CN108123436A - Voltage out-of-limit prediction model based on principal component analysis and multivariate regression algorithm - Google Patents
Voltage out-of-limit prediction model based on principal component analysis and multivariate regression algorithm Download PDFInfo
- Publication number
- CN108123436A CN108123436A CN201711246872.6A CN201711246872A CN108123436A CN 108123436 A CN108123436 A CN 108123436A CN 201711246872 A CN201711246872 A CN 201711246872A CN 108123436 A CN108123436 A CN 108123436A
- Authority
- CN
- China
- Prior art keywords
- limit
- voltage
- voltage out
- factor
- principal component
- 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
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of voltage out-of-limit prediction models based on principal component analysis and multivariate regression algorithm, the major influence factors of voltage out-of-limit prediction are determined using Principal Component Analysis first, the prediction model of voltage out-of-limit is further established with multiple regression procedure, more scientific and accuracy the out-of-limit prediction case of distribution network voltage can be obtained, so as to be conducive to comprehensively investigate the operating condition of different regions power distribution network, be conducive to find region of the voltage there are out-of-limit risk, and the early warning problem is handled early, improve operation of power networks efficiency.
Description
Technical field
The present invention relates to electric power analysis technical fields, and in particular to voltage out-of-limit is predicted.
Background technology
Voltage is one of important indicator of power quality, its concentrated expression planning of electric system, design, operation, dimension
Shield and the level of management are Important Economic, a technical indicator of power grid operation.As Net Frame of Electric Network scale expands rapidly
Greatly, new energy equipment constantly puts into operation, and the electric energy level of supply of power grid has obtained significantly being promoted, but electric load total amount
It is swift and violent to be promoted, some areas distribution net equipment is caused to be difficult to meet work requirements, distribution line terminal voltage fluctuation problem is serious, electricity
Out-of-limit problem is pressed to happen occasionally.
Due to the variability of end distribution net topology, load, while in view of line parameter circuit value and transformer operation manners
Difficulty is obtained, the feasibility of the analysis and diagnosis of voltage out-of-limit problem is carried out by way of traditional network modeling and Load flow calculation
It is more insufficient.In addition the influence factor of voltage out-of-limit problem is more, including capacity of distribution transform, with varying load, power supply distance, busbar electricity
Pressure, power factor (PF), bussed supply radius, line footpath width, associated same busbar power distribution voltage and environment temperature etc. factor, and this
Each factor in the different and different voltage out-of-limit record of a little factors proportion shared in the result for causing voltage out-of-limit
Proportion be all not quite similar.Therefore, if by the factor of be likely to result in voltage out-of-limit problem carry out waiting proportions point
Analysis, predicts the out-of-limit situation of voltage clearly unreasonable.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of voltage based on principal component analysis and multivariate regression algorithm
Out-of-limit prediction model improves the science and accuracy of voltage out-of-limit prediction.
In order to solve the above technical problems, the present invention adopts the following technical scheme that：It is calculated based on principal component analysis and multiple regression
The voltage out-of-limit prediction model of method, including,
Voltage out-of-limit relation factor analysis module, handles the data of power grid inside and outside, true using correlation analysis
There are associated factors for fixed and voltage out-of-limit；
Voltage out-of-limit relation factor screening module determines threshold crossing time according to history voltage out-of-limit data, and analyzes and should get over
The relation of lower relation factor and corresponding rating index between in limited time, if the relation factor in voltage out-of-limit there are larger offset,
Then retain, otherwise delete；
The relation factor remained is defined as influence factor by principal component analysis module, influence factor is carried out it is main into
Analysis, calculates the factor loading of each influence factor, and asks for the absolute value of the factor loading, retention factors load absolute value
The major influence factors that big influence factor is predicted as voltage out-of-limit；
Influence factor weight determination module, according to the time series data of voltage out-of-limit historical data and out-of-limit major influence factors
The multiple regression mathematical model of voltage out-of-limit and major influence factors is established, determines each major influence factors weight；
Voltage block line determining module, is trained the time series data of major influence factors, determines voltage out-of-limit oneself
Then regression model determines voltage block line according to the weight of major influence factors and voltage out-of-limit decision content；
Voltage out-of-limit probability evaluation entity, according to the geometry of position of the current voltage in hyperspace and discriminant line away from
From calculating voltage out-of-limit probability, so as to predict voltage out-of-limit situation.
