CN106548253A - Method based on the wind power prediction of nonparametric probability - Google Patents

Method based on the wind power prediction of nonparametric probability Download PDF

Info

Publication number
CN106548253A
CN106548253A CN201610979574.7A CN201610979574A CN106548253A CN 106548253 A CN106548253 A CN 106548253A CN 201610979574 A CN201610979574 A CN 201610979574A CN 106548253 A CN106548253 A CN 106548253A
Authority
CN
China
Prior art keywords
wind power
wind
data
actual measurement
probability
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201610979574.7A
Other languages
Chinese (zh)
Inventor
丁敏
吴敏
安剑奇
谢华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China University of Geosciences
Original Assignee
China University of Geosciences
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China University of Geosciences filed Critical China University of Geosciences
Priority to CN201610979574.7A priority Critical patent/CN106548253A/en
Publication of CN106548253A publication Critical patent/CN106548253A/en
Pending legal-status Critical Current

Links

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—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 a kind of method of the wind power prediction based on nonparametric probability, methods described includes：Step one, obtains the wind farm data of history in default time range, and actual measurement wind power data are divided into multiple subintervals；Wherein, the wind farm data includes surveying wind speed and actual measurement wind power；Step 2, counts the actual measurement wind power in each subinterval, and according to the wind power distribution in each actual measurement wind speed subinterval, sets up wind power probability density function respectively；Step 3, it is determined that the confidential interval of actual measurement wind power, deletes the wind power data outside confidential interval；Data in gained confidential interval are exactly the modeling data for screening；Step 4, is fitted modeling data using S type functions, sets up wind power prediction model and be predicted.

