid safety rapid analysis method based on data driving

Abstract

The invention discloses a rapid power grid safety analysis method based on data driving, and belongs to the technical field of power grid safety. The problem that mass data are managed and cannot be analyzed in the prior art is solved, the obtained electric power data are preprocessed, the processed electric power data are stored through the database, data mining and visualization processing are carried out, the database is managed through the NoSQL database technology, and the data processing efficiency is improved. Data storage of a database is simplified and more flexible, storage of mass data of the database is achieved, then video and image data of personnel involved in daily work is converted into structured data, historical data of a power grid system is combined, a power grid safety accident scale model is established based on the Haihi rule, and the power grid safety accident scale model is established. And analyzing the obtained power data through a power grid safety accident proportion model, finding out hidden dangers, events and accidents according to an analysis result, and adjusting and early warning a power grid system.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid security, and in particular to a data-driven rapid power grid security analysis method. Background Art

[0002] With the transformation of traditional power grid to smart grid mode, the power grid structure is becoming more and more complex, and massive monitoring data is pouring into the centralized control host, with significant progress in instrumentation, communication and data analysis. Smart grid is a modern power grid infrastructure that combines traditional power grid with advanced information infrastructure to realize two-way energy flow between power grid and end users. The basis for supporting the safe, self-healing, green, strong and reliable operation of smart grid is the panoramic real-time data collection, transmission and storage of power grid, as well as the rapid analysis of accumulated massive multi-source data. However, the existing power grid data source channels are insufficient, and the data analysis and mining capabilities are lacking, resulting in the phenomenon of "massive data and lack of information" in the management process, which is far from meeting the requirements of daily safety management work. At the same time, since the massive data monitored cannot be fully utilized, the safety analysis of the power grid system cannot be realized, and the operation of the power grid system cannot be made more reliable; therefore, it does not meet the existing needs. In this regard, we propose a data-driven rapid analysis method for power grid security. Summary of the invention

[0003] The purpose of the present invention is to provide a data-driven rapid analysis method for power grid safety, which monitors the power grid system through monitoring equipment to obtain and pre-process the power data of the power grid system, stores the processed power data through a database, and performs data mining and visualization on the power data. The video and image data of personnel involved in daily work are converted into structured data, and combined with the historical data of the power grid system, a power grid safety accident proportional model is established based on Heinrich's law. The acquired power data is analyzed through the power grid safety accident proportional model, so as to find out the hidden dangers, events and accidents therein according to the analysis results, and make adjustments and early warnings to the power grid system, thereby solving the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a data-driven rapid power grid security analysis method, comprising the following steps: S1: Monitor the power grid system through monitoring equipment to obtain power data of the power grid system and pre-process the obtained power data; S2: storing the processed power data in a database, and performing data mining and visualization on the power data; S3: Convert the video and image data of personnel involved in daily work into structured data, and combine it with the historical data of the power grid system to establish a power grid safety accident proportion model based on Heinrich's law; S4: Based on the established power grid safety accident ratio model, the acquired power data is analyzed to find out the hidden dangers, incidents and accidents according to the analysis results, and make adjustments and early warnings to the power grid system.

[0005] Furthermore, in S1, the power grid system is monitored, including the following monitoring equipment: various sensors, intelligent equipment, video surveillance equipment, audio communication equipment and mobile terminals. Through the above data acquisition channels, massive structured, semi-structured and unstructured data of the power grid system are obtained, mainly involving power generation, transmission, transformation, distribution, power consumption and scheduling.

[0006] Furthermore, the structured data mainly includes data stored in a relational database; the unstructured data mainly includes data generated by video surveillance and graphic image processing.

[0007] Furthermore, in S1, the acquired power data is preprocessed. Since the acquired power data is structured, semi-structured and unstructured, a large amount of unstructured and semi-structured power data is converted into a structured format through preprocessing, and the power data is cleaned, so as to achieve the homogeneity of the power data.

[0008] Furthermore, in S2, the processed power data is stored in a database, and the database is managed using NoSQL database technology. NoSQL database technology utilizes a distributed data storage method to remove the relational characteristics of the database, making the data storage of the database simplified and more flexible, thereby realizing the storage of massive data in the database.

[0009] Furthermore, in S2, data mining and visualization processing are performed on the power data, specifically: Data mining is used to find hidden information from large amounts of fuzzy, noisy, and random power data; Data visualization is used to convert the acquired power into visual data using visual graphics tools.

[0010] Furthermore, in S3, the video and image data of the personnel involved in the daily work are converted into structured data and combined with the historical data of the power grid system. The historical data is the safety production data of the power grid system in previous years. The larger the amount of statistical data of the historical data, the more the obtained rules can reflect the overall trend.

[0011] Furthermore, in S3, a power grid safety accident proportion model is established based on Heinrich's law. The established power grid safety accident proportion model reflects the regularity of power grid safety, thereby providing a scientific and complete basis for power grid safety analysis and prediction in theory.

[0012] Furthermore, in S4, based on the established power grid safety accident ratio model, the acquired power data is brought into the power grid safety accident ratio model for analysis, and the potential hidden dangers, events and accidents in the current power grid system are found out according to the analysis results.

[0013] Furthermore, according to the potential hidden dangers, events and accidents in the current power grid system, an early warning is issued to the power grid system, so as to remind the staff of relevant terminals to pay attention to the safety issues of the power grid system, so that the staff of relevant terminals can make timely adjustment measures to the power grid system.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention monitors the power grid system through monitoring equipment to obtain power data of the power grid system and pre-process it, stores the processed power data through a database, and performs data mining and visualization on the power data. The database adopts NoSQL database technology to manage the database. NoSQL database technology can remove the relational characteristics of the database by using a distributed data storage method, so that the data storage of the database is simplified and more flexible, thereby realizing the storage of massive data in the database, and then converts the video and image data of personnel involved in daily work into structured data, and combines the historical data of the power grid system to establish a power grid safety accident ratio model based on Heinrich's law, and analyzes the acquired power data through the power grid safety accident ratio model, so as to find out the hidden dangers, events and accidents therein according to the analysis results, and make adjustments and early warnings to the power grid system, so as to remind the staff of relevant terminals to pay attention to the safety issues of the power grid system and make adjustment measures in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the data-driven rapid power grid security analysis method of the present invention. DETAILED DESCRIPTION

[0016] 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.

[0017] In order to solve the problem that the existing power grid data source channels are insufficient and the data analysis and mining capabilities are insufficient, resulting in the phenomenon of "massive data and lack of information" in the management process, which is far from meeting the requirements of daily safety management work. At the same time, since the massive data monitored cannot be fully utilized, the safety analysis of the power grid system cannot be realized, and the technical problem of making the power grid system operation more reliable cannot be solved. Please refer to Figure 1 , this embodiment provides the following technical solutions: The data-driven rapid analysis method for power grid security includes the following steps: S1: Monitor the power grid system through monitoring equipment to obtain power data of the power grid system and pre-process the obtained power data; S2: storing the processed power data in a database, and performing data mining and visualization on the power data; S3: Convert the video and image data of personnel involved in daily work into structured data, and combine it with the historical data of the power grid system to establish a power grid safety accident proportion model based on Heinrich's law; S4: Based on the established power grid safety accident ratio model, the acquired power data is analyzed to find out the hidden dangers, incidents and accidents according to the analysis results, and make adjustments and early warnings to the power grid system.

[0018] Among them, power data refers to a collection of data whose content cannot be captured, managed, and processed by conventional software within a certain period of time. Power data includes digital data, image data, text data, video data, or interaction records, etc. The acquired power data needs to meet the five characteristics of big data, namely, large data volume, fast processing speed, multiple data types, low value density, and high accuracy. In addition, the acquired power data should also meet the requirements of ease of use and security. The essence of big data technology is to mine knowledge from complex related data, obtain effective information, and enhance data value. Big data technology can improve data collection efficiency, mine data value, and play a huge role in the realization of power grid system analysis and early warning.

[0019] In S1, the power grid system is monitored, including the following monitoring equipment: various sensors, intelligent equipment, video surveillance equipment, audio communication equipment and mobile terminals. Through the above data collection channels, massive structured, semi-structured and unstructured data of the power grid system are obtained, mainly involving power generation, transmission, transformation, distribution, power consumption and dispatching.

[0020] Among them, structured data mainly includes data stored in relational databases; unstructured data mainly includes data generated by video surveillance and graphic image processing.

[0021] The technical effect of the above content is as follows: monitoring equipment is set up in the monitoring area of ​​the power grid system. The monitoring equipment includes various sensors, intelligent equipment, video surveillance equipment, audio communication equipment and mobile terminals. The monitoring equipment refers to the process of automatically collecting information from various sensors and other devices under test and digital units under test. It can complete the collection of massive data from heterogeneous and multi-sources. The digital data, image data, text data, video data or interactive records of the power grid system are monitored by the monitoring equipment to obtain the power data of the power grid system. Equipment failure has always been the main source of power grid security. Comprehensive, timely and accurate grasp of the operating status of power equipment is the primary issue to ensure the safe operation of the power grid system. Therefore, the largest amount of data in the smart grid should belong to the power equipment status monitoring data, which mainly includes power grid operation data, fault and defect records, meteorological information, point detection and online monitoring data, technical parameters, etc. These data come from a wide range of sources and are rich in types. There are more and more data monitoring points, and the frequency of monitoring equipment collection is also getting higher and higher.

[0022] In S1, the acquired power data is preprocessed. Since the acquired power data is structured, semi-structured and unstructured, a large amount of unstructured and semi-structured power data is converted into a structured format through preprocessing, and the power data is cleaned to achieve the homogeneity of the power data.

[0023] Technical effects of the above contents: Since the acquired power data includes structured, semi-structured and unstructured data, different data formats in the power data will lead to the dispersion of different system information resources within the power grid system, which cannot be shared horizontally and have difficulty in vertical communication between superiors and subordinates. In addition, there are a large number of unstructured and semi-structured data in the acquired data in the form of videos, images, report texts, etc., which makes it more difficult to achieve the fusion of heterogeneous multi-source data. Therefore, the acquired power data must be preprocessed. The preprocessing operation includes converting a large amount of unstructured and semi-structured data into a structured format, as well as data cleaning of the power data. Data cleaning can perform operations such as screening, deduplication, missing value processing and outlier processing on the power data. By preprocessing the power data, the homogeneity of the power data can be achieved, thereby effectively improving the efficiency of power data processing; In the above content, the outlier processing in data cleaning adopts the deletion method and the replacement method. The deletion method is to directly delete the outliers in the data, that is, the outliers in the power data can be directly deleted by the deletion method. This method is suitable for the situation where the number of outliers in the power data is small and does not affect the overall data; the replacement method is to replace the outliers in the data center. The replacement method adopts one or more of the mean, median and mode methods. The replacement method can adopt the mean, median and mode methods, and the choice of which replacement method to use depends on the distribution of the power data and the characteristics of the outliers. For example, if the power data is normally distributed, the mean can be used for replacement. If there are more discrete values ​​in the power data, the median or mode can be used for replacement.

[0024] In S2, the processed power data is stored in a database, and the database is managed using NoSQL database technology. NoSQL database technology uses distributed data storage to remove the relational characteristics of the database, making the database data storage simplified and more flexible, thereby realizing the storage of massive data in the database.

[0025] The technical effect of the above content is: the pre-processed power data is stored in a database, and the database is managed by NoSQL database technology. NoSQL database technology uses distributed data storage to remove the relational characteristics of the database, so that the data storage of the database is simplified and more flexible, and has good scalability, thereby solving the problem of massive data storage in the database and providing high-throughput data access for applications.

[0026] In S2, data mining and visualization processing are performed on the power data, specifically: Data mining is used to find hidden information from large amounts of fuzzy, noisy, and random power data; Data visualization is used to convert the acquired power into visual data using visual graphics tools.

[0027] The technical effects of the above content are: data mining and visualization of power data. Through data mining, hidden information can be found from large amounts of fuzzy, noisy, and random power data. Through data visualization, the acquired power can be converted into visual data. This process requires the use of visual graphics tools for conversion. Visualizing the acquired power data can better realize the comprehensive display of the power data of the power grid system, thereby helping the staff of the relevant terminals to more intuitively and accurately understand the meaning expressed by the power data.

[0028] In S3, the video and image data of people involved in daily work are converted into structured data and combined with the historical data of the power grid system. The historical data is the safe production data of the power grid system in previous years. The larger the amount of historical data statistics, the more the obtained rules can reflect the overall trend.

[0029] In S3, a power grid safety accident proportion model is established based on Heinrich's law. The established power grid safety accident proportion model reflects the regularity of power grid safety, which can provide a scientific and complete basis for power grid safety analysis and prediction in theory.

[0030] The technical effect of the above content is: the video and image data of the personnel involved in the daily work are converted into structured data, and combined with the historical data of the power grid system, a power grid safety accident proportion model can be established based on Heinrich's law. The historical data are the production safety data of the power grid system in previous years. The larger the number of statistical data of the historical data, the more the obtained rules can reflect the overall trend. If the hidden dangers and accident data in the national power grid system can be counted, the macro-proportional relationship of the entire power industry can be obtained. The established power grid safety accident proportion model can reflect the regularity of power grid safety, and provide a scientific and complete basis in theory for subsequent power grid safety analysis and prediction, which is more conducive to the rapid analysis of the current power grid safety.

[0031] In S4, based on the established power grid safety accident proportion model, the acquired power data is brought into the power grid safety accident proportion model for analysis, and the possible hidden dangers, events and accidents in the current power grid system are found out according to the analysis results. According to the possible hidden dangers, events and accidents in the current power grid system, an early warning is issued to the power grid system, so as to remind the staff of relevant terminals to pay attention to the safety issues of the power grid system, so that the staff of relevant terminals can make timely adjustment measures to the power grid system.

[0032] The technical effect of the above content is as follows: on the basis of the established power grid safety accident proportional model, the acquired power data is brought into the power grid safety accident proportional model for analysis. Through the analysis, the safety problems existing in the current power grid system can be discovered, and thus according to the analysis results, the possible hidden dangers, incidents and accidents in the current power grid system can be found. If the hidden dangers, incidents and accidents in the current power grid system are found, an early warning will be issued to the relevant terminals, so as to remind the staff of the relevant terminals to pay attention to the safety problems of the power grid system. The staff of the relevant terminals will make timely adjustment measures according to the hidden dangers, incidents and accidents found in the current power grid system, thereby reducing the occurrence of power grid safety accidents and providing guarantee for the safe operation of the power grid system.

[0033] Working principle: The monitoring equipment is set in the monitoring area of ​​the power grid system, and the power grid system is monitored by the monitoring equipment to obtain the power data of the power grid system. There are more and more data monitoring points, and the frequency of monitoring equipment collection is also getting higher and higher. The acquired power data needs to first convert a large amount of unstructured and semi-structured data into a structured format, and then perform data cleaning. Through data cleaning, the power data can be screened, deduplicated, missing values ​​processed, and outliers processed, so as to ensure the accuracy of the power data. By preprocessing the power data, the homogeneity of the power data can be achieved, thereby effectively improving the efficiency of power data processing. The preprocessed power data will be stored in the database, and the NoSQL database technology is used to manage the database. The NoSQL database technology uses distributed data storage to remove the relational characteristics of the database, making the database data storage simplified and more flexible, thereby solving the problem of massive data storage in the database. At the same time, The power data is mined and visualized. Through data mining, the hidden information can be found in a large amount of fuzzy, noisy and random power data. By using the visualization of visual graphics tools, the acquired power can be converted into visual data, so as to better realize the comprehensive display of the power data of the power grid system, and then help the staff of the relevant terminals to understand the meaning expressed by the power data more intuitively and accurately. Finally, the video and image data of the personnel involved in daily work are converted into structured data, and combined with the historical data of the power grid system, a power grid safety accident proportion model can be established based on Heinrich's law. The acquired power data is brought into the power grid safety accident proportion model for analysis. Through analysis, the safety problems existing in the current power grid system can be found, so that the power grid system can be warned and adjusted, so as to remind the staff of the relevant terminals to pay attention to the safety problems of the power grid system and make timely adjustment measures to the power grid system, which provides a guarantee for the safe operation of the power grid system.

[0034] 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.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data-driven rapid power grid security analysis method, characterized in that: The following steps are involved: S1: Monitor the power grid system through monitoring equipment to obtain power data of the power grid system and pre-process the obtained power data; S2: storing the processed power data in a database, and performing data mining and visualization on the power data; S3: Convert the video and image data of personnel involved in daily work into structured data, and combine it with the historical data of the power grid system to establish a power grid safety accident proportion model based on Heinrich's law; S4: Based on the established power grid safety accident ratio model, the acquired power data is analyzed to find out the hidden dangers, incidents and accidents according to the analysis results, and make adjustments and early warnings to the power grid system.

2. The data-driven rapid power grid security analysis method according to claim 1 is characterized in that: In S1, the power grid system is monitored, including the following monitoring equipment: sensors, intelligent equipment, video monitoring equipment, audio communication equipment and mobile terminals, and structured, semi-structured and unstructured data of the power grid system are obtained through the monitoring equipment.

3. The data-driven rapid power grid security analysis method according to claim 2 is characterized in that: The structured data includes data stored in a relational database; the unstructured data includes data generated by video surveillance and graphic image processing.

4. The data-driven rapid power grid security analysis method according to claim 1 is characterized in that: In S1, the acquired power data is preprocessed. Since the acquired power data is structured, semi-structured and unstructured, a large amount of unstructured and semi-structured power data is converted into a structured format through preprocessing, and the power data is cleaned to achieve the homogeneity of the power data.

5. The data-driven rapid power grid security analysis method according to claim 1 is characterized in that: In S2, the processed power data is stored in a database, and the database is managed by NoSQL database technology. NoSQL database technology uses a distributed data storage method to remove the relational characteristics of the database, so that the data storage of the database is simplified and more flexible, thereby realizing the storage of massive data in the database.

6. The data-driven rapid power grid security analysis method according to claim 1 is characterized in that: In S2, data mining and visualization processing are performed on the power data, specifically: Data mining is used to find hidden information from large amounts of fuzzy, noisy, and random power data; Data visualization is used to convert the acquired power into visual data using visual graphics tools.

7. The data-driven rapid power grid security analysis method according to claim 1 is characterized in that: In S3, the video and image data of the personnel involved in the daily work are converted into structured data and combined with the historical data of the power grid system. The historical data is the safety production data of the power grid system in previous years. The larger the number of historical data statistics, the more the obtained rules can reflect the overall trend.

8. The data-driven rapid power grid security analysis method according to claim 1 is characterized by: In S3, a power grid safety accident ratio model is established based on Heinrich's law. The established power grid safety accident ratio model reflects the regularity of power grid safety, thereby providing a scientific and complete basis for power grid safety analysis and prediction in theory.

9. The data-driven rapid power grid security analysis method according to claim 1 is characterized by: In S4, based on the established power grid safety accident ratio model, the acquired power data is brought into the power grid safety accident ratio model for analysis, and the potential hidden dangers, events and accidents in the current power grid system are found out according to the analysis results.

10. The data-driven rapid power grid security analysis method according to claim 9, characterized in that: According to the potential hidden dangers, events and accidents in the current power grid system, early warning is issued to the power grid system to remind the staff of relevant terminals to pay attention to the safety issues of the power grid system, so that the staff of relevant terminals can make timely adjustment measures to the power grid system.

Images