CN109359896A - A kind of Guangdong power system method for prewarning risk based on SVM - Google Patents
A kind of Guangdong power system method for prewarning risk based on SVM Download PDFInfo
- Publication number
- CN109359896A CN109359896A CN201811502524.5A CN201811502524A CN109359896A CN 109359896 A CN109359896 A CN 109359896A CN 201811502524 A CN201811502524 A CN 201811502524A CN 109359896 A CN109359896 A CN 109359896A
- Authority
- CN
- China
- Prior art keywords
- route
- disaster
- power grid
- svm
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000005611 electricity Effects 0.000 claims abstract description 11
- 238000010276 construction Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 239000004020 conductor Substances 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000012706 support-vector machine Methods 0.000 abstract description 2
- 230000001771 impaired effect Effects 0.000 abstract 1
- 238000013139 quantization Methods 0.000 abstract 1
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of Guangdong power system method for prewarning risk based on SVM.The characteristics of this method is influenced using SVM study route by disaster and consequence, disaster-stricken vulnerability and impaired rear result to route carry out comprehensive analysis quantization；The present invention has comprehensively considered influence of a variety of disasters such as disaster caused by a windstorm, thunder calamity to power grid, and combats a natural disaster the significance level of performance and route in power grid in conjunction with power grid itself, and comprehensive analysis goes out the disaster-stricken loss of power grid caused by the corresponding line fault of route.It is subjective that the present invention solves the Guangdong power system Risk-warning that existing electricity has, use scope is relatively narrow, and the Meteorological Elements considered are more single, not the drawbacks of not meeting the disaster-stricken situation of actual electric network route, analytic hierarchy process (AHP) is replaced with algorithm of support vector machine, replaces single Meteorological Elements with three kinds of common Meteorological Elements, and invention also contemplates that significance level of the route in electric network composition, for the reference as power grid pre-disaster planning, better economic benefit can be brought.
Description
Technical field
The invention belongs to power grid involved in Electric Power Network Planning take precautions against natural calamities otherness planning field, and in particular to one kind be based on SVM
Guangdong power system method for prewarning risk.
Background technique
Nearly ten years, electric system major accident caused by natural calamity happens occasionally.Flood, typhoon, earthquake etc. are natural
Disaster causes destruction physically to power grid and grid equipment, and reparation takes a long time and a large amount of manpower
Material resources bring great loss to national product, life.Disaster-resistant type Power System Planning can greatly reduce natural calamity
It is lost caused by electric system and society；And Guangdong power system Risk-warning is the construction of combating a natural disaster property of power grid under hazardous condition,
Power grid is taken precautions against natural calamities the basis of transformation.
From the point of view of route angle, most directly improving the method that power grid combats a natural disaster performance is to improve route to combat a natural disaster construction mark
It is quasi-.Large-scale blackout caused by natural calamity is much caused by releasing operation due to the weak route of combating a natural disaster property in power grid；This
After a little vulnerable lines are out of service, power flow transfer leads to adjacent lines overload, circuit overload protection act, so as to cause
Cascading failure occurs.In order to avoid the appearance of this power distribution network catastrophe failure, it is necessary to be done to the combating a natural disaster property construction of distribution network line
It makes rational planning for out, to need to carry out power network line disaster alarm.
The Hazard Meteorological condition that existing power network line disaster alarm is considered is single, and generally just for power network line
Vulnerability carries out early warning, does not consider importance of the route in power grid.Its early warning implementation method mainly passes through level point
The subjective algorithm such as analysis method realizes do not have universality.
Summary of the invention
The purpose of the present invention is to provide a kind of the Guangdong power system method for prewarning risk based on SVM, this method utilization
The route historical failure information of early warning object power grid establishes the learning data set of SVM Guangdong power system Risk-warning algorithm；
Its data acquisition system should combat a natural disaster caused by construction situation, route significance level, line fault comprising weather environment, power grid locating for power grid
The data of disaster-stricken four aspects of loss of power grid.Later, SVM algorithm is learnt using learning data set, and exports SVM electricity
Cable road failure risk warning algorithm is applied to the early warning accuracy of this power grid.The route for finally establishing early warning object power grid is basic
Situation data acquisition system finds out each of early warning object power grid using the SVM Guangdong power system Risk-warning algorithm learnt
The failure risk value of route, and sort from high to low, early warning is carried out to before value-at-risk ranking 20% route.
To achieve the above object, the technical scheme is that a kind of Guangdong power system Risk-warning side based on SVM
Method includes the following steps:
Step S1, SVM Guangdong power system Risk-warning is established using the route historical failure information of early warning object power grid
The learning data set of algorithm, the learning data set include that weather environment, power grid locating for power grid combat a natural disaster construction situation, route weight
Want the data of disaster-stricken four aspects of loss of power grid caused by degree, line fault；
Step S2, SVM algorithm is learnt using the learning data set in step S1, and exports SVM power network line
Failure risk warning algorithm；
Step S3, the route basic condition data acquisition system of early warning object power grid is established；
Step S4, the early warning object of the step S2 SVM Guangdong power system Risk-warning algorithm obtained and step S3 is utilized
The route basic condition data acquisition system of power grid finds out the failure risk value of each route of early warning object power grid, and from high to low
Sequence carries out early warning to before value-at-risk ranking 20% route.
In an embodiment of the present invention, in the step S1, weather environment data locating for power grid include place on line disaster
Grade；It includes leakage conductor installation interval, the average height of construction of line shaft tower, route throwing that power grid, which combats a natural disaster construction situation data,
Enter the time limit, span；The disaster-stricken loss of power grid caused by line fault considers that user's important level, line outage cause user to lose
Electricity indicate.
In an embodiment of the present invention, in the step S1, the data in learning data set are by the event of power network line history
Barrier data directly acquire, or are sought by calculate to power network line historical failure data, wherein needing by power network line
It is as follows that historical failure data carries out the data that calculating is sought:
(1) place on line disaster loss grade:
(1.1) division of disaster caused by a windstorm grade, big flood grade, thunder calamity grade is carried out to route present position: by disaster caused by a windstorm grade, flood
Calamity grade, thunder calamity grade are respectively divided into three-level；
(1.2) height above sea level amendment is carried out to the thunder calamity grade of route:
Height above sea level per unit value μ is defined, expression formula is
In formula, hxIndicate route region altitude value, hbasicFor height above sea level a reference value；
Calculate CG lightning density correction factor α
In formula, λx、γxRespectively indicate lightning outage rate and CG lightning density in region: λbasic、γbasicIt respectively indicates
Reference area lightning outage rate and CG lightning density；
CG lightning density correction value γ after asking meter and height above sea level to influencerevise
γrevise=α × γmeasure
The γ that will be calculatedreviseValue respectively corresponds level-one thunder calamity, second level thunder by three kinds of ranges are divided into from big to small
Calamity, three-level thunder calamity correct the height above sea level that thunder calamity is classified to realize；
(2) it calculates the disaster-stricken loss of power grid caused by line fault: determining the important level of customer charge first, user is born
Lotus is divided into three-level, i.e. first order load, two stage loads, three stage loads, and selects spy according to responsible consumer list in first order load
Other important load；
Secondly, be that each user assigns weight according to customer charge grade, the corresponding significance level weight of load level: especially
The corresponding significance level weight of important load, first order load, two stage loads, three stage loads is respectively 5,3,2,1；
Finally, user loses electricity and is defined as after considering load significance level
In formula, S is the user's set influenced that has a power failure, tiFor the power failure duration of i-th of user, piFor user have a power failure power,
αiFor i-th of customer charge weight.
In an embodiment of the present invention, in the step S2, using the learning data set in step S1 to SVM algorithm into
Specific step is as follows for row study:
Step S21, SVM learning data set is formed into vector by route, vector interior element is normalized；
Step S22, vector in step S21 is randomly divided into two parts, quantitative proportion 7:3 is respectively formed training vector
Set and inspection vector set；
Step S23, the kernel function and relevant parameter for selecting SVM, are trained SVM algorithm with training vector set；
Step S24, with examining vector set to test the step S23 algorithm trained, i.e., to inspection vector set
Middle line transportation work style nearly carry out prediction and with its known to the disaster-stricken penalty values of power grid caused by line fault be compared, it is opposite to export it
Error is as early warning fault rate.
In an embodiment of the present invention, in the step S3, in the route basic condition data for forming early warning object power grid
When set, data item will be with the data item structure complete one in input vector when learning in step S2 to SVM algorithm
It causes.
Compared to the prior art, the invention has the following advantages: existing Guangdong power system Risk-warning multi-pass
Analytic hierarchy process (AHP) realization is crossed, subjective, use scope is relatively narrow；Also, existing Guangdong power system Risk-warning technology
The Meteorological Elements generally considered are more single, do not meet the disaster-stricken situation of actual electric network route.It is existing that present method solves two aboves
The drawbacks of having, replaces analytic hierarchy process (AHP) with algorithm of support vector machine, and single meteorology member is replaced with three kinds of common Meteorological Elements
Element.In addition to this, when carrying out Guangdong power system Risk-warning, invention also contemplates that route is important in electric network composition
Degree, for the reference as power grid pre-disaster planning, this method can bring better economic benefit.
Detailed description of the invention
Fig. 1 is the method for the present invention implementation flow chart.
Fig. 2 is SVM algorithm input and output schematic diagram.
Specific embodiment
With reference to the accompanying drawing, technical solution of the present invention is specifically described.
As shown in Figure 1, the present invention provides a kind of Guangdong power system method for prewarning risk based on SVM, including it is as follows
Step:
Step S1, SVM Guangdong power system Risk-warning is established using the route historical failure information of early warning object power grid
The learning data set of algorithm, the learning data set include that weather environment, power grid locating for power grid combat a natural disaster construction situation, route weight
Want the data of disaster-stricken four aspects of loss of power grid caused by degree, line fault；
Step S2, SVM algorithm is learnt using the learning data set in step S1, and exports SVM power network line
Failure risk warning algorithm；
Step S3, the route basic condition data acquisition system of early warning object power grid is established；
Step S4, the early warning object of the step S2 SVM Guangdong power system Risk-warning algorithm obtained and step S3 is utilized
The route basic condition data acquisition system of power grid finds out the failure risk value of each route of early warning object power grid, and from high to low
Sequence carries out early warning to before value-at-risk ranking 20% route.
In the step S1, weather environment data locating for power grid include place on line disaster loss grade；Power grid combats a natural disaster construction feelings
Condition data include leakage conductor installation interval, the average height of construction of line shaft tower, route the investment time limit, span；Route event
The disaster-stricken loss of power grid caused by hindering considers the electricity that user's important level, line outage cause user to lose to indicate.The step
In rapid S1, the data in learning data set are directly acquired by power network line historical failure data, or by going through to power network line
History fault data calculate and is sought, wherein needing by carrying out calculating the data sought such as to power network line historical failure data
Under:
(1) place on line disaster loss grade:
(1.1) division of disaster caused by a windstorm grade, big flood grade, thunder calamity grade is carried out to route present position: by disaster caused by a windstorm grade, flood
Calamity grade, thunder calamity grade are respectively divided into three-level；Referring to shown in table 1-3；
1 disaster caused by a windstorm grade classification table of table
| Disaster loss grade | Meteorologic district | Wind speed area |
| Level-one | D2 | 40~45 |
| Second level | D1 | 35~40 |
| Three-level | A | 30~35 |
2 big flood grade classification table of table
| Big flood grade | Level-one | Second level | Three-level |
| Daily rainfall/mm | >250 | 100~250 | 50~100 |
3 thunder calamity grade classification table of table
(1.2) height above sea level amendment is carried out to the thunder calamity grade of route:
Height above sea level per unit value μ is defined, expression formula is
In formula, hxIndicate route region altitude value, hbasicFor height above sea level a reference value；
Calculate CG lightning density correction factor α
In formula, λx、γxRespectively indicate lightning outage rate and CG lightning density in region: λbasic、γbasicIt respectively indicates
Reference area lightning outage rate and CG lightning density；
CG lightning density correction value γ after asking meter and height above sea level to influencerevise
γrevise=α × γmeasure
The γ that will be calculatedreviseValue respectively corresponds level-one thunder calamity, second level thunder by three kinds of ranges are divided into from big to small
Calamity, three-level thunder calamity correct the height above sea level that thunder calamity is classified to realize；
(2) it calculates the disaster-stricken loss of power grid caused by line fault: determining the important level of customer charge first, user is born
Lotus is divided into three-level, i.e. first order load, two stage loads, three stage loads, and selects spy according to responsible consumer list in first order load
Other important load；Ginseng is shown in Table 4；
4 load rating principle of table
Secondly, be that each user assigns weight according to customer charge grade, the corresponding significance level weight of load level: especially
The corresponding significance level weight of important load, first order load, two stage loads, three stage loads is respectively 5,3,2,1；Referring to 5 institute of table
Show；
The corresponding significance level weight table of 5 load level of table
| Load level | Weight |
| Special important load | 5 |
| First order load | 3 |
| Two stage loads | 2 |
| Three stage loads | 1 |
Finally, user loses electricity and is defined as after considering load significance level
In formula, S is the user's set influenced that has a power failure, tiFor the power failure duration of i-th of user, piFor user have a power failure power,
αiFor i-th of customer charge weight.
As shown in Fig. 2, being learnt using the learning data set in step S1 to SVM algorithm in the step S2
Specific step is as follows:
Step S21, SVM learning data set is formed into vector by route, vector interior element is normalized；
Step S22, vector in step S21 is randomly divided into two parts, quantitative proportion 7:3 is respectively formed training vector
Set and inspection vector set；
Step S23, the kernel function and relevant parameter for selecting SVM, are trained SVM algorithm with training vector set；
Step S24, with examining vector set to test the step S23 algorithm trained, i.e., to inspection vector set
Middle line transportation work style nearly carry out prediction and with its known to the disaster-stricken penalty values of power grid caused by line fault be compared, it is opposite to export it
Error is as early warning fault rate.
In the step S3, when forming the route basic condition data acquisition system of early warning object power grid, data item will be with
Data item structure in input vector when learning in step S2 to SVM algorithm is completely the same.
The following are specific implementation processes of the invention.
1) using somewhere power grid as early warning object, SVM Guangdong power system risk is established using its route historical failure information
The learning data set of warning algorithm, the data acquisition system should combat a natural disaster construction situation, route comprising weather environment, power grid locating for power grid
The data of disaster-stricken four aspects of loss of power grid caused by significance level, line fault.Five routes are selected as prediction object, number
According to as shown in table 6:
Table 6 predicts object track data situation
2) height above sea level amendment is carried out to route initial data
γrevise=α × γmeasure
Wherein predict that the correction result of object is as shown in table 7:
Table 7
3) establishing criteria divides route their location disaster loss grade, as a result shown in table 8:
Table 8
| Route | Thunder calamity | Disaster caused by a windstorm | Big flood |
| Route 1 | Second level | Second level | Second level |
| Route 2 | Three-level | Second level | Second level |
| Route 3 | Second level | Three-level | Second level |
| Route 4 | Second level | Second level | Second level |
| Route 5 | Second level | Three-level | Second level |
4) the disaster-stricken loss of power grid caused by line fault is calculated.According to the important level of customer charge, user's damage is calculated to obtain
Power loss amount is as shown in table 9:
Table 9
5) learning data set is learnt using SVM algorithm.Firstly, the feature vector of model training is formed,
T=[thunder calamity grade, disaster caused by a windstorm grade, big flood grade, shaft tower height, the investment time limit, span, loss electricity]
By taking route one as an example:
T1=[2,2,2,15,5,60,400]
It is normalized with each element maximum value, by taking route one as an example:
T1=[0.66,0.66,0.66,1,0.857,1]
After carrying out the processing of naturalization one to each route in learning data set, learnt using SVM algorithm, forms instruction
Practice model.
6) after model training is good, the route base of SVM Guangdong power system Risk-warning algorithm and early warning object power grid is utilized
This situation data acquisition system finds out the failure risk value of each route of early warning object power grid.
Feature vector of the input early warning object route without loss electricity first,
By taking route one as an example:
T1=[0.66,0.66,0.66,1,0.857]
It is 0.78 that line fault Risk Results, which can be obtained,
Five routes of early warning object are calculated, can obtain line fault Risk Results is
[0.78,0.85,0.34,0.23,0.24]
It is sorted from high to low according to line fault value-at-risk, early warning is carried out to before value-at-risk ranking 20% route, as a result
It is as follows:
Ranking results: route two, route one, route three, route five, route four
Early warning result: route one.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (5)
1. a kind of Guangdong power system method for prewarning risk based on SVM, which comprises the steps of:
Step S1, SVM Guangdong power system Risk-warning algorithm is established using the route historical failure information of early warning object power grid
Learning data set, which includes that weather environment, power grid locating for power grid combat a natural disaster the important journey of construction situation, route
The data of disaster-stricken four aspects of loss of power grid caused by degree, line fault；
Step S2, SVM algorithm is learnt using the learning data set in step S1, and exports SVM Guangdong power system
Risk-warning algorithm；
Step S3, the route basic condition data acquisition system of early warning object power grid is established；
Step S4, the early warning object power grid of the step S2 SVM Guangdong power system Risk-warning algorithm obtained and step S3 is utilized
Route basic condition data acquisition system find out early warning object power grid each route failure risk value, and arrange from high to low
Sequence carries out early warning to before value-at-risk ranking 20% route.
2. a kind of Guangdong power system method for prewarning risk based on SVM according to claim 1, which is characterized in that institute
It states in step S1, weather environment data locating for power grid include place on line disaster loss grade；Power grid combats a natural disaster construction situation data
Leakage conductor installation interval, the average height of construction of line shaft tower, route put into the time limit, span；Electricity caused by line fault
Disaster-stricken loss is netted, considers the electricity that user's important level, line outage cause user to lose to indicate.
3. a kind of Guangdong power system method for prewarning risk based on SVM according to claim 1, which is characterized in that institute
It states in step S1, the data in learning data set are directly acquired by power network line historical failure data, or by grid line
Road historical failure data calculate and is sought, wherein needing by carrying out calculating the data sought to power network line historical failure data
It is as follows:
(1) place on line disaster loss grade:
(1.1) division of disaster caused by a windstorm grade, big flood grade, thunder calamity grade is carried out to route present position: by disaster caused by a windstorm grade, big flood etc.
Grade, thunder calamity grade are respectively divided into three-level；
(1.2) height above sea level amendment is carried out to the thunder calamity grade of route:
Height above sea level per unit value μ is defined, expression formula is
In formula, hxIndicate route region altitude value, hbasicFor height above sea level a reference value；
Calculate CG lightning density correction factor α
In formula, λx、γxRespectively indicate lightning outage rate and CG lightning density in region: λbasic、γbasicRespectively indicate benchmark
Region wire tripping rate with lightning strike and CG lightning density；
CG lightning density correction value γ after asking meter and height above sea level to influencerevise
γrevise=α × γmeasure
The γ that will be calculatedreviseValue respectively corresponds level-one thunder calamity, second level thunder calamity, three by three kinds of ranges are divided into from big to small
Grade thunder calamity corrects the height above sea level that thunder calamity is classified to realize；
(2) it calculates the disaster-stricken loss of power grid caused by line fault: determining the important level of customer charge first, by customer charge point
At three-level, i.e. first order load, two stage loads, three stage loads, and is selected in first order load according to responsible consumer list and especially weighed
Want load；
Secondly, being that each user assigns weight, the corresponding significance level weight of load level: especially important according to customer charge grade
The corresponding significance level weight of load, first order load, two stage loads, three stage loads is respectively 5,3,2,1；
Finally, user loses electricity and is defined as after considering load significance level
In formula, S is the user's set influenced that has a power failure, tiFor the power failure duration of i-th of user, piFor the power that user has a power failure, αiFor
I-th of customer charge weight.
4. a kind of Guangdong power system method for prewarning risk based on SVM according to claim 1, which is characterized in that institute
It states in step S2, is learnt that specific step is as follows to SVM algorithm using the learning data set in step S1:
Step S21, SVM learning data set is formed into vector by route, vector interior element is normalized；
Step S22, vector in step S21 is randomly divided into two parts, quantitative proportion 7:3 is respectively formed training vector set
With inspection vector set；
Step S23, the kernel function and relevant parameter for selecting SVM, are trained SVM algorithm with training vector set；
Step S24, with examining vector set to test the step S23 algorithm trained, i.e., to inspection vector set middle line
Transportation work style nearly carry out prediction and with its known to the disaster-stricken penalty values of power grid caused by line fault be compared, export its relative error
As early warning fault rate.
5. a kind of Guangdong power system method for prewarning risk based on SVM according to claim 1, which is characterized in that institute
State in step S3, formed early warning object power grid route basic condition data acquisition system when, data item will with it is right in step S2
Data item structure in input vector when SVM algorithm is learnt is completely the same.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811502524.5A CN109359896B (en) | 2018-12-10 | 2018-12-10 | SVM-based power grid line fault risk early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811502524.5A CN109359896B (en) | 2018-12-10 | 2018-12-10 | SVM-based power grid line fault risk early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109359896A true CN109359896A (en) | 2019-02-19 |
| CN109359896B CN109359896B (en) | 2021-11-12 |
Family
ID=65330254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811502524.5A Active CN109359896B (en) | 2018-12-10 | 2018-12-10 | SVM-based power grid line fault risk early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359896B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322135A (en) * | 2019-06-26 | 2019-10-11 | 国网江苏省电力有限公司南京供电分公司 | A kind of method for real-time monitoring and system of grid equipment safe operation state |
| CN111126846A (en) * | 2019-12-24 | 2020-05-08 | 广东电网有限责任公司 | Method for evaluating differentiation state of overhead transmission line |
| CN111310785A (en) * | 2020-01-15 | 2020-06-19 | 杭州华网信息技术有限公司 | National power grid mechanical external damage prediction method |
| CN112287018A (en) * | 2020-11-06 | 2021-01-29 | 武汉理工大学 | Method and system for evaluating damage risk of 10kV tower under typhoon disaster |
| CN115640880A (en) * | 2022-09-30 | 2023-01-24 | 海南电网有限责任公司 | Weak link early warning method based on support vector machine |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6289716B1 (en) * | 1998-08-19 | 2001-09-18 | Electric Power Research Institute, Inc. | Method for on-line assessment and indication of transformer conditions |
| JP2004076597A (en) * | 2002-08-12 | 2004-03-11 | Toshiba Corp | Pumping start method, pumping stop method, and pumping operation control device of pumped storage power plant |
| CN104133989A (en) * | 2014-07-15 | 2014-11-05 | 华北电力大学 | Icing loss considered wind power plant time sequence output power calculation method |
| CN104463700A (en) * | 2014-12-05 | 2015-03-25 | 国家电网公司 | Power transmission line tower lightning strike risk evaluation method based on data mining technology |
| CN104462718A (en) * | 2014-12-25 | 2015-03-25 | 国家电网公司 | Method for evaluating economic operation year range of transformer substation |
| CN105223472A (en) * | 2015-10-16 | 2016-01-06 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | A kind of ultra-high-tension power transmission line Fault Locating Method based on multi-source data set theory |
| CN106447202A (en) * | 2016-09-29 | 2017-02-22 | 国网山东省电力公司 | Power equipment state evaluation method based on data mining and principal component analysis |
| CN106600140A (en) * | 2016-12-07 | 2017-04-26 | 河海大学常州校区 | Improved support vector machine-based gas pipeline fault prediction and early warning system and method |
| CN107239857A (en) * | 2017-05-31 | 2017-10-10 | 武汉大学 | Overhead transmission line methods of risk assessment based on LS_SVM and PCA |
| CN107292415A (en) * | 2017-05-02 | 2017-10-24 | 国网浙江省电力公司 | A kind of Forecasting Methodology of intelligent meter rotation time |
| CN107292478A (en) * | 2016-04-13 | 2017-10-24 | 中国电力科学研究院 | A kind of disaster influences the acquisition methods of situation on power distribution network |
| CN107730061A (en) * | 2016-08-11 | 2018-02-23 | 中国农业大学 | A kind of power distribution network overload methods of risk assessment and device |
| CN107944188A (en) * | 2017-12-13 | 2018-04-20 | 哈尔滨工业大学 | Typhoon eye of wind radius discrimination method near the ground based on weather station measured data |
| CN108009351A (en) * | 2017-11-30 | 2018-05-08 | 国网湖南省电力有限公司 | The distribution drawing drawing method of lightning stroke trip risk |
| CN108133225A (en) * | 2017-10-23 | 2018-06-08 | 南京南瑞集团公司 | A kind of icing flashover fault early warning method based on support vector machines |
| CN108399486A (en) * | 2018-01-22 | 2018-08-14 | 国网福建省电力有限公司泉州供电公司 | A kind of electrical equipment fault detection method based on least square support vector machines |
| CN108596449A (en) * | 2018-04-09 | 2018-09-28 | 南京邮电大学 | It is a kind of to consider distribution network reliability prediction technique of the weather to distribution network failure impact probability |
| CN108596252A (en) * | 2018-04-25 | 2018-09-28 | 河南工程学院 | Outdoor communication facility failure prediction analysis method based on complicated meteorology big data |
| CN108734350A (en) * | 2018-05-17 | 2018-11-02 | 燕山大学 | A kind of independent method for solving with combined dispatching of the power distribution network containing micro-capacitance sensor |
-
2018
- 2018-12-10 CN CN201811502524.5A patent/CN109359896B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6289716B1 (en) * | 1998-08-19 | 2001-09-18 | Electric Power Research Institute, Inc. | Method for on-line assessment and indication of transformer conditions |
| JP2004076597A (en) * | 2002-08-12 | 2004-03-11 | Toshiba Corp | Pumping start method, pumping stop method, and pumping operation control device of pumped storage power plant |
| CN104133989A (en) * | 2014-07-15 | 2014-11-05 | 华北电力大学 | Icing loss considered wind power plant time sequence output power calculation method |
| CN104463700A (en) * | 2014-12-05 | 2015-03-25 | 国家电网公司 | Power transmission line tower lightning strike risk evaluation method based on data mining technology |
| CN104462718A (en) * | 2014-12-25 | 2015-03-25 | 国家电网公司 | Method for evaluating economic operation year range of transformer substation |
| CN105223472A (en) * | 2015-10-16 | 2016-01-06 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | A kind of ultra-high-tension power transmission line Fault Locating Method based on multi-source data set theory |
| CN107292478A (en) * | 2016-04-13 | 2017-10-24 | 中国电力科学研究院 | A kind of disaster influences the acquisition methods of situation on power distribution network |
| CN107730061A (en) * | 2016-08-11 | 2018-02-23 | 中国农业大学 | A kind of power distribution network overload methods of risk assessment and device |
| CN106447202A (en) * | 2016-09-29 | 2017-02-22 | 国网山东省电力公司 | Power equipment state evaluation method based on data mining and principal component analysis |
| CN106600140A (en) * | 2016-12-07 | 2017-04-26 | 河海大学常州校区 | Improved support vector machine-based gas pipeline fault prediction and early warning system and method |
| CN107292415A (en) * | 2017-05-02 | 2017-10-24 | 国网浙江省电力公司 | A kind of Forecasting Methodology of intelligent meter rotation time |
| CN107239857A (en) * | 2017-05-31 | 2017-10-10 | 武汉大学 | Overhead transmission line methods of risk assessment based on LS_SVM and PCA |
| CN108133225A (en) * | 2017-10-23 | 2018-06-08 | 南京南瑞集团公司 | A kind of icing flashover fault early warning method based on support vector machines |
| CN108009351A (en) * | 2017-11-30 | 2018-05-08 | 国网湖南省电力有限公司 | The distribution drawing drawing method of lightning stroke trip risk |
| CN107944188A (en) * | 2017-12-13 | 2018-04-20 | 哈尔滨工业大学 | Typhoon eye of wind radius discrimination method near the ground based on weather station measured data |
| CN108399486A (en) * | 2018-01-22 | 2018-08-14 | 国网福建省电力有限公司泉州供电公司 | A kind of electrical equipment fault detection method based on least square support vector machines |
| CN108596449A (en) * | 2018-04-09 | 2018-09-28 | 南京邮电大学 | It is a kind of to consider distribution network reliability prediction technique of the weather to distribution network failure impact probability |
| CN108596252A (en) * | 2018-04-25 | 2018-09-28 | 河南工程学院 | Outdoor communication facility failure prediction analysis method based on complicated meteorology big data |
| CN108734350A (en) * | 2018-05-17 | 2018-11-02 | 燕山大学 | A kind of independent method for solving with combined dispatching of the power distribution network containing micro-capacitance sensor |
Non-Patent Citations (6)
| Title |
|---|
| ESKANDARPOUR ROZHIN 等: "Improving power grid resilience through predictive outage estimation", 《2017 NORTH AMERICAN POWER SYMPOSIUM (NAPS)》 * |
| TEHRANY MAHYAT SHAFAPOUR 等: "Flood susceptibility analysis and its verification using a novel ensemble support vector machine and frequency ratio method", 《STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT》 * |
| 刘继生: "输电线路运行状态监测GIS平台开发研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
| 施健 等: "基于LS-SVM的电力通信网性能劣化评估与预测模型研究", 《计算机与数字工程》 * |
| 武良: "计及电压稳定性的风电场无功能力评估及优化研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
| 王向朋 等: "高海拔下特高压直流绝缘子的污闪特性", 《高电压技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322135A (en) * | 2019-06-26 | 2019-10-11 | 国网江苏省电力有限公司南京供电分公司 | A kind of method for real-time monitoring and system of grid equipment safe operation state |
| CN111126846A (en) * | 2019-12-24 | 2020-05-08 | 广东电网有限责任公司 | Method for evaluating differentiation state of overhead transmission line |
| CN111310785A (en) * | 2020-01-15 | 2020-06-19 | 杭州华网信息技术有限公司 | National power grid mechanical external damage prediction method |
| CN112287018A (en) * | 2020-11-06 | 2021-01-29 | 武汉理工大学 | Method and system for evaluating damage risk of 10kV tower under typhoon disaster |
| CN112287018B (en) * | 2020-11-06 | 2024-03-01 | 武汉理工大学 | 10kV pole tower damage risk assessment method and system under typhoon disaster |
| CN115640880A (en) * | 2022-09-30 | 2023-01-24 | 海南电网有限责任公司 | Weak link early warning method based on support vector machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109359896B (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359896A (en) | A kind of Guangdong power system method for prewarning risk based on SVM | |
| Salman et al. | Evaluating system reliability and targeted hardening strategies of power distribution systems subjected to hurricanes | |
| US8606416B2 (en) | Energy generating system and control thereof | |
| Chen et al. | A statistical risk assessment framework for distribution network resilience | |
| CN104392391A (en) | Power grid running safety risk quantification method | |
| CN104063750B (en) | The Forecasting Methodology of the disaster-stricken influence of power system based on the anti-entropy weight of advanced AHP | |
| CN107633320B (en) | Power grid line importance degree evaluation method based on meteorological prediction and risk evaluation | |
| US11689154B2 (en) | Systems and methods for distributed-solar power forecasting using parameter regularization | |
| CN104299116A (en) | Quantitative evaluation method for security risk of operation of power network | |
| Han et al. | Comprehensive risk assessment of transmission lines affected by multi-meteorological disasters based on fuzzy analytic hierarchy process | |
| CN104657822A (en) | Power system disaster warning grading method and system based on risk evaluation result | |
| CN106251045A (en) | Distribution network reliability appraisal procedure based on multiple leading factor | |
| CN105279612A (en) | Poisson distribution-based power transmission line tripping risk assessment method | |
| CN107292478A (en) | A kind of disaster influences the acquisition methods of situation on power distribution network | |
| Salman et al. | Assessing climate change impact on system reliability of power distribution systems subjected to hurricanes | |
| Sozen et al. | Selection of the best location for solar plants in Turkey | |
| CN105760979A (en) | Power system transient risk evaluation method taking natural disasters into consideration | |
| Khalyasmaa et al. | Prediction of solar power generation based on random forest regressor model | |
| Salman | Risk-based assessment and strengthening of electric power systems subjected to natural hazards | |
| CN104574211A (en) | Power grid dispatching operating risk early warning method and system based on risk source | |
| Broström | Ice storm modelling in transmission system reliability calculations | |
| Li et al. | Risk-based management of electric power distribution systems subjected to hurricane and tornado hazards | |
| CN114266508A (en) | Correction algorithm for power distribution network power supply reliability evaluation index weight | |
| Noebels et al. | A Probabilistic and Cost-based Decision Strategy for Power Grid Resilience using Ensemble Forecasting | |
| Yu et al. | Optimal restoration strategy based on resilience improvement for power transmission systems under extreme weather events |
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 |