Preferably, it is wide to include capacity of distribution transform, power supply distance, bussed supply voltage, line footpath for the data of the power grid inside and outside
It spends, with varying load, power factor (PF), busbar voltage, line material, permission electric current, environment temperature, the regional output value.
Preferably, in principal component analysis module, retention factors load absolute value is more than 0.6 influence factor, and is made
For the major influence factors of voltage out-of-limit.
Preferably, the factor by factor loading absolute value between 0.5~0.6 when major influence factors are less than 3
As major influence factors.
Preferably, the influence factor weight determination module be established in units of taiwan area distribution transforming voltage out-of-limit to it is related because
The multivariate regression models of element, the multivariate regression models are for example shown below：
Wherein, y is voltage normalizing value；xiThe historical data after normalized is done for correlative factor；wiFor all kinds of factor shadows
Loud weight.
Preferably, voltage block line L, such as following formula：
Wherein, wiFor each weight mainly influenced that training obtains, xiFor the normalized value of influence factor, voltage out-of-limit is taken
Decision content is ± the 5% of rated voltage.
Preferably, the position according to current voltage in hyperspace is done the point to the vertical line of discriminant line L, is acquired most short
Geometric distance d, is the probability of voltage out-of-limit, and the out-of-limit probability of analysis voltage so as to predict voltage out-of-limit situation, works as d
＜ 0.025 thinks that voltage out-of-limit probability is low；As 0.025≤d ＜ 0.05, it is believed that there are out-of-limit possibility for voltage；As d ＞ 0.05, then
Think voltage out-of-limit possibility greatly, it is necessary to take immediate steps.
The technical solution adopted by the present invention, first using Principal Component Analysis determine voltage out-of-limit prediction main influence because
Element further establishes the prediction model of voltage out-of-limit with multiple regression procedure, can obtain more scientific and accuracy match somebody with somebody
Power grid out-of-limit prediction case so as to be conducive to comprehensively investigate the operating condition of different regions power distribution network, is conducive to find
Voltage and early handles the early warning problem, improves operation of power networks efficiency there are the region of out-of-limit risk, while also beneficial
In the variety analysis application of electrical network mass data.
Description of the drawings
The invention will be further described with reference to the accompanying drawings and detailed description：
Fig. 1 is the voltage out-of-limit prediction FB(flow block) of the present invention.
Specific embodiment
Principal Component Analysis is also referred to as principal component analysis, it is intended to using the thought of dimensionality reduction, multi objective is converted into several
A principal component, wherein each principal component can reflect the most information of original variable, and information contained does not repeat mutually.It is this
Complicated factor is attributed to several principal components by method while many-sided variable is introduced, and is simplified a problem, while obtain
As a result more scientific and effective data message.Each variable reflects institute to varying degrees in voltage out-of-limit forecast analysis
Some information of voltage out-of-limit, and have certain relevance between variable, if gained can be caused by not carrying out principal component analysis first
Statistics reflection information have overlapping to a certain extent.
Multiple regression rule is the regression analysis of relation between the multiple variables of research, can reflect a kind of phenomenon or
The rule that the quantity of things is correspondingly changed according to the variation of a variety of phenomenons or the quantity of things.
The present invention is directed to the operation of power networks data of magnanimity, it is proposed that a kind of based on principal component analysis and multivariate regression algorithm
Voltage out-of-limit Forecasting Methodology, it is contemplated that the influence factor of voltage out-of-limit it is more and it is different it is out-of-limit in the case of shared by each influence factor into
Because proportion is different, the principal element of voltage out-of-limit is first extracted with Principal Component Analysis, then voltage is established with multiple regression procedure and is got over
The prediction model of limit.
As shown in Figure 1, the concrete methods of realizing of the present invention is as follows：
Voltage out-of-limit relation factor analysis module, capacity of distribution transform, power supply distance, bussed supply electricity to power grid inside and outside
Pressure, line footpath width, with varying load, power factor (PF), busbar voltage, line material, allow electric current, environment temperature, regional output value etc.
Mass data is handled, and determines that there are associated factors with voltage out-of-limit using correlation analysis.
Voltage out-of-limit relation factor screening module determines threshold crossing time according to history voltage out-of-limit data, it is out-of-limit to analyze this
Line current under time, the relation with the factors such as varying load, power factor (PF), frequency Yu the rating index of these factors judge
It, with the presence or absence of larger offset (this larger offset can be manually set), if then retaining, is otherwise deleted in voltage out-of-limit
It removes.
Principal component analysis module carries out principal component analysis to the influence factor remained, calculates each influence factor
Factor loading, and the absolute value of the factor loading is asked for, the big influence factor of retention factors load absolute value is as voltage out-of-limit
The principal element of prediction.There are many factor for causing voltage out-of-limit, and influence of some factors to voltage out-of-limit is very little, therefore first
Principal component analysis is carried out with regard to influence factor, calculates the factor loading of each influence factor, the big shadow of retention factors load absolute value
The key influence factor that the factor of sound is predicted as voltage out-of-limit.Specifically in the present invention, retention factors load absolute value is more than 0.6
Influence factor, and as the major influence factors of voltage out-of-limit, when major influence factors are less than 3 by factor loading
Factor of the absolute value between 0.5~0.6 also serves as major influence factors.
Influence factor weight determination module, according to the time series data of voltage out-of-limit historical data and out-of-limit major influence factors
The mathematical model of voltage out-of-limit and correlative factor is established, determines each factor weight.
Voltage block line determining module, is trained the time series data of correlative factor, according to voltage out-of-limit historical data
With the time series data of out-of-limit major influence factors, the polynary of voltage out-of-limit in units of taiwan area distribution transforming and correlative factor is established
Regression model, so as to obtain voltage block line.
The influence factor weight determination module is voltage out-of-limit and correlative factor are established in units of taiwan area distribution transforming more
First regression model, multivariate regression models are for example shown below：
Wherein, y is voltage normalizing value；xiThe historical data after normalized is done for correlative factor；wiFor all kinds of factor shadows
Loud weight.
Voltage block line L, formula specific as follows：
Wherein, wiFor each weight mainly influenced that training obtains, xiFor the normalized value of influence factor, voltage out-of-limit is taken
Decision content is ± the 5% of rated voltage.
Voltage out-of-limit probability evaluation entity, finally according to position of the current voltage in hyperspace and the geometry of discriminant line
Distance calculates voltage out-of-limit probability, so as to carry out reliable prediction to voltage out-of-limit situation.Specifically according to current voltage in multidimensional
Position in space does the point to the vertical line of discriminant line L, acquires most short geometric distance d, be the probability of voltage out-of-limit, analyze
Voltage out-of-limit probability, so as to predict voltage out-of-limit situation, when d ＜ 0.025 think that voltage out-of-limit probability is low；When 0.025
≤ d ＜ 0.05, it is believed that there are out-of-limit possibility for voltage；As d ＞ 0.05, then it is assumed that voltage out-of-limit possibility greatly, it is necessary to adopt immediately
Take measure.
Because it the purpose of the present invention is the out-of-limit situation to distribution voltage is predicted, therefore needs to establish influence factor and electricity
Press out-of-limit correlation models.First to the history data from power grid, battalion with data and with adopting data and from outer
The meteorological data in portion etc. is pre-processed, and is cleaned redundant data, is avoided error caused by the quality problems of data source.Utilize correlation
Property analytic approach determined with voltage out-of-limit there are associated factor, the original variable as follow-up principal component analysis.
Grid company storage inside power information gathered data, marketing data and operation/maintenance data of magnanimity etc., it is external then
Have a meteorological, economic data, these data messages on the prediction of voltage out-of-limit there may be influence, in order to ensure that voltage out-of-limit is pre-
For the accuracy of survey, it is necessary to be pre-processed to power grid inside and outside mass data, cleaning redundant data avoids the quality of data source from asking
Error caused by topic.Because data volume is huge and not all data all have an impact voltage out-of-limit, therefore utilizes correlation point
Analysis method determined with voltage out-of-limit there are associated factor, the original variable as follow-up principal component analysis.
The time of out-of-limit generation is determined from history voltage out-of-limit time series data, it is out-of-limit that this is extracted according to the time series data
The information of each time-varying relation factor under time, including line current, with varying load, power factor (PF), busbar voltage, frequency etc. because
Element analyzes its relation between nominal rating index, if its value under the voltage out-of-limit time there are larger offset, and should
Deviant alreadys exceed allowable offset, it is determined that the influence factor is related to voltage out-of-limit, is retained, and otherwise deletes.
There are many factor for causing voltage out-of-limit, and influence of some factors to voltage out-of-limit is very little, such as specifically
A certain extreme weather, some can simply have an impact under special scenes, it is therefore desirable to first carry out principal component with regard to influence factor
Analysis, calculates the factor loading of each influence factor, the big influence factor of retention factors load absolute value, determine capacity of distribution transform,
Bussed supply radius, power supply distance, line footpath width, with varying load, power factor (PF), relevance with target power distribution voltage and environment temperature
Spend the key influence factor as voltage out-of-limit prediction.
Basic principle, main feature and the advantageous effect and embodiment of the present invention has been shown and described above.The present invention
From the limitation of data type, the voltage out-of-limit prediction under each voltage class is can be applied to, is a kind of general method.With
What upper emphasis illustrated be with correlation analysis determine factor relevant with voltage out-of-limit, Principal Component Analysis screening it is main influence because
Element simultaneously voltage out-of-limit model is determined by multivariate regression algorithm, ask for the voltage out-of-limit discriminant line under voltage headroom, then according to
The space length of voltage out-of-limit discriminant line determines the thought of voltage out-of-limit probability, and specific embodiment can be according to different electricity
The actual influence factor of pressure grade is independently set.Voltage out-of-limit situation as obtained by calculating the present invention, combines comprehensive to magnanimity
The analysis of electric power big data is closed, will be more suitable for future in the out-of-limit anticipation of each voltage class voltage.
Claims (7)
1. the voltage out-of-limit prediction model based on principal component analysis and multivariate regression algorithm, it is characterised in that including,
Voltage out-of-limit relation factor analysis module, handles the data of power grid inside and outside, using correlation analysis determine with
There are associated factors for voltage out-of-limit；
Voltage out-of-limit relation factor screening module determines threshold crossing time according to history voltage out-of-limit data, and analyzes this and more prescribe a time limit
Between lower relation factor and corresponding rating index relation, if the relation factor in voltage out-of-limit there are larger offset, protect
It stays, otherwise deletes；
The relation factor remained is defined as influence factor by principal component analysis module, and principal component point is carried out to influence factor
Analysis, calculates the factor loading of each influence factor, and ask for the absolute value of the factor loading, and retention factors load absolute value is big
The major influence factors that influence factor is predicted as voltage out-of-limit；
Influence factor weight determination module is established according to the time series data of voltage out-of-limit historical data and out-of-limit major influence factors
The multiple regression mathematical model of voltage out-of-limit and major influence factors determines each major influence factors weight；
Voltage block line determining module, is trained the time series data of major influence factors, determines the autoregression of voltage out-of-limit
Then model determines voltage block line according to the weight of major influence factors and voltage out-of-limit decision content；
Voltage out-of-limit probability evaluation entity, according to position of the current voltage in hyperspace and the geometric distance of discriminant line, meter
Voltage out-of-limit probability is calculated, so as to predict voltage out-of-limit situation.
2. the voltage out-of-limit prediction model according to claim 1 based on principal component analysis and multivariate regression algorithm, special
Sign is：The data of the power grid inside and outside are born including capacity of distribution transform, power supply distance, bussed supply voltage, line footpath width, distribution transforming
Load, power factor (PF), busbar voltage, line material, permission electric current, environment temperature, the regional output value.
3. the voltage out-of-limit prediction model according to claim 1 based on principal component analysis and multivariate regression algorithm, special
Sign is：In principal component analysis module, retention factors load absolute value is more than 0.6 influence factor, and is got over as voltage
The major influence factors of limit.
4. the voltage out-of-limit prediction model according to claim 3 based on principal component analysis and multivariate regression algorithm, special
Sign is：Factor of the factor loading absolute value between 0.5~0.6 also served as mainly when major influence factors are less than 3
Influence factor.
5. the voltage out-of-limit according to any one of claims 1 to 4, based on principal component analysis and multivariate regression algorithm is pre-
Survey model, it is characterised in that：The influence factor weight determination module is to establish voltage out-of-limit and phase in units of taiwan area distribution transforming
The multivariate regression models of pass factor, the multivariate regression models are for example shown below：
<mrow>
<mi>y</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>w</mi>
<mi>i</mi>
</msub>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
</mrow>
Wherein, y is voltage normalizing value；xiThe historical data after normalized is done for correlative factor；wiIt is influenced for all kinds of factors
Weight.
6. the voltage out-of-limit prediction model according to claim 5 based on principal component analysis and multivariate regression algorithm, special
Sign is：Voltage block line L, such as following formula：
<mrow>
<mrow>
<mo>|</mo>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>w</mi>
<mi>i</mi>
</msub>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>|</mo>
</mrow>
<mo>=</mo>
<mn>0.05</mn>
</mrow>
Wherein, wiFor each weight mainly influenced that training obtains, xiFor the normalized value of influence factor, voltage out-of-limit is taken to judge
It is worth for ± the 5% of rated voltage.
7. the voltage out-of-limit prediction model according to claim 1 based on principal component analysis and multivariate regression algorithm, special
Sign is：According to position of the current voltage in hyperspace, the point is done to the vertical line of discriminant line L, acquires most short geometric distance
The probability of d, as voltage out-of-limit, the out-of-limit probability of analysis voltage, so as to predict voltage out-of-limit situation, when d ＜ 0.025 recognize
It is low for voltage out-of-limit probability；As 0.025≤d ＜ 0.05, it is believed that there are out-of-limit possibility for voltage；As d ＞ 0.05, then it is assumed that voltage is got over
Possibility is limited greatly, it is necessary to take immediate steps.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711246872.6A CN108123436B (en) | 2017-12-01 | 2017-12-01 | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711246872.6A CN108123436B (en) | 2017-12-01 | 2017-12-01 | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108123436A true CN108123436A (en) | 2018-06-05 |
| CN108123436B CN108123436B (en) | 2021-07-20 |
Family
ID=62228896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711246872.6A Active CN108123436B (en) | 2017-12-01 | 2017-12-01 | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108123436B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636029A (en) * | 2018-12-10 | 2019-04-16 | 国网江苏省电力有限公司扬州供电分公司 | Power distribution network middle or short term voltage out-of-limit method for early warning based on big data |
| CN118017522A (en) * | 2024-04-08 | 2024-05-10 | 广东电网有限责任公司广州供电局 | Method, device, system and storage medium for collaborative regulation and control of transformer area voltage |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000293566A (en) * | 1999-04-09 | 2000-10-20 | Nec Ic Microcomput Syst Ltd | Method for extracting model parameter |
| CN103236692A (en) * | 2013-04-25 | 2013-08-07 | 网新创新研究开发有限公司 | Method for evaluating operation status of power system by utilizing probability tide |
| CN103295079A (en) * | 2013-06-09 | 2013-09-11 | 国家电网公司 | Electric power multi-objective decision support method based on intelligent data mining model |
| CN103310388A (en) * | 2013-05-28 | 2013-09-18 | 清华大学 | Method for calculating composite index of grid operation based on information source entropy |
| CN104156890A (en) * | 2014-08-15 | 2014-11-19 | 贵州电力试验研究院 | Wind power grid-connection scheme decision method |
| CN105787219A (en) * | 2016-04-21 | 2016-07-20 | 北京航空航天大学 | Method for building conducted interference coupling channel multiple linear regression model by near frequency point sampling |
| CN107271829A (en) * | 2017-05-09 | 2017-10-20 | 安徽继远软件有限公司 | A kind of controller switching equipment running state analysis method and device |
-
2017
- 2017-12-01 CN CN201711246872.6A patent/CN108123436B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000293566A (en) * | 1999-04-09 | 2000-10-20 | Nec Ic Microcomput Syst Ltd | Method for extracting model parameter |
| CN103236692A (en) * | 2013-04-25 | 2013-08-07 | 网新创新研究开发有限公司 | Method for evaluating operation status of power system by utilizing probability tide |
| CN103310388A (en) * | 2013-05-28 | 2013-09-18 | 清华大学 | Method for calculating composite index of grid operation based on information source entropy |
| CN103295079A (en) * | 2013-06-09 | 2013-09-11 | 国家电网公司 | Electric power multi-objective decision support method based on intelligent data mining model |
| CN104156890A (en) * | 2014-08-15 | 2014-11-19 | 贵州电力试验研究院 | Wind power grid-connection scheme decision method |
| CN105787219A (en) * | 2016-04-21 | 2016-07-20 | 北京航空航天大学 | Method for building conducted interference coupling channel multiple linear regression model by near frequency point sampling |
| CN107271829A (en) * | 2017-05-09 | 2017-10-20 | 安徽继远软件有限公司 | A kind of controller switching equipment running state analysis method and device |
Non-Patent Citations (2)
| Title |
|---|
| DUAN SHUJING等: "Fault Diagnosis for Sensors of Aero-engine Based on Improved Least Squares Support Vector Regression", 《2011 EIGHTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD)》 * |
| 段青: "基于稀疏贝叶斯学习方法的回归与分类在电力系统中的预测研究", 《中国博士学位论文全文数据库 工程科技II辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636029A (en) * | 2018-12-10 | 2019-04-16 | 国网江苏省电力有限公司扬州供电分公司 | Power distribution network middle or short term voltage out-of-limit method for early warning based on big data |
| CN118017522A (en) * | 2024-04-08 | 2024-05-10 | 广东电网有限责任公司广州供电局 | Method, device, system and storage medium for collaborative regulation and control of transformer area voltage |
| CN118017522B (en) * | 2024-04-08 | 2024-07-09 | 广东电网有限责任公司广州供电局 | Method, device, system and storage medium for collaborative regulation and control of transformer area voltage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108123436B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190067941A1 (en) | Methods and apparatus for determining conditions of power lines | |
| CN102427218B (en) | Transformer short period overload capability assessment system based on artificial intelligence technology | |
| CN106992517A (en) | Electric power line loss analysis method, device and system | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| Akbari et al. | Convex probabilistic allocation of wind generation in smart distribution networks | |
| Mendes et al. | An adaptive data compression mechanism for smart meters considering a demand side management scenario | |
| KR20200128232A (en) | Apparatus for predicting electricity demand and method thereof | |
| CN103326348A (en) | System for improving local electric network power supply ability analysis and providing entire process online monitoring | |
| CN116756530B (en) | Power grid line loss evaluation method and system for new energy access power distribution network | |
| CN114742283A (en) | Medium-voltage line loop closing current estimation and risk assessment method based on deep learning network | |
| CN106849064B (en) | Regional power grid load prediction management system based on meteorological data | |
| Madadi et al. | Application of big data analysis to operation of smart power systems | |
| CN112633762A (en) | Building energy efficiency obtaining method and equipment | |
| CN108123436A (en) | Voltage out-of-limit prediction model based on principal component analysis and multivariate regression algorithm | |
| CN103150605A (en) | Power grid planning auxiliary system | |
| CN108108871B (en) | Type selection method for wind power plant group power transmission equipment | |
| CN104063757B (en) | Transformer substation main electrical connection assessment method suitable for different development stages of power grids | |
| CN103675518A (en) | Maintenance method and device for oil-immersed high-voltage equipment | |
| CN116995799A (en) | Distributed power supply access and panoramic management and control application method and system | |
| Bagen et al. | A subsystem based probabilistic approach for the assessment of transmission capital project reliability impacts | |
| CN116167514A (en) | Method and system for predicting electric energy transmission capacity of power transmission wire | |
| CN116341701A (en) | Prediction method and system for low-voltage distributed photovoltaic power generation system | |
| CN105021888A (en) | Harmonic wave data monitoring method based on data clustering | |
| CN108847666A (en) | Analysis method, device and the realization device of power distribution network short circuit current level | |
| CN114421465A (en) | Power grid parameter identification and verification method and device based on element topology and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |