CN105939026B - Wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions - Google Patents
Wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions Download PDFInfo
- Publication number
- CN105939026B CN105939026B CN201610364697.XA CN201610364697A CN105939026B CN 105939026 B CN105939026 B CN 105939026B CN 201610364697 A CN201610364697 A CN 201610364697A CN 105939026 B CN105939026 B CN 105939026B
- Authority
- CN
- China
- Prior art keywords
- mrow
- wind power
- msubsup
- msub
- laplace
- 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.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims 1
- 230000002123 temporal effect Effects 0.000 abstract description 3
- 230000005611 electricity Effects 0.000 description 8
- 239000000203 mixture Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 229940050561 matrix product Drugs 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 230000005945 translocation Effects 0.000 description 1
Classifications
-
- H02J3/386—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
-
- 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]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a kind of wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions, the wind power data and default time scale surveyed first according to wind power plant calculate wind power undulate quantity sequence, structure mixing Laplace distributed models, it is solved to obtain the parameter of mixing Laplace distributed models according to wind power undulate quantity sequence, so as to obtain wind power probability Distribution Model.Using the obtained wind power probability Distribution Model of the present invention, energy accurate description wind power swing characteristic in particular improves the accuracy that the heavy-tailed property of wind power swing distribution describes；For in the description problem of the different horizontal wind power swings of spatial and temporal scales, which can also reach satisfied precision.
Description
Technical field
The invention belongs to wind power swing specificity analysis technical fields, more specifically, are related to a kind of based on mixing
The wind power undulate quantity probability Distribution Model method for building up of Laplace distributions.
Background technology
With the fast development of new energy power generation technology, the grid-connected demand of large-scale wind power further increases, and wind power
Fluctuation, it is intermittent not only influence power quality, Electric Power Network Planning and the difficulty of scheduling are added, also to the safety and stability of power grid
Operation causes potential risks.The control performance of minute grade scale influence of fluctuations electric system AGC；Hour grade scale influence of fluctuations
Electric system in a few days Real-Time Scheduling；Daily fluctuation influences the arrangement of electric system peak regulation method；Days influence of fluctuations electric system electricity
Power electric quantity balancing, it is accurate to analyze wind power wave characteristic, it is solves the problems, such as these basis and study wind-powered electricity generation on a large scale simultaneously
Net the important step of power generation.Effectively reliable model is established, can be applied not only to wind power prediction assessment, generation schedule is repaiied
Just, it is also applied for spinning reserve estimation.
The method of traditional description wind power wave characteristic, usually there are three types of different directions.One kind is using the time as dimension
Degree, establishes the random seriation model of wind power, i.e. Time series analysis method, such as in document：" Chen P, Pedersen T,
Bak-Jensen B, et al.ARIMA-based time series model of stochastic wind power
In generation.IEEE Trans.on Power Systems, Vol.25 (2), 2010, pp.667-676 ", wind-powered electricity generation is gone out
Power sequence regards non-stationary series as, establishes the autoregression based on wind power fluctuation and integrates moving average model.One kind is false
Determine wind power and do not meet certain prior probability distribution, and the probability nature of wind-powered electricity generation is built using Nonparametric Estimation
Mould, such as document " Yang Nan, Cui Jiazhan, Zhou Zheng, the wind power probability model nonparametric probability that is waited to optimize based on Fuzzy Ordered
In method electric power network techniques, Vol.40 (2), 2016, pp.335-340 ", using Gaussian function as wind power Multilayer networks
Kernel function, build the nonparametric estimation model of wind power.Also one kind is, right based on certain prior probability distribution
Pdf model carries out Parameterization estimate, and such as document, " woods satellite, Wen Jingyu, Ai little Meng wait wind power wave characteristics
In probability distribution research Proceedings of the CSEEs, Vol.32 (1), 2012, pp.38-46 ", using band translocation factor with stretching
The t distribution t location-scale distributions of coefficient, describe wind field power minute grade component fluctuation situation.
