CN110533265A - A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device - Google Patents

A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device Download PDF

Info

Publication number
CN110533265A
CN110533265A CN201910892080.9A CN201910892080A CN110533265A CN 110533265 A CN110533265 A CN 110533265A CN 201910892080 A CN201910892080 A CN 201910892080A CN 110533265 A CN110533265 A CN 110533265A
Authority
CN
China
Prior art keywords
data
data matrix
power distribution
distribution network
sample point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910892080.9A
Other languages
Chinese (zh)
Inventor
李维
郭俊
王洪林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Electric Power Research Institute of Yunnan Power System Ltd
Original Assignee
Electric Power Research Institute of Yunnan Power System Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Electric Power Research Institute of Yunnan Power System Ltd filed Critical Electric Power Research Institute of Yunnan Power System Ltd
Priority to CN201910892080.9A priority Critical patent/CN110533265A/en
Publication of CN110533265A publication Critical patent/CN110533265A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/10—Devices for predicting weather conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Software Systems (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Atmospheric Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Quality & Reliability (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Development Economics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a kind of power distribution network lightning stroke method for early warning and power distribution network lightning stroke prior-warning device, this method comprises: obtaining historical data, and according to the historical data, establishes the first data matrix；First data matrix is about subtracted, the second data matrix is obtained；Second data matrix is trained using support vector machines, obtains power distribution network lightning stroke Early-warning Model；The second microclimate data are obtained in real time, and according to the second microclimate data obtained in real time, establish third data matrix；The third data matrix is input in the power distribution network lightning stroke Early-warning Model, lightning stroke warning information is obtained.In this way, having fully considered that the correlation between the multivariable for causing power distribution network to be struck by lightning, lightning stroke early warning effect are preferable since the power distribution network lightning stroke Early-warning Model established covers a variety of variables.

Description

A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device
Technical field
This application involves technical field of power systems more particularly to a kind of power distribution network lightning stroke method for early warning and power distribution network thunder Hit prior-warning device.
Background technique
Power distribution network is run often by adverse weather conditions such as wind, rain, thunder and lightning or ice and snow.Wherein, thunder and lightning has become Influence one of the principal element of power distribution network safe operation.How it is monitored and early warning becomes particularly significant.
Lightning stroke is strong electric discharge phenomena in nature, causes lightning stroke to occur many because being known as.It is first exactly meteorological condition, Followed by environmental parameter locating for power transmission line corridor.For example, the landform in shaft tower location, landforms, periphery vegetation etc..Cause There are also the associated body attributes of transmission line of electricity for the factor that thunder and lightning occurs.For example, shaft tower exhales title height and voltage class etc..
It in the related technology, is that transmission line lightning stroke early warning is realized in the movement tendency prediction based on thundercloud group, according only to thundercloud Short-term thundercloud group motion profile prediction model is established in the movement of group, and when thundercloud group is close to power transmission line corridor, starting lightning stroke is in advance It is alert.Such method is only analyzed using unitary variant, and lightning stroke early warning effect is poor.
Summary of the invention
This application provides a kind of power distribution network lightning stroke method for early warning and power distribution network lightning stroke prior-warning devices, to solve related skill It in art, is only analyzed using unitary variant, the poor problem of lightning stroke early warning effect.
On the one hand, the application provides a kind of power distribution network lightning stroke method for early warning, comprising:
Historical data is obtained, and according to the historical data, establishes the first data matrix, wherein the historical data packet Include the electric power line pole tower elevation data, the first microclimate data, shaft tower terrain data, relief data, shaft tower of the power distribution network Periphery surface data, soil regime data and shaft tower, which are exhaled, claims high data；
First data matrix is about subtracted, the second data matrix is obtained；
Second data matrix is trained using support vector machines, obtains power distribution network lightning stroke Early-warning Model；
The second microclimate data are obtained in real time, and according to the second microclimate data obtained in real time, establish third data square Battle array；
The third data matrix is input in the power distribution network lightning stroke Early-warning Model, lightning stroke warning information is obtained.
Optionally, before the step of about being subtracted described to first data matrix, obtaining the second data matrix, institute State method further include:
First data matrix is normalized, the 4th data matrix is obtained；
It is described that first data matrix is about subtracted, obtain the second data matrix, comprising:
4th data matrix is about subtracted, second data matrix is obtained.
Optionally, described that 4th data matrix is about subtracted, obtain second data matrix, comprising:
Calculate the Euclidean distance in multiple sample points that the 4th data matrix is included between any two sample point；
According to the Euclidean distance between any two sample point being calculated, included in the 4th data matrix The smallest K first sample point of Euclidean distance between sample point is searched in multiple sample points, wherein K is integer, and K >=2；
According to the K first sample point, the 4th data matrix is about subtracted, obtains the second data square Battle array.
Optionally, described according to the K first sample point, the 4th data matrix is about subtracted, described in acquisition Second data matrix, comprising:
It determines in multiple sample points that the 4th data matrix is included generic second in preceding K the second sample points The destination number of sample point；
Judge whether the destination number is less than δ, wherein δ is integer, and 0 < δ≤K/2；
In the case where the destination number is less than δ, multiple sample points included in the 4th data matrix are deleted In preceding K the second sample points.
Optionally, described according to the K first sample point, the 4th data matrix is about subtracted, described in acquisition Second data matrix, comprising:
It detects in the K first sample point with the presence or absence of identical first sample point；
There are in the case where identical first sample point in the K first sample point, the 4th data square is deleted The K first sample point in multiple sample points that battle array is included, obtains second data matrix.
On the other hand, the application also provides a kind of power distribution network lightning stroke prior-warning device, comprising:
First acquisition module establishes the first data matrix for obtaining historical data, and according to the historical data, In, the historical data includes the electric power line pole tower elevation data of the power distribution network, the first microclimate data, shaft tower ground figurate number According to, relief data, shaft tower periphery surface data, soil regime data and shaft tower exhale and claim high data；
About subtract module, for about being subtracted to first data matrix, obtains the second data matrix；
Training module obtains power distribution network lightning stroke for being trained using support vector machines to second data matrix Early-warning Model；
Second obtains module, for obtaining the second microclimate data in real time, and according to the second microclimate number obtained in real time According to establishing third data matrix；
Input module obtains thunder for the third data matrix to be input in the power distribution network lightning stroke Early-warning Model Hit warning information.
Optionally, the power distribution network lightning stroke prior-warning device further include:
Normalized module obtains the 4th data matrix for first data matrix to be normalized；
The module that about subtracts is specifically used for about subtracting the 4th data matrix, obtains second data matrix.
Optionally, the module that about subtracts includes:
Computational submodule, for calculating any two sample point in multiple sample points that the 4th data matrix is included Between Euclidean distance；
Submodule is searched, the Euclidean distance between any two sample point being calculated for basis, the described 4th The smallest K first sample point of Euclidean distance between sample point is searched in multiple sample points that data matrix is included, wherein K is integer, and K >=2；
About subtract submodule, for about being subtracted to the 4th data matrix according to the K first sample point, obtains Second data matrix.
Optionally, the submodule that about subtracts includes:
Determination unit, for determining preceding K the second sample points in multiple sample points that the 4th data matrix is included In generic the second sample point destination number；
Judging unit, for judging whether the destination number is less than δ, wherein δ is integer, and 0 < δ≤K/2；
First deletes unit, for deleting institute in the 4th data matrix in the case where the destination number is less than δ The preceding K in multiple sample points the second sample points for including.
It is optionally, described about to subtract submodule further include:
Detection unit, for detecting in the K first sample point with the presence or absence of identical first sample point；
Second deletes unit, for, there are in the case where identical first sample point, deleting in the K first sample point The K first sample point in the multiple sample points for being included except the 4th data matrix obtains the second data square Battle array.
From the above technical scheme, the application provides a kind of power distribution network lightning stroke method for early warning and power distribution network lightning stroke early warning Device, which comprises obtain historical data, and according to the historical data, establish the first data matrix, wherein described Historical data includes the electric power line pole tower elevation data of the power distribution network, the first microclimate data, shaft tower terrain data, landforms Data, shaft tower periphery surface data, soil regime data and shaft tower, which are exhaled, claims high data；First data matrix is carried out about Subtract, obtains the second data matrix；Second data matrix is trained using support vector machines, it is pre- to obtain power distribution network lightning stroke Alert model；The second microclimate data are obtained in real time, and according to the second microclimate data obtained in real time, establish third data square Battle array；The third data matrix is input in the power distribution network lightning stroke Early-warning Model, lightning stroke warning information is obtained.In this way, can To establish power distribution network lightning stroke Early-warning Model, the second microclimate data can be obtained in real time, and according to obtain in real time second micro- gas Image data establishes third data matrix.And then third data matrix can be input in power distribution network lightning stroke Early-warning Model, it obtains Lightning stroke warning information.Since the power distribution network lightning stroke Early-warning Model established covers a variety of variables, fully considers and caused distribution The correlation between the multivariable of lightning stroke is netted, lightning stroke early warning effect is preferable.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below Singly introduce, it should be apparent that, for those of ordinary skills, without creative efforts, also Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 is a kind of flow chart of power distribution network lightning stroke method for early warning provided by the present application；
Fig. 2 is a kind of structure chart of power distribution network lightning stroke prior-warning device provided by the present application；
Fig. 3 is the structure chart of another power distribution network lightning stroke prior-warning device provided by the present application；
Fig. 4 is the structure chart of another power distribution network lightning stroke prior-warning device provided by the present application；
Fig. 5 is the structure chart of another power distribution network lightning stroke prior-warning device provided by the present application；
Fig. 6 is the structure chart of another power distribution network lightning stroke prior-warning device provided by the present application.
Specific embodiment
Embodiment will be illustrated in detail below, the example is illustrated in the accompanying drawings.In the following description when referring to the accompanying drawings, Unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Implement described in following embodiment Mode does not represent all embodiments consistent with the application.It is only and be described in detail in claims, the application The example of the consistent system and method for some aspects.
It is a kind of flow chart of power distribution network lightning stroke method for early warning provided by the present application referring to Fig. 1, Fig. 1.As shown in Figure 1, packet Include following steps:
Step 101 obtains historical data, and according to the historical data, establishes the first data matrix, wherein described to go through History data include the electric power line pole tower elevation data of the power distribution network, the first microclimate data, shaft tower terrain data, landforms number According to, shaft tower periphery surface data, soil regime data and shaft tower exhale and claim high data.
In a step 101, available historical data, and according to historical data, establish the first data matrix X ∈ RD, Middle D is data dimension.Wherein, historical data includes the electric power line pole tower elevation data of power distribution network, the first microclimate data, bar Tower terrain data, relief data, shaft tower periphery surface data, soil regime data and shaft tower, which are exhaled, claims high data.Above-mentioned history number Historical data accessed under normal condition is according to for power distribution network.
Step 102 about subtracts first data matrix, obtains the second data matrix.
In a step 102, the first data matrix can about be subtracted, obtains the second data matrix.
Optionally, before the step of about being subtracted described to first data matrix, obtaining the second data matrix, institute State method further include:
First data matrix is normalized, the 4th data matrix is obtained；
It is described that first data matrix is about subtracted, obtain the second data matrix, comprising:
4th data matrix is about subtracted, second data matrix is obtained.
Further, first the first data matrix can be normalized, obtains the 4th data matrix.For example, can With by the first data matrix by filling up by hand or the methods of mean value is filled up fills up missing data, and to the first data matrix into The 4th data matrix is formed after row normalized.Normalized is that instigate the mean value of each process variable be zero, and variance is 1.4th data matrix can beN is the sample number of the 4th data matrix.
Next, can about be subtracted to the 4th data matrix, the second data matrix is obtained.It should be noted that can be with The 4th data matrix is about subtracted using nearest neighbor algorithm (k-Nearest Neighbor, KNN), obtains the second data matrix.
Optionally, described that 4th data matrix is about subtracted, obtain second data matrix, comprising:
Calculate the Euclidean distance in multiple sample points that the 4th data matrix is included between any two sample point；
According to the Euclidean distance between any two sample point being calculated, included in the 4th data matrix The smallest K first sample point of Euclidean distance between sample point is searched in multiple sample points, wherein K is integer, and K >=2；
According to the K first sample point, the 4th data matrix is about subtracted, obtains the second data square Battle array.
Further, it can calculate in multiple sample points that the 4th data matrix is included between any two sample point Euclidean distance.For example,WhereinThe feature vector of example, yi∈ γ= {c1,c2,···,ckBe example classification.
The calculation formula of Euclidean distance between any two sample point such as formula (1):
Next, can be according to the Euclidean distance between any two sample point being calculated, in the 4th data matrix The smallest K first sample point of Euclidean distance between sample point is searched in the multiple sample points for being included.Wherein, K is integer, And K >=2.It is then possible to about be subtracted according to K first sample point to the 4th data matrix, the second data matrix is obtained.
Optionally, described according to the K first sample point, the 4th data matrix is about subtracted, described in acquisition Second data matrix, comprising:
It determines in multiple sample points that the 4th data matrix is included generic second in preceding K the second sample points The destination number of sample point；
Judge whether the destination number is less than δ, wherein δ is integer, and 0 < δ≤K/2；
In the case where the destination number is less than δ, multiple sample points included in the 4th data matrix are deleted In preceding K the second sample points.
It can determine in multiple sample points that the 4th data matrix is included generic second in preceding K the second sample points The destination number of sample point, and then may determine that whether the destination number is less than δ.Wherein, δ is integer, and 0 < δ≤K/2.Upper Destination number is stated less than preceding K second in the case where δ, can deleting in multiple sample points included in the 4th data matrix Sample point.
Optionally, described according to the K first sample point, the 4th data matrix is about subtracted, described in acquisition Second data matrix, comprising:
It detects in the K first sample point with the presence or absence of identical first sample point；
There are in the case where identical first sample point in the K first sample point, the 4th data square is deleted The K first sample point in multiple sample points that battle array is included, obtains second data matrix.
It can also detect in K first sample point with the presence or absence of identical first sample point.It is deposited in K first sample point In the case where identical first sample point, K first in multiple sample points that the 4th data matrix is included can be deleted Sample point obtains the second data matrix.
Step 103 is trained second data matrix using support vector machines, obtains power distribution network lightning stroke early warning mould Type.
In step 103, it can use support vector machines (Support Vector Machine, SVM) to the second data Matrix is trained, and obtains power distribution network lightning stroke Early-warning Model.
For example, the second data matrix is (x1,y1), i=1,2 ..., l, x ∈ Rn, y ∈ { 0,1 }, building optimal classification it is super flat Face ω x+b=0.For ensure classifying face can two class data separate and make the distance between two class supporting vectors maximum, It is asked to meet formula (2), can obtain class interval is 2/ | | ω | |.Then the problem of constructing optimal separating hyper plane is converted into following band The minimum problems of constraint, and Lagrangian Lagrange function is introduced, such as formula (3):
yi[(ωgxi)+b] >=1, i=1,2, L, l (2)
Wherein ai> 0 is Lagrange coefficient.Constrained optimization problem determines by the saddle point condition of Lagrange function, and And it is 0 that the solution of optimization problem, which meets at saddle point to the local derviation of ω and b,.
Dual problem (a=(a as shown in formula (4) is converted by the quadratic programming problem1,a2,…,al)):
By calculating, best initial weights vector sum is optimal to be biased respectively formula (6), formula (7):
WhereinOptimal separating hyper plane is ω*·x+b*=0, and optimal classification function such as formula (8) institute Show:
Wherein, x ∈ Rn。
At this point, SVM training terminates, the parameter value for the Early-warning Model that power distribution network can be struck by lightning is saved.
Step 104 obtains the second microclimate data in real time, and according to the second microclimate data obtained in real time, establishes the Three data matrixes.
At step 104, the second microclimate data can be obtained in real time, and according to the second microclimate number obtained in real time According to establishing third data matrix.
The third data matrix is input in the power distribution network lightning stroke Early-warning Model by step 105, obtains lightning stroke early warning Information.
In step 105, third data matrix can be input in power distribution network lightning stroke Early-warning Model, obtains lightning stroke early warning Information.
It should be noted that being that the movement tendency prediction based on thundercloud group realizes that transmission line lightning stroke is pre- in the related technology Alert, short-term thundercloud group motion profile prediction model is established in the movement according only to thundercloud group, when thundercloud is rolled into a ball close to transmission line of electricity Starting lightning stroke early warning when corridor.Such method is only analyzed using unitary variant, and lightning stroke early warning effect is poor.
And in this application, it can establish power distribution network lightning stroke Early-warning Model, the second microclimate data can be obtained in real time, and According to the second microclimate data obtained in real time, third data matrix is established.And then third data matrix can be input to and be matched Power grid is struck by lightning in Early-warning Model, obtains lightning stroke warning information.By established power distribution network lightning stroke Early-warning Model cover it is a variety of Variable has fully considered that the correlation between the multivariable for causing power distribution network to be struck by lightning, lightning stroke early warning effect are preferable.
A kind of power distribution network lightning stroke method for early warning provided by the present application.Historical data is obtained, and according to the historical data, is built Vertical first data matrix, wherein the historical data includes the electric power line pole tower elevation data of the power distribution network, first micro- gas Image data, shaft tower terrain data, relief data, shaft tower periphery surface data, soil regime data and shaft tower, which are exhaled, claims high data；It is right First data matrix is about subtracted, and the second data matrix is obtained；Using support vector machines to second data matrix into Row training obtains power distribution network lightning stroke Early-warning Model；The second microclimate data are obtained in real time, and according to obtain in real time second micro- gas Image data establishes third data matrix；The third data matrix is input in the power distribution network lightning stroke Early-warning Model, is obtained Lightning stroke warning information.In this way, can establish power distribution network lightning stroke Early-warning Model, the second microclimate data, and root can be obtained in real time The the second microclimate data obtained when factually, establish third data matrix.And then third data matrix can be input to distribution In net lightning stroke Early-warning Model, lightning stroke warning information is obtained.Since the power distribution network lightning stroke Early-warning Model established covers a variety of changes Amount has fully considered that the correlation between the multivariable for causing power distribution network to be struck by lightning, lightning stroke early warning effect are preferable.
Referring to fig. 2, Fig. 2 is a kind of structure chart of power distribution network lightning stroke prior-warning device provided by the present application.As shown in Fig. 2, matching Power grid lightning stroke prior-warning device 200 includes the first acquisition module 201, about subtracts module 202, the acquisition module of training module 203, second 204 and input module 205, in which:
First acquisition module 201 establishes the first data matrix for obtaining historical data, and according to the historical data, Wherein, the historical data includes the electric power line pole tower elevation data of the power distribution network, the first microclimate data, shaft tower landform Data, relief data, shaft tower periphery surface data, soil regime data and shaft tower, which are exhaled, claims high data；
About subtract module 202, for about being subtracted to first data matrix, obtains the second data matrix；
Training module 203 obtains power distribution network thunder for being trained using support vector machines to second data matrix Hit Early-warning Model；
Second obtains module 204, for obtaining the second microclimate data in real time, and according to the second microclimate obtained in real time Data establish third data matrix；
Input module 205 is obtained for the third data matrix to be input in the power distribution network lightning stroke Early-warning Model Lightning stroke warning information.
Optionally, the prior-warning device as shown in figure 3, power distribution network is struck by lightning further include:
Normalized module 206 obtains the 4th data square for first data matrix to be normalized Battle array；
The module 202 that about subtracts is specifically used for about subtracting the 4th data matrix, obtains the second data square Battle array.
Optionally, as shown in figure 4, the module 202 that about subtracts includes:
Computational submodule 2021, for calculating any two sample in multiple sample points that the 4th data matrix is included Euclidean distance between this point；
Submodule 2022 is searched, the Euclidean distance between any two sample point being calculated for basis, described The smallest K first sample point of Euclidean distance between sample point is searched in multiple sample points that 4th data matrix is included, Wherein, K is integer, and K >=2；
About subtract submodule 2023, for about being subtracted to the 4th data matrix according to the K first sample point, Obtain second data matrix.
Optionally, as shown in figure 5, the submodule 2023 that about subtracts includes:
Determination unit 20231, for determining preceding K the second samples in multiple sample points that the 4th data matrix is included The destination number of the second generic sample point in this point；
Judging unit 20232, for judging whether the destination number is less than δ, wherein δ is integer, and 0 < δ≤K/2；
First deletes unit 20233, for deleting the 4th data square in the case where the destination number is less than δ Preceding K the second sample points in multiple sample points included in battle array.
Optionally, as shown in fig. 6, described about subtract submodule 2023 further include:
Detection unit 20234, for detecting in the K first sample point with the presence or absence of identical first sample point；
Second deletes unit 20235, for the case where there are identical first sample points in the K first sample point Under, the K first sample point in multiple sample points that the 4th data matrix is included is deleted, second number is obtained According to matrix.
Power distribution network lightning stroke prior-warning device 200 can be realized power distribution network lightning stroke prior-warning device in the embodiment of the method for Fig. 1 and realize Each process, to avoid repeating, which is not described herein again.And power distribution network lightning stroke prior-warning device 200 may be implemented to establish power distribution network It is struck by lightning Early-warning Model, can obtain the second microclimate data in real time, and according to the second microclimate data obtained in real time, establish the Three data matrixes.And then third data matrix can be input in power distribution network lightning stroke Early-warning Model, obtain lightning stroke warning information. Since the power distribution network lightning stroke Early-warning Model established covers a variety of variables, the multivariable for causing power distribution network to be struck by lightning has been fully considered Between correlation, lightning stroke early warning effect it is preferable.
Similar portion cross-reference between embodiment provided by the present application, specific embodiment provided above is only It is several examples under the total design of the application, does not constitute the restriction of the application protection scope.For those skilled in the art For member, any other embodiment expanded without creative efforts according to application scheme all belongs to In the protection scope of the application.

Claims (10)

  1. The method for early warning 1. a kind of power distribution network is struck by lightning characterized by comprising
    Historical data is obtained, and according to the historical data, establishes the first data matrix, wherein the historical data includes institute State electric power line pole tower elevation data, the first microclimate data, shaft tower terrain data, the relief data, shaft tower periphery of power distribution network Surface data, soil regime data and shaft tower, which are exhaled, claims high data；
    First data matrix is about subtracted, the second data matrix is obtained；
    Second data matrix is trained using support vector machines, obtains power distribution network lightning stroke Early-warning Model；
    The second microclimate data are obtained in real time, and according to the second microclimate data obtained in real time, establish third data matrix；
    The third data matrix is input in the power distribution network lightning stroke Early-warning Model, lightning stroke warning information is obtained.
  2. 2. the method as described in claim 1, which is characterized in that about subtracted described to first data matrix, obtained Before the step of second data matrix, the method also includes:
    First data matrix is normalized, the 4th data matrix is obtained；
    It is described that first data matrix is about subtracted, obtain the second data matrix, comprising:
    4th data matrix is about subtracted, second data matrix is obtained.
  3. 3. method according to claim 2, which is characterized in that it is described that 4th data matrix is about subtracted, obtain institute State the second data matrix, comprising:
    Calculate the Euclidean distance in multiple sample points that the 4th data matrix is included between any two sample point；
    According to the Euclidean distance between any two sample point being calculated, the 4th data matrix included it is multiple The smallest K first sample point of Euclidean distance between sample point is searched in sample point, wherein K is integer, and K >=2；
    According to the K first sample point, the 4th data matrix is about subtracted, obtains second data matrix.
  4. 4. method as claimed in claim 3, which is characterized in that it is described according to the K first sample point, to the 4th number About subtracted according to matrix, obtain second data matrix, comprising:
    Determine the second sample generic in preceding K the second sample points in multiple sample points that the 4th data matrix is included The destination number of point；
    Judge whether the destination number is less than δ, wherein δ is integer, and 0 < δ≤K/2；
    In the case where the destination number is less than δ, delete in multiple sample points included in the 4th data matrix Preceding K the second sample points.
  5. 5. method as claimed in claim 3, which is characterized in that it is described according to the K first sample point, to the 4th number About subtracted according to matrix, obtain second data matrix, comprising:
    It detects in the K first sample point with the presence or absence of identical first sample point；
    There are in the case where identical first sample point in the K first sample point, the 4th data matrix institute is deleted The K first sample point in the multiple sample points for including obtains second data matrix.
  6. The prior-warning device 6. a kind of power distribution network is struck by lightning characterized by comprising
    First acquisition module establishes the first data matrix, wherein institute for obtaining historical data, and according to the historical data State historical data include the electric power line pole tower elevation data of the power distribution network, the first microclimate data, shaft tower terrain data, Looks data, shaft tower periphery surface data, soil regime data and shaft tower, which are exhaled, claims high data；
    About subtract module, for about being subtracted to first data matrix, obtains the second data matrix；
    Training module obtains power distribution network lightning stroke early warning for being trained using support vector machines to second data matrix Model；
    Second obtains module, for obtaining the second microclimate data in real time, and according to the second microclimate data obtained in real time, builds Vertical third data matrix；
    It is pre- to obtain lightning stroke for the third data matrix to be input in the power distribution network lightning stroke Early-warning Model for input module Alert information.
  7. The prior-warning device 7. power distribution network as claimed in claim 6 is struck by lightning, which is characterized in that the power distribution network lightning stroke prior-warning device is also Include:
    Normalized module obtains the 4th data matrix for first data matrix to be normalized；
    The module that about subtracts is specifically used for about subtracting the 4th data matrix, obtains second data matrix.
  8. The prior-warning device 8. power distribution network as claimed in claim 7 is struck by lightning, which is characterized in that the module that about subtracts includes:
    Computational submodule, for calculating in multiple sample points that the 4th data matrix is included between any two sample point Euclidean distance；
    Submodule is searched, the Euclidean distance between any two sample point being calculated for basis, in the 4th data The smallest K first sample point of Euclidean distance between sample point is searched in multiple sample points that matrix is included, wherein K is Integer, and K >=2；
    About subtract submodule, for about being subtracted to the 4th data matrix, described in acquisition according to the K first sample point Second data matrix.
  9. The prior-warning device 9. power distribution network as claimed in claim 8 is struck by lightning, which is characterized in that the submodule that about subtracts includes:
    Determination unit, it is same in preceding K the second sample points for determining in multiple sample points that the 4th data matrix is included The destination number of second sample point of classification；
    Judging unit, for judging whether the destination number is less than δ, wherein δ is integer, and 0 < δ≤K/2；
    First deletes unit, for deleting included in the 4th data matrix in the case where the destination number is less than δ Multiple sample points in preceding K the second sample points.
  10. The prior-warning device 10. power distribution network as claimed in claim 8 is struck by lightning, which is characterized in that described about to subtract submodule further include:
    Detection unit, for detecting in the K first sample point with the presence or absence of identical first sample point；
    Second deletes unit, for, there are in the case where identical first sample point, deleting institute in the K first sample point The K first sample point in multiple sample points that the 4th data matrix is included is stated, second data matrix is obtained.
CN201910892080.9A 2019-09-20 2019-09-20 A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device Pending CN110533265A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910892080.9A CN110533265A (en) 2019-09-20 2019-09-20 A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910892080.9A CN110533265A (en) 2019-09-20 2019-09-20 A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device

Publications (1)

Publication Number Publication Date
CN110533265A true CN110533265A (en) 2019-12-03

Family

ID=68669391

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910892080.9A Pending CN110533265A (en) 2019-09-20 2019-09-20 A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device

Country Status (1)

Country Link
CN (1) CN110533265A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111275193A (en) * 2020-01-15 2020-06-12 杭州华网信息技术有限公司 National power grid lightning stroke prediction method
CN113295935A (en) * 2021-06-01 2021-08-24 兰州资源环境职业技术学院 Lightning stroke risk assessment method based on high-precision lightning positioning technology
CN115099531A (en) * 2022-08-19 2022-09-23 国网江苏省电力有限公司苏州供电分公司 Power transmission line lightning stroke early warning method and system based on support vector machine

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104268576A (en) * 2014-10-11 2015-01-07 国家电网公司 Electric system transient stability classification method based on TNN-SVM
CN106771847A (en) * 2016-11-21 2017-05-31 国网福建省电力有限公司厦门供电公司 A kind of 35kV power distribution networks transmission line lightning stroke Risk Forecast Method
CN107085755A (en) * 2017-05-15 2017-08-22 内蒙古电力(集团)有限责任公司 A kind of photovoltaic plant short term power Forecasting Methodology and system
CN107784015A (en) * 2016-08-30 2018-03-09 中国电力科学研究院 A kind of Data Reduction method based on the online historical data of power system
CN107832875A (en) * 2017-10-27 2018-03-23 云南电网有限责任公司电力科学研究院 A kind of transmission line lightning stroke failure prediction method of improved adaptive GA-IAGA Support Vector Machines Optimized
CN109543870A (en) * 2018-05-28 2019-03-29 云南大学 A kind of electric power line pole tower lightning stroke method for early warning keeping embedded mobile GIS based on neighborhood

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104268576A (en) * 2014-10-11 2015-01-07 国家电网公司 Electric system transient stability classification method based on TNN-SVM
CN107784015A (en) * 2016-08-30 2018-03-09 中国电力科学研究院 A kind of Data Reduction method based on the online historical data of power system
CN106771847A (en) * 2016-11-21 2017-05-31 国网福建省电力有限公司厦门供电公司 A kind of 35kV power distribution networks transmission line lightning stroke Risk Forecast Method
CN107085755A (en) * 2017-05-15 2017-08-22 内蒙古电力(集团)有限责任公司 A kind of photovoltaic plant short term power Forecasting Methodology and system
CN107832875A (en) * 2017-10-27 2018-03-23 云南电网有限责任公司电力科学研究院 A kind of transmission line lightning stroke failure prediction method of improved adaptive GA-IAGA Support Vector Machines Optimized
CN109543870A (en) * 2018-05-28 2019-03-29 云南大学 A kind of electric power line pole tower lightning stroke method for early warning keeping embedded mobile GIS based on neighborhood

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
聂海福: "全景数据驱动的输电线路杆塔雷击预警模型研究及***设计", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111275193A (en) * 2020-01-15 2020-06-12 杭州华网信息技术有限公司 National power grid lightning stroke prediction method
CN113295935A (en) * 2021-06-01 2021-08-24 兰州资源环境职业技术学院 Lightning stroke risk assessment method based on high-precision lightning positioning technology
CN115099531A (en) * 2022-08-19 2022-09-23 国网江苏省电力有限公司苏州供电分公司 Power transmission line lightning stroke early warning method and system based on support vector machine
CN115099531B (en) * 2022-08-19 2023-01-31 国网江苏省电力有限公司苏州供电分公司 Power transmission line lightning stroke early warning method and system based on support vector machine

Similar Documents

Publication Publication Date Title
CN110533265A (en) A kind of power distribution network lightning stroke method for early warning and power distribution network are struck by lightning prior-warning device
US10891481B2 (en) Automated detection of features and/or parameters within an ocean environment using image data
CN110149237B (en) Hadoop platform computing node load prediction method
US20170261646A1 (en) Self-correcting multi-model numerical rainfall ensemble forecasting method
CN102072992B (en) Detailed terrain data-based transmission line failure-shielding and lightning-protection performance evaluation method
Mohandes et al. Wind speed extrapolation using machine learning methods and LiDAR measurements
CN104463700A (en) Power transmission line tower lightning strike risk evaluation method based on data mining technology
CN105488528A (en) Improved adaptive genetic algorithm based neural network image classification method
CN104200081B (en) The forecasting procedure and system of landfall typhoon characterization factor based on historical data
Chou Modelling watershed scale soil loss prediction and sediment yield estimation
CN108898247A (en) A kind of power grid Rainfall Disaster Risk Forecast Method, system and storage medium
CN109901020A (en) The fault recognition method for electric transmission line of sparse autocoder optimization neural network
CN108564263A (en) One kind is for the disaster-stricken prediction technique of electric power line pole tower under squall line environment
CN104039008B (en) A kind of hybrid locating method
CN115359366A (en) Remote sensing image target detection method based on parameter optimization
CN103345552A (en) Method and device for assessing reliability of power ICT communication network
Lu et al. An integrated damage modeling and assessment framework for overhead power distribution systems considering tree-failure risks
CN109284877A (en) Based on AIGA-WLSSVM Buried Pipeline rate prediction method
CN113313342A (en) Method and system for analyzing power grid equipment fault probability caused by multiple natural disasters
CN109523776A (en) Public transport operation plan generating means, method and system
CN116415495A (en) Lightning trip-out rate acquisition method and equipment for complex terrain and meteorological environment
CN116091801A (en) Rainfall image similarity searching method based on deep learning
CN113872524B (en) Method and device for positioning low-efficiency group strings and computer storage medium
CN114611777A (en) Method for predicting reservoir warehousing flow of flood season based on stacked long and short memory networks
CN115130661A (en) Model parameter optimization method, and time sequence data anomaly detection method and device

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20191203