Description

Method based on the wind power prediction of nonparametric probability
Technical field
The present invention relates to wind power prediction field, more particularly to a kind of wind power based on nonparametric probability The method of prediction.
Background technology
With the quick consumption of fossil energy, the mankind are faced with the Double jeopardy of lack of energy and environmental degradation, therefore Reproducible wind energy is cleaned in recent years has worldwide also therefore suffered from extensive attention and development.Domestic wind-powered electricity generation total installed capacity holds Amount has leapt to the first in the world, and the use of the extensive development and reduction fossil energy of wind-powered electricity generation alleviates the energy to a certain extent Crisis.But, as wind energy has very strong intermittent and randomness, with increasing with installed capacity not for wind-powered electricity generation number Disconnected increase, the large-scale grid connection of wind-powered electricity generation bring huge challenge to the safety and economic operation of electrical network.The uncertainty of wind can be led Cause wind-driven generator generate electricity by preferable wind power curve, under same velocity wind levels, the work(that wind-driven generator sends Rate can be presented larger fluctuation.Wind-power electricity generation is effectively predicted, dispatching of power netwoks department can be helped to carry out distributed power source Operation plan, improve ability of the electrical network using wind-powered electricity generation, reduce as wind-powered electricity generation is rationed the power supply the economic loss brought, increase wind energy turbine set and throw Money return rate.
The content of the invention
The present invention provides a kind of method of the wind power prediction based on nonparametric probability, solves prior art The uncertainty of apoplexy can cause the technical problem that wind-driven generator can not generate electricity by preferable wind power curve, reached and carried The high technique effect to wind power Accurate Prediction precision.
To solve above-mentioned technical problem, the present invention provides a kind of wind power prediction based on nonparametric probability Method, methods described include：
Step one, obtains the wind farm data of history in default time range, and actual measurement wind power data are divided into Multiple subintervals；Wherein, the wind farm data includes surveying wind speed and actual measurement wind power；
Step 2, counts the actual measurement wind power in each subinterval, and according to the wind in each actual measurement wind speed subinterval Electrical power is distributed, and sets up wind power probability density function respectively；
Step 3, it is determined that the confidential interval of actual measurement wind power, deletes the wind power data outside confidential interval；Gained is put Data in letter interval are exactly the modeling data for screening；
Step 4, is fitted modeling data using S type functions, sets up wind power prediction model and be predicted.
Preferably, actual measurement wind power data are divided into into multiple subintervals described in the step one, specially：
By actual measurement wind speed by arranging from small to large, with the actual measurement wind speed after sequence as abscissa, corresponding actual measurement wind-powered electricity generation work( Rate is ordinate, history of forming actual measurement wind speed-actual measurement wind power statistics group, actual measurement wind speed is entered with certain resolution ratio Row is divided at equal intervals, and actual measurement wind power data are divided into multiple subintervals.
Preferably, built according to the wind power distribution in each actual measurement wind speed subinterval respectively described in the step 2 Vertical wind power probability density function, specially：
From data sample data distribution characteristics in itself, wind power is estimated by training data itself To set up wind power distribution function, the wind power of each wind speed point of wind energy turbine set is calculated according to wind energy turbine set wind power distribution function Distributed model.
Preferably, the confidential interval of actual measurement wind power is determined described in the step 3, specially：
(1) set up the confidential interval object function of minimum length：
min(X2-X1) (ⅰ)
Wherein, X2-X1Represent confidential interval, X2For the confidential interval upper bound, X1For confidential interval lower bound；
(2) constraints is determined according to the confidence level for providing：
F(X2)-F(X1)=(1- α) (II)；
Wherein, probability-distribution functions of the F (X) for probability density function f (x), (1- α) are the confidence level of setting；
(3) wind power is estimated using nonparametric probability method, using nonparametric probability side Method sets up probability density function：
In formula, f (x) is probability density function, and N is total sample number, and h is bandwidth, xiTo give sample, K () is core letter Number；
K () is selected to be gaussian kernel function, then the probability density function of power is：
Probability-distribution function of note F (x) for power, Q (X1≤x≤X2) represent in confidential interval X1～X2Interior wind power The probability that value occurs, i.e. confidence level, then have：
Q(X1≤X≤X2)=F (X2)-F(X1) (ⅴ)
Acquisition concentrates on the wind power under a certain confidence level, and the wind power meets a certain confidence level Q (X1≤ x≤X2) Lowest Confidence Interval, seek X when meeting formula (V)2-X1Minimum of a value.
(4) its shortest confidence interval under a certain confidence level is asked for using Lagrange multiplier algorithm, sets up glug Bright day function：
L=(X2-X1)+λ[F(X2)-F(X1)-Q(X1≤x≤X2)] (ⅵ)
Order：
I.e.：
Obtain：
Wushu (IV) substitutes into formula (IV), solves using optimal method, obtains X1、X2, and min (X2-X1) numerical value.
Preferably, modeling data is fitted using S type functions described in the step 4, sets up wind power prediction model and enter Row prediction, specially：
Forecast model is obtained using S type curve matchings, and the modeling data for screening, using the forecast model to wind Electrical power is predicted.
Preferably, the utilization S type curve matchings, and the modeling data for screening obtain forecast model, using described Forecast model is predicted to wind power, specially：
The modeling data for screening is substituted into into S type curvesFitting, obtains k, a and b；Wherein, will screening Wind speed is surveyed in modeling data out as input v, the power output of corresponding wind energy turbine set is used as output P；
K, a and b for obtaining are substituted into into S type curvesIn, forecast model is obtained, the wind speed number that NWP is predicted According to as input, corresponding prediction wind power is obtained according to forecast model；In formula, v is air speed data, and P is corresponding wind Electrical power.
The application has the beneficial effect that：
A kind of method of wind power prediction based on nonparametric probability that the present invention is provided, methods described are unfavorable With the priori about data distribution, data are not added with any it is assumed that using from data sample data in itself The method of distribution characteristics, fully relies on training data and is estimated in itself, and the probability density function that can be used for arbitrary shape is estimated Meter, more can response data itself true distribution；
Further, power distribution of the present invention based on nonparametric probability, directly from a bit of wind speed interval Power data find rule in itself, capture the true distribution of data, its probability density function is probably arbitrary shape, for example： It is asymmetric and non-unimodal.For asymmetric non-unimodal probability density function, its Lowest Confidence Interval is sought using optimal method, Obtain that wind power siding-to-siding block length is most short, the more accurate and effective of the data after process improves the essence of wind power interval prediction Degree.
Further, the present invention does the power distribution in little wind speed interval to the historical data after rejecting power abnormity point and builds Vertical probability density function, with the confidential interval under probability theory theoretical calculation certain confidence level, so that it is determined that the wind speed interval Reliable wind power value range.Reliable wind farm wind velocity-wind power the data in confidential interval are fitted using S type functions, As forecast model.Recycle NWP prediction of wind speed as prediction input data, be output as predicting wind power.It is pre- after process Survey modeling data and more conform to actual conditions, improve the precision of wind power prediction.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, embodiment will be described below Needed for accompanying drawing to be used be briefly described, it should be apparent that, drawings in the following description be only the present invention some Embodiment.
Fig. 1 is flow process of the application better embodiment based on the wind power forecasting method of nonparametric probability Figure；
Fig. 2 is the datagram of one embodiment rejecting abnormalities collection point of step 3 in the application Fig. 1；
Fig. 3 is the wind power frequency histogram in certain wind speed interval in Fig. 2；
Fig. 4 is the datagram of frequency histogram and norm of nonparametric kernel density Function Fitting in Fig. 2；
Fig. 5 is the datagram after processing using norm of nonparametric kernel density in Fig. 2.
Specific embodiment
In order to be better understood from above-mentioned technical proposal, below in conjunction with Figure of description and specific embodiment to upper State technical scheme to be described in detail.
The method of the wind power prediction based on nonparametric probability that the present invention that the application is provided is provided, it is described Method does not utilize the priori about data distribution, and data are not added with any it is assumed that using from data sample The method of data distribution characteristics, fully relies on training data and is estimated in itself, and the probability that can be used for arbitrary shape is close Degree Function Estimation, more can response data itself true distribution；Directly the power data from a bit of wind speed interval is sought in itself Rule is looked for, the true distribution of data is captured, its probability density function is probably arbitrary shape, for example：It is asymmetric and non-unimodal.It is right In asymmetric non-unimodal probability density function, its Lowest Confidence Interval is sought using optimal method, obtain wind power interval Length is most short, the more accurate and effective of the data after process, improves the precision of wind power interval prediction.The present invention is to rejecting work( The power distribution that historical data after rate abnormity point is done in little wind speed interval sets up probability density function, counts with probability theory is theoretical The confidential interval under certain confidence level is calculated, so that it is determined that the reliable wind power value range of the wind speed interval.Using S type functions Reliable wind farm wind velocity-wind power data in fitting confidential interval, as forecast model.NWP prediction of wind speed is recycled to make To predict input data, it is output as predicting wind power.Prediction modeling data after process more conforms to actual conditions, improves The precision of wind power prediction.
The method of the wind power prediction based on nonparametric probability that the application is provided, refers to Fig. 1, the side Method includes：
Step one S100, obtains the wind farm data of history in default time range, and actual measurement wind power data are drawn It is divided into multiple subintervals；Wherein, the wind farm data includes surveying wind speed and actual measurement wind power；
Actual measurement wind power data are divided into into multiple subintervals described in the step one, specially：
By actual measurement wind speed by arranging from small to large, with the actual measurement wind speed after sequence as abscissa, corresponding actual measurement wind-powered electricity generation work( Rate is ordinate, history of forming actual measurement wind speed-actual measurement wind power statistics group, actual measurement wind speed is entered with certain resolution ratio Row is divided at equal intervals, and actual measurement wind power data are divided into multiple subintervals.
Assume that the maximum of wind speed, minimum of a value are respectively vmaxAnd vmin, wind speed resolution granularity is Δ v, then interval number n For：
Then institute by stages DiFor：
Di=[vmin+(i-1)Δv,vmin+ i Δ v] i=1,2 ... n；.
Step 2 S200, counts the actual measurement wind power in each subinterval, and according in each actual measurement wind speed subinterval Wind power distribution, set up wind power probability density function respectively；
According to the wind power distribution in each actual measurement wind speed subinterval described in the step 2, wind-powered electricity generation work(is set up respectively Rate probability density function, specially：
From data sample data distribution characteristics in itself, wind power is estimated by training data itself To set up wind power distribution function, the wind power of each wind speed point of wind energy turbine set is calculated according to wind energy turbine set wind power distribution function Distributed model.
Step 3 S300, it is determined that the confidential interval of actual measurement wind power, deletes the wind power data outside confidential interval；Institute The data obtained in confidential interval are exactly the modeling data for screening；Fig. 2 rejects different for one embodiment of step 3 in the application Fig. 1 The datagram of normal collection point；Fig. 3 is the wind power frequency histogram in certain wind speed interval in Fig. 2；Fig. 4 is straight for frequency in Fig. 2 The datagram of side's figure and norm of nonparametric kernel density Function Fitting；Fig. 5 is the datagram after processing using norm of nonparametric kernel density in Fig. 2.
The confidential interval of actual measurement wind power is determined described in the step 3, specially：
(1) set up the confidential interval object function of minimum length：
min(X2-X1) (ⅰ)
Wherein, X2-X1Represent confidential interval, X2For the confidential interval upper bound, X1For confidential interval lower bound；
(2) constraints is determined according to the confidence level for providing：
F(X2)-F(X1)=(1- α) (II)；
Wherein, probability-distribution functions of the F (X) for probability density function f (x), (1- α) are the confidence level of setting；
(3) wind power is estimated using nonparametric probability method, using nonparametric probability side Method sets up probability density function：
In formula, f (x) is probability density function, and N is total sample number, and h is bandwidth, xiTo give sample, K () is core letter Number；
K () is selected to be gaussian kernel function, then the probability density function of power is：
Probability-distribution function of note F (x) for power, Q (X1≤x≤X2) represent in confidential interval X1～X2Interior wind power The probability that value occurs, i.e. confidence level, then have：
Q(X1≤X≤X2)=F (X2)-F(X1) (ⅴ)
Acquisition concentrates on the wind power under a certain confidence level, and the wind power meets a certain confidence level Q (X1≤ x≤X2) Lowest Confidence Interval, seek X when meeting formula (V)2-X1Minimum of a value.
(4) its shortest confidence interval under a certain confidence level is asked for using Lagrange multiplier algorithm, sets up glug Bright day function：
L=(X2-X1)+λ[F(X2)-F(X1)-Q(X1≤x≤X2)] (ⅵ)
Order：
I.e.：
Obtain：
Wushu (IV) substitutes into formula (IV), solves using optimal method, obtains X1、X2, and min (X2-X1) numerical value.
Step 4 S400, is fitted modeling data using S type functions, sets up wind power prediction model and be predicted.
In step 4 with reference to the characteristics of the wind speed-power curve of Wind turbines, whole wind farm wind velocity-power curve should be big Body obeys similar rule：Low wind speed area, exerts oneself less；Pilot process is exerted oneself；After more than rated wind speed, exert oneself flat Surely；After more than fan safe wind speed, it is zero to exert oneself, and selects S type functions.
Modeling data is fitted using S type functions described in the step 4, wind power prediction model is set up and is predicted, Specially：
Forecast model is obtained using S type curve matchings, and the modeling data for screening, using the forecast model to wind Electrical power is predicted.
The utilization S type curve matchings, and the modeling data for screening obtains forecast model, using the forecast model Wind power is predicted, specially：
The modeling data for screening is substituted into into S type curvesFitting, obtains k, a and b；Wherein, will screening Wind speed is surveyed in modeling data out as input v, the power output of corresponding wind energy turbine set is used as output P；
K, a and b for obtaining are substituted into into S type curvesIn, forecast model is obtained, the wind speed number that NWP is predicted According to as input, corresponding prediction wind power is obtained according to forecast model；In formula, v is air speed data, and P is corresponding wind Electrical power.
The application has the beneficial effect that：
A kind of method of wind power prediction based on nonparametric probability that the present invention is provided, methods described are unfavorable With the priori about data distribution, data are not added with any it is assumed that using from data sample data in itself The method of distribution characteristics, fully relies on training data and is estimated in itself, and the probability density function that can be used for arbitrary shape is estimated Meter, more can response data itself true distribution；
Further, power distribution of the present invention based on nonparametric probability, directly from a bit of wind speed interval Power data find rule in itself, capture the true distribution of data, its probability density function is probably arbitrary shape, for example： It is asymmetric and non-unimodal.For asymmetric non-unimodal probability density function, its Lowest Confidence Interval is sought using optimal method, Obtain that wind power siding-to-siding block length is most short, the more accurate and effective of the data after process improves the essence of wind power interval prediction Degree.
Further, the present invention does the power distribution in little wind speed interval to the historical data after rejecting power abnormity point and builds Vertical probability density function, with the confidential interval under probability theory theoretical calculation certain confidence level, so that it is determined that the wind speed interval Reliable wind power value range.Reliable wind farm wind velocity-wind power the data in confidential interval are fitted using S type functions, As forecast model.Recycle NWP prediction of wind speed as prediction input data, be output as predicting wind power.It is pre- after process Survey modeling data and more conform to actual conditions, improve the precision of wind power prediction.
It should be noted last that, above specific embodiment only to illustrate technical scheme and unrestricted, Although being described in detail to the present invention with reference to example, it will be understood by those within the art that, can be to the present invention Technical scheme modify or equivalent, without deviating from the spirit and scope of technical solution of the present invention, which all should be covered In the middle of scope of the presently claimed invention.

Claims (6)

1. a kind of method of the wind power prediction based on nonparametric probability, it is characterised in that methods described includes：
Step one, obtains the wind farm data of history in default time range, actual measurement wind power data is divided into multiple Subinterval；Wherein, the wind farm data includes surveying wind speed and actual measurement wind power；
Step 2, counts the actual measurement wind power in each subinterval, and according to the wind-powered electricity generation work(in each actual measurement wind speed subinterval Rate is distributed, and sets up wind power probability density function respectively；
Step 3, it is determined that the confidential interval of actual measurement wind power, deletes the wind power data outside confidential interval；Gained confidence area Interior data are exactly the modeling data for screening；
Step 4, is fitted modeling data using S type functions, sets up wind power prediction model and be predicted.
2. the method for claim 1, it is characterised in that actual measurement wind power data are divided described in the step one For multiple subintervals, specially：
By actual measurement wind speed by arranging from small to large, with the actual measurement wind speed after sequence as abscissa, corresponding actual measurement wind power is Ordinate, history of forming actual measurement wind speed-actual measurement wind power statistics group, actual measurement wind speed is carried out with certain resolution ratio etc. Interval divides, and actual measurement wind power data are divided into multiple subintervals.
3. the method for claim 1, it is characterised in that according to each actual measurement wind speed subinterval described in the step 2 Interior wind power distribution, sets up wind power probability density function, specially respectively：
From data sample data distribution characteristics in itself, carry out estimation to wind power to build by training data itself Vertical wind power distribution function, calculates the wind power distribution of each wind speed point of wind energy turbine set according to wind energy turbine set wind power distribution function Model.
4. the method for claim 1, it is characterised in that the confidence of actual measurement wind power is determined described in the step 3 Interval, specially：
(1) set up the confidential interval object function of minimum length：
min(X2-X1) (ⅰ)
Wherein, X2-X1Represent confidential interval, X2For the confidential interval upper bound, X1For confidential interval lower bound；
(2) constraints is determined according to the confidence level for providing：
F(X2)-F(X1)=(1- α) (II)；
Wherein, probability-distribution functions of the F (X) for probability density function f (x), (1- α) are the confidence level of setting；
(3) wind power is estimated using nonparametric probability method, is built using nonparametric probability method Vertical probability density function is：
f ( x ) = 1 N h Σ i = 1 N K ( x - x i h ) - - - ( i i i ) ;
In formula, f (x) is probability density function, and N is total sample number, and h is bandwidth, xiTo give sample, K () is kernel function；
K () is selected to be gaussian kernel function, then the probability density function of power is：
f ( x ) = 1 N h Σ i = 1 N 1 2 π exp ( - 1 2 ( x - x i h ) 2 ) - - - ( i v ) ;
Probability-distribution function of note F (x) for power, Q (X1≤x≤X2) represent in confidential interval X1～X2Interior wind power value occurs Probability, i.e. confidence level then has：
Q(X1≤X≤X2)=F (X2)-F(X1) (ⅴ)
Acquisition concentrates on the wind power under a certain confidence level, and the wind power meets a certain confidence level Q (X1≤x≤ X2) Lowest Confidence Interval, seek X when meeting formula (V)2-X1Minimum of a value；
(4) its shortest confidence interval under a certain confidence level is asked for using Lagrange multiplier algorithm, sets up Lagrange Function：
L=(X2-X1)+λ[F(X2)-F(X1)-Q(X1≤x≤X2)] (ⅵ)
Order：
∂ L ∂ X 1 = - 1 - λ ∂ F ∂ X 1 = 0 ∂ L ∂ X 2 = 1 + λ ∂ F ∂ X 2 = 0 ∂ L ∂ λ = F ( X 2 ) - F ( X 1 ) - Q ( X 1 ≤ x ≤ X 2 ) = 0 - - - ( v i i )
I.e.：
- 1 - λ f ( X 1 ) = 0 1 + λ f ( X 2 ) = 0 F ( X 2 ) - F ( X 1 ) - Q ( X 1 ≤ x ≤ X 2 ) - - - ( v i i i )
Obtain：
f ( X 1 ) = f ( X 2 ) = - 1 λ ∫ X 1 X 2 f ( x ) = Q ( X 1 ≤ x ≤ X 2 ) - - - ( i x )
Wushu (IV) substitutes into formula (IV), solves using optimal method, obtains X1、X2, and min (X2-X1) numerical value.
5. the method for claim 1, it is characterised in that using S type functions fitting modeling number described in the step 4 According to setting up wind power prediction model and be predicted, specially：
Forecast model is obtained using S type curve matchings, and the modeling data for screening, using the forecast model to wind-powered electricity generation work( Rate is predicted.
6. method as claimed in claim 5, it is characterised in that the utilization S type curve matchings, and the modeling number for screening According to forecast model is obtained, wind power is predicted using the forecast model, specially：
The modeling data for screening is substituted into into S type curvesFitting, obtains k, a and b；Wherein, will screen Modeling data in survey wind speed as input v, the power output of corresponding wind energy turbine set is used as output P；
K, a and b for obtaining are substituted into into S type curvesIn, forecast model is obtained, the air speed data that NWP is predicted is made For input, corresponding prediction wind power is obtained according to forecast model；In formula, v is air speed data, and P is corresponding wind-powered electricity generation work( Rate.
CN201610979574.7A 2016-11-08 2016-11-08 Method based on the wind power prediction of nonparametric probability Pending CN106548253A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610979574.7A CN106548253A (en) 2016-11-08 2016-11-08 Method based on the wind power prediction of nonparametric probability

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610979574.7A CN106548253A (en) 2016-11-08 2016-11-08 Method based on the wind power prediction of nonparametric probability

Publications (1)

Publication Number Publication Date
CN106548253A true CN106548253A (en) 2017-03-29

Family

ID=58394633

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610979574.7A Pending CN106548253A (en) 2016-11-08 2016-11-08 Method based on the wind power prediction of nonparametric probability

Country Status (1)

Country Link
CN (1) CN106548253A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657116A (en) * 2017-09-26 2018-02-02 福州大学 A kind of method of the affine modeling of wind power curve
CN107704953A (en) * 2017-09-20 2018-02-16 河海大学 The short-term wind-electricity power probability density Forecasting Methodology of EWT quantile estimate forests
CN107885959A (en) * 2017-12-06 2018-04-06 华北电力大学 A kind of wind-powered electricity generation modeling and performance estimating method based on confidence equivalent power curve belt
CN108416695A (en) * 2018-02-24 2018-08-17 合肥工业大学 Electric load probability density prediction technique based on deep learning and system, medium
CN108599147A (en) * 2018-04-13 2018-09-28 华北电力大学 Combination section prediction technique based on normal state exponential smoothing and Density Estimator
CN109190789A (en) * 2018-07-19 2019-01-11 清华大学 Long-term wind power power forecasting method, device, computer equipment and storage medium
CN110084433A (en) * 2019-05-05 2019-08-02 西南交通大学 Wind power prediction error piecewise fitting method based on gauss hybrid models
CN111460360A (en) * 2020-04-24 2020-07-28 国能日新科技股份有限公司 Power curve fitting data preprocessing method and device based on density distribution
CN113554203A (en) * 2020-04-24 2021-10-26 国能日新科技股份有限公司 Wind power prediction method and device based on high-dimensional gridding and LightGBM
CN113918376A (en) * 2021-12-14 2022-01-11 湖南天云软件技术有限公司 Fault detection method, device, equipment and computer readable storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103996079A (en) * 2014-05-29 2014-08-20 东南大学 Wind power weighting predication method based on conditional probability
CN105303266A (en) * 2015-11-23 2016-02-03 国网山东省电力公司经济技术研究院 Method for accurately estimating wind power prediction error interval
CN106021972A (en) * 2016-08-08 2016-10-12 北京国能日新系统控制技术有限公司 Method for correcting wind power data based on nonparametric kernel density estimation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103996079A (en) * 2014-05-29 2014-08-20 东南大学 Wind power weighting predication method based on conditional probability
CN105303266A (en) * 2015-11-23 2016-02-03 国网山东省电力公司经济技术研究院 Method for accurately estimating wind power prediction error interval
CN106021972A (en) * 2016-08-08 2016-10-12 北京国能日新系统控制技术有限公司 Method for correcting wind power data based on nonparametric kernel density estimation

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107704953A (en) * 2017-09-20 2018-02-16 河海大学 The short-term wind-electricity power probability density Forecasting Methodology of EWT quantile estimate forests
CN107657116B (en) * 2017-09-26 2020-05-08 福州大学 Method for affine modeling of power curve of wind power plant
CN107657116A (en) * 2017-09-26 2018-02-02 福州大学 A kind of method of the affine modeling of wind power curve
CN107885959A (en) * 2017-12-06 2018-04-06 华北电力大学 A kind of wind-powered electricity generation modeling and performance estimating method based on confidence equivalent power curve belt
CN107885959B (en) * 2017-12-06 2020-09-18 华北电力大学 Wind power modeling and performance evaluation method based on confidence equivalent power curve band
CN108416695A (en) * 2018-02-24 2018-08-17 合肥工业大学 Electric load probability density prediction technique based on deep learning and system, medium
CN108599147A (en) * 2018-04-13 2018-09-28 华北电力大学 Combination section prediction technique based on normal state exponential smoothing and Density Estimator
CN108599147B (en) * 2018-04-13 2021-01-05 华北电力大学 Combined interval prediction method based on normal exponential smoothing method and kernel density estimation
CN109190789A (en) * 2018-07-19 2019-01-11 清华大学 Long-term wind power power forecasting method, device, computer equipment and storage medium
CN110084433B (en) * 2019-05-05 2022-10-21 西南交通大学 Wind power prediction error piecewise fitting method based on Gaussian mixture model
CN110084433A (en) * 2019-05-05 2019-08-02 西南交通大学 Wind power prediction error piecewise fitting method based on gauss hybrid models
CN111460360A (en) * 2020-04-24 2020-07-28 国能日新科技股份有限公司 Power curve fitting data preprocessing method and device based on density distribution
CN113554203A (en) * 2020-04-24 2021-10-26 国能日新科技股份有限公司 Wind power prediction method and device based on high-dimensional gridding and LightGBM
CN111460360B (en) * 2020-04-24 2023-05-26 国能日新科技股份有限公司 Power curve fitting data preprocessing method and device based on density distribution
CN113554203B (en) * 2020-04-24 2023-12-26 国能日新科技股份有限公司 Wind power prediction method and device based on high-dimensional meshing and LightGBM
CN113918376A (en) * 2021-12-14 2022-01-11 湖南天云软件技术有限公司 Fault detection method, device, equipment and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN106548253A (en) Method based on the wind power prediction of nonparametric probability
Shi et al. Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features
CN103259285B (en) Method for optimizing short running of electric power system comprising large-scale wind power
CN104573879B (en) Photovoltaic plant based on optimal similar day collection goes out force prediction method
CN104882905B (en) A kind of new energy for considering transient security constraint receives capability assessment method
CN103258142B (en) Based on the short-term wind speed forecasting method of wind farm of synoptic model
CN107766990A (en) A kind of Forecasting Methodology of photovoltaic power station power generation power
CN106505631B (en) Intelligent wind power wind power prediction system
CN104933483A (en) Wind power forecasting method dividing based on weather process
CN106979126B (en) Wind power generating set high wind speed section effective wind speed estimation method based on SVR
CN104319807B (en) A kind of method obtaining windy electric field capacity credibility based on Copula function
CN102184453A (en) Wind power combination predicting method based on fuzzy neural network and support vector machine
CN106529719A (en) Method of predicting wind power of wind speed fusion based on particle swarm optimization algorithm
CN103218673A (en) Method for predicating short-period output power of photovoltaic power generation based on BP (Back Propagation) neural network
CN105069521A (en) Photovoltaic power plant output power prediction method based on weighted FCM clustering algorithm
CN103077300A (en) Forecasting method for generating capacity of distributed photovoltaic power supply on basis of type-2 fuzzy logic
CN103996079B (en) Wind power weighting predication method based on conditional probability
CN104392284B (en) A kind of big-and-middle small power station based on scenario analysis can dissolve in short term electricity maximum coordination optimization dispatching method
CN109636054A (en) Solar energy power generating amount prediction technique based on classification and error combination prediction
CN105243502A (en) Hydropower station scheduling risk assessment method and system based on runoff interval prediction
CN104182804A (en) Prediction output uncertainty considered day-ahead power generation method of small hydropower and large and medium-sized hydropower station coordination
CN106611243A (en) Residual correction method for wind speed prediction based on GARCH (Generalized ARCH) model
CN105896578A (en) Random production simulation method used for wind energy-solar photovoltaic energy-stored energy combined power generating system
Luo et al. Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine
CN105140967A (en) Estimation method with new energy power system peak regulation demands

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: 20170329