Since the randomness of wind power variation is strong, on different spatial and temporal scales, wind power fluctuation pattern difference is big,
The Time series analysis method of single spatial and temporal scales is difficult the wave characteristic of accurate description wind power.And utilize non-parametric estmation
Method describes the wave characteristic of wind power, generally requires the sample data of magnanimity, and has confirmed wind-powered electricity generation by available data
Specific regularity is presented in the probability distribution of power swing, therefore Nonparametric Estimation is not optimal case.Wind power
Very strong heavy-tailed property, for Parameterization estimate method, traditional distributed model, it is difficult to accurately is presented in the probability distribution of fluctuation
Reflect that wind power fluctuates the crest probability near average.
The content of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of wind-powered electricity generations based on mixing Laplace distributions
Power waves momentum probability Distribution Model method for building up provides what wind power under a kind of energy accurate description different time and space scales fluctuated
Probability Distribution Model is especially described in the heavy-tailed property of distribution, is being effectively improved fitting precision.
For achieving the above object, the present invention is based on the wind power undulate quantity probability distribution of mixing Laplace distributions
Method for establishing model comprises the following steps：
S1：The wind power data surveyed according to wind power plant and default time scale Δ t calculate wind power undulate quantity
Sequence P=[p1, p2, p3,···,pM]T, the dimension of wherein M expression wind power undulate quantity sequences；
S2：Structure mixing Laplace distributed models：
Wherein, α={ α1,α2,···,αNRepresent weight parameter collection, αiFor the weight of i-th Laplace distribution, andμ={ μ1,μ2,···,μNRepresent Mean Parameters collection, μiRepresent i-th of Laplace distribution
Middle wind power undulate quantity serial variance, δ={ δ1,δ2,···,δNRepresent variance parameter collection, δiRepresent i-th of Laplace
Wind power undulate quantity serial mean in distribution；N is distributed number, N ＞ 1 for Laplace；fi(p|μi,δi) represent i-th of single M
Tie up the probability density function of Laplace distributions；
S3：According to wind power undulate quantity sequence P=[p1, p2, p3,···,pM]TThe mixing obtained to step S2
Laplace distributed models are solved, its weight parameter collection α, Mean Parameters collection μ and variance parameter collection δ are obtained, so as to obtain wind
The probability Distribution Model of electrical power undulate quantity.
The present invention is based on the wind power undulate quantity probability Distribution Model method for building up of mixing Laplace distributions, first root
Wind power undulate quantity sequence, structure mixing are calculated according to the wind power data and default time scale of wind power plant actual measurement
Laplace distributed models solve to obtain the parameter of mixing Laplace distributed models according to wind power undulate quantity sequence, so as to
Obtain wind power probability Distribution Model.It, can accurate description wind using the obtained wind power probability Distribution Model of the present invention
Power swing characteristic in particular improves the accuracy of the heavy-tailed property description of wind power swing distribution；For the different time
In the description problem of scale level and different spaces scale level wind power swing, which can also reach satisfied precision,
For the assessment of electric system peak regulation nargin, wind power prediction assessment, generation schedule amendment, probabilistic load flow and balance of electric power and ener
The problems such as analysis, provides reliable base reference.
Description of the drawings
Fig. 1 is that the present invention is based on the wind power undulate quantity probability Distribution Model method for building up of mixing Laplace distributions
Flow chart；
Fig. 2 is the solution flow chart for mixing Laplace distributed models；
Fig. 3 is the present invention and the wind power undulate quantity probability distribution graph of contrast model in the present embodiment；
Fig. 4 is the different time scales present invention and the wind power undulate quantity probability distribution of contrast model in the present embodiment
Figure；
Fig. 5 is the different spaces scale present invention and the wind power undulate quantity probability distribution of contrast model in the present embodiment
Figure.
Specific embodiment
The specific embodiment of the present invention is described below in conjunction with the accompanying drawings, so as to those skilled in the art preferably
Understand the present invention.Requiring particular attention is that in the following description, when known function and the detailed description of design perhaps
When can desalinate the main contents of the present invention, these descriptions will be ignored herein.
Embodiment
Fig. 1 is that the present invention is based on the wind power undulate quantity probability Distribution Model method for building up of mixing Laplace distributions
Flow chart.As shown in Figure 1, the wind power undulate quantity probability Distribution Model foundation side the present invention is based on mixing Laplace distributions
Method comprises the following steps：
S101：Calculate wind power undulate quantity：
The wind power data surveyed according to wind power plant and default time scale Δ t calculate wind power undulate quantity sequence
Arrange P=[p1,p2,p3,···,pM]T, the dimension of wherein M expression wind power undulate quantity sequences.
In the prior art, typically using wind power data first-order difference Δ P=P (t+ Δ t)-P (t) be used as wind
Electrical power undulate quantity can also use wind power output change rate Pv=[P (t+ Δ t)-P (t)]/PNAs wind power undulate quantity,
(t+ Δs t), P (t) represent the wind power of moment t+ Δ t and moment t, P to middle P respectivelyNRepresent specified installed capacity.Due to wind speed
Size directly affects wind power output, although after first-order difference, the non-stationary of wind power fluctuation is weakened, if selection
Time scale Δ t time spans are big, and wind power is present with larger fluctuation in Δ t or the regularity of presentation is poor.Therefore, in order to
The natural fluctuation situation of energy accurate response wind power, weakens volatility series average and the coupling of variance and the Singular variance of sequence
Property first carries out wind power output natural logrithm conversion in the present embodiment, then does first-order difference, to describe wind power undulate quantity,
That is the wind power undulate quantity p of moment ttCalculation formula be：
pt=lnP (t+ Δ t)-lnP (t)
Obviously, when the length of the wind power data sequence of wind power plant actual measurement is L, M=L- Δs t.
S102：Structure mixing Laplace distributed models：
Laplace distributed models are widely used in Speech processing, are a two parameter probabilistic models.It is single
The mathematic(al) representation of Laplace distribution density functions can be denoted as：
Wherein, exp represents exponential function.
It is had shown that through research, single distribution can not accurately describe wind power fluctuation pattern.Therefore the present invention is single
On the basis of Laplace distributions, derive that finite element mixes Laplace distributed models.It is assumed that wind power undulate quantity sequence P=
[p1, p2, p3,···,pM]TThe distribution after the weighting of N number of Laplace distributions is obeyed, then its mathematic(al) representation is：
Wherein, f (P | α, μ, B) represents mixing Laplace distributed model distribution probability density functions；α={ α1,
α2,···,αNRepresent weight parameter collection, andαiFor the weight of i-th of Laplace distribution, i=1,2 ..., N；
μ={ μ1,μ2,···,μNRepresent Mean Parameters collection, B={ B1,B2,···,BNRepresent covariance matrix parameter set；N is
Laplace is distributed number, in general N ＞ 1, consider the complexity and model accuracy of model, the value range of N for 2≤
N≤5；fi(P|μi,Bi) it is the probability density function that single M ties up Laplace distributions, expression formula is：
μiFor fi(P|μi,Bi) the corresponding equal value sequence of wind power undulate quantity, μi=[μi,1,μi,2,···μi,M]T；Bi
For fi(P|μi,Bi) covariance matrix, after natural logrithm difference processing, vectorial P is regarded as mutually independent, therefore
It can obtain：
It is calculated to simplify, present invention assumes that M dimension wind power undulate quantity sequences have identical average and variance, it can
：
μi=[μi,1,μi,2,···μi,M]T=[μi,μi,···μi]T=μiE
It can be seen that μ={ μ at this time1,μ2,···,μNRepresent Mean Parameters collection, μiRepresent i-th of Laplace distribution apoplexy
Electrical power undulate quantity serial variance, δ={ δ1,δ2,···,δNRepresent variance parameter collection, δiRepresent i-th of Laplace distribution
Middle wind power undulate quantity serial mean.
Therefore mean vector and covariance matrix can be expressed as a constant and a unit matrix product, then single
The probability density function of one M dimension Laplace distributions is represented by：
Wherein, p represents wind power undulate quantity.
Mixing Laplace distributed models are represented by：
As it can be seen that Θ={ αi,μi,δiBe finite element mixing Laplace parameter set, i.e. Θ={ α1,α2,···,
αN；μ1,μ2,···,μN；δ1,δ2,···,δN}
S103：Solve mixing Laplace distributed models：
The mixing Laplace distributed models that step S102 is obtained are solved, obtain its weight parameter collection α, average ginseng
Manifold μ and variance parameter collection δ, so as to obtain wind power probability Distribution Model.
