CN103117546A - Ultrashort-term slide prediction method for wind power - Google Patents
Ultrashort-term slide prediction method for wind power Download PDFInfo
- Publication number
- CN103117546A CN103117546A CN2013100646156A CN201310064615A CN103117546A CN 103117546 A CN103117546 A CN 103117546A CN 2013100646156 A CN2013100646156 A CN 2013100646156A CN 201310064615 A CN201310064615 A CN 201310064615A CN 103117546 A CN103117546 A CN 103117546A
- Authority
- CN
- China
- Prior art keywords
- wind power
- prediction
- asd
- decomposition
- constantly
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an ultrashort-term slide prediction method for wind power. An atomic sparse decomposition method with quite high non-stable signal tracking and prediction capacity is used as a front decomposition method of a neural network. A wind power time sequence is decomposed into an atomic component and a residual error component, the atomic component is automatically predicted, the residual error component is predicted by the neural network, atomic decomposition results are updated by adding the latest wind power real-time data, and further the wind power of a next moment is slidably predicted. Actual wind field data prove that the model can effectively avoid non-stability of the wind power, sparser decomposition effects are achieved, and statistical intervals of absolute average error and root mean square error computation values can be remarkably reduced. Therefore, the ultrashort-term slide prediction method has the advantages that non-stability of the wind power can be effectively avoided, the sparser decomposition effects are achieved, and the statistical intervals of the absolute average error and root mean square error computation values can be remarkably reduced.
Description
Technical field
The present invention relates to a kind of ultra-short term wind power forecasting method, especially relate to a kind of ultra-short term wind power slip Forecasting Methodology.
Background technology
The new forms of energy that wind energy is lower as cost in regenerative resource, technology is more ripe, reliability is higher, development in recent years are very fast and begin to play a significant role in energy supply.Along with the increase of wind energy turbine set scale, the fluctuation of wind speed and non-stationary become the restriction wind-powered electricity generation on a large scale, the Tough questions that efficiently is incorporated into the power networks.The wind power Predicting Technique is one of key technology that solves wind-powered electricity generation fluctuation, wind-electricity integration and dispatching of power netwoks, and this also accurately has higher requirement to the prediction of wind power.
For obtaining higher precision of prediction, lot of domestic and international research concentrates on the suitable forecast model of structure.According to the difference of input variable, existing forecast model can be divided into physical model, statistical model and physical statistics mixed model.Physical model uses information such as technical characterictic (hub height, power curve and thrust coefficient) as meteorology (numerical weather forecast etc.), topology (lofty mountains form etc.) and wind-powered electricity generation unit as the mode input amount, purpose is the best estimate that obtains local wind speed, and then utilizes MOS method (MOS) to reduce prediction residual; Statistical model uses explanatory variable and On-line Measuring Method, usually uses as recursive technique such as recurrent least square method and artificial neural network methods; Mixed model is as optimal models, first obtains the physical quantitys such as air-flow in wind-powered electricity generation unit zone, re-uses advanced statistical model and replenishes the information that physical model obtains, thereby can access more accurate predicted value.Because the physical message around wind energy turbine set in physical method etc. has a significant impact the accuracy that predicts the outcome, and statistical method can be revised prediction model parameters at any time according to characteristics and the position of wind energy turbine set self, can obtain higher accuracy.
domestic wind power is observed and predicted proposed up-to-date specification requirement with predicting, the middle clear of State Grid Corporation of China's issue company standard (Q/GDW392-2009) " wind energy turbine set access electric power network technique regulation detailed rules for the implementation (trying) " in 2009, wind power forecasting system should be able to report related data to scheduling institution by private network, should possess at least and forecast function and ultra-short term forecast function a few days ago, declare the next day of wind power prediction curve a few days ago to scheduling institution before 12 o'clock every days, predict the outcome according to ultra-short term, roll and adjust 2 hours later wind power prediction curves.The external research that mainly concentrates on forecast model, more Zao than domestic starting, technology is also relatively ripe.For obtaining the predicted value of 0.5~36 hour in advance, Denmark University of Science and Technology (DTU) proposes the wind power forecast model of the self adaptation recurrence least square estimation technique of a kind of note and forgetting factor; Carlos the third-largest in Madrid proposes the Sipreolico model, and this model is comprised of nine self adaptation nonparametric statistics models, uses recursive least squares or Kalman filtering algorithm cycle calculations; TrueWind company proposes a kind of EWIND model, and this model uses the local effect of disposable Parameters design research down wind NWP model output variable.
In existing wind power prediction modeling method, the method that the non-stationary property of considering original wind power sequence is seldom arranged, neural net is a kind of widely used wind power prediction modeling method, but because the convergence of its adaptive training is affected by the factors such as step-length, hidden layer neuron number, hidden layer output function and output layer output function, training time is longer, non-stationary property that often can not the Complete Mappings wind power.Therefore the present invention adopts a kind of have very strong non-stationary signal tracking, New Methods of Signal Processing---the atom Its Sparse Decomposition method of predictive ability, as the preposition decomposition means of neural net.Wind power in reality has very strong non-stationary, can regard former subcomponent with a plurality of different parameters and the stack of residual component as, and its non-stationary atomic parameter that causes constantly changes.Former subcomponent is carried out from prediction, and residual component is carried out neural network prediction, is finally predicted the outcome after stack.
Existing atom sparse resolution theory has proposed the wind power signal is carried out the concept of Its Sparse Decomposition, adopt the Atomic Decomposition algorithm to wind power decompositions of sliding, and replace primary signal with residual signals and predict the residual signals in the next moment as the input variable of neural net.Because the energy (with respect to primary signal) of residual signals is very little, can greatly avoid having so non-stationary neural network prediction is exerted an influence of the signal component (linear combination of atom) of Dominant energy.Therefore, than the neural net prediction method of routine, institute's extraction/prediction method has the ability of processing better non-stationary property.
The basic ideas of atom Its Sparse Decomposition are: what take is a kind of adaptive decomposition strategy of greediness, its former word bank is high redundancy (excessively complete), can therefrom select adaptively one group of optimum Match atom and sparse this signal that represents thereof to guarantee arbitrary signal.
(1) structure of wordbook
Atom represents by general kernel function usually, and in the signal process field, various kernel function can be used to represent atom, for example SIN function, Chirp function.The kernel function that the present invention adopts is Gaussian function, is shown below:
In formula: g (x) is gaussian kernel function, and c and σ are respectively center and scale parameter.Select different center and scale parameter, can construct a series of different atoms.The set of these atoms is called wordbook.
(2) Atomic Decomposition of doubledictionary collection
In the iteration decomposable process, the atom to be selected of each iteration can be divided into two classes: the old atom that before had been selected and the new atom that not yet was selected.Therefore, cross the wordbook that complete wordbook can be divided into two separation, one by old atomic building, and one by new atomic building.
In the incipient stage, all atoms all belong to new wordbook, and several times in iteration, most of selecteed optimum atom belongs to new wordbook in the front of decomposable process, and along with the continuation of iteration, old wordbook slowly increases.When old wordbook was enough large, selecteed optimum atom major part belonged to old wordbook.From the angle of sparse property, the choosing of new atom is unfavorable for the sparse property of decomposing, for the purpose that reaches Its Sparse Decomposition should be chosen atom as far as possible from old wordbook.Therefore, proposed a kind of optimum atom that is conducive to decompose sparse property and chosen flow process, concrete k step iteration is described below:
According to the decomposition result of k before the step, cross complete wordbook and be divided into old and new two wordbooks.Described their linear dependence due to the inner product (each is two product of signals sums constantly) of two signals: the absolute value of inner product is larger, and the correlation of two signals is stronger; Inner product is zero, two signal linear independences.So, calculate respectively the inner product of each atom in residue signal and two wordbooks, and select inner product maximum in each wordbook: c
oldAnd c
new, the atom in the old and new wordbook of its correspondence is used respectively Φ
oldAnd Φ
newExpression.
If | c
old| 〉=| c
new|, select Φ
oldAs the optimum atom in this time iteration, i.e. Φ
opt=Φ
old, c
oldAs the iteration coefficient of this optimum atom, i.e. c
opt=c
oldObviously, the decomposition of k before the step makes the existing decomposition coefficient of each atom in old wordbook.Therefore, need c
optAdd selected atom Φ to
oldDecomposition coefficient on add up.At last, upgrade the k residual signals in step, i.e. R
(k)=R
(k-1)-c
optΦ
opt
If | c
old|<| c
new|, the optimum atom in k step is selected in accordance with the following steps so:
1) calculate respectively residual error on old and new wordbook:
R
old=R
(k-1)-c
oldΦ
old,
R
new=R
(k-1)-c
newΦ
newFormula two
2) calculate relative error r:
In formula: || || the European norm of expression signal.
3) determine optimum atom by given threshold value T:
If r≤T selects Φ
oldAs the optimum atom in this time iteration, follow-up computational process and | c
old| 〉=| c
new| identical in situation;
If r〉T, select Φ
newAs the optimum atom in this time iteration, even new variables more is c
opt=c
new, Φ
opt=Φ
new, R
(k)=R
newThis atom is added in old wordbook, and delete from new wordbook, coefficient c
optDecomposition coefficient as this atom.
4) upgrade threshold values
By given threshold value T, select optimum atom in old and new wordbook.Be to guarantee convergence and stability, T is a function that successively decreases along with iterative steps, and the present invention adopts is Annealing function in simulated annealing:
In formula: 0.7≤α<1, T
0The expression initial temperature, and to set be the current iteration step number less than 1, k, and N is the annealing speed factor.Along with the increase of iteration, T is tending towards 0.Shown in related algorithm flow process accompanying drawing 1.
But this area not yet has at present uses the sparse theory of atom to the technical scheme appearance of wind power prediction.
Summary of the invention
The present invention solves the existing technical problem of prior art; Provide that a kind of can effectively to process wind power non-stationary, produced more sparse decomposition effect, can reduce significantly a kind of ultra-short term wind power slip Forecasting Methodology between the Statistical Area of absolute average error, root-mean-square error calculated value.
Above-mentioned technical problem of the present invention is mainly solved by following technical proposals:
A kind of ultra-short term wind power slip Forecasting Methodology is characterized in that: comprises the following steps,
Step 1 adopts the wind power primary signal is carried out the data preliminary treatment, determines in whole data area first that namely maximum and minimum value carry out unified normalization conversion process again, is zero to one interval value with the mode input output transform; Concrete normalization formula is as follows:
In formula: x is the component that inputs or outputs of model;
Be the component that inputs or outputs after the process normalized; x
maxAnd x
minBe respectively maximum and the minimum value of mode input or output variable;
Step 3, data sample and step 2 gained wind power end value after processing based on step 1 gained, take normalization absolute average error and normalization root-mean-square error as foundation, adopt statistics normal distribution approximating method commonly used to carry out quantitative assessment to prediction effect.
In above-mentioned ultra-short term wind power slip Forecasting Methodology, described step 2 comprises following substep, and the definition current time is t, and next is t+1 constantly;
Step 2.1, the atom Its Sparse Decomposition also carries out from prediction:
Step 2.11 is carried out n Atomic Decomposition to the wind power data, and the time period of self-defined Atomic Decomposition is t-m to t, and wherein, t, m are positive integer:
In formula: r (t) is residual component; a
j(t) be j former subcomponent, equal the product of atom and its decomposition coefficient;
Step 2.12, residual signals carries out next residual prediction constantly as the t+1 input variable constantly of step 2;
Step 2.13 is predicted t+1 atom component value constantly certainly according to the expression formula of former subcomponent;
Step 2.2, neural net is carried out residual prediction:
According to step 2.1 gained residual component value, carry out t+1 residual prediction constantly as the input variable of neural net residual prediction method;
Step 2.3, the prediction of sliding: neural net residual prediction result and atom Its Sparse Decomposition are namely obtained next wind power predicted value constantly from the stack that predicts the outcome; The time window that adopts time scale to determine carries out t+1 prediction constantly, after obtaining predicted value, the time window slip is pushed ahead a moment, be Atomic Decomposition time period be t-m+1 to t+1, repeated execution of steps 2.1 is to step 2.3 until finish execution in step 2.4 after reaching the prediction total time that the user sets;
Step 2.4, the correction that predicts the outcome namely adopts linear regression method to proofread and correct, and calibration model is as follows:
In formula: P
ASD, tBe the wind power prediction t predicted value constantly that adopts the inventive method to obtain;
Be the t moment predicted value after proofreading and correct; e
ASD, t=a+bP
ASD, t, a and b are parameter, adopt least square method to calculate, and are estimated by historical wind power and error sample data thereof, method is as follows:
In formula: N
cBe sample size; e
ASD, i=P
ASD, i-P
Meas, iBe historical wind power predicated error; P
Meas, iBe wind energy turbine set actual measurement wind power data;
With the predicted value that obtains in step 2.3 correction that predicts the outcome, obtain final wind power predicted value.
In above-mentioned ultra-short term wind power slip Forecasting Methodology, described step 3 comprises following substep,
Step 3.1 based on the final wind power predicted value of step 2 gained, adopts general in the world normalization absolute average error e
NMAEWith normalization root-mean-square error e
NRMSEBe foundation, be defined as follows:
In formula: x (i) is actual value;
Be predicted value; N is the forecast sample number; P
Cap.Rated capacity for blower fan;
Step 3.2 based on the final wind power predicted value of step 2 gained, adopts probabilistic method to analyze, and the normal distribution approximating method that namely statistics is commonly used carries out quantitative assessment to prediction effect.
Therefore, the present invention has following advantage: can effectively process wind power non-stationary, produce more sparse decomposition effect, can reduce significantly between the Statistical Area of absolute average error, root-mean-square error calculated value.
Description of drawings
Fig. 1 is the algorithm flow chart of atom sparse resolution theory of the present invention.
Fig. 2 is neural net residual prediction method network configuration of the present invention.
Fig. 3 is 3 not homoatomic comparisons of the present invention.
Embodiment
Below by embodiment, and by reference to the accompanying drawings, technical scheme of the present invention is described in further detail.
Embodiment:
The present invention relates to a kind of ultra-short term wind power slip Forecasting Methodology.Because the wind power sequence has stronger non-stationary property, neural net can not its characteristic of Complete Mappings, and the present invention adopts a kind ofly has that very strong non-stationary signal is followed the tracks of, the atom Its Sparse Decomposition method of predictive ability, as the preposition decomposition method of neural net.Be former subcomponent and residual component with the wind power Time Series, former subcomponent is carried out from prediction, residual component is carried out neural network prediction, then upgrades the result of Atomic Decomposition by appending up-to-date wind power real time data, and then the next wind power constantly of the prediction of sliding.Verify with actual wind field data, proved that this model can be processed wind power effectively non-stationary, produce more sparse decomposition effect, can reduce significantly between the Statistical Area of absolute average error, root-mean-square error calculated value.
Choose January 1 calendar year 2001 to 23 days June in 2008, abroad certain blower fan power output data as sample, describes technical solution of the present invention in detail with case study on implementation by reference to the accompanying drawings.
The ultra-short term wind power slip Forecasting Methodology that case study on implementation provides can adopt computer software programs to realize automatic operational process.The contained step of the flow process of case study on implementation is as follows:
Step 1 when carrying out model prediction,, is tackled different components and carry out respectively normalized in its span when differing greatly when each component dimension difference that inputs or outputs vector or size.Employing is carried out the data preliminary treatment to the wind power primary signal, first determines in whole data area that namely maximum and minimum value carry out unified normalization conversion process again, is zero to one interval value with the mode input output transform; Concrete normalization formula is as follows:
In formula: x is the component that inputs or outputs of model;
Be the component that inputs or outputs after the process normalized; x
maxAnd x
minBe respectively maximum and the minimum value of mode input or output variable.
And step 2 comprises following substep,
Step 2.1, the atom Its Sparse Decomposition also carries out from prediction:
1) the wind power data are carried out n Atomic Decomposition:
In formula: r (t) is residual component; a
j(t) be j former subcomponent, equal the product of atom and its decomposition coefficient.
2) residual signals carries out next residual prediction constantly as the input variable of step 2;
3) certainly predict next atom component value constantly according to the expression formula of former subcomponent;
In the atom Its Sparse Decomposition, atom represents by general kernel function usually, and in the signal process field, various kernel function can be used to represent atom, for example SIN function, Chirp function.The kernel function that the present invention adopts is Gaussian function, is shown below:
In formula: g (x) is gaussian kernel function, and c and σ are respectively center and scale parameter.Select different center and scale parameter, can construct a series of different atoms.The set of these atoms is called wordbook.Three different atoms have been enumerated in accompanying drawing 1.Wherein, g1 represents that the center is 0, and yardstick is 2 atom; G2 represents that the center is 2, and yardstick is 2 atom; G3 represents that the center is 0, and yardstick is 3 atom.
Step 2.2, neural net is carried out residual prediction: according to step 2.1 gained residual component value, carry out next residual prediction constantly as the input variable of neural net residual prediction method, shown in dependency structure accompanying drawing 2;
Step 2.3, the prediction of sliding: generally speaking, a definite wind power sequence through the preposition decomposition of forecast model after, must obtain that one group of parameter is determined, stably and have the former subcomponent of Dominant energy and non-stationary, randomness is strong but the little residual component of energy.Because former subcomponent is occupied leading role, this method is used as stationary sequence to the wind power data in essence still unilaterally and is processed.Therefore, the present invention proposes a kind of slip Forecasting Methodology, sets up the forecast model of 50 the bests by step 2.1 and step 2.2.Adopt up-to-date input variable and corresponding different models to the prediction of sliding of next 15min wind power.The input variable that each model is corresponding is different: model i (M
i) with 400 wind powers before the i point as input variable, to the i point prediction; M
i+1Utilize measured value that i orders and 399 wind powers before the i point as input variable, i+1 point slided predict ..., the like.
The time window that adopts time scale to determine carries out next prediction constantly, obtains after predicted value time window and slides and push ahead a moment, continues similarly prediction.The advantage of the method is, former subcomponent stably although the decomposition in time window obtains, but along with time window constantly to front slide, atom component parameters between time window and time window is constantly to change, when training sample is enough large, the time window number is a lot, can be considered the wind power data have been carried out the non-stationary processing; Simultaneously, along with time window ground slip, former subcomponent is regulated the parameter of self adaptively, to adapt to the wind power data of non-stationary, has greatly strengthened the generalization ability of forecast model.
Step 2.4, correction predicts the outcome:
Adopt linear regression method to proofread and correct, calibration model is as follows:
In formula: P
ASD, tBe the wind power prediction t predicted value constantly that adopts the inventive method to obtain;
Be the t moment predicted value after proofreading and correct; e
ASD, t=a+bP
ASD, t, a and b are parameter, can adopt least square method to calculate, and are estimated by historical wind power and error sample data thereof, method is as follows:
In formula: N
cBe sample size; e
ASD, i=P
ASD, i-P
Meas, iBe historical wind power predicated error; P
Meas, iBe wind energy turbine set actual measurement wind power data.
And step 3 comprises following substep,
Step 3.1 adopts general in the world normalization absolute average error e
NMAEWith normalization root-mean-square error e
NRMSEBe foundation, be defined as follows:
In formula: x (i) is actual value;
Be predicted value; N is the forecast sample number; P
Cap.Rated capacity for blower fan.
Step 3.2 adopts probabilistic method to analyze, and the normal distribution approximating method that namely statistics is commonly used carries out quantitative assessment to prediction effect.
Specific embodiment described in the present invention is only to the explanation for example of the present invention's spirit.Those skilled in the art can make various modifications or replenish or adopt similar mode to substitute described specific embodiment, but can't depart from spirit of the present invention or surmount the defined scope of appended claims.
Claims (3)
1. ultra-short term wind power slip Forecasting Methodology is characterized in that: comprises the following steps,
Step 1 adopts the wind power primary signal is carried out the data preliminary treatment, determines in whole data area first that namely maximum and minimum value carry out unified normalization conversion process again, is zero to one interval value with the mode input output transform; Concrete normalization formula is as follows:
In formula: x is the component that inputs or outputs of model;
Be the component that inputs or outputs after the process normalized; x
maxAnd x
minBe respectively maximum and the minimum value of mode input or output variable;
Step 2, data sample after processing based on step 1 gained, adopt atom Its Sparse Decomposition method, be former subcomponent and residual component with the wind power Time Series, former subcomponent is carried out from prediction, residual component is carried out neural network prediction, then upgrades the result of Atomic Decomposition by appending up-to-date wind power real time data, and then the next wind power constantly of the prediction of sliding; Adopt again linear regression method to proofread and correct, obtain next wind power constantly, repeat this step until reach the prediction total time that the user sets, namely obtain the final predicted value of wind power of the prediction total time of user's setting;
Step 3, data sample and step 2 gained wind power end value after processing based on step 1 gained, take normalization absolute average error and normalization root-mean-square error as foundation, adopt statistics normal distribution approximating method commonly used to carry out quantitative assessment to prediction effect.
2. ultra-short term wind power slip Forecasting Methodology according to claim 1, it is characterized in that: described step 2 comprises following substep, and the definition current time is t, and next is t+1 constantly;
Step 2.1, the atom Its Sparse Decomposition also carries out from prediction:
Step 2.11 is carried out n Atomic Decomposition to the wind power data, and the time period of self-defined Atomic Decomposition is t-m to t, and wherein, t, m are positive integer:
In formula: r (t) is residual component; a
j(t) be j former subcomponent, equal the product of atom and its decomposition coefficient;
Step 2.12, residual signals carries out next residual prediction constantly as the t+1 input variable constantly of step 2;
Step 2.13 is predicted t+1 atom component value constantly certainly according to the expression formula of former subcomponent;
Step 2.2, neural net is carried out residual prediction:
According to step 2.1 gained residual component value, carry out t+1 residual prediction constantly as the input variable of neural net residual prediction method;
Step 2.3, the prediction of sliding: neural net residual prediction result and atom Its Sparse Decomposition are namely obtained next wind power predicted value constantly from the stack that predicts the outcome; The time window that adopts time scale to determine carries out t+1 prediction constantly, after obtaining predicted value, the time window slip is pushed ahead a moment, be Atomic Decomposition time period be t-m+1 to t+1, repeated execution of steps 2.1 is to step 2.3 until reach execution in step 2.4 after the prediction total time that the user sets;
Step 2.4, the correction that predicts the outcome namely adopts linear regression method to proofread and correct, and calibration model is as follows:
In formula: P
ASD, tBe the wind power prediction t predicted value constantly that adopts the inventive method to obtain;
Be the t moment predicted value after proofreading and correct; e
ASD, t=a+bP
ASD, t, a and b are parameter, adopt least square method to calculate, and are estimated by historical wind power and error sample data thereof, method is as follows:
In formula: N
cBe sample size; e
ASD, i=P
ASD, i-P
Meas, iBe historical wind power predicated error; P
Meas, iBe wind energy turbine set actual measurement wind power data;
With the predicted value that obtains in step 2.3 correction that predicts the outcome, obtain final wind power predicted value.
3. ultra-short term wind power slip Forecasting Methodology according to claim 1, it is characterized in that: described step 3 comprises following substep,
Step 3.1 based on the final wind power predicted value of step 2 gained, adopts general in the world normalization absolute average error e
NMAEWith normalization root-mean-square error e
NRMSEBe foundation, be defined as follows:
In formula: x (i) is actual value;
Be predicted value; N is the forecast sample number; P
Cap.Rated capacity for blower fan;
Step 3.2 based on the final wind power predicted value of step 2 gained, adopts probabilistic method to analyze, and the normal distribution approximating method that namely statistics is commonly used carries out quantitative assessment to prediction effect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310064615.6A CN103117546B (en) | 2013-02-28 | 2013-02-28 | A kind of Ultrashort-term slide prediction method for wind power |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310064615.6A CN103117546B (en) | 2013-02-28 | 2013-02-28 | A kind of Ultrashort-term slide prediction method for wind power |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103117546A true CN103117546A (en) | 2013-05-22 |
CN103117546B CN103117546B (en) | 2016-03-16 |
Family
ID=48415852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310064615.6A Expired - Fee Related CN103117546B (en) | 2013-02-28 | 2013-02-28 | A kind of Ultrashort-term slide prediction method for wind power |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103117546B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103425867A (en) * | 2013-06-24 | 2013-12-04 | 武汉大学 | Short-term wind power combination prediction method |
CN103473322A (en) * | 2013-09-13 | 2013-12-25 | 国家电网公司 | Photovoltaic generation power ultra-short term prediction method based on time series model |
CN103489041A (en) * | 2013-09-17 | 2014-01-01 | 国家电网公司 | Short-term wind power forecast method |
CN103617464A (en) * | 2013-12-10 | 2014-03-05 | 钱胜利 | Device for ultra-short-period predication of wind power and predication method |
CN104376388A (en) * | 2014-12-08 | 2015-02-25 | 国家电网公司 | Ultra-short period wind power prediction method based on wind speed factor control model |
CN104571262A (en) * | 2015-01-16 | 2015-04-29 | 江南大学 | Method for predicating interval probability of short-term wind power |
CN106203723A (en) * | 2016-07-19 | 2016-12-07 | 河海大学 | Wind power short-term interval prediction method based on RT reconstruct EEMD RVM built-up pattern |
CN106682760A (en) * | 2016-09-13 | 2017-05-17 | 上海电机学院 | Wind power climbing prediction method |
CN106712112A (en) * | 2017-02-17 | 2017-05-24 | 云南电网有限责任公司 | Probability distribution-based wind farm cluster output power smoothing effect analysis method |
CN106709586A (en) * | 2015-07-15 | 2017-05-24 | 华北电力大学(保定) | Wind power plant short-term wind speed prediction method and system |
CN107798426A (en) * | 2017-10-16 | 2018-03-13 | 武汉大学 | Wind power interval Forecasting Methodology based on Atomic Decomposition and interactive fuzzy satisfying method |
CN109840613A (en) * | 2018-10-25 | 2019-06-04 | 浙江理工大学 | A kind of short-term wind speed forecasting method merging coding and decoding and linear regression |
CN110175639A (en) * | 2019-05-17 | 2019-08-27 | 华北电力大学 | A kind of short-term wind power forecast method based on Feature Selection |
CN110327043A (en) * | 2019-08-05 | 2019-10-15 | 哈尔滨工业大学 | A kind of event related potential waveform map method for solving based on sparse modeling |
CN110826791A (en) * | 2019-10-31 | 2020-02-21 | 东北电力大学 | Hybrid wind power prediction method based on long-time and short-time memory neural network |
CN112036658A (en) * | 2020-09-09 | 2020-12-04 | 华东交通大学 | Wind power real-time prediction method based on random forgetting long-term and short-term memory |
CN113193556A (en) * | 2021-05-12 | 2021-07-30 | 燕山大学 | Short-term wind power prediction method based on probability prediction model |
CN113723752A (en) * | 2021-07-26 | 2021-11-30 | 国网江苏省电力有限公司江阴市供电分公司 | Decomposition algorithm performance evaluation method in combined wind power prediction model |
CN114501010A (en) * | 2020-10-28 | 2022-05-13 | Oppo广东移动通信有限公司 | Image encoding method, image decoding method and related device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004289918A (en) * | 2003-03-20 | 2004-10-14 | Fujitsu Ltd | Power supply method |
CN101916998A (en) * | 2010-07-12 | 2010-12-15 | 东北电力科学研究院有限公司 | Support vector machine-based wind electric powder prediction device and method |
CN102184453A (en) * | 2011-05-16 | 2011-09-14 | 上海电气集团股份有限公司 | Wind power combination predicting method based on fuzzy neural network and support vector machine |
-
2013
- 2013-02-28 CN CN201310064615.6A patent/CN103117546B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004289918A (en) * | 2003-03-20 | 2004-10-14 | Fujitsu Ltd | Power supply method |
CN101916998A (en) * | 2010-07-12 | 2010-12-15 | 东北电力科学研究院有限公司 | Support vector machine-based wind electric powder prediction device and method |
CN102184453A (en) * | 2011-05-16 | 2011-09-14 | 上海电气集团股份有限公司 | Wind power combination predicting method based on fuzzy neural network and support vector machine |
Non-Patent Citations (1)
Title |
---|
贾清泉等: "原子稀疏分解算法在电力***扰动信号分析中的应用", 《电力***保护与控制》, vol. 38, no. 19, 1 October 2010 (2010-10-01), pages 17 - 21 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103425867A (en) * | 2013-06-24 | 2013-12-04 | 武汉大学 | Short-term wind power combination prediction method |
CN103473322A (en) * | 2013-09-13 | 2013-12-25 | 国家电网公司 | Photovoltaic generation power ultra-short term prediction method based on time series model |
CN103489041A (en) * | 2013-09-17 | 2014-01-01 | 国家电网公司 | Short-term wind power forecast method |
CN103617464B (en) * | 2013-12-10 | 2016-08-17 | 北方大贤风电科技(北京)有限公司 | The device predicted for the ultra-short term of wind power and Forecasting Methodology |
CN103617464A (en) * | 2013-12-10 | 2014-03-05 | 钱胜利 | Device for ultra-short-period predication of wind power and predication method |
CN104376388A (en) * | 2014-12-08 | 2015-02-25 | 国家电网公司 | Ultra-short period wind power prediction method based on wind speed factor control model |
CN104571262A (en) * | 2015-01-16 | 2015-04-29 | 江南大学 | Method for predicating interval probability of short-term wind power |
CN104571262B (en) * | 2015-01-16 | 2017-10-24 | 江南大学 | Short-term wind-electricity power interval probability Forecasting Methodology |
CN106709586A (en) * | 2015-07-15 | 2017-05-24 | 华北电力大学(保定) | Wind power plant short-term wind speed prediction method and system |
CN106203723A (en) * | 2016-07-19 | 2016-12-07 | 河海大学 | Wind power short-term interval prediction method based on RT reconstruct EEMD RVM built-up pattern |
CN106682760A (en) * | 2016-09-13 | 2017-05-17 | 上海电机学院 | Wind power climbing prediction method |
CN106712112B (en) * | 2017-02-17 | 2019-11-01 | 云南电网有限责任公司 | A kind of analysis method of the wind power plant cluster output smoothing effect based on probability distribution |
CN106712112A (en) * | 2017-02-17 | 2017-05-24 | 云南电网有限责任公司 | Probability distribution-based wind farm cluster output power smoothing effect analysis method |
CN107798426A (en) * | 2017-10-16 | 2018-03-13 | 武汉大学 | Wind power interval Forecasting Methodology based on Atomic Decomposition and interactive fuzzy satisfying method |
CN109840613B (en) * | 2018-10-25 | 2021-02-23 | 浙江理工大学 | Short-term wind speed prediction method integrating coding and decoding and linear regression |
CN109840613A (en) * | 2018-10-25 | 2019-06-04 | 浙江理工大学 | A kind of short-term wind speed forecasting method merging coding and decoding and linear regression |
CN110175639A (en) * | 2019-05-17 | 2019-08-27 | 华北电力大学 | A kind of short-term wind power forecast method based on Feature Selection |
CN110175639B (en) * | 2019-05-17 | 2021-06-11 | 华北电力大学 | Short-term wind power prediction method based on feature selection |
CN110327043B (en) * | 2019-08-05 | 2022-04-01 | 哈尔滨工业大学 | Event-related potential waveform map solving method based on sparse modeling |
CN110327043A (en) * | 2019-08-05 | 2019-10-15 | 哈尔滨工业大学 | A kind of event related potential waveform map method for solving based on sparse modeling |
CN110826791A (en) * | 2019-10-31 | 2020-02-21 | 东北电力大学 | Hybrid wind power prediction method based on long-time and short-time memory neural network |
CN112036658A (en) * | 2020-09-09 | 2020-12-04 | 华东交通大学 | Wind power real-time prediction method based on random forgetting long-term and short-term memory |
CN112036658B (en) * | 2020-09-09 | 2022-06-14 | 华东交通大学 | Wind power real-time prediction method based on forgetting long-term and short-term memory with difference |
CN114501010A (en) * | 2020-10-28 | 2022-05-13 | Oppo广东移动通信有限公司 | Image encoding method, image decoding method and related device |
CN114501010B (en) * | 2020-10-28 | 2023-06-06 | Oppo广东移动通信有限公司 | Image encoding method, image decoding method and related devices |
CN113193556A (en) * | 2021-05-12 | 2021-07-30 | 燕山大学 | Short-term wind power prediction method based on probability prediction model |
CN113723752A (en) * | 2021-07-26 | 2021-11-30 | 国网江苏省电力有限公司江阴市供电分公司 | Decomposition algorithm performance evaluation method in combined wind power prediction model |
Also Published As
Publication number | Publication date |
---|---|
CN103117546B (en) | 2016-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103117546A (en) | Ultrashort-term slide prediction method for wind power | |
Liu et al. | Random forest solar power forecast based on classification optimization | |
Hu et al. | A hybrid approach based on the Gaussian process with t-observation model for short-term wind speed forecasts | |
Ye et al. | An ensemble method for short-term wind power prediction considering error correction strategy | |
CN111027775A (en) | Step hydropower station generating capacity prediction method based on long-term and short-term memory network | |
CN110766200A (en) | Method for predicting generating power of wind turbine generator based on K-means mean clustering | |
CN104036328A (en) | Self-adaptive wind power prediction system and prediction method | |
Han et al. | Probabilistic flood forecasting using hydrologic uncertainty processor with ensemble weather forecasts | |
CN112994092B (en) | Independent wind-solar storage micro-grid system size planning method based on power prediction | |
Zhang et al. | Interval prediction of ultra-short-term photovoltaic power based on a hybrid model | |
CN103996087A (en) | Method and system for forecasting new energy power generation power | |
CN115186923A (en) | Photovoltaic power generation power prediction method and device and electronic equipment | |
Deo et al. | Cloud cover bias correction in numerical weather models for solar energy monitoring and forecasting systems with kernel ridge regression | |
CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
Yang et al. | Short‐term photovoltaic power dynamic weighted combination forecasting based on least squares method | |
CN111967660B (en) | Ultra-short-term photovoltaic prediction residual error correction method based on SVR | |
Zhou et al. | A Hybrid Method for Ultrashort‐Term Wind Power Prediction considering Meteorological Features and Seasonal Information | |
Alharbi et al. | Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks | |
CN116581755B (en) | Power prediction method, device, equipment and storage medium | |
CN111697560B (en) | Method and system for predicting load of power system based on LSTM | |
CN112734073A (en) | Photovoltaic power generation short-term prediction method based on long and short-term memory network | |
Fernandez-Jimenez et al. | Day-ahead probabilistic photovoltaic power forecasting models based on quantile regression neural networks | |
Flieller et al. | Introduction of ensemble based forecasts to the electricity dispatch simulator SimSEE | |
CN112036672B (en) | New energy power generation ultra-short term power prediction method and system based on iterative correction | |
Di et al. | Ultra-short term load forecasting based on elman neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160316 Termination date: 20170228 |