Power grid fault identification system based on big data

Abstract

The invention discloses a power grid fault identification system based on big data. The system comprises a data acquisition module used for acquiring real-time operation data in power grid operation; the data storage module stores real-time operation data; the data processing module preprocesses the real-time operation data; the fault identification module is used for inputting the real-time operation data into a fault identification model and identifying a fault type; the fault analysis module compares the voltage phasor difference and the current phasor difference of different PMU nodes, calculates the fault position and evaluates the fault involved range when the fault occurs; the fault processing scheme generation module is used for generating a fault processing scheme; the alarm and processing module is used for sending fault information to operation and maintenance personnel; and the visualization module is used for displaying the fault type, the fault factor and the fault related range when the fault occurs, and providing an interactive operation interface for operation and maintenance personnel. The fault processing speed is increased by analyzing the fault information, the possibility of human errors is reduced, and the processing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to a power grid fault identification system based on big data. Background Art

[0002] With the continuous growth of electricity demand in modern society, the operation and management of power grids are facing huge challenges, and the complexity of power grids is also increasing. Among them, the power system not only includes power generation, transmission, and distribution, but also involves a large number of intelligent devices and sensors, which generate massive amounts of data, which are of great value in fault detection and maintenance management. However, in the field of power grid fault identification, there are still problems such as insufficient data processing capabilities and low accuracy of model identification fault information. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides a power grid fault identification system based on big data.

[0004] The power grid fault identification system based on big data includes the following:

[0005] Data acquisition module: used to collect real-time operation data of the power grid, including current, voltage, power, phase and frequency;

[0006] Data storage module: used to store the real-time operation data of the data acquisition module;

[0007] Data processing module: used to pre-process real-time operation data, including data cleaning, format conversion and feature extraction;

[0008] Fault identification module: used to obtain historical fault operation data, train the historical fault operation data through machine learning algorithms, build a fault identification model, input the pre-processed real-time operation data into the fault identification model, and identify the fault type;

[0009] Fault analysis module: The voltage and current phasors at different locations in the power grid are collected through PMU equipment. The fault location is calculated by comparing the voltage and current phasor differences of different PMU nodes and the fluctuation of the operating data when the fault occurs. The fault type and location are combined with the power grid topology and load distribution to evaluate the scope of the fault when the fault occurs.

[0010] Fault handling solution generation module: used to match the fault type, fault location and fault scope with the fault handling solution rule base to generate a fault handling solution;

[0011] Alarm and processing module: used to send fault type, fault location, fault scope and fault handling plan to operation and maintenance personnel;

[0012] Visualization module: used to display the fault type, fault factor and fault scope when a fault occurs, and provide an interactive operation interface for operation and maintenance personnel.

[0013] Preferably, the data acquisition module includes

[0014] Equipment collection unit: used to collect real-time operation data of the power grid through current sensors, voltage sensors, power measurement equipment, phase angle meters and frequency meters;

[0015] Time synchronization unit: used to mark the timestamp of real-time running data;

[0016] Data communication unit: used to transmit the marked real-time operation data to the data storage module.

[0017] Preferably, the data storage module comprises:

[0018] Distributed storage unit: uses a distributed database to store real-time operation data;

[0019] Data organization unit: used to organize and index the stored real-time operation data;

[0020] Data security unit: encrypts and backs up real-time operation data, and sets access rights through the permission management mechanism;

[0021] Data access unit: used to provide a query window for other modules or users to access and retrieve data.

[0022] Preferably, the data processing module includes

[0023] Data cleaning unit: used to remove incomplete, erroneous or duplicate data from real-time operation data;

[0024] Format conversion unit: converts real-time operation data from different devices and sensors into a standardized format;

[0025] Feature extraction unit: extracts key feature values ​​through big data analysis methods, including abnormal voltage fluctuation amplitude, abnormal current fluctuation amplitude, abnormal frequency fluctuation amplitude and power imbalance.

[0026] Preferably, the fault identification module includes:

[0027] Historical fault operation data acquisition unit: used to acquire historical fault operation data;

[0028] Fault identification model building unit: Based on historical fault operation data, a fault identification model is built using machine learning algorithms, including decision trees, support vector machines, and neural networks;

[0029] Fault detection unit: inputs the pre-processed real-time operation data into the fault identification model to identify the fault types including short circuit, overload and ground fault;

[0030] Model optimization unit: continuously collects real-time operation data and optimizes fault identification models.

[0031] Preferably, the fault analysis module includes:

[0032] Phase measurement unit: used for PMU to collect voltage and current phases at different locations in real time;

[0033] Phase comparison unit: detects areas of abnormal fluctuations in the power grid by comparing the voltage phase difference and current phase difference of different PMU nodes;

[0034] Fault location calculation unit: combines the fluctuations of the operation data of each node when the fault occurs to calculate the specific location of the fault;

[0035] Fault scope assessment unit: According to the fault location and the grid topology, the connection relationship between the nodes and lines adjacent to the fault location is determined, and the fault scope is assessed based on the connection relationship and the operating status of the faulty node and its adjacent nodes.

[0036] Preferably, the fault handling solution generating module includes:

[0037] Data acquisition unit: used to obtain historical fault cases and historical fault handling solutions;

[0038] Fault handling solution rule base building unit: used to build a fault handling solution rule base based on historical fault cases and historical fault handling solutions;

[0039] Fault handling solution generation unit: used to match the fault type, fault location and fault scope with the fault handling solution rule base to generate a fault handling solution.

[0040] Preferably, the alarm and processing module includes:

[0041] Early warning unit: used to issue early warnings to alert operation and maintenance personnel;

[0042] Information sending unit: used to send the fault type, fault location, fault scope and fault handling plan to the operation and maintenance personnel;

[0043] Emergency control unit: used to link the power control subunit and automatically execute preset emergency control measures, including cutting off the fault line and activating the backup power supply;

[0044] Alarm log unit: used to record detailed information of fault alarms, including fault type, fault occurrence time, fault location and fault scope.

[0045] Preferably, the visualization module includes:

[0046] Fault status display unit: used to display the fault location, fault type and fault scope;

[0047] Real-time status monitoring unit: used to display the operating status of each device in the power grid in real time;

[0048] Human-computer interaction unit: used to provide an interactive operation interface, where users can manually control the data acquisition module, data storage module, data processing module, fault identification module, fault analysis module and alarm and processing module.

[0049] The invention discloses a power grid fault identification system based on big data, which has the following beneficial effects: through real-time data collection and processing, abnormal conditions in the power grid can be quickly detected, and operation and maintenance personnel can be notified in time, which greatly shortens the time from the occurrence of the fault to the fault processing, and improves the stability and reliability of the power grid; by using the data collected by the PMU device, combined with the fault analysis module, the location of the fault can be accurately determined, which helps the operation and maintenance team to quickly arrive at the scene for repair and reduce the power outage time; by constructing a fault identification model, various types of faults can be effectively identified, and even the fault location can be accurately calculated, which is of great significance for narrowing the fault search range and accelerating the maintenance process, and improves the accuracy of fault diagnosis; the fault processing solution generation module can automatically match the best processing solution according to the specific situation of the fault, which not only speeds up the speed of fault processing, but also reduces the possibility of human errors and improves processing efficiency; the alarm and processing module and the visualization module provide clear operation guidance and intuitive information display for the operation and maintenance personnel, making the operation and maintenance work more efficient and orderly, and also facilitating the supervision and evaluation of the fault processing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 Module block diagram of the power grid fault identification system based on big data provided by the present invention

[0052] Figure 2 A unit block diagram of the data acquisition module provided by the present invention;

[0053] Figure 3 A unit block diagram of a data storage module provided by the present invention;

[0054] Figure 4 Unit block diagram of the data processing module provided by the invention;

[0055] Figure 5 Unit block diagram of the fault identification module provided by the invention;

[0056] Figure 6 Unit block diagram of the fault analysis module provided by the invention;

[0057] Figure 7 A unit block diagram of a fault handling solution generation module provided by the invention;

[0058] Figure 8 Unit block diagram of the alarm and processing module provided by the invention;

[0059] Fig. 9 A unit block diagram of the visualization module provided by the invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are 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.

[0061] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0062] refer to Figure 1 The power grid fault identification system based on big data provided by the present invention includes the following:

[0063] Data acquisition module 11: used to collect real-time operation data of the power grid, including current, voltage, power, phase and frequency;

[0064] Data storage module 12: used to store real-time operation data of data acquisition module 11;

[0065] Data processing module 13: used for preprocessing real-time operation data, including data cleaning, format conversion and feature extraction;

[0066] Fault identification module 14: used to obtain historical fault data, train the historical fault data through machine learning algorithms, build a fault identification model, input the pre-processed real-time operation data into the fault identification model, and identify the fault type;

[0067] Fault analysis module 15: collects voltage phasors and current phasors at different locations in the power grid through PMU equipment, calculates the fault location by comparing the voltage phasor differences and current phasor differences of different PMU nodes, combined with the fluctuation of operating data when the fault occurs, and evaluates the scope of the fault according to the fault type and fault location, combined with the power grid topology and load distribution;

[0068] Fault handling solution generation module 16: used to match the fault type, fault location and fault scope with the fault handling solution rule base to generate a fault handling solution;

[0069] Alarm and processing module 17: used to send the fault type, fault location, fault scope and fault handling plan to the operation and maintenance personnel;

[0070] Visualization module 18: used to display the fault type, fault factor and fault scope when a fault occurs, and provide an interactive operation interface for operation and maintenance personnel.

[0071] The present invention provides a power grid fault identification system based on big data. Through real-time data collection and processing, abnormal conditions in the power grid can be quickly detected, and operation and maintenance personnel can be notified in time, which greatly shortens the time from fault occurrence to fault handling and improves the stability and reliability of the power grid. The data collected by the PMU device is combined with a fault analysis module to accurately determine the location of the fault, which helps the operation and maintenance team to quickly arrive at the site for repair and reduce power outage time. By constructing a fault identification model, various types of faults can be effectively identified, and even the fault location can be accurately calculated, which is of great significance for narrowing the fault search range and accelerating the maintenance process, and improves the accuracy of fault diagnosis. The fault handling solution generation module can automatically match the best handling solution according to the specific situation of the fault, which not only speeds up the speed of fault handling, but also reduces the possibility of human error and improves the processing efficiency. The alarm and processing module and the visualization module provide clear operation guidance and intuitive information display for the operation and maintenance personnel, making the operation and maintenance work more efficient and orderly, and also facilitating the supervision and evaluation of the fault handling process.

[0072] refer to Figure 2 In a preferred embodiment, the data acquisition module 11 includes:

[0073] Equipment collection unit 111: used to collect real-time operation data of the power grid through current sensors, voltage sensors, power measurement equipment, phase angle measuring instruments and frequency meters;

[0074] Time synchronization unit 112: used to mark the timestamp of real-time operation data. Ensure that all collected data have consistent timestamps. Especially in phasor measurement, time synchronization is the key to ensure data accuracy and consistency;

[0075] Data communication unit 113: used to transmit the marked real-time operation data to the data storage module through a communication network including an optical fiber network and wireless transmission.

[0076] refer to Figure 3 In a preferred embodiment, the data storage module 12 includes

[0077] Distributed storage unit 121: uses a distributed database to store real-time operation data to ensure efficient access and management of massive data in the power system.

[0078] Data organization unit 122: used to organize and index the stored real-time operation data;

[0079] Data security unit 123: encrypts and backs up real-time operation data, and sets access rights through the authority management mechanism; ensures the security and integrity of data during transmission and storage;

[0080] Data access unit 124: used to provide a query window for other modules or users to access and retrieve data.

[0081] refer to Figure 4 In a preferred embodiment, the data processing module 13 includes

[0082] Data cleaning unit 131: used to remove incomplete, erroneous or duplicate data in real-time operation data; to ensure the quality of input data.

[0083] Format conversion unit 132: converts the real-time operation data format from different devices and sensors into a standardized format; ensures the consistency of subsequent algorithms.

[0084] Feature extraction unit 133: extracts key feature values, including abnormal voltage fluctuation amplitude, abnormal current fluctuation amplitude, abnormal frequency fluctuation amplitude and power imbalance, through big data analysis method; and provides accurate input data for the fault identification module.

[0085] refer to Figure 5 In a preferred embodiment, the fault identification module 14 includes

[0086] Historical fault operation data acquisition unit 141: used to acquire historical fault operation data;

[0087] Fault identification model building unit 142: based on the historical fault data of the power grid, a fault identification model is built using machine learning algorithms, including decision trees, support vector machines and neural networks;

[0088] Fault detection unit 143: inputs real-time operation data into a fault identification model to identify fault types including short circuit, overload and ground fault;

[0089] Model optimization unit 144: continuously collects real-time operation data, optimizes the fault identification model, and improves the identification accuracy and response speed of the model.

[0090] refer to Figure 6 In a preferred embodiment, the fault analysis module 15 includes

[0091] Phase measurement unit 151: collects voltage phase information and current phase information of different positions in real time through PMU;

[0092] Phase comparison unit 152: detects abnormal fluctuation areas in the power grid by comparing voltage phase difference and current phase difference of different PMU nodes;

[0093] Specifically, under normal operating conditions, the phasor differences between different nodes are limited. If a section of the power grid fails, the phasor differences will increase significantly, especially in the case of short circuit, grounding and other faults, the changes in current phasors and voltage phasors will be very drastic, and the fault area can be identified by phasor differences; if the voltage phasor of a node suddenly decreases, while the phasors of adjacent nodes remain normal, there may be a short circuit or grounding fault in the area. A sudden increase in the current phasor of a node may indicate a sharp increase in load or a line fault.

[0094] Fault location calculation unit 153: calculates the specific location of the fault according to the area of ​​abnormal fluctuation and the fluctuation of the operation data of each node when the fault occurs;

[0095] Specifically, PMU equipment is installed at key nodes of the transmission line, including substations and access points. The PMU equipment collects voltage and current data hundreds of times per second to capture electrical fluctuations at the moment of fault occurrence. The traveling wave signal is extracted from the collected data through signal processing methods such as fast Fourier transform (FFT), and the rising and falling edges of the signal are analyzed to identify the characteristics of the traveling wave. The changes in voltage and current signals are detected to identify the starting point of the traveling wave, and the propagation time and amplitude change of the waveform are calculated. The propagation speed of the traveling wave is determined by calculating the time difference between the traveling wave reaching different PMU nodes. At this time, the timestamp when the fault occurs needs to be accurately recorded. Based on the known traveling wave propagation speed and time difference, the distance of the fault from each PMU device can be calculated. Using triangulation or other positioning algorithms, the exact location of the fault is calculated based on the time difference and propagation distance of each node, which usually involves data from multiple PMU nodes.

[0096] Fault scope assessment unit 154: determines the connection relationship between nodes and lines adjacent to the fault location according to the fault location and the grid topology, and assesses the scope of the fault, including the affected lines and substations, according to the connection relationship and the operating status of the faulty node and its adjacent nodes.

[0097] Specifically, when a transmission line fails, it is possible to identify which substations, transmission lines, and loads may be affected based on the topology.

[0098] refer to Figure 7 In a preferred embodiment, the fault handling solution generation module 16 includes:

[0099] Data acquisition unit 161: used to acquire historical fault cases and historical fault handling solutions;

[0100] A fault handling solution rule base establishing unit 162 is used to establish a fault handling solution rule base according to historical fault cases and historical fault handling solutions;

[0101] The fault handling solution generating unit 163 is used to generate a fault handling solution by matching the fault type, fault location and fault scope with a preset fault handling solution rule base.

[0102] refer to Figure 8 In a preferred embodiment, the alarm and processing module 17 includes

[0103] Early warning unit 171: used to issue early warnings to remind operation and maintenance personnel;

[0104] Information sending unit 172: used to send the fault type, fault location, fault scope and fault handling solution to the operation and maintenance personnel;

[0105] Emergency control unit 173: Linked with the power control subunit, when the fault is serious, it executes the preset emergency control measures, including cutting off the fault line and activating the backup power supply;

[0106] The alarm log unit 174 is used to record detailed information of the fault alarm, including the fault type, fault occurrence time, fault location and fault scope.

[0107] refer to Fig. 9 In a preferred embodiment, the visualization module 18 comprises:

[0108] Fault status display unit 181: used to display the fault location, fault type and fault scope, so as to help operation and maintenance personnel to intuitively understand the fault status.

[0109] Real-time status monitoring unit 182: used to display the operating status of each device in the power grid in real time;

[0110] Human-computer interaction unit 183: used to provide an interactive operation interface, and the user can manually control the data acquisition module, data storage module, data processing module, fault identification module, fault analysis module and alarm and processing module.

Claims

1. The power grid fault identification system based on big data is characterized by: These include: Data acquisition module: used to collect real-time operation data of the power grid, including current, voltage, power, phase and frequency; Data storage module: used to store the real-time operation data of the data acquisition module; Data processing module: used for preprocessing the real-time operation data, including data cleaning, format conversion and feature extraction; Fault identification module: used to obtain historical fault operation data, train the historical fault operation data through machine learning algorithms, build a fault identification model, input the pre-processed real-time operation data into the fault identification model, and identify the fault type; Fault analysis module: used for PMU equipment to collect voltage phasors and current phasors at different locations in the power grid, and calculate the fault location by comparing the voltage phasor differences and current phasor differences of different PMU nodes, combined with the fluctuation of operating data when the fault occurs, and evaluate the scope of the fault when the fault occurs according to the fault type and the fault location, combined with the power grid topology and load distribution; A fault handling solution generation module is used to match the fault type, the fault location and the scope of the fault with the fault handling solution rule base to generate a fault handling solution; Alarm and processing module: used to send the fault type, fault location, fault scope and fault processing plan to the operation and maintenance personnel; Visualization module: used to display the fault type, fault factor and fault scope when a fault occurs, and provide an interactive operation interface for operation and maintenance personnel.

2. The power grid fault identification system based on big data according to claim 1 is characterized in that: The data acquisition module comprises: Equipment collection unit: used to collect real-time operation data of the power grid through current sensors, voltage sensors, power measurement equipment, phase angle meters and frequency meters; Time synchronization unit: used to mark the timestamp of the real-time operation data; Data communication unit: used to transmit the marked real-time operation data to the data storage module.

3. The power grid fault identification system based on big data according to claim 1 is characterized in that: The data storage module comprises: Distributed storage unit: using a distributed database to store the real-time operation data; Data organization unit: used to organize and index the stored real-time operation data; Data security unit: encrypting and backing up the real-time operation data, and setting access rights through a rights management mechanism; Data access unit: used to provide a query window for other modules or users to access and retrieve data.

4. The power grid fault identification system based on big data according to claim 1 is characterized in that: The data processing module comprises: Data cleaning unit: used to remove incomplete, erroneous or duplicate data in the real-time operation data; Format conversion unit: converts real-time operation data from different devices and sensors into a standardized format; Feature extraction unit: extracts key feature values ​​through big data analysis methods, including abnormal voltage fluctuation amplitude, abnormal current fluctuation amplitude, abnormal frequency fluctuation amplitude and power imbalance.

5. The power grid fault identification system based on big data according to claim 1 is characterized in that: The fault identification module comprises: Historical fault operation data acquisition unit: used to acquire historical fault operation data; A fault identification model building unit: based on the historical fault operation data, a machine learning algorithm including a decision tree, a support vector machine and a neural network is used to build a fault identification model; Fault detection unit: inputs the preprocessed real-time operation data into the fault identification model, and identifies the fault types including short circuit, overload and ground fault; Model optimization unit: continuously collects real-time operation data and optimizes the fault identification model.

6. The power grid fault identification system based on big data according to claim 1 is characterized in that: The fault analysis module comprises: Phase measurement unit: used for PMU to collect voltage and current phases at different locations in real time; Phase comparison unit: detects areas of abnormal fluctuations in the power grid by comparing the voltage phase difference and current phase difference of different PMU nodes; Fault location calculation unit: combines the fluctuations of the operation data of each node when the fault occurs to calculate the specific location of the fault; Fault scope assessment unit: According to the fault location and in combination with the grid topology, determine the connection relationship between the nodes and lines adjacent to the fault location, and assess the scope of the fault according to the connection relationship and the operating status of the faulty node and its adjacent nodes.

7. The power grid fault identification system based on big data according to claim 1 is characterized in that: The fault handling solution generation module includes: Data acquisition unit: used to obtain historical fault cases and historical fault handling solutions; A fault handling solution rule base establishing unit: used to establish a fault handling solution rule base according to the historical fault cases and the historical fault handling solutions; A fault handling solution generating unit is used to generate a fault handling solution by matching the fault type, the fault location and the scope of the fault with the fault handling solution rule base.

8. The power grid fault identification system based on big data according to claim 1 is characterized in that: The alarm and processing module includes: Early warning unit: used to issue early warnings to alert operation and maintenance personnel; An information sending unit is used to send the fault type, the fault location, the scope of the fault and the fault handling solution to the operation and maintenance personnel; Emergency control unit: used to link the power control subunit and automatically execute preset emergency control measures, including cutting off the fault line and activating the backup power supply; Alarm log unit: used to record detailed information of fault alarms, including fault type, fault occurrence time, fault location and fault scope.

9. The power grid fault identification system based on big data according to claim 1 is characterized in that: The visualization module comprises: Fault status display unit: used to display the fault location, fault type and fault scope; Real-time status monitoring unit: used to display the operating status of each device in the power grid in real time; Human-computer interaction unit: used to provide an interactive operation interface, and the user can manually control the data acquisition module, the data storage module, the data processing module, the fault identification module, the fault analysis module and the alarm and processing module.

Images