The EM algorithm for mixing Laplace distributions is used in the present embodiment to solve mixing Laplace distributions
Model.Fig. 2 is the solution flow chart for mixing Laplace distributed models.As shown in Fig. 2, the solution of mixing Laplace distributed models
Process comprises the following steps：
S201：Order solves number d=1.
S202：Initiation parameter：
Initialize weight parameter collectionMean Parameters collectionAnd variance
Parameter setUsually random assignment.Make iterations t=1.
S203：Calculate posterior probability：
To wind power undulate quantity sequence P=[p1,p2,p3,···pM]TIn each undulate quantity pj, j=1,2 ...,
M calculates it in the t times iteration by the posterior probability of k-th of Laplace distribution generation according to Bayes' theoremMeter
Calculating formula is：
Wherein, k=1,2 ..., N, πt-1(x) the mixing Laplace distributed models obtained for expression according to the t-1 times iteration
The probability that obtained event x occurs.Represent pjWithLaplace is tieed up for the single M of parameter
Probability in distribution.Obviously,Represent the weight parameter α obtained during the t-1 times iterationk, mean μkAnd side
Poor δk。
S204：Calculate the parameter of each Laplace distributions：
P is determined according to step S203jBy the posterior probability η of k-th of Laplace distribution generationk t(pj), demand solution
The parameter of k Laplace distribution.
Establish wind power swing vector P=[p1,p2,p3,···,pm]TMaximum likelihood function：
Wherein, Θ is the parameter set of mixing Laplace distributed models；
Introduce variable Φ (Θ), it is assumed that obtain parameter set after certain step iterationIt always needs to find out new Θ, makeSo as to：
Wherein：And for specific pj,For constant；Order
So as to which as Φ (Θ) ＞ 0 and constantly increase, H (Θ) will continue to increase, and Φ (Θ) need only be asked to obtain maximum
When Θ.
μ is asked for Φ (Θ)k、δkDerivative, can obtain：
Sgn () represents sign function in formula.
OrderIt can obtain：
By Lagrangian method, can obtain：
In summary, the posterior probability obtained according to step S202Calculate k-th of Laplace in the t times iteration
The parameter calculation formula of distribution is：
S205：Judge whether | Θt-Θt-1|≤ε, wherein Θt、Θt-1The t times and the t-1 times iteration gained are represented respectively
The parameter set arrived, i.e., the vector formed all parameters of weight parameter collection, Mean Parameters collection and variance parameter concentration together, ε tables
Show default error threshold.If it is not, entering step S206, S207 is otherwise entered step.
S206：Make t=t+1, return to step S203.
S207：It obtains this and solves mixing Laplace distributed model parameters：
Using the mixing Laplace distributed models parameter that the t times iteration obtains as the ginseng of mixing Laplace distributed models
Number.
S208：Judge whether that d ＜ D, D represent default solution total degree, D >=1, if so, entering step S209, otherwise
Enter step S210.
S209：D=d+1, return to step S202.
S210：Calculate final mixing Laplace distributed model parameters：
Since initial parameter value is randomly provided in solution procedure, in order to avoid iteration local convergence, this implementation
Example sets the different initial parameter value of D groups, carries out D solution, D times is solved pair of obtained mixing Laplace distributed models
Parameter is answered to be averaged, using average value as the parameter of final mixing Laplace distributed models.
I.e.Wherein αi(d)、μi(d) and δi(d)
It represents to solve obtained parameter the d times respectively.
In summary, the present invention mixes Laplace distributed models by building, and is asked by surveying wind power data
Solution obtains its parameter, so as to obtain wind power probability Distribution Model, can be drawn to obtain wind power probability according to the model
Distribution curve, so as to show the wind power wave characteristic of wind power plant.
It, to the validity of wind power wave characteristic, is adopted in order to illustrate wind power probability Distribution Model obtained by the present invention
It is compared with four wind power probability Distribution Models into row index, four contrast models are normal distribution model, logistic points
Cloth model, GMM (Gaussian Mixture Model, Gaussian mixtures) models and t Location-Scale models.Institute
Attached most importance to exponential tail ψ (X), mean absolute error MAE, residual standard deviation RSD, goodness of fit R using index2Four indexs.Institute's base
In wind power data be wind power plant cluster 10min grade of Sichuan Province measured power data, each wind field 47520 samples
Data.The quantity N=2 of Laplace in mixing Laplace distributed models is set in the present embodiment.Table 1 is that the present invention and four are right
Than the index contrast table of model.
| Model | MAE | RSD | R2 | ψ |
| Normal distribution model | 3.1793×10-3 | 9.3728×10-3 | 0.73963 | 1.7320 |
| Logistic distributed models | 1.8137×10-3 | 6.7692×10-3 | 0.86092 | 2.6544 |
| GMM model | 1.2561×10-3 | 5.2273×10-3 | 0.91387 | 3.7683 |
| T Location-Scale models | 1.0637×10-3 | 4.5494×10-3 | 0.93452 | 4.3506 |
| Mix Laplace distributed models | 8.4161×10-4 | 3.0110×10-3 | 0.97157 | 5.5092 |
Table 1
As shown in Table 1, it is minimum that the MAE and RSD of Laplace distributed models are mixed, R2Closer to 1, show to mix
Laplace distributed models more can accurately reflect wind power swing rule, as can be seen that mixing from the ψ indexs of each distribution
Laplace distributed models have apparent advantage in heavy-tailed property description.
Time scale Δ t=10min is set, draws the wind power undulate quantity probability point of the present invention and four contrast models
Butut.Fig. 3 is the present invention and the wind power undulate quantity probability distribution graph of contrast model in the present embodiment.As shown in figure 3,
In 10min grades of time scales, when wind power swing is larger, GMM distributed models and t Location-Scale models can be preferable
Ground fitting wind power fluctuation, but it is smaller or when more open steady in wind power fluctuation, and both models fail to
It describes well.And the mixing Laplace distributed models of the present invention can closer to the probability histogram of wind power undulate quantity,
Particularly in the case of wind power fluctuation less, mixing Laplace distributed models of the invention are than other contrast models more
Tool advantage.
The undulate quantity of wind power and the time scale of selection are maintained close ties with, and different time scales corresponds to the ripple of wind power
Dynamic characteristic differs greatly.In actual electric network operation, usual wind power is in the fluctuation characteristic of second (s) grade and point (min) grade
High frequency and secondary high frequency provide foundation, and when (h) grade and day (d) grade wave characteristic, dispatching, rationally dissolving for wind-powered electricity generation
Wind power provides reference, while is also the evaluation index of wind power prediction.Therefore, in order to verify the present invention mixing Laplace
The validity that distributed model embodies wind power wave characteristic under different time and space scales, to the actual measurement under different time and space scales
Power data structure mixing Laplace distributed models.
Fig. 4 is the different time scales present invention and the wind power undulate quantity probability distribution of contrast model in the present embodiment
Figure.As shown in figure 4, on the mixing Laplace distributed models of the present invention on different time scales accuracy than other model highers,
And the heavy-tailed property of distribution can be accurately reflected, therefore mix the wind-powered electricity generation work(that Laplace distributed models are suitable for different time scales
Rate fluctuation pattern describes.
Fig. 5 is the different spaces scale present invention and the wind power undulate quantity probability distribution of contrast model in the present embodiment
Figure.As shown in figure 5, fluctuating distribution for the wind power of different spaces scale, mixing Laplace distributed models also can accurately be intended
It closes.
In summary, the obtained wind power undulate quantity probability distribution mould based on mixing Laplace distributions of the present invention
Type can accurately realize the description to wind power fluctuation pattern under different time and space scales.
Although the illustrative specific embodiment of the present invention is described above, in order to the technology of the art
Personnel understand the present invention, it should be apparent that the invention is not restricted to the scope of specific embodiment, to the common skill of the art
For art personnel, if various change appended claim limit and definite the spirit and scope of the present invention in, these
Variation is it will be apparent that all utilize the innovation and creation of present inventive concept in the row of protection.
Claims (3)
1. a kind of wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions, which is characterized in that
Comprise the following steps：
S1：The wind power data surveyed according to wind power plant and default time scale Δ t calculate wind power undulate quantity sequence
P=[p1,p2,p3,…,pM]T, the dimension of wherein M expression wind power undulate quantity sequences；
S2：Structure mixing Laplace distributed models：
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>P</mi>
<mo>|</mo>
<mi>&alpha;</mi>
<mo>,</mo>
<mi>&mu;</mi>
<mo>,</mo>
<mi>&delta;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<msub>
<mi>f</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mo>|</mo>
<msub>
<mi>&mu;</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>&delta;</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein, α={ α1,α2,…,αNRepresent weight parameter collection, αiFor the weight of i-th Laplace distribution, andμ
={ μ1,μ2,…,μNRepresent Mean Parameters collection, μiRepresent wind power undulate quantity serial variance in i-th of Laplace distribution；δ
={ δ1,δ2,…,δNRepresent variance parameter collection, δiRepresent wind power undulate quantity serial mean in i-th of Laplace distribution；N
Number, N ＞ 1 are distributed for Laplace；fi(p|μi,δi) represent the probability density function that i-th of single Laplace is distributed；
S3：According to wind power undulate quantity sequence P=[p1,p2,p3,…,pM]TThe mixing Laplace that step S2 is obtained is distributed
Model is solved, and obtains its weight parameter collection α, Mean Parameters collection μ and variance parameter collection δ, so as to obtain wind power fluctuation
The probability Distribution Model of amount, the method for solving of mixing Laplace distributed models are：
S3.1：Order solves number d=1；
S3.2：Initialize weight parameter collectionMean Parameters collectionAnd variance
Parameter setMake iterations t=1；
S3.3：To wind power undulate quantity sequence P=[p1,p2,p3,…pM]TIn each undulate quantity pj, it is calculated at the t times
By the posterior probability of k-th of Laplace distribution generation in iterationCalculation formula is：
<mrow>
<msubsup>
<mi>&eta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mi>&alpha;</mi>
<mi>k</mi>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mi>f</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msubsup>
<mi>&mu;</mi>
<mi>k</mi>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>&delta;</mi>
<mi>k</mi>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mi>f</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msubsup>
<mi>&mu;</mi>
<mi>i</mi>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>&delta;</mi>
<mi>i</mi>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
Wherein, k=1,2 ..., N；
S3.4：The parameter of each Laplace distributions is calculated respectively：
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msubsup>
<mi>&mu;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msubsup>
<mi>&eta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
</mrow>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msubsup>
<mi>&eta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msubsup>
<mi>&alpha;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>M</mi>
</mfrac>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msubsup>
<mi>&eta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msubsup>
<mi>&delta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mo>=</mo>
<msqrt>
<mn>2</mn>
</msqrt>
<mfrac>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msubsup>
<mi>&eta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>|</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>&mu;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mo>|</mo>
</mrow>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msubsup>
<mi>&eta;</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
S3.5：If | Θt-Θt-1|≤ε, wherein Θt、Θt-1It represents respectively the t times and the obtained parameter of the t-1 times iteration
Collection vector, ε represent default error threshold, obtain the parameter of the mixing Laplace distributed models of this solution, otherwise make t=t
+ 1, return to step S3.3；
S3.6：If d ＜ D make d=d+1, return to step S3.2, otherwise by the mixing Laplace distributed models of D solution
Parameter is averaged, using average value as the parameter of final mixing Laplace distributed models.
2. wind power undulate quantity probability Distribution Model method for building up according to claim 1, which is characterized in that the step
The computational methods of wind power undulate quantity are in rapid S1：
pt=lnP (t+ Δ t)-lnP (t)
Wherein, ptRepresent the wind power undulate quantity of moment t, (t+ Δs t), P (t) represent the wind of moment t+ Δ t and moment t to P respectively
Electrical power.
3. wind power undulate quantity probability Distribution Model method for building up according to claim 1, which is characterized in that the step
The value range of Laplace distribution numbers N is 2≤N≤5 in rapid S2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610364697.XA CN105939026B (en) | 2016-05-27 | 2016-05-27 | Wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610364697.XA CN105939026B (en) | 2016-05-27 | 2016-05-27 | Wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105939026A CN105939026A (en) | 2016-09-14 |
| CN105939026B true CN105939026B (en) | 2018-05-29 |
Family
ID=57152362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610364697.XA Active CN105939026B (en) | 2016-05-27 | 2016-05-27 | Wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105939026B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840858A (en) * | 2017-11-29 | 2019-06-04 | 中国电力科学研究院有限公司 | A kind of wind power fluctuation clustering method and system based on Gaussian function |
| CN110210052A (en) * | 2019-04-23 | 2019-09-06 | 东北电力大学 | The method of photovoltaic power generation power output fluctuation component statistical specificity analysis |
| CN111030106B (en) * | 2019-12-26 | 2021-04-27 | 福州大学 | Wind power fluctuation quality assessment method based on waveform similarity theory |
| CN111027229B (en) * | 2019-12-26 | 2021-12-07 | 中南大学 | Wind power curve fitting method based on sparse heteroscedastic multi-spline regression |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2471311A1 (en) * | 2009-11-13 | 2012-07-04 | Mitsubishi Electric Corporation | Method and apparatus for determining rank of node in multi-hop wireless network |
| CN104158217A (en) * | 2014-08-22 | 2014-11-19 | 东北电力大学 | Output power fluctuation characteristic description method for clustered wind-solar combined power generation system |
-
2016
- 2016-05-27 CN CN201610364697.XA patent/CN105939026B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2471311A1 (en) * | 2009-11-13 | 2012-07-04 | Mitsubishi Electric Corporation | Method and apparatus for determining rank of node in multi-hop wireless network |
| CN104158217A (en) * | 2014-08-22 | 2014-11-19 | 东北电力大学 | Output power fluctuation characteristic description method for clustered wind-solar combined power generation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105939026A (en) | 2016-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Research and application of a combined model based on multi-objective optimization for multi-step ahead wind speed forecasting | |
| CN107425520B (en) | Active power distribution network three-phase interval state estimation method containing node injection power uncertainty | |
| CN104319807B (en) | A kind of method obtaining windy electric field capacity credibility based on Copula function | |
| CN106485362B (en) | A kind of power generation dispatching method for predicting error model and dimensionality reduction technology based on higher-dimension wind-powered electricity generation | |
| CN105939026B (en) | Wind power undulate quantity probability Distribution Model method for building up based on mixing Laplace distributions | |
| CN103117546B (en) | A kind of Ultrashort-term slide prediction method for wind power | |
| CN104463371B (en) | Markov chain modeling based on wind power variable quantity, Forecasting Methodology | |
| CN104573876A (en) | Wind power plant short-period wind speed prediction method based on time sequence long memory model | |
| CN103198235B (en) | Based on the wind power prediction value Pre-Evaluation method of the longitudinal moment probability distribution of wind power | |
| CN102102626A (en) | Method for forecasting short-term power in wind power station | |
| CN103971175B (en) | Short-term load prediction method of multistage substations | |
| CN106655190A (en) | Method for solving P-OPF (Probabilistic-Optimal Power Flow) of wind power stations | |
| CN105656031A (en) | Security risk assessment method of wind-power-included electric power system based on Gaussian mixture distribution characteristics | |
| CN106548256A (en) | A kind of method and system of wind energy turbine set space-time dynamic correlation modeling | |
| CN108336739A (en) | A kind of Probabilistic Load Flow on-line calculation method based on RBF neural | |
| CN107844849A (en) | A kind of new energy output short term prediction method returned based on experience wavelet transformation with improving Gaussian process | |
| CN108074015A (en) | A kind of ultrashort-term wind power prediction method and system | |
| CN105591407A (en) | Research method of renewable energy power plant active power prediction error correlation | |
| CN103235984A (en) | Computing method of longitudinal moment probability distribution of power output of wind power station | |
| CN106372440B (en) | A kind of adaptive robust state estimation method of the power distribution network of parallel computation and device | |
| CN106208136A (en) | Meter and benefit and the dispatching method a few days ago containing uncertain wind-powered electricity generation of risk | |
| CN105743093A (en) | Power distribution network power flow calculation method considering wind power and photovoltaic power output uncertainty | |
| CN107947201A (en) | Study of Power System Small Disturbance Stability method of discrimination caused by a kind of wind power swing | |
| Lin et al. | Scenarios analysis method based on wind and photovoltaic power output correlation | |
| Zhengxiang et al. | Application and comparison of several intelligent algorithms on Muskingum routing model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |