A smart power dispatching system and dispatching method
By using the fault data processing, log generation, and information push units of the intelligent power dispatching system, the problems of low information sharing and cumbersome processes in the power dispatching system have been solved, achieving efficient and accurate fault information processing and management, and improving the convenience and security of power grid dispatching.
Patent Information
- Application Number
- CN202311309692.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-10
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-10-10
AI Technical Summary
The existing power dispatching system suffers from low information sharing and cumbersome processes, resulting in low efficiency and high error rate among dispatchers, posing potential risks. Furthermore, the intelligent dispatching system platform is not sufficiently complete.
An intelligent power dispatching system was designed, including fault data processing, fault log generation, fault data analysis, and fault information push units. The fault data processing unit reads and merges information from different systems, generates fault logs using natural language processing, performs data statistics and classification, and automatically generates visual tables through robotic process automation to realize the automatic push and release of information.
It has improved the automation and intelligence of power dispatching, reduced the time spent on repetitive manual recording, improved the efficiency of information collection and the level of engineering quality analysis, reduced the error rate, enhanced information transparency and management depth, and reduced the pressure on the dispatching console.
Smart Images

Figure CN117196253B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power technology, and in particular to an intelligent power dispatching system and method. Background Technology
[0002] Currently, the power system requires the monitoring and dispatch of massive amounts of information, causing dispatchers to spend a significant amount of time on tedious record-keeping, thus wasting considerable time and energy. This ironically reduces the time and effort available for incident handling and analysis. Typically, a district or county has only two dispatchers on duty per shift, each handling dozens to hundreds of phone calls daily, spending 150-200 minutes on calls, and monitoring over 500 real-time information entries. Simultaneously, with the continuous development of the distribution network, its structure and information volume are increasing. Dispatch duty systems, local load control systems, and power supply control systems all require querying, verification, and maintenance, resulting in complex and repetitive tasks. Each fault must be manually recorded in these systems, and the fault information must be immediately disseminated to various work groups. These tedious steps waste a significant amount of time, reducing the time and effort available for incident handling and analysis, increasing the error rate of dispatchers, and posing certain risks to power grid dispatching operations.
[0003] To effectively improve the level of information management in power dispatching and enhance the efficiency of fault information retrieval and analysis, some practitioners have proposed the construction of an artificial intelligence dispatching system platform. However, the current intelligent dispatching system platform is still not perfect, with many areas requiring human intervention. Furthermore, the information sharing in the dispatching and control process is low, the workflow is cumbersome, and the efficiency of work quality management needs to be improved. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide an intelligent power dispatching system and dispatching method with high information sharing and high degree of process automation.
[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:
[0006] An intelligent power dispatching system includes:
[0007] The fault data processing unit is used to match and fuse fault data information read from different systems;
[0008] The fault log generation unit is used to generate corresponding fault logs by processing the fused fault data information through natural language.
[0009] The fault data analysis unit is used to statistically analyze, classify, and filter the fused fault data information to obtain fault data information under different dimensions.
[0010] The fault information push unit is used to push fault data information to the corresponding line maintenance users to remind them to check in time, and to publish fault data information to the cloud for users to view in real time.
[0011] The fault data processing unit includes:
[0012] The fault data reading module is used to read trip information tables and fault outage information tables from the provincial load system, and to export single-area power outage information tables from the power supply command system.
[0013] The geographic location mapping module is used to map the lines and branches under operation and maintenance to specific power supply stations and their geographical locations in order to generate a line operation and maintenance relationship mapping table.
[0014] The weather acquisition module is used to acquire real-time weather data for various counties and districts within a given region.
[0015] The data fusion module is used to merge the fault information data obtained by the fault data reading module and the weather data obtained by the weather acquisition module, and then use the geographic location matching module to match it to the specific operation and maintenance power supply station in the same data table.
[0016] The fault log generation unit includes:
[0017] The fault data decomposition module is used to decompose the fused fault data information into several groups of small morphemes;
[0018] The fault log generation module is used to organize and sort the disassembled groups of small morphemes according to the normal language order to generate fault log records; and to classify the generated fault log records according to the scheduling jurisdiction to obtain the logs of each county.
[0019] The fault data analysis unit includes:
[0020] The fault data statistics module is used to generate load loss tables, fault count tables, cumulative power outage duration tables, and power outage duration tables for each county, and arrange them in descending order.
[0021] The fault data classification module is used to classify the data generated by the fault data statistics module by county and station, so as to generate fault logs for each county, load loss tables for each county and station, fault count tables for each station, cumulative power outage duration tables for each station, and power outage duration tables for each piece of equipment.
[0022] The fault data filtering module is used to automatically filter power outage types and generate corresponding tables through a robotic process.
[0023] The visualization generation module is used to present the generated tables in a visual format;
[0024] The fault information push unit includes:
[0025] The fault information push module is used to extract data that the dispatcher has not yet had time to analyze, generate fault text, and notify the corresponding line operation and maintenance management personnel.
[0026] The fault information publishing module is used to automatically publish relevant information to the cloud, set to publish at a certain time interval, and use the information published this time to overwrite the information published last time.
[0027] As a further improvement to the above technical solution:
[0028] The trip information table and fault outage information table include the following data: outage time, restoration time, substation name, equipment name, outage type, protection action information, whether reclosing was successful, outage reason, load loss, power loss, whether it caused load loss for important users, and remarks;
[0029] The power outage information table includes the following data: power outage information number, reporting status, on-site power restoration type, number of affected users, number of affected transformer substations, municipal / prefecture-level company, district / county-level company, initial power outage end time, substation name, line name, whether a text message was sent to the customer, whether a text message was sent to the transformer substation manager, power outage type, voltage level, initial reporting time when changes or additions are entered, initial publication time, final power outage start time, final power outage end time, power outage area, initial on-site power restoration time, final on-site power restoration time, whether it was a daytime outage and nighttime restoration, information source, power outage scope, power outage reason, and whether power was adjusted during the outage.
[0030] The line operation and maintenance relationship correspondence table includes the following data: line name, operation and maintenance unit, and geographical location.
[0031] The data fusion module includes a data matching unit, which is used to determine whether the beginning of the device name obtained in the fault data reading module, the name of the line and branch line under maintenance in the geographical location corresponding module, and the geographical location name in the weather acquisition module are consistent. If they are consistent, the data of the same geographical location in the fault data reading module, the geographical location corresponding module, and the weather acquisition module are matched in the same data table.
[0032] The fault log generation module includes a natural language processing component, which ensures the logic and fluency of the statements based on the judgment of conditional statements, and simulates the tone of a dispatcher's speech by inserting auxiliary words and conjunctions to generate fault log records; the conditional statements include the cause of power outage, protection action information, power restoration status, and whether it is an important user.
[0033] The fault data filtering module includes:
[0034] The power outage statistics component is used to filter out power outages as "emergency repair" and generate corresponding tables;
[0035] The planned maintenance statistics component is used to filter power outages by type "planned maintenance" and generate corresponding tables.
[0036] The filtering of the non-power restoration statistics component includes: filtering for power outage type as "fault repair", selecting power outage start time from 7 days ago to today, filtering for "first on-site power restoration time" as null, generating a new DataFrame data structure, changing the first power outage end time to "power outage time", adding a "current time" column to obtain the current time; adding a "power outage duration" column with the content "current time" - "power outage time"; adding a "maintenance station" column, which is combined with the maintenance station in the line station correspondence table; and selecting "substation name", "line name", "power outage time", "current time", "number of affected users", and "number of affected transformer areas" to generate corresponding tables.
[0037] The filtering of the planned maintenance statistics component includes: filtering the power outage type as "planned maintenance", and if "whether it is a daytime outage and nighttime restoration" is yes, then selecting "first on-site power restoration time" within today as empty; the corresponding table is generated through the filtering.
[0038] The relevant information released by the fault information release module includes: fault information reports, fault log record reports, reports of equipment not powered on, and reports of equipment scheduled for power outage today;
[0039] The fault information report includes the following data: power loss, load loss, number of faults, and cumulative power outage duration;
[0040] The fault log report includes the following data: power outage time, faulty equipment name, fault type, lost load, and power consumption;
[0041] The report on unpowered equipment includes the following data: affected transformer area, power outage area, and number of households without power.
[0042] The planned power outage equipment report for today includes the following data: affected area, number of affected users, and number of transformer substations.
[0043] The intelligent power dispatching system also includes a data storage unit for storing tables, information data, and files generated by the fault data processing unit, fault log generation unit, fault data analysis unit, and fault information push unit.
[0044] This invention also provides an intelligent power dispatching method, comprising the following steps:
[0045] S1. Read fault data information from different systems and perform matching and fusion;
[0046] S2. Generate corresponding fault logs from the fused fault data information through natural language processing;
[0047] S3. Statistically analyze, classify and filter the merged fault data information to obtain fault data information under different dimensions;
[0048] S4. Push fault data information to the corresponding line maintenance users to remind them to check in time, and publish fault data information to the cloud for users to view in real time;
[0049] Step S1 includes:
[0050] Read the trip information table and fault outage information table from the provincial load system, and export the single-area power outage information table from the power supply command system;
[0051] The operation and maintenance lines and branch lines are mapped to specific operation and maintenance power supply stations and their geographical locations to generate a line operation and maintenance relationship mapping table;
[0052] Obtain real-time weather data for each county and district in a certain region;
[0053] The fault information data and weather information data are merged and mapped to specific operation and maintenance power supply stations to be matched into the same data table; wherein, the fault information data includes trip information table, fault outage information table and single-station area power outage information table;
[0054] Step S2 includes:
[0055] The merged fault data information is broken down into several groups of small morphemes;
[0056] The disassembled groups of small morphemes are organized and sorted according to the normal language order to generate fault log records;
[0057] The generated fault log records are classified according to the scheduling jurisdiction to obtain the logs for each county;
[0058] Step S3 includes:
[0059] Generate a load loss table for each county, a fault count table for each county, a cumulative power outage duration table for each county, and a power outage duration table for each piece of equipment, and arrange them in descending order;
[0060] The fault information data is categorized by county and station to generate fault logs for each county, load loss tables for each county and station, fault count tables for each station, cumulative power outage duration tables for each station, and power outage duration tables for each piece of equipment. The corresponding tables are generated by automatically filtering outage types through a robotic process.
[0061] Present the generated table in a visual format;
[0062] Step S4 includes:
[0063] Extract data that the dispatcher has not yet had time to analyze, generate fault text, and notify the corresponding line's operation and maintenance management personnel;
[0064] The system automatically publishes relevant information to the cloud, sets a certain time interval for publication, and overwrites the previously published information with the information published this time.
[0065] As a further improvement to the above technical solution:
[0066] In step S1, a function is used to determine whether the string of the name of the line and branch line under maintenance starts with another given substring. If the result is yes, the line and branch line under maintenance are mapped to the specific power supply station and county under maintenance.
[0067] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent power dispatching method described above.
[0068] Compared with the prior art, the advantages of the present invention are as follows:
[0069] 1. The intelligent power dispatching system of the present invention achieves automation and intelligence of the distribution network dispatching working mode through the joint efforts of the fault data processing unit, the fault log generation unit, the fault data analysis unit, and the fault information push unit, thereby improving the convenience, efficiency and accuracy of the work.
[0070] 2. The intelligent power dispatching system of the present invention realizes the sharing of distribution network dispatching and control information through a fault data reading module, a geographical location correspondence module, a weather acquisition module, and a data fusion module, which facilitates timely and clear fault information and enhances the depth and transparency of distribution network dispatching and management.
[0071] 3. The intelligent power dispatching system of the present invention can automatically generate corresponding fault logs and fault information pivot tables through the fault data decomposition module, fault log generation module, and visualization generation module. This greatly reduces the time spent on manual repetitive recording, and the displayed content is concise and clear, with no redundancy. It accurately reflects massive amounts of fault information and ensures that no fault data points are missed, thereby improving the efficiency of information collection and the level of engineering quality analysis, and promoting the standardized management of distribution network dispatching.
[0072] 4. The intelligent power dispatching system of the present invention realizes automatic synchronous notification of multiple faults through a fault information push module and a fault information release module, thereby reducing the pressure on the dispatching console when there are many faults. Attached Figure Description
[0073] Figure 1 This is a schematic block diagram of the intelligent power dispatching system according to an embodiment of the present invention.
[0074] Figure 2 This is an information processing flowchart of the intelligent power dispatching system according to an embodiment of the present invention.
[0075] Figure 3 This is a schematic block diagram of the fault information publishing module in an embodiment of the present invention.
[0076] Figure 4 This is a flowchart illustrating the process of generating logs by the fault log generation unit in this embodiment of the invention.
[0077] Figure 5 This is a flowchart of the intelligent power dispatching method in an embodiment of the present invention. Detailed Implementation
[0078] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0079] Example 1
[0080] To facilitate user demonstration and improve development efficiency, the intelligent power dispatching system in this embodiment adopts the Python language and has a PC web interface with web page display and input units, and a mobile interface with mobile display and input units.
[0081] like Figure 1 and Figure 2 As shown, this embodiment provides an intelligent power dispatching system, including:
[0082] The fault data processing unit is used to match and fuse fault data information read from different systems;
[0083] The fault log generation unit is used to generate corresponding fault logs by processing the fused fault data information through natural language.
[0084] The fault data analysis unit is used to statistically analyze, classify, and filter the fused fault data information to obtain fault data information under different dimensions.
[0085] The fault information push unit is used to push fault data information to the corresponding line maintenance users to remind them to check in time, and to publish fault data information to the cloud for users to view in real time.
[0086] The fault data processing unit includes:
[0087] The fault data reading module is used to read trip information tables and fault outage information tables from the provincial load system, and to export single-area power outage information tables from the power supply command system.
[0088] The geographic location mapping module is used to map the lines and branches under operation and maintenance to specific power supply stations and their geographical locations in order to generate a line operation and maintenance relationship mapping table.
[0089] The weather acquisition module is used to acquire real-time weather data for various counties and districts within a given region.
[0090] The data fusion module is used to merge the fault information data obtained by the fault data reading module and the weather data obtained by the weather acquisition module, and then use the geographic location matching module to match it to the specific operation and maintenance power supply station in the same data table.
[0091] The fault log generation unit includes:
[0092] The fault data decomposition module is used to decompose the fused fault data information into several groups of small morphemes;
[0093] The fault log generation module is used to organize and sort the disassembled groups of small morphemes according to the normal language order to generate fault log records; and to classify the generated fault log records according to the scheduling jurisdiction to obtain the logs of each county.
[0094] The fault data analysis unit includes:
[0095] The fault data statistics module is used to generate load loss tables, fault count tables, cumulative power outage duration tables, and power outage duration tables for each county, and arrange them in descending order.
[0096] The fault data classification module is used to classify the data generated by the fault data statistics module by county and station, so as to generate fault logs for each county, load loss tables for each county and station, fault count tables for each station, cumulative power outage duration tables for each station, and power outage duration tables for each piece of equipment.
[0097] The fault data filtering module is used to automatically filter power outage types and generate corresponding tables through a robotic process.
[0098] The visualization generation module is used to present the generated tables in a visual format;
[0099] The fault information push unit includes:
[0100] The fault information push module is used to extract data that the dispatcher has not yet had time to analyze, generate fault text, and notify the corresponding line operation and maintenance management personnel.
[0101] The fault information publishing module is used to automatically publish relevant information to the cloud, set to publish at a certain time interval, and use the information published this time to overwrite the information published last time.
[0102] The above units or modules will be explained in detail below through specific examples.
[0103] Fault Data Reading Module: Trip information table data is automatically obtained through information pushed by devices with installed automated monitoring units and analyzed by dispatchers. The fault outage information table is stored in the data storage unit. Users can export attribute information, fault occurrence and recovery time, protection action information, etc., of each faulty line device from the power supply command system and provincial load loss system via PC web interface or mobile terminal, and store them in the data storage unit. It can be understood that through the synchronization and sharing of online data from platforms such as the provincial load system and power supply command system, the required fault data information can be easily read, strengthening the sharing of distribution network dispatching and control information, enabling timely and clear fault information, increasing the depth and transparency of distribution network dispatching management, improving information timeliness, and accelerating information flow.
[0104] Geographic Location Mapping Module: The data read from the load system does not contain information on maintenance stations. Furthermore, the dispatching area does not completely overlap with the county. For example, in Huaihua, the dispatching area for high-voltage equipment in substations with voltage levels of 110kV and above belongs to the Huaihua Dispatch Center, but in reality, most of it is located in other counties. Therefore, it is also necessary to obtain the county information. Thus, a database named dfsl was created for the power line maintenance information. Because faulty lines are branch lines starting with the main line name, the `startsWith()` function is used to map the data to the database. The `startsWith()` method determines whether the current string begins with another given substring, returning true or false based on the result. This method maps the maintained lines and branch lines to specific maintenance stations and counties. Then, a mapping table is created for each main line equipment name, its corresponding maintenance station, substation, dispatching area, and city.
[0105] Weather Acquisition Module: This module crawls weather information from various regions within the security management system and merges the crawled weather information into the fault data information based on the region. The data is then uploaded to a designated folder on the intranet via cloud storage. The weather module runs four times daily. Taking Huaihua as an example, the weather data for Huaihua city proper and each county should consider Huaihua's geological dispatch system and the actual location within the county seat to ensure accurate correspondence between weather information and geographical location.
[0106] Data Fusion Module: If the device name in the data input unit begins with the line name used in the substation correspondence table module, the data from the fault data reading module is associated with the substation correspondence table module. Based on the geographical attribute, fault information data and weather information data are matched in the same data table. The contents of the data table are sorted by row number, outage time, substation name, device name, whether it caused load loss for important users, outage type, protection action information, whether reclosing was successful, recovery time, outage reason, load loss, power loss, remarks, control range, and weather.
[0107] The fault log generation unit decomposes the matched data from the DataFrame structure obtained through station mapping and weather crawling into various small morphemes, and organizes and sorts them according to normal language order to ensure smooth reading. Several conditional statements are used to ensure the logic and fluency of the text, based on factors such as the cause of power outage, protection action information, power restoration status, and whether the user is important. Modal particles and conjunctions are inserted to simulate the tone of a dispatcher, automatically generating log records. These logs are then categorized according to dispatch jurisdiction to obtain dispatch logs for each county. Fault log records include power outage time, equipment name, fault type, protection action information, and dispatch handling process. In short, the fault log generation module can automatically generate the required logs, reducing manual recording time compared to the original method of manually writing logs. The log content is accurate and complete, without redundancy, accurately reflecting massive amounts of fault information, thus improving information collection efficiency and engineering quality analysis.
[0108] Fault data filtering module: After logging into the power supply control system via RPA (Robotic Process Automation), click on power outage information entry, select the power outage start time from 7 days ago to today, and export the table "Power Outage Information Entry - Power Outage Information Content.xlsx".
[0109] The visualization generation module uses the `pivot_table` function to obtain the number of faults, load loss, power loss, and outage duration for each substation in the Huaihua area. It directly calculates these indicators, arranges them in descending order, and generates an Excel table and pivot chart for use by various professionals in power distribution and marketing. The pivot chart generated by the visualization module provides a more intuitive display of fault information, facilitating monitoring and data analysis by relevant personnel.
[0110] Fault Information Push Module: In the D5000 system, most circuit breaker trips within substations are pushed to the provincial dispatch load system. For faults automatically pushed to the OMS provincial dispatch load system, data that dispatchers haven't had time to analyze is extracted. The Twilio voice integration module automatically notifies the substation for analysis and action. Specifically, a fault text message is automatically generated and sent to the corresponding line maintenance owner via SMS, along with an automatic reminder call. Upon receiving the reminder call, the equipment owner checks the line for power outages in the marketing system. This fault information push module ensures on-site analysis even in adverse weather conditions where dispatchers cannot immediately assess the fault, effectively preventing dispatchers from missing important information.
[0111] Fault Information Publishing Module: This module automatically publishes relevant information to the intranet cloud drive on both mobile and web platforms. It is set to run every 15 minutes, overwriting the previous information upon each run. Fault information and reports can then be viewed on the intranet cloud drive and the "iGuoWang" mobile app. This allows for automatic synchronization of multiple fault notifications for line faults that can be pushed to the OMS load system, reducing the pressure on the dispatch console when multiple faults are present.
[0112] In this embodiment, the trip information table and the fault outage information table include the following data: power outage time, restoration time, substation name, equipment name, power outage type, protection action information, whether reclosing was successful, power outage reason, load loss, power loss, whether it caused load loss for important users, and remarks;
[0113] The power outage information form includes the following data: power outage information number, reporting status, on-site power restoration type, number of affected users, number of affected transformer substations, municipal / prefecture-level company, district / county-level company, initial power outage end time, substation name, line name, whether a text message was sent to customers, whether a text message was sent to the transformer substation manager, power outage type, voltage level, initial reporting time for changes or additions, initial publication time, final power outage start time, final power outage end time, power outage area, initial on-site power restoration time, final on-site power restoration time, whether it was a daytime outage and nighttime restoration, information source, power outage scope, reason for power outage, and whether power was adjusted during the outage.
[0114] The line operation and maintenance relationship mapping table includes the following data: line name, operation and maintenance unit, and geographical location.
[0115] In this embodiment, the data fusion module includes a data matching unit, which is used to determine whether the beginning of the device name obtained in the fault data reading module, the name of the line and branch line under maintenance in the geographical location corresponding module, and the geographical location name in the weather acquisition module are consistent. If they are consistent, the data of the same geographical location in the fault data reading module, the geographical location corresponding module, and the weather acquisition module are matched in the same data table.
[0116] In this embodiment, the fault log generation module includes: a natural language processing component, which is used to ensure the logic and fluency of the statement based on the judgment of the conditional statement, and to simulate the tone of the dispatcher's speech by inserting auxiliary words and conjunctions to generate fault log records; the conditional statement includes the reason for power outage, protection action information, power restoration status and whether it is an important user.
[0117] Specifically, Figure 4 The flowchart for generating fault logs is as follows: First, determine if protection action information exists in the merged fault data. If it exists, delete the protection action information column, its corresponding label, and punctuation. Then, check if the recovery time is empty. If not, directly check if the recovery time is empty. If the recovery time is empty, delete the recovery time column and its corresponding label, and mark "To be calculated" in the power loss column. Then, check if the remarks column is empty. If it is not empty, directly check if the remarks column is empty. If the remarks column is empty, delete the remarks column. Then, determine if the user is an important user. If the remarks column is not empty, directly determine if the user is an important user. If the user is an important user, combine the processed fault data into a list and create a document. If the user is not an important user, delete the "Is it an important user?" column and then combine the data into a list and create a document.
[0118] In this embodiment, the fault data filtering module includes:
[0119] The power outage statistics component is used to filter out power outages as "emergency repair" and generate corresponding tables;
[0120] The planned maintenance statistics component is used to filter power outages by type "planned maintenance" and generate corresponding tables.
[0121] The filtering process for the outage statistics component includes: filtering for outage type as "fault repair," selecting outage start time from 7 days ago to today, and filtering for "first on-site power restoration time" which is null. A new DataFrame structure is generated, changing the first outage end time to "outage time," adding a "current time" column to retrieve the current time, adding a "outage duration" column with the content "current time" - "outage time," adding a "maintenance station" column, and combining it with the maintenance stations in the line-station correspondence table; generating corresponding tables by selecting "substation name," "line name," "outage time," "current time," "number of affected users," and "number of affected transformer areas"; extracting the data obtained from the above filtering and naming it "Outage Equipment.xls," and generating a related pivot table.
[0122] The filtering of the planned maintenance statistics component includes: filtering the power outage type as "planned maintenance", and if "whether it is a daytime outage and nighttime power restoration" is yes, then selecting "first on-site power restoration time" for today as empty; generating the corresponding table; and extracting the data obtained from the above filtering and naming it "Today's planned maintenance equipment already started.xls".
[0123] In this embodiment, as Figure 3 As shown, the relevant information released by the fault information release module includes: fault information report, fault log record report, unpowered equipment report, and equipment scheduled for power outage today report;
[0124] The fault information report includes the following data: power loss, load loss, number of faults, and cumulative power outage duration; among them, the municipal company directory contains the summarized data of each county company, and the county company directory contains the summarized data of each power supply station.
[0125] The fault log report includes the following data: power outage time, name of the faulty equipment, fault type, lost load, and power consumption;
[0126] The report on equipment without power restoration includes the following data: affected transformer area, power outage area, and number of households without power;
[0127] Today's planned power outage equipment report includes the following data: affected area, number of affected users, and number of transformer substations.
[0128] In this embodiment, the intelligent power dispatching system also includes a data storage unit for storing the tables, information data, and files generated in the fault data processing unit, fault log generation unit, fault data analysis unit, and fault information push unit.
[0129] Example 2
[0130] This embodiment provides an intelligent power dispatching method, including the following steps:
[0131] S1. Read fault data information from different systems and perform matching and fusion;
[0132] S2. Generate corresponding fault logs from the fused fault data information through natural language processing;
[0133] S3. Statistically analyze, classify and filter the merged fault data information to obtain fault data information under different dimensions;
[0134] S4. Push fault data information to the corresponding line maintenance users to remind them to check in time, and publish fault data information to the cloud for users to view in real time;
[0135] Step S1 includes:
[0136] Read the trip information table and fault outage information table from the provincial load system, and export the single-area power outage information table from the power supply command system;
[0137] The operation and maintenance lines and branch lines are mapped to specific operation and maintenance power supply stations and their geographical locations to generate a line operation and maintenance relationship mapping table;
[0138] Obtain real-time weather data for each county and district in a certain region;
[0139] The fault information data and weather information data are merged and mapped to specific operation and maintenance power supply stations to be matched into the same data table; among them, the fault information data includes trip information table, fault outage information table and single-unit area power outage information table;
[0140] Step S2 includes:
[0141] The merged fault data information is broken down into several groups of small morphemes;
[0142] The disassembled groups of small morphemes are organized and sorted according to the normal language order to generate fault log records;
[0143] The generated fault log records are classified according to the scheduling jurisdiction to obtain the logs for each county;
[0144] Step S3 includes:
[0145] Generate a load loss table for each county, a fault count table for each county, a cumulative power outage duration table for each county, and a power outage duration table for each piece of equipment, and arrange them in descending order;
[0146] The fault information data is categorized by county and station to generate fault logs for each county, load loss tables for each county and station, fault count tables for each station, cumulative power outage duration tables for each station, and power outage duration tables for each piece of equipment. The corresponding tables are generated by automatically filtering outage types through a robotic process.
[0147] Present the generated table in a visual format;
[0148] Step S4 includes:
[0149] Extract data that the dispatcher has not yet had time to analyze, generate fault text, and notify the corresponding line's operation and maintenance management personnel;
[0150] The system automatically publishes relevant information to the cloud, sets a certain time interval for publication, and overwrites the previously published information with the information published this time.
[0151] In this embodiment, in step S1, a function is used to determine whether the string of the name of the line and branch line under maintenance starts with another given substring. If the determination result is yes, the line and branch line under maintenance are mapped to the specific power supply station and county under maintenance.
[0152] The intelligent power dispatching method of this embodiment will be illustrated below with a specific example.
[0153] Figure 5This example illustrates a flowchart of the steps involved in the intelligent power dispatching method, which includes the following steps:
[0154] Step 1: Automatically read the trip loss load table and fault loss load table from the provincial load system, export the single-area power outage information table from the power supply control system, and store it in the data storage unit; among them, the trip information table data is automatically pushed from the equipment with installed automated monitoring units and is analyzed by the dispatcher, and the fault outage information table is stored in the data storage unit.
[0155] Step 2: Create a line maintenance relationship mapping table, corresponding to the maintenance stations and geographical locations of the lines. The specific method for location mapping follows the steps in the geographical location mapping module of Example 1.
[0156] Step 3: Crawl real-time weather data from various counties and districts on the security risk management platform, and merge the crawled weather information into the fault data information and store it according to the region.
[0157] Step 4: Merge the fault information table extracted in Step 1 with the real-time weather data obtained in Step 3 using geographical location, and assign the corresponding specific operation and maintenance unit based on the main line name. Associate the distribution network line fault data from Step 1 with the substation correspondence table module, and match the data in the data input unit with the weather unit in the same data table based on the geographical attribute.
[0158] Step 5: After processing the DataFrame structure corresponding to the station and the weather crawler, the matched data is broken down into various small morphemes and organized and sorted according to normal language order to make it easier to read. Several conditional statements are used to ensure the logic and fluency of the text, based on conditions such as the reason for power outage, protection action information, power restoration status, and whether it is an important user. Then, modal particles and conjunctions are inserted to simulate the tone of a dispatcher, so that log records are automatically generated. The above logs are then classified according to the dispatching jurisdiction to obtain the dispatching logs for each county.
[0159] Step 6: Automatically push suspected equipment alerts. Most circuit breaker trips within the D5000 system substation will be pushed to the provincial load dispatch system. Data that dispatchers haven't yet been able to analyze is extracted, and a fault text message is automatically generated and sent to the corresponding line maintenance owner via SMS, along with an automatic alert call. Upon receiving the alert, the equipment owner checks the line for power outages in the marketing system. This process allows for on-site assessment even in adverse weather conditions where dispatchers cannot immediately assess the fault. It also effectively prevents dispatchers from missing potential monitoring.
[0160] Step 7: Classify the above data by county and station, and generate and visualize the fault logs for each county, the load loss table for each county and station, the fault count table for each station, the cumulative power outage duration table for each station, and the power outage duration table for each piece of equipment.
[0161] Step 8: Using the pivot_table function, the generated DataFrame structure is used to obtain the number of faults, load loss, power loss, and outage duration for each station in the Huaihua area. Various key indicators are directly statistically analyzed and arranged in descending order, generating an Excel spreadsheet and pivot chart for use by the power distribution and marketing departments.
[0162] Step 9: After logging into the power supply command system, click on "Power Outage Information Entry". Select "7 days ago to today" as the power outage start time, and export the table "Power Outage Information Entry - Power Outage Information Content.xlsx".
[0163] Step 10: Automatically publish the relevant information to the cloud drive. Set it to run every 15 minutes. The information after the run will overwrite the information of the previous run. You can then view the fault information and reports on the intranet cloud drive and the "iGuoWang" mobile app.
[0164] Example 3
[0165] This embodiment provides a computer-readable storage medium storing a computer program, which is used to be programmed or configured by a microprocessor to execute the intelligent power dispatching method described in Embodiment 2.
[0166] While the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Any person skilled in the art can make many possible variations and modifications to the technical solutions of the present invention, or modify them into equivalent embodiments, without departing from the scope of the present invention. Therefore, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention, without departing from the scope of the present invention, should fall within the protection scope of the present invention.
Claims
1. An intelligent power dispatching system, characterized in that, include: The fault data processing unit is used to match and fuse fault data information read from different systems; The fault log generation unit is used to generate corresponding fault logs by processing the fused fault data information through natural language. The fault data analysis unit is used to statistically analyze, classify, and filter the fused fault data information to obtain fault data information under different dimensions. The fault information push unit is used to push fault data information to the corresponding line maintenance users to remind them to check in time, and to publish fault data information to the cloud for users to view in real time. The fault data processing unit includes: The fault data reading module is used to read trip information tables and fault outage information tables from the provincial load system, and to export single-area power outage information tables from the power supply command system. The geographic location mapping module is used to map the lines and branches under operation and maintenance to specific power supply stations and their geographical locations in order to generate a line operation and maintenance relationship mapping table. The weather acquisition module is used to acquire real-time weather data for various counties and districts within a given region. The data fusion module is used to merge the fault information data obtained by the fault data reading module and the weather data obtained by the weather acquisition module, and then use the geographic location matching module to match it to the specific operation and maintenance power supply station in the same data table. The fault log generation unit includes: The fault data decomposition module is used to decompose the fused fault data information into several groups of small morphemes; The fault log generation module is used to organize and sort the disassembled groups of small morphemes according to the normal language order to generate fault log records; and to classify the generated fault log records according to the scheduling jurisdiction to obtain the logs of each county. The fault data analysis unit includes: The fault data statistics module is used to generate load loss tables, fault count tables, cumulative power outage duration tables, and power outage duration tables for each county, and arrange them in descending order. The fault data classification module is used to classify the data generated by the fault data statistics module by county and station, so as to generate fault logs for each county, load loss tables for each county and station, fault count tables for each station, cumulative power outage duration tables for each station, and power outage duration tables for each piece of equipment. The fault data filtering module is used to automatically filter power outage types and generate corresponding tables through a robotic process. The visualization generation module is used to present the generated tables in a visual format; The fault information push unit includes: The fault information push module is used to extract data that the dispatcher has not yet had time to analyze, generate fault text, and notify the corresponding line operation and maintenance management personnel. The fault information publishing module is used to automatically publish relevant information to the cloud, set to publish at a certain time interval, and use the information published this time to overwrite the information published last time.
2. The intelligent power dispatching system according to claim 1, characterized in that: The trip information table and fault outage information table include the following data: outage time, restoration time, substation name, equipment name, outage type, protection action information, whether reclosing was successful, outage reason, load loss, power loss, whether it caused load loss for important users, and remarks; The power outage information table includes the following data: power outage information number, reporting status, on-site power restoration type, number of affected users, number of affected transformer substations, municipal / prefecture-level company, district / county-level company, initial power outage end time, substation name, line name, whether a text message was sent to the customer, whether a text message was sent to the transformer substation manager, power outage type, voltage level, initial reporting time when changes or additions are entered, initial publication time, final power outage start time, final power outage end time, power outage area, initial on-site power restoration time, final on-site power restoration time, whether it was a daytime outage and nighttime restoration, information source, power outage scope, power outage reason, and whether power was adjusted during the outage. The line operation and maintenance relationship mapping table includes the following data: Line name, operation and maintenance unit, and geographical location.
3. The intelligent power dispatching system according to claim 1, characterized in that: The data fusion module includes a data matching unit, which is used to determine whether the beginning of the device name obtained in the fault data reading module, the name of the line and branch line under maintenance in the geographical location corresponding module, and the geographical location name in the weather acquisition module are consistent. If they are consistent, the data of the same geographical location in the fault data reading module, the geographical location corresponding module, and the weather acquisition module are matched in the same data table.
4. The intelligent power dispatching system according to claim 1, characterized in that: The fault log generation module includes a natural language processing component, which ensures the logic and fluency of the statements based on the judgment of conditional statements, and simulates the tone of a dispatcher's speech by inserting auxiliary words and conjunctions to generate fault log records; the conditional statements include the cause of power outage, protection action information, power restoration status, and whether it is an important user.
5. The intelligent power dispatching system according to claim 1, characterized in that, The fault data filtering module includes: The power outage statistics component is used to filter out power outages as "emergency repair" and generate corresponding tables; The planned maintenance statistics component is used to filter power outages by type "planned maintenance" and generate corresponding tables. The filtering of the non-power restoration statistics component includes: filtering for power outage type as "fault repair", selecting power outage start time from 7 days ago to today, filtering for "first on-site power restoration time" as null, generating a new DataFrame data structure, changing the first power outage end time to "power outage time", adding a "current time" column to obtain the current time; adding a "power outage duration" column with the content "current time" - "power outage time"; adding a "maintenance station" column, which is combined with the maintenance station in the line station correspondence table; and selecting "substation name", "line name", "power outage time", "current time", "number of affected users", and "number of affected transformer areas" to generate corresponding tables. The filtering of the planned maintenance statistics component includes: filtering the power outage type as "planned maintenance", and if "whether it is a daytime outage and nighttime restoration" is yes, then selecting "first on-site power restoration time" within today as empty; the corresponding table is generated through the filtering.
6. The intelligent power dispatching system according to claim 1, characterized in that: The relevant information released by the fault information release module includes: fault information reports, fault log record reports, reports of equipment not powered on, and reports of equipment scheduled for power outage today; The fault information report includes the following data: power loss, load loss, number of faults, and cumulative power outage duration; The fault log report includes the following data: power outage time, faulty equipment name, fault type, lost load, and power consumption; The report on unpowered equipment includes the following data: affected transformer area, power outage area, and number of households without power. The planned power outage equipment report for today includes the following data: affected area, number of affected users, and number of transformer substations.
7. The intelligent power dispatching system according to any one of claims 1 to 6, characterized in that: The intelligent power dispatching system also includes a data storage unit for storing tables, information data, and files generated by the fault data processing unit, fault log generation unit, fault data analysis unit, and fault information push unit.
8. A smart power dispatching method based on the smart power dispatching system according to any one of claims 1 to 6, characterized in that, Including the following steps: S1. Read fault data information from different systems and perform matching and fusion; S2. Generate corresponding fault logs from the fused fault data information through natural language processing; S3. Statistically analyze, classify and filter the merged fault data information to obtain fault data information under different dimensions; S4. Push fault data information to the corresponding line maintenance users to remind them to check in time, and publish fault data information to the cloud for users to view in real time; Step S1 includes: Read the trip information table and fault outage information table from the provincial load system, and export the single-area power outage information table from the power supply command system; The operation and maintenance lines and branch lines are mapped to specific operation and maintenance power supply stations and their geographical locations to generate a line operation and maintenance relationship mapping table; Obtain real-time weather data for each county and district in a certain region; The fault information data and weather information data are merged and mapped to specific operation and maintenance power supply stations to be matched into the same data table; wherein, the fault information data includes trip information table, fault outage information table and single-station area power outage information table; Step S2 includes: The merged fault data information is broken down into several groups of small morphemes; The disassembled groups of small morphemes are organized and sorted according to the normal language order to generate fault log records; The generated fault log records are classified according to the scheduling jurisdiction to obtain the logs for each county; Step S3 includes: Generate a load loss table for each county, a fault count table for each county, a cumulative power outage duration table for each county, and a power outage duration table for each piece of equipment, and arrange them in descending order; The fault information data is categorized by county and station to generate fault logs for each county, load loss tables for each county and station, fault count tables for each station, cumulative power outage duration tables for each station, and power outage duration tables for each piece of equipment. The corresponding tables are generated by automatically filtering outage types through a robotic process. Present the generated table in a visual format; Step S4 includes: Extract data that the dispatcher has not yet had time to analyze, generate fault text, and notify the corresponding line's operation and maintenance management personnel; The system automatically publishes relevant information to the cloud, sets a certain time interval for publication, and overwrites the previously published information with the information published this time.
9. The intelligent power dispatching method according to claim 8, characterized in that: In step S1, a function is used to determine whether the string of the name of the line and branch line under maintenance starts with another given substring. If the result is yes, the line and branch line under maintenance are mapped to the specific power supply station and county under maintenance.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent power dispatching method as described in any one of claims 8 to 9.
Citation Information
Patent Citations
Intelligent power distribution network event handling method based on robot process automation
CN113890008A
Power grid dispatching-based operation and maintenance method
WO2019233047A1
