CN116822334A - Visual power grid model fault response method and system - Google Patents
Visual power grid model fault response method and system Download PDFInfo
- Publication number
- CN116822334A CN116822334A CN202310627217.4A CN202310627217A CN116822334A CN 116822334 A CN116822334 A CN 116822334A CN 202310627217 A CN202310627217 A CN 202310627217A CN 116822334 A CN116822334 A CN 116822334A
- Authority
- CN
- China
- Prior art keywords
- fault
- graph
- power grid
- data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000004044 response Effects 0.000 title claims abstract description 46
- 230000000007 visual effect Effects 0.000 title claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000013480 data collection Methods 0.000 claims abstract description 15
- 238000003745 diagnosis Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000012423 maintenance Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000008439 repair process Effects 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 7
- 230000007246 mechanism Effects 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000000547 structure data Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000032683 aging Effects 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 238000002347 injection Methods 0.000 claims description 3
- 239000007924 injection Substances 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 claims description 3
- 238000010008 shearing Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 239000000243 solution Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The application discloses a visual power grid model fault response method which comprises the following steps: data collection and pretreatment; constructing a power grid topological graph, and designing a training graph neural network HGAT model; performing fault location response and diagnosis repair; and visually displaying fault positioning and diagnosis results, and providing alarm and notification functions. The visual power grid model fault response method and the system provided by the application automatically learn and understand the relationship between the topological structure of the power grid and the equipment, and improve the accuracy and efficiency of fault positioning. After the fault is identified, the system can automatically perform fault processing, and the self-repairing capability of the power grid is enhanced. Through visual display, operation and maintenance personnel can intuitively know the state and potential faults of the power grid, and optimize the operation and maintenance management process. The system can accurately position and provide suggestions for manually handling faults, improves the continuity and stability of power supply, and improves the service quality of a power grid. The method has good expansibility and adaptability, and can be suitable for power grids of various scales and types.
Description
Technical Field
The application relates to the technical field of intelligent management of power systems, in particular to a visual power grid model fault response method and system.
Background
The visual power grid model fault response method and the visual power grid model fault response system are key technologies in the operation and maintenance of the power system, and aim to help operation and maintenance personnel to discover and process faults in the power system in time through visual display of fault positioning and diagnosis results. However, the conventional method has some drawbacks in facing a complicated power system and monitoring data in real time, and the emerging technology has advantages and merits of breaking through the conventional limitations.
Modeling techniques in the traditional method, such as tidal current calculation, short circuit analysis and dynamic stability analysis, generally need to manually perform parameter setting and model construction, so that modeling is complex, time and labor are consumed, fault positioning and diagnosis depend on a static power grid model, and real-time requirements are difficult to meet. In the context of large-scale power systems and real-time monitoring of data, the real-time nature of conventional methods is limited. The fault location accuracy of the traditional method is limited by the accuracy of the model and real-time monitoring data. In complex power systems, errors often exist in fault location, resulting in difficulties for operation and maintenance personnel to accurately locate and handle the fault.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present application has been made in view of the above-described problems.
Therefore, the technical problems solved by the application are as follows: how to monitor the data in real time to accurately locate and diagnose the faults, and realize quick response through the real-time data acquisition and fusion technology, thereby improving the efficiency and accuracy of the visual power grid model fault response.
In order to solve the technical problems, the application provides the following technical scheme: a visual grid model fault response method, comprising:
data collection and pretreatment;
constructing a power grid topological graph, and designing a training graph neural network HGAT model;
performing fault location response and diagnosis repair;
and visually displaying fault positioning and diagnosis results, and providing alarm and notification functions.
As a preferable scheme of the visual power grid model fault response method, the application comprises the following steps:
the data collection includes: device state data, electrical parameter data, meteorological data, topology data, fault history data, and device attribute data.
As a preferable scheme of the visual power grid model fault response method, the application comprises the following steps:
data cleaning: processing the missing value, the repeated value and the abnormal value;
data conversion: normalization, logarithmic transformation and One-Hot coding;
characteristic engineering: performing feature selection, feature extraction, feature construction and feature combination on the data;
data enhancement: rotating, scaling, shearing and noise injection are carried out on the data, and additional training samples are generated;
processing unbalanced data: processing by using an oversampling method and a undersampling method;
data fusion: information from different sources is integrated to produce a comprehensive view.
As a preferable scheme of the visual power grid model fault response method, the application comprises the following steps:
the construction of the power grid topological graph comprises the following steps:
topological structure data of the power grid, including connection relation between devices and line length;
adding nodes and edges, and distributing attributes for the nodes and the edges;
automatically learning the topology structure of the power grid from the original data by using a deep learning method;
automatically optimizing the topology design of the power grid by using a reinforcement learning method;
after constructing the topological graph, carrying out various graph theory analyses, calculating the degree of the node and searching the connected component of the graph;
the calculating the degree of the node and searching the connected component of the graph comprises the following steps:
when in an undirected graph, the degree of a node is the number of edges connecting the node;
respectively calculating the input degree and the output degree of the nodes in the directed graph;
when in an undirected graph, the connected component refers to one sub-graph in the graph, any two nodes in the sub-graph are connected by a path, and the sub-graph is not part of any larger sub-graph;
when a strong connected component is found in the directed graph, a bidirectional path exists between any two nodes in the subgraph.
As a preferable scheme of the visual power grid model fault response method, the application comprises the following steps:
the design training diagram neural network HGAT model comprises:
using PyTorch and PyTorch-geometry libraries to implement HGAT models;
inputting power grid topological graph information and preprocessing data information, and performing HGAT model training;
the HGAT model captures the relationship between the topological structure of the power grid and the equipment through the graphs of the object level and the triplet level, and strengthens the relationship through a graph attention mechanism;
for the object level graph, a specific calculation formula of the graph annotation force mechanism is as follows:
wherein alpha is ij Attention to be sides i to jForce coefficient, f is a scoring function of the attention mechanism, h i 、h j And is h k The feature vectors of the nodes i, j and k, W is a weight matrix capable of learning, and N (i) is a neighbor node of the node i;
for the triplet level map, the calculation formula of the attention mechanism is as follows:
wherein beta is ijk Is the attention coefficient of the triplet i, j, k, g is the scoring function of the attention mechanism, h m 、h n For the eigenvectors of nodes m, n, W is a learnable weight matrix, R (i) is a set of all triples related to node i;
the object level and the triplet level graphs are processed through a graph attention network that gives different edges in the graph different weights, focusing the model on more important relationships.
As a preferable scheme of the visual power grid model fault response method, the application comprises the following steps:
the fault location response and diagnosis repair are specifically as follows:
in the HGAT model, the outputs of the object level graph and the triplet level graph are fused to provide a comprehensive state representation of the power grid device, and the fused representation is sent to a classifier for detecting the fault location and type of the power grid;
when the fault type is an automatic switch fault, detecting the fault position and signal of the switch through a fault indicator and a sensor, automatically switching the power grid to a standby line, and ensuring the continuity of power supply;
when the fault type is voltage abnormality, monitoring voltage abnormality through a voltage sensor, automatically adjusting parameters of power distribution equipment, and ensuring voltage temperature;
when the fault type is overload fault, detecting current abnormality through a current sensor, and automatically starting standby equipment and adjusting power grid load distribution;
when the fault type is power grid damage or aging, detecting and evaluating equipment conditions through a power grid health condition monitoring system, and early warning and repairing and replacing in advance.
As a preferable scheme of the visual power grid model fault response method, the application comprises the following steps:
the visual presentation, comprising:
the output of the HGAT is displayed on the power dispatching platform in a graphic form, the HGAT model monitors the repair process in real time and updates the state of the power grid, if the fault repair is successful, the model outputs the normal state of the power grid, otherwise, new fault positioning and processing suggestions are provided, and an alarm is given to inform maintenance personnel of performing the fault repair.
A visual grid model fault response system comprising:
and a data collection module: is responsible for collecting data and preprocessing the data;
the construction module comprises: receiving data of the data collection module, and constructing a power grid topological graph according to the preprocessed data;
the graph neural network module: designing and training the graph neural network model, and learning the relationship between the topological structure of the power grid and the equipment;
fault location response module: receiving the output of the graph neural network module, fusing the output of the object level graph and the output of the triplet level graph, providing a comprehensive state representation of power grid equipment, positioning power grid faults and responding to the faults, and diagnosing and repairing the faults;
and a visualization module: receiving the output of the fault location response module, and visually displaying fault location and diagnosis results; the module also provides alarm and notification functions, when the system detects a fault exceeding a preset threshold value, the system automatically triggers an alarm to notify operation and maintenance personnel to process in time;
the data collection module, the construction module, the graph neural network module, the fault location response module and the visualization module are sequentially connected.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method as described above.
The application has the beneficial effects that: the visual power grid model fault response method and the system provided by the application automatically learn and understand the relationship between the topological structure of the power grid and the equipment, and improve the accuracy and efficiency of fault positioning. After the fault is identified, the system can automatically perform fault processing, and the self-repairing capability of the power grid is enhanced. Through visual display, operation and maintenance personnel can intuitively know the state and potential faults of the power grid, and optimize the operation and maintenance management process. The system can accurately position and provide suggestions for manually handling faults, improves the continuity and stability of power supply, and improves the service quality of a power grid. The method has good expansibility and adaptability, and can be suitable for power grids of various scales and types.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is an overall flow chart of a visual grid model fault response method according to a first embodiment of the present application;
FIG. 2 is a block diagram of a visual power grid model fault response system according to a second embodiment of the present application;
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present application can be understood in detail, a more particular description of the application, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present application have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present application, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, for one embodiment of the present application, a method for visualizing a fault response of a power grid model is provided, including:
s1: data collection and pretreatment;
the equipment state data, the electrical parameter data, the meteorological data, the topological structure data, the fault history data and the equipment attribute data, and the collected data are subjected to the following steps:
data cleaning: processing the missing value, the repeated value and the abnormal value;
data conversion: normalization, logarithmic transformation and One-Hot coding;
characteristic engineering: performing feature selection, feature extraction, feature construction and feature combination on the data;
data enhancement: rotating, scaling, shearing and noise injection are carried out on the data, and additional training samples are generated;
processing unbalanced data: processing by using an oversampling method and a undersampling method;
further, in the case of class imbalance, the model may be biased toward a majority class, which may result in poor performance of the model in predicting a minority class. The use of over-sampling and under-sampling methods can help balance the data.
Data fusion: information from different sources is integrated to produce a comprehensive view.
It should be noted that, when data fusion is performed, consistency and compatibility of data are ensured.
S2: constructing a power grid topological graph, and designing a training graph neural network HGAT model;
topological structure data of the power grid, including connection relation between devices and line length;
adding nodes and edges, and distributing attributes for the nodes and the edges;
automatically learning the topology structure of the power grid from the original data by using a deep learning method;
automatically optimizing the topology design of the power grid by using a reinforcement learning method;
after constructing the topological graph, carrying out various graph theory analyses, calculating the degree of the node and searching the connected component of the graph;
the calculating the degree of the node and searching the connected component of the graph comprises the following steps:
when in an undirected graph, the degree of a node is the number of edges connecting the node;
respectively calculating the input degree and the output degree of the nodes in the directed graph;
when in an undirected graph, the connected component refers to one sub-graph in the graph, any two nodes in the sub-graph are connected by a path, and the sub-graph is not part of any larger sub-graph;
when a strong connected component is found in the directed graph, a bidirectional path exists between any two nodes in the subgraph.
Using PyTorch and PyTorch-geometry libraries to implement HGAT models;
inputting power grid topological graph information and preprocessing data information, and performing HGAT model training;
the HGAT model captures the relationship between the topological structure of the power grid and the equipment through the graphs of the object level and the triplet level, and strengthens the relationship through a graph attention mechanism;
for the object level graph, a specific calculation formula of the graph annotation force mechanism is as follows:
wherein alpha is ij Is the attention coefficient of edges i to j, f is the scoring function of the attention mechanism, h i 、h j And is h k The feature vectors of the nodes i, j and k, W is a weight matrix capable of learning, and N (i) is a neighbor node of the node i;
for the triplet level map, the calculation formula of the attention mechanism is as follows:
wherein beta is ijk Is the attention coefficient of the triplet i, j, k, g is the scoring function of the attention mechanism, h m 、h n For the eigenvectors of nodes m, n, W is a learnable weight matrix, R (i) is a set of all triples related to node i;
the object level and the triplet level graphs are processed through a graph attention network that gives different edges in the graph different weights, focusing the model on more important relationships.
It should be noted that, as the state of the power grid changes, the model needs to be updated and maintained regularly. A suitable model update strategy (e.g., periodic update, online learning, sliding window update, triggered update, etc.) is designed to ensure that the model always accurately reflects the actual state of the grid. .
S3: performing fault location response and diagnosis repair;
in the HGAT model, the outputs of the object level graph and the triplet level graph are fused to provide a comprehensive state representation of the power grid device, and the fused representation is sent to a classifier for detecting the fault location and type of the power grid;
when the fault type is an automatic switch fault, detecting the fault position and signal of the switch through a fault indicator and a sensor, automatically switching the power grid to a standby line, and ensuring the continuity of power supply;
when the fault type is voltage abnormality, monitoring voltage abnormality through a voltage sensor, automatically adjusting parameters of power distribution equipment, and ensuring voltage temperature;
when the fault type is overload fault, detecting current abnormality through a current sensor, and automatically starting standby equipment and adjusting power grid load distribution;
when the fault type is power grid damage or aging, detecting and evaluating equipment conditions through a power grid health condition monitoring system, and early warning and repairing and replacing in advance.
Further, after repairing the fault, continuous monitoring needs to be performed on the running condition of the power grid to ensure that the fault is completely solved and the power grid is restored to a normal state. Meanwhile, an in-depth analysis of the cause of the occurrence of the fault is required to prevent the occurrence of a similar fault again.
It should be noted that all fault events and repair operations should be recorded in detail and data analyzed, which can help to improve fault response flow and improve operational stability and safety of the grid.
S4: and visually displaying fault positioning and diagnosis results, and providing alarm and notification functions.
The output of the HGAT is displayed on the power dispatching platform in a graph form, so that operation and maintenance personnel can intuitively see the state and potential faults of the power grid;
the HGAT model monitors the repairing process in real time and updates the state of the power grid, if the fault repairing is successful, the model outputs the normal state of the power grid, otherwise, new fault positioning and processing suggestions are provided, and a maintainer is warned and informed to carry out the fault repairing.
In this embodiment, a visual power grid model fault response system is further included:
and a data collection module: is responsible for collecting data and preprocessing the data;
the construction module comprises: receiving data of the data collection module, and constructing a power grid topological graph according to the preprocessed data;
the graph neural network module: designing and training the graph neural network model, and learning the relationship between the topological structure of the power grid and the equipment;
fault location response module: receiving the output of the graph neural network module, fusing the output of the object level graph and the output of the triplet level graph, providing a comprehensive state representation of power grid equipment, positioning power grid faults and responding to the faults, and diagnosing and repairing the faults;
and a visualization module: receiving the output of the fault location response module, and visually displaying fault location and diagnosis results; the module also provides alarm and notification functions, when the system detects a fault exceeding a preset threshold value, the system automatically triggers an alarm to notify operation and maintenance personnel to process in time;
the data collection module, the construction module, the graph neural network module, the fault location response module and the visualization module are sequentially connected.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method as described above.
Example 2
In order to verify the beneficial effects of the application, scientific demonstration is carried out through economic benefit calculation and comparison experiments.
First, for the above-described embodiment method, the method is applied to the electric network management in comparison with the conventional method. The comparative results are shown in the following table:
by applying the my application, the fault determination position accuracy and the automatic repair success rate are both remarkably improved, and meanwhile, the time for providing the electric interruption by the network is greatly reduced. More importantly, the HGAT model can provide early warning faults, and precious time is provided for the operation and maintenance of the power system. Moreover, the reaction time of alarming and notifying is also greatly shortened, thereby ensuring the stable operation of the power system.
It should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application may be modified or substituted without departing from the spirit and scope of the technical solution of the present application, which is intended to be covered in the scope of the claims of the present application.
Claims (10)
1. A method for visualizing a fault response of a power grid model, comprising:
data collection and pretreatment;
constructing a power grid topological graph, and designing a training graph neural network HGAT model;
performing fault location response and diagnosis repair;
and visually displaying fault positioning and diagnosis results, and providing alarm and notification functions.
2. The visual grid model fault response method as claimed in claim 1, wherein: the data collection includes: device state data, electrical parameter data, meteorological data, topology data, fault history data, and device attribute data.
3. The visual grid model fault response method as claimed in claim 2, wherein: the pretreatment comprises the following steps:
data cleaning: processing the missing value, the repeated value and the abnormal value;
data conversion: normalization, logarithmic transformation and One-Hot coding;
characteristic engineering: performing feature selection, feature extraction, feature construction and feature combination on the data;
data enhancement: rotating, scaling, shearing and noise injection are carried out on the data, and additional training samples are generated;
processing unbalanced data: processing by using an oversampling method and a undersampling method;
data fusion: information from different sources is integrated to produce a comprehensive view.
4. A method of visualizing a fault response in a power grid model as in claim 3, wherein: the construction of the power grid topological graph comprises the following steps:
topological structure data of the power grid, including connection relation between devices and line length;
adding nodes and edges, and distributing attributes for the nodes and the edges;
automatically learning the topology structure of the power grid from the original data by using a deep learning method;
automatically optimizing the topology design of the power grid by using a reinforcement learning method;
after constructing the topological graph, carrying out various graph theory analyses, calculating the degree of the node and searching the connected component of the graph;
the calculating the degree of the node and searching the connected component of the graph comprises the following steps:
when in an undirected graph, the degree of a node is the number of edges connecting the node;
respectively calculating the input degree and the output degree of the nodes in the directed graph;
when in an undirected graph, the connected component refers to one sub-graph in the graph, any two nodes in the sub-graph are connected by a path, and the sub-graph is not part of any larger sub-graph;
when a strong connected component is found in the directed graph, a bidirectional path exists between any two nodes in the subgraph.
5. The visual grid model fault response method as claimed in claim 4, wherein: the design training diagram neural network HGAT model comprises:
using PyTorch and PyTorch-geometry libraries to implement HGAT models;
inputting power grid topological graph information and preprocessing data information, and performing HGAT model training;
the HGAT model captures the relationship between the topological structure of the power grid and the equipment through the graphs of the object level and the triplet level, and strengthens the relationship through a graph attention mechanism;
for the object level graph, a specific calculation formula of the graph annotation force mechanism is as follows:
wherein alpha is ij Is the attention coefficient of edges i to j, f is the scoring function of the attention mechanism, h i 、h j And is h k The feature vectors of the nodes i, j and k, W is a weight matrix capable of learning, and N (i) is a neighbor node of the node i;
for the triplet level map, the calculation formula of the attention mechanism is as follows:
wherein beta is ijk Is the attention coefficient of the triplet i, j, k, g is the scoring function of the attention mechanism, h m 、h n For the eigenvectors of nodes m, n, W is a learnable weight matrix, R (i) is a set of all triples related to node i;
the object level and the triplet level graphs are processed through a graph attention network that gives different edges in the graph different weights, focusing the model on more important relationships.
6. The visual grid model fault response method as claimed in claim 5, wherein: the fault location response and diagnosis repair are specifically as follows:
in the HGAT model, the outputs of the object level graph and the triplet level graph are fused to provide a comprehensive state representation of the power grid device, and the fused representation is sent to a classifier for detecting the fault location and type of the power grid;
when the fault type is an automatic switch fault, detecting the fault position and signal of the switch through a fault indicator and a sensor, automatically switching the power grid to a standby line, and ensuring the continuity of power supply;
when the fault type is voltage abnormality, monitoring voltage abnormality through a voltage sensor, automatically adjusting parameters of power distribution equipment, and ensuring voltage temperature;
when the fault type is overload fault, detecting current abnormality through a current sensor, and automatically starting standby equipment and adjusting power grid load distribution;
when the fault type is power grid damage or aging, detecting and evaluating equipment conditions through a power grid health condition monitoring system, and early warning and repairing and replacing in advance.
7. The visual grid model fault response method as claimed in claim 6, wherein: the visual presentation, comprising:
the output of the HGAT is displayed on the power dispatching platform in a graphic form, the HGAT model monitors the repair process in real time and updates the state of the power grid, if the fault repair is successful, the model outputs the normal state of the power grid, otherwise, new fault positioning and processing suggestions are provided, and an alarm is given to inform maintenance personnel of performing the fault repair.
8. A visual grid model fault response system, comprising:
and a data collection module: is responsible for collecting data and preprocessing the data;
the construction module comprises: receiving data of the data collection module, and constructing a power grid topological graph according to the preprocessed data;
the graph neural network module: designing and training the graph neural network model, and learning the relationship between the topological structure of the power grid and the equipment;
fault location response module: receiving the output of the graph neural network module, fusing the output of the object level graph and the output of the triplet level graph, providing a comprehensive state representation of power grid equipment, positioning power grid faults and responding to the faults, and diagnosing and repairing the faults;
and a visualization module: receiving the output of the fault location response module, and visually displaying fault location and diagnosis results; the module also provides alarm and notification functions, when the system detects a fault exceeding a preset threshold value, the system automatically triggers an alarm to notify operation and maintenance personnel to process in time;
the data collection module, the construction module, the graph neural network module, the fault location response module and the visualization module are sequentially connected.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310627217.4A CN116822334A (en) | 2023-05-30 | 2023-05-30 | Visual power grid model fault response method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310627217.4A CN116822334A (en) | 2023-05-30 | 2023-05-30 | Visual power grid model fault response method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116822334A true CN116822334A (en) | 2023-09-29 |
Family
ID=88142086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310627217.4A Pending CN116822334A (en) | 2023-05-30 | 2023-05-30 | Visual power grid model fault response method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822334A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454315A (en) * | 2023-12-21 | 2024-01-26 | 国网浙江省电力有限公司宁波供电公司 | Man-machine terminal picture data interaction method and system |
| CN117559445A (en) * | 2024-01-10 | 2024-02-13 | 国网辽宁省电力有限公司经济技术研究院 | Power distribution management method and system based on power flow and stability analysis |
-
2023
- 2023-05-30 CN CN202310627217.4A patent/CN116822334A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454315A (en) * | 2023-12-21 | 2024-01-26 | 国网浙江省电力有限公司宁波供电公司 | Man-machine terminal picture data interaction method and system |
| CN117559445A (en) * | 2024-01-10 | 2024-02-13 | 国网辽宁省电力有限公司经济技术研究院 | Power distribution management method and system based on power flow and stability analysis |
| CN117559445B (en) * | 2024-01-10 | 2024-03-26 | 国网辽宁省电力有限公司经济技术研究院 | Power distribution management method and system based on power flow and stability analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10962999B2 (en) | Microgrid model based automated real time simulation for market based electric power system optimization | |
| US10867087B2 (en) | Systems and methods for real-time DC microgrid power analytics for mission-critical power systems | |
| CN116822334A (en) | Visual power grid model fault response method and system | |
| CN103837796B (en) | The transmission line malfunction visualization report method of a kind of sing on web and GIS and system | |
| EP2697699B1 (en) | Dynamic assessment system for high-voltage electrical components | |
| Chen et al. | A 3D visualized expert system for maintenance and management of existing building facilities using reliability-based method | |
| CN112910089A (en) | Transformer substation secondary equipment fault logic visualization method and system | |
| KR101094195B1 (en) | Power facility management system using two dimensional code and administation server, and method for managing the same | |
| CN112803592B (en) | Intelligent fault early warning method and system suitable for distributed power station | |
| BRPI1100290A2 (en) | Method for detecting behavior in electrical substation equipment | |
| CN104820953A (en) | Power distribution network operation safety assessment and warning system | |
| CN103530708A (en) | Power transmission and distribution equipment hidden danger troubleshooting information management and decision support system | |
| CN111896845A (en) | Power distribution network fault diagnosis method and system based on multi-source information fusion | |
| CN115760073A (en) | Transformer substation equipment maintenance system and method based on BIM model | |
| CN111586188A (en) | Electric energy monitoring system and method | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN213126080U (en) | Equipment remote monitoring and fault early warning system | |
| CN111460027B (en) | Intelligent dynamic monitoring method and system suitable for energy Internet | |
| CN112070400A (en) | Method and device for evaluating security situation of power grid database | |
| CN113095952B (en) | Power grid splitting early warning method and system considering real-time and N-X forecast information | |
| CN115618303A (en) | Dispatching automation monitoring and fault positioning system based on information fusion technology | |
| Liu et al. | Research on online status evaluation technology for main equipment of power transmission and transformation based on digital twin | |
| CN114398947A (en) | Expert system-based power grid fault automatic classification method and system | |
| CN107121616A (en) | A kind of method and apparatus for being used to carry out intelligence instrument fault location | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |