CN109522599A - Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon - Google Patents
Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon Download PDFInfo
- Publication number
- CN109522599A CN109522599A CN201811199911.6A CN201811199911A CN109522599A CN 109522599 A CN109522599 A CN 109522599A CN 201811199911 A CN201811199911 A CN 201811199911A CN 109522599 A CN109522599 A CN 109522599A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- typhoon
- electricity
- training
- indicate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon.Machine learning training sample eigenmatrix, training sample label are constructed based on a large amount of typhoon meteorology historical datas, faulty transmission line historical data, normal transmission line historical data；Utilize training sample eigenmatrix, training sample label training Random Forest model；Forecast sample feature is constructed based on typhoon weather forecast data, current transmission line of electricity data, the Random Forest model after the forecast sample feature input training of building is exported according to Random Forest model as a result, judging whether current transmission line of electricity may break down.The prediction of transmission line of electricity catastrophic failure caused by typhoon can be achieved in the present invention, and dispatching of power netwoks personnel can carry out in advance catastrophic failure emergency trouble shooting measures according to prediction result, so that it is guaranteed that the safe operation of power grid.The present invention is based on big data technologies, break through the analysis model limitation of conventional method, consider more potential association influence factors, promote predictablity rate.
Description
Technical field
The present invention relates to transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon, belong to electric power network technique field.
Background technique
Using global warming as under the climate change background of main feature, extreme weather climate damage be increased significantly, to society
The influence of meeting economic development increasingly sharpens.China is located in northwest Pacific west bank, is the most active area of global tropical cyclone
One.Tropical cyclone bring strong wind, heavy rain and storm tide etc. are to the infrastructure in coastal cities, property, personal safety and industry
Production activity causes to seriously affect.Typhoon may cause transmission of electricity in its moving process as a kind of strong tropical cyclone
Route catastrophic failure, to cause serious power grid accident.
Currently, predicting for the transmission line malfunction that typhoon causes, the mode based on fixed risk evaluation model is mostly used
(such as: establishing prediction model with typhoon wind speed), this method carry out the pre- of typhoon risk equipment according to the prediction model pre-established
It surveys, there are models to consider that correlative factor is limited, is difficult to the disadvantages of accurately establishing true complex model, and predictablity rate is lower.With
The construction of smart grid, more stringent requirements are proposed for safety of the power grid to transmission line of electricity.
Therefore, by carrying out modeling study to transmission line of electricity catastrophic failure caused by typhoon based on machine learning, using big
The generation of transmission line of electricity catastrophic failure is more accurately predicted in the advantage of data technique, is conducive to dispatching of power netwoks operations staff and shifts to an earlier date
Carry out the emergency trouble shooting measures of burst line fault, it is ensured that the safe operation of power grid.
Summary of the invention
It is an object of the invention to overcome deficiency in the prior art, a kind of burst of transmission line of electricity caused by typhoon is provided therefore
Hinder prediction technique, can more accurately and effectively realize the on-line prediction of transmission line of electricity catastrophic failure caused by typhoon.
In order to achieve the above objectives, the technical scheme adopted by the invention is that:
Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon characterized by comprising
Based on a large amount of typhoon meteorology historical datas, faulty transmission line historical data, normal transmission line historical data, structure
Build training sample eigenmatrix, training sample label；
Utilize training sample eigenmatrix, training sample label training Random Forest model；
Forecast sample feature is constructed based on typhoon weather forecast data, current transmission line of electricity data；
By the Random Forest model after the forecast sample feature input training of building, result is exported by Random Forest model；
It is exported according to Random Forest model as a result, judging whether current transmission line of electricity may break down.
Further, the building training sample eigenmatrix, the specific method is as follows for training sample label:
Construct training sample eigenmatrix X=[x1,x2,…,x9]i；I=1,2 ..., n, wherein x1Indicate that transmission line of electricity is attached
Close-table wind wind speed, x2Indicate transmission line of electricity nearby typhoon wind direction, x3Indicate center of typhoon wind speed, x4Expression center of typhoon air pressure,
x5Indicate fresh gale circle radius, x6Indicate storm circle radius, x7Indicate center of typhoon movement speed, x8Indicate that center of typhoon is mobile
Direction, x9Indicate that transmission line of electricity indicates the total sample number of training sample set away from center of typhoon distance, n；
It constructs training sample label Y=[y]i；I=1,2 ..., n, wherein n indicates the total sample number of training sample set, y
Indicate transmission line status, the corresponding y value of faulty transmission line is 1, and the corresponding y value of normal transmission line is 0.
Further, the specific method is as follows for training Random Forest model:
A line feature vector x is randomly extracted from training sample eigenmatrix X1,x2,…,x9, while sample drawn mark
Corresponding label y, extracts n times altogether in label, and n feature vector of acquisition and n sample label are constituted new sample characteristics square
Battle array XjWith sample label Yj, wherein j=1,2 ..., 9；
One is established based on decision tree theory with j-th of feature xjFor the j decision tree of categorical attribute, using eigenmatrix
XjWith sample label YjLearning training is carried out to j decision tree；It repeats the above steps, successively obtains No. 1 decision tree, No. 2 decisions
Tree, No. 3 decision trees, No. 4 decision trees, No. 5 decision trees, No. 6 decision trees, No. 7 decision trees, No. 8 decision trees, No. 9 decision trees, 9
The set of decision tree after training is the Random Forest model after training.
Further, the specific of forecast sample feature is constructed based on typhoon weather forecast data, current transmission line of electricity data
Method is as follows: forecast sample eigenmatrix X '=[x ' of building1,x′2,…,x′9], wherein x '1Indicate that current transmission line of electricity is attached
Close-table wind wind speed forecasting value, x '2Indicate current transmission line of electricity nearby typhoon wind direction predicted value, x '3Indicate center of typhoon wind speed forecasting
Value, x '4Indicate measured value, the x ' at center of typhoon air pressure nearest time point5The measured value at expression fresh gale circle radius nearest time point,
x′6Indicate measured value, the x ' at storm circle radius nearest time point7Indicate the actual measurement at center of typhoon movement speed nearest time point
Value, x '8Indicate measured value, the x ' at center of typhoon moving direction nearest time point9Indicate transmission line of electricity away from center of typhoon distance.
Further, by the Random Forest model after the forecast sample feature input training of building, by Random Forest model
Export result, in particular to:
In Random Forest model, share 9 trained decision trees, by the forecast sample eigenmatrix X ' of building=
[x′1,x′2,…,x′9] Random Forest model after training is inputted, every trained decision tree can all generate transmission line of electricity event
Hinder probability, the normal probability of transmission line of electricity, 9 transmission line malfunction probability that 9 decision trees generate are subjected to average, 9 transmissions of electricity
The normal probability of route is averaged, and the maximum classification of probability of occurrence is Random Forest model final output, when failure is general
It is 1 that rate maximum, which then exports result, is 0 when normal maximum probability then exports result.
Further, Random Forest model output result is 1, indicates that current transmission line of electricity is likely to break down.This
When, dispatching of power netwoks operations staff needs to carry out the emergency trouble shooting measures of burst line fault in advance, so that it is guaranteed that the safety of power grid
Operation.
Further, Random Forest model output result is 0, indicates that current transmission line of electricity is normal.
Compared with prior art, the beneficial effects of the present invention are:
Is trained to transmission line of electricity catastrophic failure caused by typhoon by the method based on historical data machine learning
It practises and being modeled with prediction, accurately predict the generation of transmission line of electricity catastrophic failure much sooner, be conducive to dispatching of power netwoks operations staff
The emergency trouble shooting measures for carrying out burst line fault in advance, so that it is guaranteed that the safe operation of power grid.With the biography based on fixed model
System prediction technique is compared, and this method is based on big data technology, can break through the analysis model limitation of conventional method, is considered more latent
In association influence factor, predictablity rate is effectively promoted.
Meanwhile the random forests algorithm that the present invention uses, it is a kind of machine learning algorithm newly risen, there is accuracy rate
High, the advantages that being suitable for reply large data sets, is easy to spread.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
Transmission line of electricity catastrophic failure prediction technique caused by typhoon of the present invention, based on a large amount of typhoon meteorology historical datas, event
Hinder transmission line of electricity historical data, normal transmission line historical data constructs machine learning training sample eigenmatrix, training sample
Label, and then training sample eigenmatrix, training sample label training Random Forest model are utilized, it is finally meteorological pre- based on typhoon
Count off constructs forecast sample feature according to, current transmission line of electricity data, will be random after the forecast sample feature input training of building
Forest model is exported according to Random Forest model as a result, can determine whether current transmission line of electricity may break down.
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, being flow chart of the invention, include the following steps:
Step 1: being based on a large amount of typhoon meteorology historical datas, faulty transmission line historical data, normal transmission line history
Data construct training sample eigenmatrix, training sample label；
Construct training sample eigenmatrix X=[x1,x2,…,x9]i；I=1,2 ..., n, wherein x1Indicate that transmission line of electricity is attached
Close-table wind wind speed, x2Indicate transmission line of electricity nearby typhoon wind direction, x3Indicate center of typhoon wind speed, x4Expression center of typhoon air pressure,
x5Indicate fresh gale circle radius, x6Indicate storm circle radius, x7Indicate center of typhoon movement speed, x8Indicate that center of typhoon is mobile
Direction, x9Indicate that transmission line of electricity indicates the total sample number of training sample set away from center of typhoon distance, n；Construct training sample label
Y=[y]i；I=1,2 ..., n, wherein n indicates the total sample number of training sample set, and y indicates transmission line status, faulty transmission
The corresponding y value of route is 1, and the corresponding y value of normal transmission line is 0.
Step 2: utilizing training sample eigenmatrix, training sample label training Random Forest model.The training with
The method of machine forest model are as follows:
A line feature vector x is randomly extracted from training sample eigenmatrix X1,x2,…,x9, while sample drawn mark
Corresponding label y, extracts n times altogether in label, and n feature vector of acquisition and n sample label are constituted new sample characteristics square
Battle array XjWith sample label Yj, wherein j=1,2 ..., 9.One is established based on decision tree theory with j-th of feature xjBelong to for classification
The j decision tree of property, using eigenmatrix XjWith sample label YjLearning training is carried out to j decision tree.It constantly repeats above-mentioned
Step successively obtains No. 1 decision tree, No. 2 decision trees, No. 3 decision trees, No. 4 decision trees, No. 5 decision trees, No. 6 decision trees, No. 7
Decision tree, No. 8 decision trees, No. 9 decision trees, the set of the decision tree after 9 training are the Random Forest model after training.
Step 3: constructing forecast sample feature based on typhoon weather forecast data, current transmission line of electricity data；
Construct forecast sample eigenmatrix X '=[x '1,x′2,…,x′9], wherein x1' indicate near current transmission line of electricity
Typhoon wind speed forecasting value, x '2Indicate current transmission line of electricity nearby typhoon wind direction predicted value, x '3Indicate center of typhoon wind speed forecasting
Value, x '4Indicate measured value, the x ' at center of typhoon air pressure nearest time point5Indicate the actual measurement at 7 grades of solar or lunar halo radius nearest time points
Value, x '6Indicate measured value, the x ' at storm circle radius nearest time point7Indicate the reality at center of typhoon movement speed nearest time point
Measured value, x '8Indicate measured value, the x ' at center of typhoon moving direction nearest time point9Indicate transmission line of electricity away from center of typhoon distance.
Step 4: by the Random Forest model after the forecast sample feature input training of building, it is defeated by Random Forest model
Result out；It is exported according to Random Forest model as a result, judging whether current transmission line of electricity may break down；
In Random Forest model, share 9 trained decision trees, by the forecast sample eigenmatrix X ' of building=
[x′1,x′2,…,x′9] Random Forest model after training is inputted, every trained decision tree can all generate transmission line of electricity event
Hinder probability, the normal probability of transmission line of electricity, 9 transmission line malfunction probability that 9 decision trees generate are subjected to average, 9 transmissions of electricity
The normal probability of route is averaged, and the maximum classification of probability of occurrence is Random Forest model final output.When failure is general
It is 1 that rate maximum, which then exports result, indicates that current transmission line of electricity is likely to break down；When normal maximum probability then exports result
It is 0, indicates that current transmission line of electricity is normal.
The present invention can be achieved transmission line of electricity catastrophic failure caused by typhoon and predict, by based on historical data machine learning
Method is trained study to transmission line of electricity catastrophic failure caused by typhoon and prediction models, much sooner accurately prediction transmission of electricity
The generation of route catastrophic failure is conducive to the emergency trouble shooting measures that dispatching of power netwoks operations staff carries out burst line fault in advance,
So that it is guaranteed that the safe operation of power grid.Compared with the traditional prediction method based on fixed model, this method is based on big data technology,
The analysis model limitation that conventional method can be broken through, considers more potential association influence factors, effectively promotes predictablity rate.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (7)
1. transmission line of electricity catastrophic failure method for early warning caused by typhoon characterized by comprising
Based on typhoon meteorology historical data, faulty transmission line historical data, normal transmission line historical data, training sample is constructed
Eigen matrix, training sample label；
Utilize training sample eigenmatrix, training sample label training Random Forest model；
Forecast sample feature is constructed based on typhoon weather forecast data, current transmission line of electricity data；
By the Random Forest model after the forecast sample feature input training of building, result is exported by Random Forest model；
It is exported according to Random Forest model as a result, judging whether current transmission line of electricity may break down.
2. transmission line of electricity catastrophic failure method for early warning caused by typhoon according to claim 1, which is characterized in that the structure
Build that training sample eigenmatrix, the specific method is as follows for training sample label:
Construct training sample eigenmatrix X=[x1,x2,…,x9]i；I=1,2 ..., n, wherein x1Indicate transmission line of electricity platform nearby
Wind wind speed, x2Indicate transmission line of electricity nearby typhoon wind direction, x3Indicate center of typhoon wind speed, x4Indicate center of typhoon air pressure, x5It indicates
Fresh gale circle radius, x6Indicate storm circle radius, x7Indicate center of typhoon movement speed, x8Expression center of typhoon moving direction,
x9Indicate that transmission line of electricity indicates the total sample number of training sample set away from center of typhoon distance, n；
It constructs training sample label Y=[y]i；I=1,2 ..., n, wherein n indicates the total sample number of training sample set, and y indicates defeated
Electric wire line state, the corresponding y value of faulty transmission line are 1, and the corresponding y value of normal transmission line is 0.
3. transmission line of electricity catastrophic failure method for early warning caused by typhoon according to claim 2, which is characterized in that training with
The specific method is as follows for machine forest model:
A line feature vector x is randomly extracted from training sample eigenmatrix X1,x2,…,x9, while in sample drawn label
Corresponding label y, extracts n times altogether, and n feature vector of acquisition and n sample label are constituted new sample characteristics matrix Xj
With sample label Yj, wherein j=1,2 ..., 9；
One is established based on decision tree theory with j-th of feature xjFor the j decision tree of categorical attribute, using eigenmatrix XjWith
Sample label YjLearning training is carried out to j decision tree；It repeats the above steps, successively obtains No. 1 decision tree, No. 2 decision trees, 3
Number decision tree, No. 4 decision trees, No. 5 decision trees, No. 6 decision trees, No. 7 decision trees, No. 8 decision trees, No. 9 decision trees, 9 training
The set of decision tree afterwards is the Random Forest model after training.
4. transmission line of electricity catastrophic failure method for early warning caused by typhoon according to claim 1, which is characterized in that be based on platform
The specific method is as follows: the forecast sample of building as forecast data, current transmission line of electricity data construct forecast sample feature for general mood
Eigenmatrix X '=[x '1,x′2,…,x′9], wherein x '1Indicate current transmission line of electricity nearby typhoon wind speed forecasting value, x '2It indicates
Typhoon wind direction predicted value, x ' near current transmission line of electricity3Indicate center of typhoon wind speed forecasting value, x '4Indicate center of typhoon air pressure most
Measured value, the x ' at nearly time point5Indicate measured value, the x ' at fresh gale circle radius nearest time point6Indicate that storm circle radius is nearest
Measured value, the x ' at time point7Indicate measured value, the x ' at center of typhoon movement speed nearest time point8Indicate center of typhoon movement side
To measured value, the x ' at nearest time point9Indicate transmission line of electricity away from center of typhoon distance.
5. transmission line of electricity catastrophic failure method for early warning caused by typhoon according to claim 4, which is characterized in that will construct
Forecast sample feature input training after Random Forest model, by Random Forest model export result, in particular to:
In Random Forest model, 9 trained decision trees are shared, by forecast sample eigenmatrix X '=[x ' of building1,x
′2,…,x′9] input training after Random Forest model, every trained decision tree can all generate transmission line malfunction probability,
9 transmission line malfunction probability that 9 decision trees generate, are carried out that average, 9 transmission lines of electricity are normal by the normal probability of transmission line of electricity
Probability is averaged, and the maximum classification of probability of occurrence is Random Forest model final output, when probability of malfunction maximum then
Exporting result is 1, is 0 when normal maximum probability then exports result.
6. transmission line of electricity catastrophic failure method for early warning caused by typhoon according to claim 5, it is characterised in that: random gloomy
It is 1 that woods model, which exports result, indicates that current transmission line of electricity is likely to break down.
7. transmission line of electricity catastrophic failure method for early warning caused by typhoon according to claim 5, it is characterised in that: random gloomy
It is 0 that woods model, which exports result, indicates that current transmission line of electricity is normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811199911.6A CN109522599A (en) | 2018-10-16 | 2018-10-16 | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811199911.6A CN109522599A (en) | 2018-10-16 | 2018-10-16 | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109522599A true CN109522599A (en) | 2019-03-26 |
Family
ID=65771887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811199911.6A Pending CN109522599A (en) | 2018-10-16 | 2018-10-16 | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109522599A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543675A (en) * | 2019-07-31 | 2019-12-06 | 国网江苏省电力有限公司 | Power transmission line fault identification method |
| CN110716101A (en) * | 2019-09-05 | 2020-01-21 | 广州供电局有限公司 | Power line fault positioning method and device, computer and storage medium |
| CN111027629A (en) * | 2019-12-13 | 2020-04-17 | 国网山东省电力公司莱芜供电公司 | Power distribution network fault outage rate prediction method and system based on improved random forest |
| CN111126672A (en) * | 2019-12-02 | 2020-05-08 | 国网浙江省电力有限公司电力科学研究院 | High-voltage overhead transmission line typhoon disaster prediction method based on classification decision tree |
| CN111222709A (en) * | 2020-01-15 | 2020-06-02 | 杭州华网信息技术有限公司 | National power grid tree line discharge prediction method |
| CN111444240A (en) * | 2020-03-26 | 2020-07-24 | 北京国网富达科技发展有限责任公司 | Power transmission line fault early warning method and device |
| CN112529287A (en) * | 2020-12-08 | 2021-03-19 | 广东电网有限责任公司电力科学研究院 | Distribution line broken rod prediction method and device under typhoon disaster |
| CN113792923A (en) * | 2021-09-10 | 2021-12-14 | 云南电网有限责任公司大理供电局 | Visual scheduling window method based on power failure sensitivity prediction model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108152867A (en) * | 2017-12-29 | 2018-06-12 | 南方电网科学研究院有限责任公司 | The typhoon early warning system and method for transmission line of electricity |
-
2018
- 2018-10-16 CN CN201811199911.6A patent/CN109522599A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108152867A (en) * | 2017-12-29 | 2018-06-12 | 南方电网科学研究院有限责任公司 | The typhoon early warning system and method for transmission line of electricity |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543675A (en) * | 2019-07-31 | 2019-12-06 | 国网江苏省电力有限公司 | Power transmission line fault identification method |
| CN110716101A (en) * | 2019-09-05 | 2020-01-21 | 广州供电局有限公司 | Power line fault positioning method and device, computer and storage medium |
| CN110716101B (en) * | 2019-09-05 | 2021-11-02 | 广东电网有限责任公司广州供电局 | Power line fault positioning method and device, computer and storage medium |
| CN111126672A (en) * | 2019-12-02 | 2020-05-08 | 国网浙江省电力有限公司电力科学研究院 | High-voltage overhead transmission line typhoon disaster prediction method based on classification decision tree |
| CN111027629A (en) * | 2019-12-13 | 2020-04-17 | 国网山东省电力公司莱芜供电公司 | Power distribution network fault outage rate prediction method and system based on improved random forest |
| CN111027629B (en) * | 2019-12-13 | 2024-02-27 | 国网山东省电力公司莱芜供电公司 | Power distribution network fault power failure rate prediction method and system based on improved random forest |
| CN111222709A (en) * | 2020-01-15 | 2020-06-02 | 杭州华网信息技术有限公司 | National power grid tree line discharge prediction method |
| CN111222709B (en) * | 2020-01-15 | 2023-12-12 | 国网冀北电力有限公司超高压分公司 | National power grid tree line discharge prediction method |
| CN111444240A (en) * | 2020-03-26 | 2020-07-24 | 北京国网富达科技发展有限责任公司 | Power transmission line fault early warning method and device |
| CN112529287A (en) * | 2020-12-08 | 2021-03-19 | 广东电网有限责任公司电力科学研究院 | Distribution line broken rod prediction method and device under typhoon disaster |
| CN113792923A (en) * | 2021-09-10 | 2021-12-14 | 云南电网有限责任公司大理供电局 | Visual scheduling window method based on power failure sensitivity prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522599A (en) | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon | |
| CN104123682B (en) | A kind of Distribution Network Failure methods of risk assessment based on meteorological effect factor | |
| CN110222946B (en) | Typhoon scene simulation-based power distribution network overhead line weak link identification method | |
| CN109492777A (en) | A kind of Wind turbines health control method based on machine learning algorithm platform | |
| CN111612315A (en) | Novel power grid disastrous gale early warning method | |
| CN109118035B (en) | Grid early warning information-based typhoon and waterlogging disaster power distribution network risk assessment method | |
| CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
| CN103440400A (en) | Power system short-term risk determination method taking disaster factors into account | |
| CN105279612A (en) | Poisson distribution-based power transmission line tripping risk assessment method | |
| CN110378549B (en) | Transmission tower bird damage grade assessment method based on FAHP-entropy weight method | |
| CN107069975A (en) | A kind of distributed transmission facility status data reponse system and its method | |
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| CN111126672A (en) | High-voltage overhead transmission line typhoon disaster prediction method based on classification decision tree | |
| Xie et al. | Short-term power load forecasting model based on fuzzy neural network using improved decision tree | |
| CN107422180A (en) | A kind of power prediction system of the photovoltaic plant based on cloud monitoring | |
| CN106529741A (en) | Space relevant characteristic-based ultra-short-period wind power prediction method | |
| CN106611243A (en) | Residual correction method for wind speed prediction based on GARCH (Generalized ARCH) model | |
| CN104239973A (en) | Offshore wind power construction maintenance window region selecting method based on wind wave prediction | |
| CN114548601A (en) | Power distribution network power failure prediction method and system under extreme disasters based on BP neural network | |
| CN105894706B (en) | A kind of forest fire prediction technique and its system | |
| CN104484704A (en) | Wind power plant theoretical power determination method based on BP neural network | |
| CN114386833A (en) | Elasticity evaluation and mobile energy storage regulation and control method for active power distribution network | |
| CN104166883A (en) | Power grid dispatching dynamic capacity increasing evaluation method based on state multi-dimension comprehensive evaluation | |
| CN106651131A (en) | Power-transmission-line anti-typhoon early warning method and system thereof | |
| CN115204712B (en) | Offshore and coastal wind power plant site selection evaluation method |
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: 20190326 |