CN111598123B - Power distribution network line vectorization method and device based on neural network - Google Patents
Power distribution network line vectorization method and device based on neural network Download PDFInfo
- Publication number
- CN111598123B CN111598123B CN202010251558.2A CN202010251558A CN111598123B CN 111598123 B CN111598123 B CN 111598123B CN 202010251558 A CN202010251558 A CN 202010251558A CN 111598123 B CN111598123 B CN 111598123B
- Authority
- CN
- China
- Prior art keywords
- line
- transmission line
- injection
- target transmission
- injected
- 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.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 42
- 230000005540 biological transmission Effects 0.000 claims abstract description 275
- 238000002347 injection Methods 0.000 claims abstract description 141
- 239000007924 injection Substances 0.000 claims abstract description 141
- 239000013598 vector Substances 0.000 claims abstract description 121
- 239000011159 matrix material Substances 0.000 claims abstract description 103
- 238000004519 manufacturing process Methods 0.000 claims description 25
- 239000007943 implant Substances 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 230000000717 retained effect Effects 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 5
- 230000014759 maintenance of location Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000002513 implantation Methods 0.000 claims 1
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000007477 logistic regression Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000013501 data transformation Methods 0.000 description 2
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a neural network-based power distribution network line vectorization method and device, wherein the method comprises the following steps: constructing a graph model based on the connection relation between transmission lines of the power distribution network and electrical equipment; acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes corresponding to the target transmission lines respectively based on the graph model; based on a neural network, performing feature embedding on the injected characteristic vectors and the injected adjacent matrix at nodes of the graph model to obtain a first line characteristic vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection; and updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line. The invention can accurately represent the characteristic information of the power distribution network, thereby improving the result of data analysis or fault prediction of the power distribution network.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a power distribution network line vectorization method and device based on a neural network.
Background
The smart grid is a development direction in the field of electric power at present, but is still in a concept and starting stage at present. The smart grid is established on the basis of an integrated high-speed bidirectional communication network, and achieves the purposes of reliability, safety, economy, high efficiency, environmental friendliness and safe use of the power grid through the application of advanced sensing and measuring technology, advanced equipment technology, advanced control method and advanced decision support system technology. The realization of partial functions of the smart grid, access of a power generation form, analysis of transmission risks, analysis of power transfer and the like all require datamation of the power distribution network; some existing power distribution network modeling modes are usually used for modeling and analyzing a specific problem in a power distribution network; the obtained power grid datamation characteristics are difficult to effectively express the overall characteristics of the power distribution network, namely, the characteristic information of the power distribution network is difficult to accurately express, so that an accurate analysis result cannot be obtained.
Therefore, a data method capable of accurately representing the characteristics of the power distribution network is still lacked at present.
Disclosure of Invention
In view of the above problems, the present invention provides a power distribution network line vectorization method and apparatus based on a neural network, which can accurately represent characteristic information of a power distribution network, thereby improving a result of data analysis or fault prediction of the power distribution network.
In a first aspect, the present application provides the following technical solutions through an embodiment of the present application:
a power distribution network line vectorization method based on a neural network comprises the following steps:
constructing a graph model based on the connection relation between transmission lines of the power distribution network and electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes corresponding to the target transmission lines respectively based on the graph model; the target transmission line is a transmission line corresponding to any node; the injected eigenvectors represent the properties of the target transmission line and the corresponding injection; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
based on a neural network, performing feature embedding on the injected feature vector and the injected adjacent matrix at a node of the graph model to obtain a first line feature vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection;
and updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line.
Preferably, the obtaining of the injection feature vector includes:
obtaining a consumption of the implant and a production of the implant based on the type of the implant; wherein the injected consumption is an electrical device consuming electrical energy and the injected generation is an electrical device producing electrical energy;
representing attributes of the target transmission line, consumption of the injection, and production of the injection as two-dimensional information;
obtaining the injection eigenvector based on the two-dimensional information corresponding to the attributes of the target transmission line, the consumption of the injection, and the production of the injection.
Preferably, the line adjacency matrix includes a start-point adjacency matrix and an end-point adjacency matrix; the acquisition of the line adjacency matrix comprises the following steps:
determining the target transmission line as a bipolar object based on the graph model; wherein the bi-polar object represents that the target transmission line has a start point and an end point;
obtaining a starting point adjacency matrix based on first connection information of a starting point of the target transmission line; wherein the first connection information includes: the starting point of the target transmission line is connected with the starting point of the adjacent transmission line, and the starting point of the target transmission line is connected with the end point of the adjacent transmission line;
obtaining the end point adjacency matrix based on second connection information of the end point of the target transmission line; wherein the second connection information includes: the end point of the target transmission line is connected with the start point of the adjacent transmission line, and the end point of the target transmission line is connected with the end point of the adjacent transmission line.
Preferably, the acquiring of the injection adjacency matrix comprises:
obtaining the injection adjacency matrix based on the target transmission line and the injected third connection information; wherein the third connection information includes: the injection is connected to the beginning of the target transmission line and the injection is connected to the end of the target transmission line.
Preferably, the updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line includes:
obtaining first propagation information based on the sum of products of the starting point adjacency matrix and the end point adjacency matrix and first reservation information, respectively; wherein the first retention information is the first line feature vector;
obtaining second reservation information based on a sum of the first propagation information and the first reservation information;
obtaining second propagation information based on a sum of products of the start-point adjacency matrix and the end-point adjacency matrix, respectively, and the second reservation information;
iteratively updating the second retained information based on a sum of the second propagation information and the second retained information until the second line feature vector is obtained.
Preferably, the feature embedding the injected feature vector and the injected adjacency matrix at a node of the graph model based on the neural network to obtain the first line feature vector of the target transmission line includes:
mapping the injected characteristic vectors to a d-dimensional space based on a neural network to obtain d-dimensional vectors; wherein d is an integer greater than 2;
and right multiplying the d-dimensional vector by the injection adjacency matrix to obtain the first line characteristic vector.
Preferably, the mapping the injected feature vector into a d-dimensional space based on the neural network to obtain a d-dimensional vector includes:
based on the number of neurons is (d) in 10, d), mapping the injected feature vector to a d-dimensional space to obtain a d-dimensional vector; wherein d is in Is the dimension of the injected feature vector.
In a second aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment of the present application:
a power distribution network line vectorization device based on a neural network comprises:
the graph model building module is used for building a graph model based on the connection relation between the transmission line of the power distribution network and the electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
the characteristic acquisition module is used for acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes which respectively correspond to the target transmission lines on the basis of the graph model; the target transmission line is a transmission line corresponding to any node; the injection eigenvectors represent attributes of the target transmission line and the corresponding injections; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
the injection embedding module is used for embedding the injection characteristic vector and the injection adjacent matrix into the characteristic of the node of the graph model based on a neural network to obtain a first line characteristic vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection;
and the characteristic vector acquisition module is used for updating the first line characteristic vector based on the line adjacency matrix to acquire a second line characteristic vector of the target transmission line.
Preferably, the feature obtaining module is specifically configured to:
obtaining a consumption of the implant and a production of the implant based on the type of the implant; wherein the injected consumption is an electrical device consuming electrical energy and the injected generation is an electrical device producing electrical energy;
representing attributes of the target transmission line, the injected consumption, and the injected production as two-dimensional information;
obtaining the injection eigenvector based on the two-dimensional information corresponding to the attributes of the target transmission line, the consumption of the injection, and the production of the injection.
In a third aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment of the present application:
a computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any of the first aspects.
The embodiment of the invention provides a power distribution network line vectorization method based on a neural network, which is characterized in that a graph model is constructed through connection relations between transmission lines of a power distribution network and electrical equipment; the transmission lines are used as nodes in the graph model, the connection of the transmission lines is used as the edges of the graph model, and the electrical equipment is used for injection of the graph model, so that the connection relation between the transmission lines and the transmission lines in the power distribution network is abstractly expressed; furthermore, based on a graph model, acquiring an injection characteristic vector, a line adjacent matrix and an injection adjacent matrix which respectively correspond to the target transmission line, and abstracting and datafying the attribute corresponding to the target transmission line, the injection correspondingly connected and the adjacent transmission lines by injecting the characteristic vector, the line adjacent matrix and the injection adjacent matrix; finally, based on the neural network, performing feature embedding on the injected feature vector and the injected adjacent matrix at the nodes of the graph model to obtain a first line feature vector of the target transmission line, so that the first line feature vector comprises attributes corresponding to the target transmission line and injection-related features correspondingly connected, and the obtained data has better stability and is not easy to distort due to the feature embedding performed in the neural network mode; finally, updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line, wherein the second line eigenvector not only contains the attribute characteristics of the target transmission line, the injection and the connection information of the target transmission line, but also contains the adjacency information of the target transmission line and the adjacent transmission line; therefore, the detailed characteristics of the power distribution network can be accurately represented by using the second line characteristic vector, and the complexity of transmission line characteristics in the power distribution network is fully considered, so that the second line characteristic vector obtained after the power distribution network can be subjected to data transformation can be widely applied to data analysis and prediction in the situations of line faults, power transfer and the like, and the accuracy is higher.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a method for vectorizing a power distribution network line based on a neural network according to a first embodiment of the present invention;
fig. 2 shows a functional block diagram of a power distribution network line vectoring device based on a neural network according to a second embodiment of the present invention;
fig. 3 is a flowchart illustrating a method for locating a fault of a power distribution network line according to a third embodiment of the present invention;
FIG. 4 is a diagram illustrating an exemplary graph model construction process for a power distribution network according to a third embodiment of the present invention;
FIG. 5 shows an exemplary feature embedding process diagram in a third embodiment of the present invention;
FIG. 6 is a diagram illustrating an exemplary iterative update of a line feature vector in a third embodiment of the present invention;
fig. 7 shows a functional block diagram of a power distribution network line fault location device according to a fourth embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
First embodiment
Referring to fig. 1, a first embodiment of the present invention provides a power distribution network line vectorization method based on a neural network, and fig. 1 shows a flowchart of the power distribution network line vectorization method based on the neural network.
Specifically, the method comprises the following steps:
step S10: constructing a graph model based on the connection relation between transmission lines of the power distribution network and electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as edges of the graph model, and the electrical equipment serves as the injection of the graph model;
step S20: acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes corresponding to the target transmission lines respectively based on the graph model; the target transmission line is a transmission line corresponding to any node; the injection eigenvectors represent attributes of the target transmission line and the corresponding injections; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
step S30: based on a neural network, performing feature embedding on the injected feature vector and the injected adjacent matrix at a node of the graph model to obtain a first line feature vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection;
step S40: and updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line.
In step S10, power is transmitted to the power distribution network by using a transmission line (i.e., a power transmission line), and electrical equipment such as loads, substations, power stations, and switches in the power system are connected to the transmission line. Specifically, a topological connection diagram can be constructed by determining the interconnection relationship of transmission lines according to an electrical diagram of the power distribution network, so as to form a diagram model. The properties of each transmission line may include the number of wires and the physical properties of the wires, such as resistivity, diameter, length, etc. of the wires. The properties of the transmission line may be represented in a vectorized representation, e.g. a two-dimensional vector representation.
The injection includes electrical equipment at the end of the line, such as loads, substations, power stations, switches, etc. Specifically, the abstraction of power consumption resources such as dedicated transformers and utility transformers is injected consumption, one consumption being defined by one active power consumption and one reactive power consumption; electrical equipment in the grid, such as generators, substations and the like, that produce electrical power resources are abstracted into injected production, each production being defined by an active input and an input voltage. The total number of injections is the sum of the consumed number of injections and the produced number of injections. Each implant can be represented using a two-dimensional information.
In step S20, the target transmission line is a transmission line corresponding to any node, that is, each transmission line in the distribution network can go through steps S20-S40, so as to obtain a second eigenvector of the transmission line.
Further, for the target transmission line, the acquisition of the injection eigenvector comprises the following processes:
1. based on the type of implant, obtaining a consumption of the implant and a production of the implant; wherein the injected consumption is an electrical device consuming electrical energy and the injected generation is an electrical device producing electrical energy;
2. representing the attribute of the target transmission line, the injected consumption and the injected production as two-dimensional information;
3. an injection feature vector is obtained based on two-dimensional information corresponding to the attributes of the target transmission line, the injected consumption, and the injected production.
Therefore, the attribute information of the target transmission line and the injected connection information can be represented in a datamation mode by injecting the characteristic vectors, and the subsequent processing process is facilitated.
Further, the line adjacency matrix for the target transmission line includes: a start-point adjacency matrix and an end-point adjacency matrix; specifically, the obtaining of the line adjacency matrix comprises the following steps:
1. determining the target transmission line as a bipolar object based on the graph model; wherein the dipole object represents a target transmission line having a start point and an end point;
2. obtaining a starting point adjacency matrix based on first connection information of a starting point of the target transmission line; wherein the first connection information includes: the starting point of the target transmission line is connected with the starting point of the adjacent transmission line, and the starting point of the target transmission line is connected with the end point of the adjacent transmission line;
3. acquiring an end point adjacency matrix based on second connection information of the end point of the target transmission line; wherein the second connection information includes: the end point of the target transmission line is connected to the start point of the adjacent transmission line, and the end point of the target transmission line is connected to the end point of the adjacent transmission line.
The starting point adjacency matrix can perform data representation on transmission line information adjacent to the starting point of the target transmission line, and the end point adjacency matrix can perform data representation on transmission line information adjacent to the end point of the target transmission line; therefore, at least four kinds of adjacent information of the target transmission line (a starting point connection starting point, a starting point connection end point, an end point connection starting point and an end point connection end point) are reserved, and the accuracy is improved.
Further, the obtaining of the injection adjacency matrix of the target transmission line comprises:
acquiring an injection adjacency matrix based on the target transmission line and the injected third connection information; wherein the third connection information includes: the injection is connected to the beginning of the target transmission line and the injection is connected to the end of the target transmission line.
In step S20, the line adjacency relation and the injection connection relation of the target transmission line can be characterized by obtaining the injection eigenvector, the line adjacency matrix and the injection adjacency matrix corresponding to the target transmission line, so as to ensure that the target transmission line can include multiple characteristics of the power distribution network after vectorization, avoid singularization of the characteristics, and improve the accuracy of the data.
Since a plurality of characteristics of the distribution network are acquired in step S20, it is necessary to perform characteristic fusion in step S30 to acquire data that can comprehensively express the target transmission line. The feature embedding of step S30 specifically includes:
1. mapping the injected characteristic vectors to a d-dimensional space based on a neural network to obtain d-dimensional vectors; wherein d is an integer greater than 2; one specific implementation way is as follows: based on the number of neurons is (d) in 10, the three-layer neural network of d) maps the injected characteristic vectors into a d-dimensional space to obtain d-dimensional vectors; wherein d is in Is the dimension of the injected feature vector. d in Can be two-dimensional, three-dimensional, etc., and d is greater than d in The method can improve the robustness of the data, well resist noise and avoid serious data distortion caused by local data pollution.
2. Multiplying the d-dimensional vector to the injection adjacency matrix to obtain a first line characteristic vector; so that the first line eigenvector contains the attribute characteristics of the target transmission line and the connection information between the injection and target transmission lines.
In step S40, the further fusing the line adjacency matrix specifically includes:
1. obtaining first propagation information based on the sum of products of the starting point adjacency matrix and the end point adjacency matrix with the first reservation information, respectively; wherein the first retention information is a first line feature vector;
2. obtaining second reservation information based on the sum of the first propagation information and the first reservation information;
3. obtaining second propagation information based on the sum of products of the starting point adjacency matrix and the end point adjacency matrix and the second reserved information respectively;
4. and continuously performing iterative updating on the second reserved information based on the sum of the second propagation information and the second reserved information until the second line feature vector is obtained.
In the specific implementation of step S40, the number of iterative updates may be set more empirically, for example, it may be 1, 5, 10, 50, 100, 1000, etc., without limitation. And when the iteration is carried out for 1 time, the second reserved information is the second line feature vector, and the steps 3 and 4 are not executed any more. The finally obtained second line characteristic vector not only contains the attribute characteristics of the target transmission line, the injection and the connection information of the target transmission line, but also contains the adjacent information of the target transmission line and the adjacent transmission line. Therefore, the second line characteristic vector can more accurately represent the characteristics of the transmission line in the power distribution network, and the power distribution network can be widely applied to data analysis and prediction in the scenes of line faults, power transfer and the like after being digitalized.
In the power distribution network line vectorization method based on the neural network, a graph model is constructed by the connection relationship between transmission lines of the power distribution network and electrical equipment; the transmission lines are used as nodes in the graph model, the connection of the transmission lines is used as the edges of the graph model, and the electrical equipment is used for injection of the graph model, so that the connection relation between the transmission lines and the transmission lines in the power distribution network is abstractly expressed; furthermore, based on a graph model, acquiring an injection characteristic vector, a line adjacent matrix and an injection adjacent matrix which respectively correspond to the target transmission line, and abstracting and datafying the attribute corresponding to the target transmission line, the injection correspondingly connected and the adjacent transmission lines by injecting the characteristic vector, the line adjacent matrix and the injection adjacent matrix; finally, based on a neural network, embedding characteristics of the injected characteristic vectors and the injected adjacent matrixes in the nodes of the graph model to obtain a first line characteristic vector of the target transmission line, so that the first line characteristic vector comprises attributes corresponding to the target transmission line and injection-related characteristics corresponding to connection, and the acquired data has better stability and is not easy to distort due to the characteristic embedding in the neural network mode; finally, updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line, wherein the second line eigenvector not only contains the attribute characteristics of the target transmission line, the injection and the connection information of the target transmission line, but also contains the adjacency information of the target transmission line and the adjacent transmission line; therefore, the detailed characteristics of the power distribution network can be accurately represented by using the second line characteristic vector, and the complexity of transmission line characteristics in the power distribution network is fully considered, so that the second line characteristic vector obtained after the power distribution network can be subjected to data transformation can be widely applied to data analysis and prediction in the situations of line faults, power transfer and the like, and the accuracy is higher.
Second embodiment
Based on the same inventive concept, a second embodiment of the present invention provides a power distribution network line vectoring apparatus 300 based on a neural network. Fig. 2 shows a functional block diagram of a power distribution network line vectoring device 300 based on a neural network according to a second embodiment of the present invention.
Specifically, the power distribution network line vectoring device 300 based on the neural network includes:
the graph model building module 301 is configured to build a graph model based on a connection relationship between a transmission line of a power distribution network and electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
a feature obtaining module 302, configured to obtain, based on the graph model, an injection feature vector, a line adjacency matrix, and an injection adjacency matrix that correspond to the target transmission line, respectively; the target transmission line is a transmission line corresponding to any node; the injection eigenvectors represent attributes of the target transmission line and the corresponding injections; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
an injection embedding module 303, configured to perform feature embedding on the injection eigenvector and the injection adjacency matrix at a node of the graph model based on a neural network, to obtain a first line eigenvector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection;
a feature vector obtaining module 304, configured to update the first line feature vector based on the line adjacency matrix, and obtain a second line feature vector of the target transmission line.
As an optional implementation manner, the feature obtaining module 302 is specifically configured to:
obtaining a consumption of the implant and a production of the implant based on the type of the implant; wherein the injected consumption is an electrical device consuming electrical energy and the injected generation is an electrical device producing electrical energy;
representing attributes of the target transmission line, consumption of the injection, and production of the injection as two-dimensional information;
obtaining the injection eigenvector based on two-dimensional information corresponding to the attributes of the target transmission line, the consumption of the injection, and the production of the injection.
It should be noted that, the specific implementation and technical effects of the power distribution network line vectoring device 300 based on the neural network according to the embodiment of the present invention are the same as those of the foregoing method embodiment, and for a brief description, reference may be made to corresponding contents in the foregoing method embodiment for what is not mentioned in the apparatus embodiment.
Third embodiment
Referring to fig. 3, a third embodiment of the present invention provides a method for locating a fault of a power distribution network line, and fig. 1 shows a flowchart of the method for locating a fault of a power distribution network line.
Specifically, the method comprises the following steps:
step S100: constructing a graph model based on the connection relation between transmission lines of the power distribution network and electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
step S200: vectorizing a target transmission line of the power distribution network based on the graph model, and embedding connection relations between the target transmission line and adjacent transmission lines and between the target transmission line and the injection to obtain a line characteristic vector of the target transmission line; the target transmission line is a transmission line corresponding to any node;
step S300: and inputting the line characteristic vector into a trained prediction model to obtain the fault probability of the target transmission line.
The detailed description of step S100 can refer to the description of step S10 in the first embodiment, and is not repeated herein. Specifically, an example is illustrated (and subsequently continued use is made of the example), where l is available i The method comprises the steps of representing the ith bus, representing the starting point and the end point of the bus respectively by s and e, abstracting a transmission line as a node in a graph model, abstracting the connection condition of the starting point and the end point corresponding to the transmission line as an edge, abstracting electrical equipment at the tail end of the transmission line, such as a load, a transformer substation, a power station, a switch and the like in a power system as injection in j Indicating the j-th implant. As shown in FIG. 4, where 4 nodes are shown, 3 implants (in) 1 、in 2 、in 3 ) And 4 sides (l) 1 、l 2 、l 3 、l 4 )。
In step S200, the method specifically includes:
step S210: acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes corresponding to the target transmission lines respectively based on the graph model; wherein the injected eigenvectors represent attributes of the target transmission line and corresponding injections; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
step S220: based on a neural network, performing feature embedding on the injected feature vector and the injected adjacent matrix at a node of the graph model to obtain a first line feature vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection;
step S230: and updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line.
The detailed descriptions of steps S210-S230 in this embodiment refer to the descriptions of steps S20-S40 in the first embodiment, and are not repeated herein.
The steps S210 to S230 are explained by using the above example in the present embodiment, and the abstraction of the power consumption of the dedicated transformer and the public transformer in the power grid is the injected consumption, one consumption C ∈ C, and one active power consumption P c (megawatts) and a reactive power consumption Q c (megavolt-ampere reactive) definition; abstracting the production of electric energy of generators, substations and the like in a power grid into injected production, wherein each production P belongs to P and is input by active power P p In megawatts and an input voltage V p Defined (in volts). By n in Represents the total number of injections: n is in Where | P | represents the amount produced, | C | represents the amount consumed, P is the set of productions, and C is the set of consumptions. Each transmission line having a property or injection of d in 2-dimensional information. Then adopt
Representing all the injected feature vectors.
Further, the transmission line is modeled as a bipolar objectIt is necessary to distinguish the start point and the end point of each transmission line. Thus, each connection between two transmission lines can be of four different types: (s) i ，s j )、(s i ，e j )、(e i ，s j )、(e i ，e j ) Wherein s is i And e i Respectively the start and end points, s, of the transmission line i j And e j Respectively, the start and end of transmission line j, as shown in fig. 4. Further, a contiguous matrix of start and end points of each transmission line
And
is represented as follows:
further, using matrices
The connection mode of the injection (production of the injection and consumption of the injection) and the starting point and the end point of the transmission line is shown, and specifically:
further, fusion of the injected eigenvectors and the injected adjacency matrix is performed. The purpose of feature embedding is to inject the attribute information of the transmission line into (d) in Dimension) into a d-dimensional space. For each transmission line, the attribute information and injection can adopt a neuron number (d) in 10, d) of a three-layer neural network E:
to take into account the connection information of the injection to the line, the obtained eigenvectors E (X) of the injection in the d-dimensional space are right-multiplied by the adjacency matrix A of the injection in Then, a first line feature vector can be obtained, namely:
H (0) ＝A in °E(X)
H (0) i.e. the first line eigenvector, the final result is an n × d result, where n is the number of transmission lines, and each transmission line is represented by a d-dimensional vector, which can be referred to as the embedding process shown in fig. 5.
Further, the first line eigenvector is updated based on the line adjacency matrix for fusion. The transmission line characteristic information is iteratively updated by the adjacency relationship between the transmission lines. The iteration number can be set to be K, and A is adopted s And A e Feature vectors H learned respectively with the current time step (k) Multiplication and then addition of (retained information) to obtain propagation information info of k iterations in the graph model (k) The method is used for updating the characteristic vector of the transmission line and the characteristic vector of the first line, and specifically comprises the following steps:
info (k) ＝sum(A s H (k) ，A e H (k) )
the specific iterative intermediate process is shown in fig. 6. Will retain information H (k) And propagation information info (k) Adding to represent the learned characteristic information H at the current time step (k+1) As follows:
H (k+1) ＝H (k) +sum(A s H (k) ，A e H (k) )＝(I+sum(A s ，A e ))(H (k) )
and for K ∈ { 0., K-1}, wherein I is an identity function, and a second line feature vector is obtained after iteration is finished.
In step S300, taking the prediction model as a logistic regression model as an example for explanation, the training of the logistic regression model includes:
1. obtaining a training sample based on the historical data of the power distribution network; wherein the training sample comprises a fault condition of the target transmission line and a historical line feature vector of the target transmission;
2. training the logistic regression model based on the training samples and a preset loss function to obtain model parameters of the logistic regression model; wherein the loss function is a cross entropy function;
3. and obtaining the trained logistic regression model based on the model parameters of the logistic regression model.
Specifically, the basic formula of the logistic regression model adopted in this embodiment is:
wherein, y (i) The fault true condition of the ith line is shown, 1 represents a fault, and 0 represents a non-fault.
Further, the parameters in the model are optimized by a gradient descent method, which is as follows:
finally, determining model parameters to obtain a trained logistic regression model, wherein the model can be applied to the actual scene to predict the fault condition of the transmission line, and the training sample is represented by the line characteristic vector of the historical condition corresponding to the transmission line, so that a more accurate prediction model can be obtained, and a higher prediction effect is realized.
In step S400, vectors are used in the power distribution network line fault in the real scene according to the trained prediction model
Indicating a fault condition for n lines, where 1 indicates a fault and 0 indicates no fault. The prediction system formed by the prediction model of the present embodiment can be expressed as Y ═ S (X, a) s ，A e ，A inj )。
In the method for positioning the line fault of the power distribution network, a graph model is constructed through the connection relation between the transmission line of the power distribution network and the electrical equipment; the transmission lines are used as nodes in the graph model, the connection of the transmission lines is used as the edges of the graph model, and the electrical equipment is used as the injection of the graph model, so that the connection relation between the transmission lines and the transmission lines in the power distribution network is abstractly expressed; furthermore, vectorizing a target transmission line of the power distribution network based on a graph model, and embedding connection relations between the target transmission line and adjacent transmission lines and between the target transmission line and injection, so as to obtain a line characteristic vector of the target transmission line, wherein the line characteristic vector contains characteristic information of the target transmission line in the power distribution network, and the complexity of transmission line connection in the power distribution network is fully considered; furthermore, the transmission line with the fault in the power distribution network can be accurately and quickly positioned by training a prediction model and predicting the fault based on the line characteristic vector.
In addition, the implementation process and the implementation effect of the method provided by the embodiment can refer to the corresponding contents in the foregoing method embodiments.
Fourth embodiment
Based on the same inventive concept, the second embodiment of the present invention provides a power distribution network line fault location apparatus 400. Fig. 7 shows a functional block diagram of a distribution network line fault location apparatus 400 according to a second embodiment of the present invention.
The distribution network line fault locating device 400 includes:
the graph model building module 401 is configured to build a graph model based on a connection relationship between a transmission line of a power distribution network and electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
a feature vector obtaining module 402, configured to vectorize a target transmission line of the power distribution network based on the graph model, and embed a connection relationship between the target transmission line and an adjacent transmission line, and between the target transmission line and the injection, to obtain a line feature vector of the target transmission line; the target transmission line is a transmission line corresponding to any node;
and a fault positioning module 403, configured to input the line feature vector into a trained prediction model, and obtain a fault probability of the target transmission line.
In an alternative embodiment, the prediction model is a logistic regression model; the apparatus further comprises a model training module to:
obtaining a training sample based on the historical data of the power distribution network; wherein the training sample comprises a fault condition of the target transmission line and a historical line feature vector of the target transmission;
training the logistic regression model based on the training samples and a preset loss function to obtain model parameters of the logistic regression model; wherein the loss function is a cross entropy function;
and obtaining the trained logistic regression model based on the model parameters of the logistic regression model.
It should be noted that, the specific implementation and technical effects of the distribution network line fault location apparatus 400 provided in the embodiment of the present invention are the same as those of the foregoing method embodiment, and for brevity, reference may be made to corresponding contents in the foregoing method embodiment where no part of the embodiment of the apparatus is mentioned.
The device-integrated functional modules provided by the present invention may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, all or part of the flow in the method of implementing the above embodiments may also be implemented by instructing relevant hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the above method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an apparatus according to an embodiment of the invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (7)
1. A power distribution network line vectorization method based on a neural network is characterized by comprising the following steps:
constructing a graph model based on the connection relation between transmission lines of the power distribution network and electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes corresponding to the target transmission lines respectively based on the graph model; the target transmission line is a transmission line corresponding to any node; the injection eigenvectors represent attributes of the target transmission line and the corresponding injections; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
based on a neural network, performing feature embedding on the injected characteristic vectors and the injected adjacent matrix at nodes of the graph model to obtain a first line characteristic vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection;
updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line;
the characteristic embedding is carried out on the injected characteristic vector and the injected adjacent matrix at the nodes of the graph model based on the neural network to obtain a first line characteristic vector of the target transmission line, and the method comprises the following steps: mapping the injected feature vectors to a d-dimensional space based on a neural network to obtain d-dimensional vectors; wherein d is an integer greater than 2; multiplying the d-dimensional vector to the injection adjacency matrix to obtain the first line characteristic vector; the mapping the injected feature vectors into a d-dimensional space based on the neural network to obtain d-dimensional vectors, including: based on the number of neurons is (d) in 10, d), mapping the injected feature vector to a d-dimensional space to obtain a d-dimensional vector; wherein d is in Is the dimension of the injected feature vector;
the line adjacency matrix comprises a starting point adjacency matrix and an end point adjacency matrix; the updating the first line eigenvector based on the line adjacency matrix to obtain a second line eigenvector of the target transmission line includes: obtaining first propagation information based on the sum of the products of the starting point adjacency matrix and the end point adjacency matrix and first reservation information respectively; wherein the first retention information is the first line feature vector; obtaining second reservation information based on a sum of the first propagation information and the first reservation information; obtaining second propagation information based on a sum of products of the start-point adjacency matrix and the end-point adjacency matrix, respectively, and the second reservation information; iteratively updating the second retained information based on a sum of the second propagation information and the second retained information until the second line feature vector is obtained.
2. The method of claim 1, wherein the obtaining of the injected eigenvector comprises:
obtaining a consumption of the implant and a production of the implant based on the type of the implant; wherein the injected consumption is an electrical device consuming electrical energy and the injected generation is an electrical device producing electrical energy;
representing attributes of the target transmission line, the injected consumption, and the injected production as two-dimensional information;
obtaining the injection eigenvector based on the two-dimensional information corresponding to the attributes of the target transmission line, the consumption of the injection, and the production of the injection.
3. The method of claim 1, wherein the obtaining of the line adjacency matrix comprises:
determining the target transmission line as a bipolar object based on the graph model; wherein the bi-polar object represents that the target transmission line has a start point and an end point;
obtaining a starting point adjacency matrix based on first connection information of a starting point of the target transmission line; wherein the first connection information includes: the starting point of the target transmission line is connected with the starting point of the adjacent transmission line, and the starting point of the target transmission line is connected with the end point of the adjacent transmission line;
acquiring a terminal point adjacency matrix based on second connection information of the terminal point of the target transmission line; wherein the second connection information includes: the end point of the target transmission line is connected with the start point of the adjacent transmission line, and the end point of the target transmission line is connected with the end point of the adjacent transmission line.
4. The method of claim 3, wherein the obtaining of the injection adjacency matrix comprises:
obtaining the injection adjacency matrix based on the target transmission line and the injected third connection information; wherein the third connection information includes: the injection is connected to the beginning of the target transmission line and the injection is connected to the end of the target transmission line.
5. A power distribution network line vectorization device based on a neural network is characterized by comprising the following components:
the graph model building module is used for building a graph model based on the connection relation between the transmission line of the power distribution network and the electrical equipment; wherein the transmission lines serve as nodes in the graph model, the connection of the transmission lines serves as an edge of the graph model, and the electrical equipment serves as the injection of the graph model;
the characteristic acquisition module is used for acquiring injection characteristic vectors, line adjacency matrixes and injection adjacency matrixes which respectively correspond to the target transmission lines on the basis of the graph model; the target transmission line is a transmission line corresponding to any node; the injected eigenvectors represent the properties of the target transmission line and the corresponding injection; the line adjacency matrix represents the connection relation between the target transmission line and the adjacent transmission line; the injection adjacency matrix represents the connection relation between injection and the target transmission line;
the injection embedding module is used for embedding the injection characteristic vector and the injection adjacent matrix into the characteristic of the node of the graph model based on a neural network to obtain a first line characteristic vector of the target transmission line; wherein the first line eigenvector comprises a connection relationship between the target transmission line and the injection; the implantation ofThe module is specifically configured to map the injected feature vector into a d-dimensional space based on a neural network, so as to obtain a d-dimensional vector; wherein d is an integer greater than 2; multiplying the d-dimensional vector to the injection adjacency matrix to obtain the first line characteristic vector; the mapping the injected feature vector into a d-dimensional space based on the neural network to obtain a d-dimensional vector, including: based on the number of the neurons respectively being (d) in 10, d), mapping the injected feature vector to a d-dimensional space to obtain a d-dimensional vector; wherein d is in Is the dimension of the injected feature vector;
the characteristic vector acquisition module is used for updating the first line characteristic vector based on the line adjacency matrix to acquire a second line characteristic vector of the target transmission line; the line adjacency matrix comprises a starting point adjacency matrix and an end point adjacency matrix; the feature vector acquisition module is specifically configured to acquire first propagation information based on a sum of products of the starting point adjacency matrix and the end point adjacency matrix, respectively, and first reservation information; wherein the first retention information is the first line feature vector; obtaining second reservation information based on a sum of the first propagation information and the first reservation information; obtaining second propagation information based on a sum of products of the start-point adjacency matrix and the end-point adjacency matrix, respectively, and the second reservation information; iteratively updating the second retained information based on a sum of the second propagation information and the second retained information until the second line feature vector is obtained.
6. The apparatus of claim 5, wherein the feature acquisition module is specifically configured to:
obtaining a consumption of the implant and a production of the implant based on the type of the implant; wherein the injected consumption is an electrical device consuming electrical energy and the injected generation is an electrical device producing electrical energy;
representing attributes of the target transmission line, the injected consumption, and the injected production as two-dimensional information;
obtaining the injection eigenvector based on two-dimensional information corresponding to the attributes of the target transmission line, the consumption of the injection, and the production of the injection.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010251558.2A CN111598123B (en) | 2020-04-01 | 2020-04-01 | Power distribution network line vectorization method and device based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010251558.2A CN111598123B (en) | 2020-04-01 | 2020-04-01 | Power distribution network line vectorization method and device based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598123A CN111598123A (en) | 2020-08-28 |
| CN111598123B true CN111598123B (en) | 2022-09-02 |
Family
ID=72190470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010251558.2A Active CN111598123B (en) | 2020-04-01 | 2020-04-01 | Power distribution network line vectorization method and device based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598123B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111537831B (en) * | 2020-04-01 | 2022-06-24 | 华中科技大学鄂州工业技术研究院 | Power distribution network line fault positioning method and device |
| CN112214775B (en) * | 2020-10-09 | 2024-04-05 | 深圳赛安特技术服务有限公司 | Injection attack method, device, medium and electronic equipment for preventing third party from acquiring key diagram data information and diagram data |
| CN112666423B (en) * | 2020-12-03 | 2021-08-17 | 广州电力通信网络有限公司 | Testing device for power communication network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016004361A1 (en) * | 2014-07-02 | 2016-01-07 | North Carolina A&T State University | System and method for assessing smart power grid networks |
| CN106384302A (en) * | 2016-09-30 | 2017-02-08 | 南方电网科学研究院有限责任公司 | Power distribution network reliability assessment method and system |
| CN108280574A (en) * | 2018-01-19 | 2018-07-13 | 国家电网公司 | A kind of evaluation method and device of distribution net work structure maturity |
| WO2019001071A1 (en) * | 2017-06-28 | 2019-01-03 | 浙江大学 | Adjacency matrix-based graph feature extraction system and graph classification system and method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100114890A1 (en) * | 2008-10-31 | 2010-05-06 | Purediscovery Corporation | System and Method for Discovering Latent Relationships in Data |
| US8024051B2 (en) * | 2009-02-24 | 2011-09-20 | Oracle America, Inc. | Parallel power grid analysis |
| US20190005384A1 (en) * | 2017-06-29 | 2019-01-03 | General Electric Company | Topology aware graph neural nets |
-
2020
- 2020-04-01 CN CN202010251558.2A patent/CN111598123B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016004361A1 (en) * | 2014-07-02 | 2016-01-07 | North Carolina A&T State University | System and method for assessing smart power grid networks |
| CN106384302A (en) * | 2016-09-30 | 2017-02-08 | 南方电网科学研究院有限责任公司 | Power distribution network reliability assessment method and system |
| WO2019001071A1 (en) * | 2017-06-28 | 2019-01-03 | 浙江大学 | Adjacency matrix-based graph feature extraction system and graph classification system and method |
| CN108280574A (en) * | 2018-01-19 | 2018-07-13 | 国家电网公司 | A kind of evaluation method and device of distribution net work structure maturity |
Non-Patent Citations (4)
| Title |
|---|
| A Complex-Network Approach to the Generation of Synthetic Power Transmission Networks;Rafael Espejo et al;《IEEE Systems Journal》;20180828;全文 * |
| GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models;Jiaxuan You et al;《Proceedings of the 35th International Conference on Machine Learning》;20181231;全文 * |
| 含分布式电源配电网故障恢复与可靠性评估研究;王昌照;《中国博士学位论文数据库》;20150615;全文 * |
| 基于有序二叉决策图的电网主动解列策略搜索方法研究;马帅;《中国硕士学位论文全文数据库》;20170615;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598123A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111598123B (en) | Power distribution network line vectorization method and device based on neural network | |
| CN111537831B (en) | Power distribution network line fault positioning method and device | |
| Koutsoukis et al. | Numerical observability method for optimal phasor measurement units placement using recursive Tabu search method | |
| CN109120462B (en) | Method and device for predicting opportunistic network link and readable storage medium | |
| CN110766038B (en) | Unsupervised landform classification model training and landform image construction method | |
| CN111383303A (en) | Method and device for automatically generating plane of residential building | |
| CN112883801A (en) | Accurate identification method for household distribution box system diagram subgraph in CAD distribution system diagram | |
| Yu et al. | Two‐step method for the online parameter identification of a new simplified composite load model | |
| CN111159897A (en) | Target optimization method and device based on system modeling application | |
| CN115240048A (en) | Deep learning operator positioning fusion method and device for image classification | |
| CN113962163A (en) | Optimization method, device and equipment for realizing efficient design of passive microwave device | |
| Zhu et al. | Fault location in AC transmission lines with back‐to‐back MMC‐HVDC using ConvNets | |
| CN111126607B (en) | Data processing method, device and system for model training | |
| CN117350336A (en) | Charging load prediction and model training method, device, equipment and storage medium | |
| CN112183303A (en) | Transformer equipment image classification method and device, computer equipment and medium | |
| CN116978450A (en) | Protein data processing method, device, electronic equipment and storage medium | |
| Lima et al. | Modelling of non‐uniform lines using rational approximation and mode revealing transformation | |
| Shi et al. | Study on quick judgement of small signal stability using CNN | |
| Aboulhassan et al. | Comparative Visual Analysis of Structure‐Performance Relations in Complex Bulk‐Heterojunction Morphologies | |
| CN111696120B (en) | Point cloud data segmentation method and device, electronic equipment and storage medium | |
| Zhang et al. | SLIC segmentation method for full‐polarised remote‐sensing image | |
| Kalra et al. | Automated scheme for linearisation points selection in TPWL method applied to non‐linear circuits | |
| CN113313079B (en) | Training method and system of vehicle attribute recognition model and related equipment | |
| CN117649530B (en) | Point cloud feature extraction method, system and equipment based on semantic level topological structure | |
| CN117540828B (en) | Training method and device for training subject recommendation model, electronic equipment and storage medium |
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 |