CN117498561A - Power grid abnormal operation state monitoring method based on edge calculation - Google Patents
Power grid abnormal operation state monitoring method based on edge calculation Download PDFInfo
- Publication number
- CN117498561A CN117498561A CN202410004580.5A CN202410004580A CN117498561A CN 117498561 A CN117498561 A CN 117498561A CN 202410004580 A CN202410004580 A CN 202410004580A CN 117498561 A CN117498561 A CN 117498561A
- Authority
- CN
- China
- Prior art keywords
- power distribution
- power
- power grid
- data
- graph
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 38
- 238000004364 calculation method Methods 0.000 title claims abstract description 29
- 238000009826 distribution Methods 0.000 claims abstract description 163
- 238000010586 diagram Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 238000012502 risk assessment Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
- H02J3/0012—Contingency detection
Abstract
The invention discloses a method for monitoring an abnormal operation state of a power grid based on edge calculation, which comprises the following steps: s1, acquiring power grid monitoring data in a target area, and preprocessing the power grid monitoring data to obtain a power grid monitoring data set of each power distribution area; s2, acquiring a historical power grid monitoring dataset of each power distribution area, and constructing graph data of each power distribution area according to the power grid monitoring dataset; s3, sequentially inputting the graph data of all the power distribution areas into the GCN and the GRU to obtain a fault risk relation graph of all the power distribution areas; and S4, obtaining monitoring results of abnormal operation states of the power distribution network according to the fault risk relation diagrams of all the power distribution areas. The invention combines the GCN and the GRU network to rapidly analyze the fault risk of the distribution area, thereby accelerating the speed of finding the fault risk, improving the distribution fault diagnosis rate and solving the problem that the current distribution network monitoring method is difficult to rapidly determine the fault range in a short time.
Description
Technical Field
The invention belongs to the technical field of operation monitoring of power distribution networks, and particularly relates to a power grid abnormal operation state monitoring method based on edge calculation.
Background
The electric power system is a foundation stone for national economic development and operation, and people can not leave the electric power industry in production and life, and only the stable electric power system operation is maintained, so that the industrial production and the human life can be ensured. However, due to the influence of unstable factors, abnormal states can occur in the operation process of the power system, if the power system is not monitored at the first time, sudden large-scale power failure events can be caused, and the influence on the life and various industries of people can be caused. In case of failure of the power system, the power supply is affected when the failure cannot be guaranteed, so that the smart grid gradually replaces the traditional power grid for further supplying the power to the society, and the digital processing technology is applied to the power system to perform core management on the data flow and the information flow. In the current stage, the abnormal detection of the power grid still depends on the scheduled maintenance, namely, the abnormal state of the power grid is searched in the regular maintenance, a large amount of manpower and material resources are required, so that a large amount of cost is caused, the method cannot quickly respond to sudden power faults, and the fault range is difficult to quickly determine in a short time.
Disclosure of Invention
Aiming at the defects in the prior art, the method for monitoring the abnormal running state of the power grid based on the edge calculation solves the problem that the current power distribution network monitoring method is difficult to quickly determine the fault range in a short time.
In order to achieve the aim of the invention, the invention adopts the following technical scheme: an abnormal operation state monitoring method of a power grid based on edge calculation comprises the following steps:
s1, acquiring power grid monitoring data in a target area, and preprocessing the power grid monitoring data to obtain a power grid monitoring data set of each power distribution area;
s2, acquiring a historical power grid monitoring dataset of each power distribution area, and constructing graph data of each power distribution area according to the power grid monitoring dataset;
s3, sequentially inputting the graph data of all the power distribution areas into the GCN and the GRU to obtain a fault risk relation graph of all the power distribution areas;
and S4, obtaining monitoring results of abnormal operation states of the power distribution network according to the fault risk relation diagrams of all the power distribution areas.
Further: in the step S1, the power grid monitoring data comprise the temperature, the voltage and the current of a power distribution network node;
the step S1 comprises the following sub-steps:
s11, acquiring power grid monitoring data in a designated time period of all power distribution network nodes, dividing the power grid monitoring data of all the power distribution network nodes according to power distribution areas, and obtaining the power grid monitoring data of the power distribution network nodes of a plurality of power distribution areas and the power grid monitoring data of the power distribution network nodes;
s12, carrying out fusion processing on the power grid monitoring data of the power distribution network nodes of each power distribution area by an edge calculation method to obtain the power grid monitoring data of each power distribution area;
s13, constructing a power grid monitoring data set according to the power grid monitoring data of all the power distribution areas.
Further: in the S12, obtain the firstlGrid monitoring data for individual distribution areasX l The expression of (2) is specifically:
in the method, in the process of the invention,x i is the firstiGrid monitoring data, omega, of individual grid nodes i Is the firstiAnd the weight of each power distribution network node.
The beneficial effects of the above-mentioned further scheme are: the edge calculation method fuses the data collected by the power distribution network nodes of each power distribution area, avoids the collected data from being too scattered in subsequent network calculation, and realizes timely sensing of power distribution network faults through the concentrated fusion of multiple data.
Further: the step S2 is specifically as follows:
and acquiring a historical power grid monitoring data set of each power distribution area, establishing node characteristic representation according to the historical power grid monitoring data set and the power grid monitoring data set of each power distribution area through risk analysis, constructing an abnormal pattern according to the node characteristic representation, and taking the abnormal pattern as pattern data of the power distribution area.
Further: in the step S3, the method for obtaining the fault risk relation diagram of any distribution area includes the following sub-steps:
s31, inputting graph data of the power distribution area into a GCN, and performing graph convolution operation on each node through the GCN to obtain first graph data;
s32, inputting the first image data into the GRU, and performing encoding and decoding processing through the GRU to obtain second image data;
and S33, splicing the second graph data with the graph data of the power distribution area to obtain a fault risk relation graph of the power distribution area.
The beneficial effects of the above-mentioned further scheme are: the coding GRU models the characteristics of the nodes of the power distribution network by utilizing a multi-characteristic attention mechanism, and excavates the rules of different power grid monitoring data and risk factors of each power distribution network in different time periods. And the decoding GRU introduces a time attention mechanism, dynamically learns the hidden layer states of the encoder at different moments, and can well combine the characteristics of the power grid monitoring data and the risk factors of the power distribution network.
Further: in S31, the calculation process of performing the graph convolution operation by the node is specifically represented by the following formula:
in the method, in the process of the invention,is the firstlInput of layer neural network, < >>,nFor the number of distribution network nodes in the graph data of the distribution area, each node uses +.>Feature vector representation of dimension +_>Is an adjacency matrix of the undirected graph, +.>Is thatNOrder identity matrix>Is an intermediate matrix>Is->Degree matrix of->For normalizing matrix rows and columns,/for the matrix rows and columns>Is the firstlWeight matrix of layer, < >>Wherein->For output dimension +.>To activate the function.
Further: the step S32 specifically includes:
and inputting the first graph data into the GRU, modeling the characteristics of each power distribution network node in the first graph data through the coding GRU to obtain a coding vector, and inputting the coding vector into the decoding GRU to obtain the second graph data.
Further: the step S33 specifically includes:
and inputting the second graph data and the graph data of the power distribution area into a Linear layer, and splicing the second graph data and the graph data of the power distribution area with the same size after the second graph data and the graph data of the power distribution area are adjusted to be the same size through a Linear function to obtain a fault risk relation graph of the power distribution area.
Further: the step S4 specifically comprises the following steps:
and obtaining the power failure fault risks of each distribution area of the power distribution network according to the fault risk relation diagrams of all the distribution areas, and taking the power failure fault risks as monitoring results of abnormal running states of the power distribution network, wherein the power failure fault risks comprise lightning protection factors, insulating factors and equipment old factors.
The beneficial effects of the invention are as follows:
(1) The invention provides a power grid abnormal operation state monitoring method based on edge calculation, which is used for rapidly analyzing the fault risk of a power distribution area according to a power grid monitoring data set and a historical power grid monitoring data set of each power distribution area and combining a GCN and a GRU network, so that the speed of finding the fault risk is increased, the power distribution fault diagnosis rate is improved, and the problem that the current power distribution network monitoring method is difficult to rapidly determine the fault range in a short time is solved.
(2) According to the invention, a multi-feature attention mechanism and a time attention mechanism are introduced into the GRU, the GRU inputs the power grid monitoring data with a graph structure and the feature data of the risk factors of the power distribution network, the multi-feature attention mechanism is utilized to model the features of the nodes of the power distribution network, and the time attention mechanism can be utilized to well combine the power grid monitoring data and the features of the risk factors of the power distribution network, so that the abnormal running state of the power distribution network is reasonably monitored.
Drawings
Fig. 1 is a flowchart of a method for monitoring an abnormal operation state of a power grid based on edge calculation.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, in one embodiment of the present invention, a method for monitoring an abnormal operation state of a power grid based on edge calculation includes the following steps:
s1, acquiring power grid monitoring data in a target area, and preprocessing the power grid monitoring data to obtain a power grid monitoring data set of each power distribution area;
s2, acquiring a historical power grid monitoring dataset of each power distribution area, and constructing graph data of each power distribution area according to the power grid monitoring dataset;
s3, sequentially inputting the graph data of all the power distribution areas into the GCN and the GRU to obtain a fault risk relation graph of all the power distribution areas;
and S4, obtaining monitoring results of abnormal operation states of the power distribution network according to the fault risk relation diagrams of all the power distribution areas.
In the step S1, the power grid monitoring data comprise the temperature, the voltage and the current of a power distribution network node;
the step S1 comprises the following sub-steps:
s11, acquiring power grid monitoring data in a designated time period of all power distribution network nodes, dividing the power grid monitoring data of all the power distribution network nodes according to power distribution areas, and obtaining the power grid monitoring data of the power distribution network nodes of a plurality of power distribution areas and the power grid monitoring data of the power distribution network nodes;
s12, carrying out fusion processing on the power grid monitoring data of the power distribution network nodes of each power distribution area by an edge calculation method to obtain the power grid monitoring data of each power distribution area;
s13, constructing a power grid monitoring data set according to the power grid monitoring data of all the power distribution areas.
In the S12, obtain the firstlGrid monitoring data for individual distribution areasX l The expression of (2) is specifically:
in the method, in the process of the invention,x i is the firstiGrid monitoring data, omega, of individual grid nodes i Is the firstiAnd the weight of each power distribution network node.
In the embodiment, the edge calculation method fuses the data collected by the power distribution network nodes of each power distribution area, so that the collected data is prevented from being too scattered in subsequent network calculation, and timely sensing of power distribution network faults is realized through the centralized fusion of the data.
The step S2 is specifically as follows:
acquiring a historical power grid monitoring data set of each power distribution area, establishing node characteristic representation according to the historical power grid monitoring data set and the power grid monitoring data set of each power distribution area through risk analysis, constructing an abnormal pattern according to the node characteristic representation, and taking the abnormal pattern as pattern data of the power distribution area;
by constructing an abnormal pattern according to the historical power grid monitoring data set and the power grid monitoring data set of each power distribution area, the relation of temperature, residual current, voltage, loop current and other data in the power distribution system can be reflected, so that whether faults occur or not can be judged, and the fault conditions of loop power supply, power supply faults, tripping, current limitation violations and the like are specifically included. The heterogeneous graph comprises nodes and edges, the node characteristics represent risk factors of the power distribution network, and the types of the edges are the relation between the risk factors of the power distribution network and power grid monitoring data.
In the step S3, the method for obtaining the fault risk relation diagram of any distribution area includes the following sub-steps:
s31, inputting graph data of the power distribution area into a GCN, and performing graph convolution operation on each node through the GCN to obtain first graph data;
s32, inputting the first image data into the GRU, and performing encoding and decoding processing through the GRU to obtain second image data;
and S33, splicing the second graph data with the graph data of the power distribution area to obtain a fault risk relation graph of the power distribution area.
In S31, the calculation process of performing the graph convolution operation by the node is specifically represented by the following formula:
in the method, in the process of the invention,is the firstlInput of layer neural network, < >>,nFor the number of distribution network nodes in the graph data of the distribution area, each node uses +.>Feature vector representation of dimension +_>Is an adjacency matrix of the undirected graph, +.>Is thatNOrder identity matrix>Is an intermediate matrix>Is->Degree matrix of->For normalizing matrix rows and columns,/for the matrix rows and columns>Is the firstlWeight matrix of layer, < >>Wherein->For output dimension +.>To activate the function.
In this embodiment, the GCN extracts the hidden graph information by using the structure information of the graph that connects the edges and the vertices and the attribute information attached to the graph structure, the convolutional layer receptive field becomes larger with the increase of the convolutional layer, and a more abstract information representation is obtained, and after the feature extraction of the graph neural network of the GCN, the information of each power distribution network node in the graph data of the power distribution area is updated.
The step S32 specifically includes:
and inputting the first graph data into the GRU, modeling the characteristics of each power distribution network node in the first graph data through the coding GRU to obtain a coding vector, and inputting the coding vector into the decoding GRU to obtain the second graph data.
In this embodiment, the encoded GRU models the characteristics of the nodes of the power distribution network by using a multi-characteristic attention mechanism, and excavates the rules of different monitoring data of the power grid and risk factors of each power distribution network in different time periods. And the decoding GRU introduces a time attention mechanism, dynamically learns the hidden layer states of the encoder at different moments, and can well combine the characteristics of the power grid monitoring data and the risk factors of the power distribution network.
The step S33 specifically includes:
and inputting the second graph data and the graph data of the power distribution area into a Linear layer, and splicing the second graph data and the graph data of the power distribution area with the same size after the second graph data and the graph data of the power distribution area are adjusted to be the same size through a Linear function to obtain a fault risk relation graph of the power distribution area.
In this embodiment, the fault risk relation diagram of the power distribution area is obtained, which can reflect the power failure fault risk condition in the power distribution area, so as to ensure reliable operation of the power distribution network, avoid occurrence of power failure accidents, and perform timely treatment according to the power failure fault risk condition.
The step S4 specifically comprises the following steps:
and obtaining the power failure fault risks of each distribution area of the power distribution network according to the fault risk relation diagrams of all the distribution areas, and taking the power failure fault risks as monitoring results of abnormal running states of the power distribution network, wherein the power failure fault risks comprise lightning protection factors, insulating factors and equipment old factors.
The beneficial effects of the invention are as follows: the invention provides a power grid abnormal operation state monitoring method based on edge calculation, which is used for rapidly analyzing the fault risk of a power distribution area according to a power grid monitoring data set and a historical power grid monitoring data set of each power distribution area and combining a GCN and a GRU network, so that the speed of finding the fault risk is increased, the power distribution fault diagnosis rate is improved, and the problem that the current power distribution network monitoring method is difficult to rapidly determine the fault range in a short time is solved.
According to the invention, a multi-feature attention mechanism and a time attention mechanism are introduced into the GRU, the GRU inputs the power grid monitoring data with a graph structure and the feature data of the risk factors of the power distribution network, the multi-feature attention mechanism is utilized to model the features of the nodes of the power distribution network, and the time attention mechanism can be utilized to well combine the power grid monitoring data and the features of the risk factors of the power distribution network, so that the abnormal running state of the power distribution network is reasonably monitored.
In the description of the present invention, it should be understood that the terms "center," "thickness," "upper," "lower," "horizontal," "top," "bottom," "inner," "outer," "radial," and the like indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the present invention and to simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be configured and operated in a particular orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be interpreted as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defined as "first," "second," "third," or the like, may explicitly or implicitly include one or more such feature.
Claims (9)
1. The method for monitoring the abnormal operation state of the power grid based on the edge calculation is characterized by comprising the following steps of:
s1, acquiring power grid monitoring data in a target area, and preprocessing the power grid monitoring data to obtain a power grid monitoring data set of each power distribution area;
s2, acquiring a historical power grid monitoring dataset of each power distribution area, and constructing graph data of each power distribution area according to the power grid monitoring dataset;
s3, sequentially inputting the graph data of all the power distribution areas into the GCN and the GRU to obtain a fault risk relation graph of all the power distribution areas;
and S4, obtaining monitoring results of abnormal operation states of the power distribution network according to the fault risk relation diagrams of all the power distribution areas.
2. The method for monitoring abnormal operation state of a power grid based on edge calculation according to claim 1, wherein in S1, the power grid monitoring data includes temperature, voltage and current of nodes of the power distribution network;
the step S1 comprises the following sub-steps:
s11, acquiring power grid monitoring data in a designated time period of all power distribution network nodes, dividing the power grid monitoring data of all the power distribution network nodes according to power distribution areas, and obtaining the power grid monitoring data of the power distribution network nodes of a plurality of power distribution areas and the power grid monitoring data of the power distribution network nodes;
s12, carrying out fusion processing on the power grid monitoring data of the power distribution network nodes of each power distribution area by an edge calculation method to obtain the power grid monitoring data of each power distribution area;
s13, constructing a power grid monitoring data set according to the power grid monitoring data of all the power distribution areas.
3. The method for monitoring abnormal operation state of power grid based on edge calculation according to claim 2, wherein in S12, the first step is obtainedlGrid monitoring data for individual distribution areasX l The expression of (2) is specifically:
in the method, in the process of the invention,x i is the firstiGrid monitoring data, omega, of individual grid nodes i Is the firstiAnd the weight of each power distribution network node.
4. The method for monitoring abnormal operation state of a power grid based on edge calculation according to claim 1, wherein S2 specifically is:
and acquiring a historical power grid monitoring data set of each power distribution area, establishing node characteristic representation according to the historical power grid monitoring data set and the power grid monitoring data set of each power distribution area through risk analysis, constructing an abnormal pattern according to the node characteristic representation, and taking the abnormal pattern as pattern data of the power distribution area.
5. The method for monitoring abnormal operation states of a power grid based on edge calculation according to claim 1, wherein in S3, the method for obtaining a fault risk relation diagram of any distribution area comprises the following sub-steps:
s31, inputting graph data of the power distribution area into a GCN, and performing graph convolution operation on each node through the GCN to obtain first graph data;
s32, inputting the first image data into the GRU, and performing encoding and decoding processing through the GRU to obtain second image data;
and S33, splicing the second graph data with the graph data of the power distribution area to obtain a fault risk relation graph of the power distribution area.
6. The method for monitoring abnormal operation states of a power grid based on edge calculation according to claim 5, wherein in S31, the calculation process of performing a graph convolution operation by a node is specifically represented by the following formula:
in the method, in the process of the invention,is the firstlInput of layer neural network, < >>,nFor the number of distribution network nodes in the graph data of the distribution area, each node uses +.>Feature vector representation of dimension +_>Is an adjacency matrix of the undirected graph, +.>Is thatNOrder identity matrix>Is an intermediate matrix>Is->Degree matrix of->For normalizing matrix rows and columns,/for the matrix rows and columns>Is the firstlWeight matrix of layer, < >>Wherein->For output dimension +.>To activate the function.
7. The method for monitoring abnormal operation state of a power grid based on edge calculation according to claim 5, wherein S32 specifically is:
and inputting the first graph data into the GRU, modeling the characteristics of each power distribution network node in the first graph data through the coding GRU to obtain a coding vector, and inputting the coding vector into the decoding GRU to obtain the second graph data.
8. The method for monitoring abnormal operation state of a power grid based on edge calculation according to claim 5, wherein S33 specifically comprises:
and inputting the second graph data and the graph data of the power distribution area into a Linear layer, and splicing the second graph data and the graph data of the power distribution area with the same size after the second graph data and the graph data of the power distribution area are adjusted to be the same size through a Linear function to obtain a fault risk relation graph of the power distribution area.
9. The method for monitoring abnormal operation state of a power grid based on edge calculation according to claim 1, wherein S4 specifically is:
and obtaining the power failure fault risks of each distribution area of the power distribution network according to the fault risk relation diagrams of all the distribution areas, and taking the power failure fault risks as monitoring results of abnormal running states of the power distribution network, wherein the power failure fault risks comprise lightning protection factors, insulating factors and equipment old factors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410004580.5A CN117498561B (en) | 2024-01-03 | 2024-01-03 | Power grid abnormal operation state monitoring method based on edge calculation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410004580.5A CN117498561B (en) | 2024-01-03 | 2024-01-03 | Power grid abnormal operation state monitoring method based on edge calculation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117498561A true CN117498561A (en) | 2024-02-02 |
CN117498561B CN117498561B (en) | 2024-03-19 |
Family
ID=89680481
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410004580.5A Active CN117498561B (en) | 2024-01-03 | 2024-01-03 | Power grid abnormal operation state monitoring method based on edge calculation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117498561B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114137358A (en) * | 2021-11-17 | 2022-03-04 | 国网天津市电力公司信息通信公司 | Power transmission line fault diagnosis method based on graph convolution neural network |
CN114245337A (en) * | 2021-12-17 | 2022-03-25 | 吉林大学 | Water supply pipe network leakage positioning sensor arrangement method based on graph convolution network |
CN114597970A (en) * | 2022-03-18 | 2022-06-07 | 合肥工业大学 | Active power distribution network partitioning method based on graph convolution network |
CN114818483A (en) * | 2022-04-14 | 2022-07-29 | 东南大学溧阳研究院 | Electromechanical disturbance positioning and propagation prediction method based on graph neural network |
CN115542070A (en) * | 2022-08-15 | 2022-12-30 | 云南电网有限责任公司 | Distribution network line fault positioning method and storage medium |
CN116366673A (en) * | 2023-04-11 | 2023-06-30 | 国网甘肃省电力公司信息通信公司 | Data analysis and sharing method oriented to management of power grid information machine room |
CN116467674A (en) * | 2023-04-10 | 2023-07-21 | 国网辽宁省电力有限公司抚顺供电公司 | Intelligent fault processing fusion updating system and method for power distribution network |
CN117040109A (en) * | 2023-07-05 | 2023-11-10 | 国网江苏省电力有限公司无锡供电分公司 | Substation room risk early warning method based on heterogeneous data feature fusion |
CN117081240A (en) * | 2023-07-31 | 2023-11-17 | 云南电网有限责任公司 | Power grid fusion control method and system based on multi-access edge computing technology |
-
2024
- 2024-01-03 CN CN202410004580.5A patent/CN117498561B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114137358A (en) * | 2021-11-17 | 2022-03-04 | 国网天津市电力公司信息通信公司 | Power transmission line fault diagnosis method based on graph convolution neural network |
CN114245337A (en) * | 2021-12-17 | 2022-03-25 | 吉林大学 | Water supply pipe network leakage positioning sensor arrangement method based on graph convolution network |
CN114597970A (en) * | 2022-03-18 | 2022-06-07 | 合肥工业大学 | Active power distribution network partitioning method based on graph convolution network |
CN114818483A (en) * | 2022-04-14 | 2022-07-29 | 东南大学溧阳研究院 | Electromechanical disturbance positioning and propagation prediction method based on graph neural network |
CN115542070A (en) * | 2022-08-15 | 2022-12-30 | 云南电网有限责任公司 | Distribution network line fault positioning method and storage medium |
CN116467674A (en) * | 2023-04-10 | 2023-07-21 | 国网辽宁省电力有限公司抚顺供电公司 | Intelligent fault processing fusion updating system and method for power distribution network |
CN116366673A (en) * | 2023-04-11 | 2023-06-30 | 国网甘肃省电力公司信息通信公司 | Data analysis and sharing method oriented to management of power grid information machine room |
CN117040109A (en) * | 2023-07-05 | 2023-11-10 | 国网江苏省电力有限公司无锡供电分公司 | Substation room risk early warning method based on heterogeneous data feature fusion |
CN117081240A (en) * | 2023-07-31 | 2023-11-17 | 云南电网有限责任公司 | Power grid fusion control method and system based on multi-access edge computing technology |
Non-Patent Citations (1)
Title |
---|
郭创新 等: "基于图神经网络和强化学习的电网风险态势感知", 《电网与清洁能源》, 31 December 2023 (2023-12-31), pages 41 - 49 * |
Also Published As
Publication number | Publication date |
---|---|
CN117498561B (en) | 2024-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104363106B (en) | A kind of communicating for power information fault pre-alarming analysis method based on big data technology | |
CN109241169A (en) | The multi-source heterogeneous data fusion geo-database integration method of power distribution network operation information | |
CN110388315B (en) | Oil transfer pump fault identification method, device and system based on multi-source information fusion | |
CN106777392A (en) | The real-time processing method of the Wind turbines scada data based on stream calculation | |
CN111985558A (en) | Electric energy meter abnormity diagnosis method and system | |
CN113746663B (en) | Performance degradation fault root cause positioning method combining mechanism data and dual drives | |
CN115730749B (en) | Power dispatching risk early warning method and device based on fusion power data | |
CN111177128B (en) | Metering big data batch processing method and system based on improved outlier detection algorithm | |
CN116523140A (en) | Method and device for detecting electricity theft, electronic equipment and storage medium | |
CN113469457B (en) | Power transmission line fault probability prediction method integrating attention mechanism | |
CN111768022A (en) | Equipment detection method and device for coal machine production equipment | |
CN107742883A (en) | A kind of power system topology island system for rapidly identifying and method based on Spark | |
CN117498561B (en) | Power grid abnormal operation state monitoring method based on edge calculation | |
CN115865611A (en) | Fault processing method and device of network equipment and electronic equipment | |
CN111537819A (en) | Distribution automation monitoring method, system, terminal and storage medium | |
CN115457211A (en) | Transformer substation management method and system based on digital twins | |
CN115834406A (en) | Power grid transient stability prediction method based on convolutional neural network | |
Leite et al. | Failure probability metric by machine learning for online risk assessment in distribution networks | |
CN113869589A (en) | Power transmission line accident prediction method based on knowledge graph and inspection system | |
CN113887799A (en) | Artificial intelligent alarm method for safety production of hydraulic power plant | |
CN112488873A (en) | Intelligent mining construction method for health codes and state tracks of power supply and utilization equipment | |
CN110889614A (en) | Power grid system important user power supply risk analysis method based on SCADA big data | |
CN116150257B (en) | Visual analysis method, system and storage medium for electric power communication optical cable resources | |
CN105468871B (en) | A kind of momenttum wheel success Envelope Analysis and application process | |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |