CN109102101A - Wind speed prediction method and system for wind power plant - Google Patents
Wind speed prediction method and system for wind power plant Download PDFInfo
- Publication number
- CN109102101A CN109102101A CN201710474284.1A CN201710474284A CN109102101A CN 109102101 A CN109102101 A CN 109102101A CN 201710474284 A CN201710474284 A CN 201710474284A CN 109102101 A CN109102101 A CN 109102101A
- Authority
- CN
- China
- Prior art keywords
- wind
- data
- wind speed
- wind power
- linear regression
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012417 linear regression Methods 0.000 claims abstract description 89
- 238000010219 correlation analysis Methods 0.000 claims abstract description 26
- 230000006870 function Effects 0.000 claims description 46
- 238000012360 testing method Methods 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 230000005611 electricity Effects 0.000 claims description 5
- 238000011478 gradient descent method Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 10
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 4
- 238000000611 regression analysis Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000001965 increasing effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H02J3/386—
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- 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
-
- 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
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for predicting wind speed of a wind power plant, wherein the method for predicting the wind speed of the wind power plant comprises the following steps: acquiring historical data of a wind power plant; performing dimensionality reduction on the acquired historical data; carrying out wind speed correlation analysis on the data subjected to the dimensionality reduction treatment; and establishing a linear regression model according to the wind speed correlation analysis result, and predicting the wind speed of the specific wind generating set in the wind power plant based on the established linear regression model. The method can accurately predict the wind speed of a certain specific wind generating set, so that the wind speed and the wind direction instrument can still keep high wind power efficiency after the fault of the wind speed and the wind direction instrument, can effectively reduce the downtime as an emergency system, improve the availability of the wind generating set, increase the unit output of the wind generating set, and has obvious economic benefit.
Description
Technical field
The present invention relates to technical field of wind power, in particular, being related to the prediction technique and system of a kind of wind farm wind velocity.
Background technique
Wind power technology has become the main contributions in the growing clean electric power market in the whole world now, accurately and reliably wind
Power power generation prediction is widely regarded as the main reason for increasing wind-power electricity generation permeability.Due to wind-driven generator high air transportion outdoors
Row, and anemoclinograph, outside unit hatch cover, running environment is extremely complex: not only will in face of vibration, dust, be exposed to the sun, freeze,
The various extreme conditions such as drench with rain, and marine, beach wind field installation unit also suffers salt air corrosion year in year out, wind speed and direction
The probability of instrument failure is relatively high.
Under normal conditions, the emergency control method when prior art fails for wind-driven generator wind speed and direction is: wind field
Interior all units control (SCADA) system and other geographical locations centered on oneself, through the data acquisition and monitoring of wind field
Three nearest units form small network；When unit operates normally, collected wind speed and direction signal is passed through SCADA by unit
System feedback shows various information real-time perfoming of the unit including wind speed and direction to central controller, central controller；
When unit anemoclinograph failure, to be reported first to central processing unit, central controller carries out heterochromatic display in significant position,
It is given a warning to monitoring personnel；Meanwhile system assumes that similar 3 wind power generating set wind speed and directions are similar, by similar wind
The data of the anemoclinograph of power generator group pass central controller back, and central controller confirms that 1-2 typhoon power is sent out after screening
After the information of motor group is effective, sequential selection of the SCADA system according to the first unit of priority, the second unit, third unit
Wind speed and direction data simultaneously send data to center unit, so that wind power generating set be allow to obtain after anemoclinograph failure
Obtain wind speed and direction data continuous service.
However, the prior art only assumes that the wind speed and direction of neighbouring wind generating set is identical, to wind-driven generator wind
Fast anemoscope failure carries out emergency flight control, does not consider wind speed variation or decaying after a certain distance, prediction deviation is very
Greatly, it is difficult to meet the safe operation of wind power generating set.
Summary of the invention
The present invention provides a kind of prediction technique of wind farm wind velocity and systems, by dropping to wind power plant historical data
Dimension processing carries out regression analysis modeling with correlation analysis and based on machine learning method, more can accurately predict some spy
Determine the wind speed of wind power generating set.
An aspect of of the present present invention provides the prediction technique of wind farm wind velocity, and the prediction technique is the following steps are included: obtain
Take the historical data of wind power plant；Dimension-reduction treatment is carried out to the historical data of acquisition；Wind speed phase is carried out to the data after dimension-reduction treatment
The analysis of closing property；Linear regression model (LRM) is established according to wind speed correlation analysis result, and based on the linear regression model (LRM) of foundation come pre-
Survey the wind speed of the specific wind power generating set in wind power plant.
Preferably, the historical data includes historical wind speed data and history floor data.
Preferably, the historical data of described pair of acquisition carry out the step of dimension-reduction treatment include: the historical data that will acquire into
Row centralization handles and seeks objective function according to centralization processing result；Objective function and constraint condition are collectively formed into maximum
Change Solve problems；Lagrangian is constructed, is solved to obtain maximum eigenvalue to Solve problems are maximized；According to maximum special
The corresponding maximal eigenvector of value indicative obtains the result of dimension-reduction treatment.
Preferably, the step of data to after dimension-reduction treatment carry out wind speed correlation analysis includes: to dimension-reduction treatment
Data afterwards are pre-processed；Pretreated data are divided into training sample and test tuple；Calculate separately test tuple with
Euler's distance of training tuple, takes apart from the smallest K trained tuple；By the most multiple mark of the appearance of described K trained tuple
Label are set as the classification of test tuple；Training sample is divided at least one region according to the classification of test tuple；Calculate error
Rate, and select K value corresponding to minimal error rate, wherein K value corresponding to the minimal error rate is expressed as in the wind power plant
The wind speed of K wind power generating set has linear dependence.
Preferably, described that linear regression model (LRM) is established according to wind speed correlation analysis result, and linear time based on foundation
The step of wind speed for returning model to predict the specific wind power generating set in wind power plant includes: respectively to the wind speed in different zones
Data carry out linear regression analysis；Linear regression model (LRM) is established according to linear regression analysis result, and passes through model and history number
According to building loss function；Loss function minimum value is solved, linear return is established according to parameter corresponding with loss function minimum value
Return model, and predicts based on the linear regression model (LRM) of foundation the wind speed of the specific wind power generating set in wind power plant.
Preferably, the loss function minimum value by least square method and or gradient descent method seek.
Preferably, further include determined according to the wind power curve of the specific wind power generating set prediction wind speed whether
There is deviation.
It preferably, further include that intensified learning is carried out to the linear regression model (LRM) of foundation.
Another aspect provides the forecasting system of wind farm wind velocity, the forecasting system includes: data processing
Program module, for obtaining the historical data of wind power plant and carrying out dimension-reduction treatment to the historical data of acquisition；Correlation analysis journey
Sequence module, for carrying out wind speed correlation analysis to the data after dimension-reduction treatment；Forecasting wind speed program module, for according to wind speed
Correlation analysis result establishes linear regression model (LRM), and the specific wind in wind power plant is predicted based on the linear regression model (LRM) of foundation
The wind speed of power generator group.
Preferably, historical data includes historical wind speed data and history floor data in the data processor module.
Preferably, the data processor module includes: objective function program module, and the historical data that will acquire carries out
Centralization handles and seeks objective function according to centralization processing result；Maximum eigenvalue program module, by objective function and about
Beam condition collectively forms maximization Solve problems, and constructs Lagrangian, is solved to obtain to Solve problems are maximized
Maximum eigenvalue；Dimension-reduction treatment program module obtains dimension-reduction treatment according to the corresponding maximal eigenvector of maximum eigenvalue
As a result.
Preferably, the correlation analysis program module includes: data preprocessing procedures module, to the number after dimension-reduction treatment
According to being pre-processed；Euler is divided into training sample and test tuple apart from program module, by pretreated data, calculates separately
Test Euler's distance of tuple and training tuple；Region division program module takes Euler apart from the smallest K trained tuple, and
To occur most multiple label in described K trained tuple to be set as testing the classification of tuple, will be instructed according to the classification of test tuple
Practice sample and is divided at least one region；Linearly related program module calculates error rate, and selects corresponding to minimal error rate
K value, wherein the wind speed that K value corresponding to the minimal error rate is expressed as K wind power generating set in the wind power plant has line
Property correlation.
Preferably, the forecasting wind speed program module includes: model-builder program module, respectively to the wind in different zones
Fast data carry out linear regression analysis, and establish linear regression model (LRM) according to linear regression analysis result；Forecasting wind speed program mould
Block constructs loss function according to linear regression model (LRM) and historical data, solves corresponding parameter when loss function minimum value, and
The wind speed of the specific wind power generating set in wind power plant is predicted based on the parameter of solution and the linear regression model (LRM) of foundation.
Preferably, the loss function minimum value by least square method and or gradient descent method seek.
Preferably, further includes: test bias program module, according to the wind power curve of the specific wind power generating set come
Whether the wind speed of test prediction there is deviation.
Preferably, further includes: intensified learning program module carries out intensified learning to the linear regression model (LRM) of foundation.
Another aspect provides a kind of computer readable storage mediums, are stored with computer program, the meter
When calculation machine program is run by processor, processor executes the prediction technique of wind farm wind velocity as described above.
Another aspect provides a kind of computer equipments, the storage including processor and storage computer program
Device, when the computer program is run by processor, processor executes the prediction technique of wind farm wind velocity as described above.
In the present invention, by the processing and analysis to historical data, using correlation analysis and based on machine learning
Regression analysis modeling, accurately predicts the wind speed of some specific wind power generating set, makes it in anemoclinograph event
Higher generating efficiency is still maintained after barrier, downtime is effectively reduced, improves wind power generating set availability.
Detailed description of the invention
Pass through the description carried out below in conjunction with attached drawing, above and other aspects, the feature of exemplary embodiment of the present invention
It will be more readily apparent from advantage, in the accompanying drawings:
Fig. 1 shows the flow chart of the prediction technique of the wind farm wind velocity of embodiment according to the present invention；
Fig. 2 shows the knots that utilization closest node (KNN) algorithm of embodiment according to the present invention carries out correlation analysis
Fruit；
Fig. 3 shows the forecasting wind speed result of specific wind power generating set in the wind power plant of embodiment according to the present invention；
Fig. 4 shows the forecasting system block diagram of the wind farm wind velocity of embodiment according to the present invention；
Fig. 5 shows the block diagram of the data processor module of embodiment according to the present invention；
Fig. 6 shows the block diagram of the correlation analysis program module of embodiment according to the present invention；
Fig. 7 shows the block diagram of the forecasting wind speed program module of embodiment according to the present invention.
In the accompanying drawings, identical label will be understood to refer to identical element, feature and structure.
Specific embodiment
The present invention of the description to help comprehensive understanding to be defined by the claims and their equivalents referring to the drawings is provided
Exemplary embodiment.Description referring to the drawings includes various specific details to help to understand, but the specific detail
It only is seen as illustrative.Therefore, it will be appreciated by those of ordinary skill in the art that not departing from scope and spirit of the present invention
In the case where, the embodiments described herein can be made various changes and modifications.In addition, for clarity and briefly, public affairs can be omitted
Know the description of function and structure.
Fig. 1 is the flow chart for showing the prediction technique of wind farm wind velocity of embodiment according to the present invention.
As shown in Figure 1, firstly, obtaining the historical data of wind power plant in step S100.Specifically, going through for wind power plant is obtained
History data may include historical wind speed data and history floor data.According to an embodiment of the invention, for example, can be from SCADA system
Read the historical wind speed data and history floor data of wind power plant.Wherein, history floor data includes wind generating set yaw
Angle, variable pitch angle, temperature etc. influence the data of wind power plant wind power generating set operation, will be inconsistent in history data set, wrong
Data entry accidentally removes, and data are normalized.
Next, carrying out dimension-reduction treatment to the historical data of acquisition in step S200.Specifically, to historical wind speed data
Dimension-reduction treatment is carried out with history floor data.According to an embodiment of the invention, by carrying out dimension-reduction treatment to historical data, it will be extra large
The wind power generating set history data of amount is simplified in the case where loss data characteristics on a small quantity, to facilitate rapider standard
True establishes forecasting wind speed model.According to an embodiment of the invention, principal component analysis (PCA) algorithm can be used to carry out Data Dimensionality Reduction
Processing.
In wind power generating set forecasting wind speed, data are denoted as vector, exist for some specific wind power generating set
The wind speed at a certain moment and other relevant informations form a set within one day, wherein the time be a record indicate rather than
Metric.According to an embodiment of the invention, it should be understood that wind speed is related with which metric, and due to the work of wind power generating set
Condition is numerous, so carrying out dimension-reduction treatment to data.Dimension-reduction treatment will cause the loss of data, but real data itself has correlation
Property, the loss of information can be reduced as far as possible while dimensionality reduction.For example, given data acquisition system isIt is right
It carries out centralization processing, centralization result are as follows:
In above formula,The fan operation data comprising wind speed, wind direction etc. are represented,The average value of each column data is represented,It representsWith average valueDifference.Data after centralization be distributed on the first direction main shaft u1 dissipate most open, also
It is to say the sum of the absolute value of projection on the direction u1 maximum, x and u1 are exactly done inner product by the method for calculating projection, and u1 is unit
Vector, acquiring objective function isObjective function is converted to obtainAnd with constraint item
PartIt constitutes and maximizes Solve problems.
Construct LagrangianTo u1Derivation:
XXTu1=λ u1
Above formula derivation result is brought into objective function to obtain:
Know that the corresponding feature vector of eigenvalue λ is u1, maximum eigenvalue is sought, and find out relatively according to maximum eigenvalue
The maximal eigenvector answered.Wherein, feature vector u1Indicate the fan operations data such as wind speed, wind direction.Implementation according to the present invention
Example, the historical data for selecting the time to obtain on January 1st, 2016 run matrix for the matrix of 11572*270, from the feature sought
Preceding 5 maximum eigenvalue are chosen in value, and corresponding maximal eigenvector, the maximum feature are found out according to maximum eigenvalue
Vector constitutes the eigenmatrix of a 270*5, finally, sample data is multiplied to obtain the matrix of 11572*5 with eigenmatrix, i.e.,
The air speed data and floor data in historical data with correlation are obtained by PCA dimension-reduction treatment, wherein obtain after dimensionality reduction
History floor data it is few, here by the few history operating condition of data ignore in next step calculate in.Wind-driven generator
Group historical data lose its data characteristics it is few in the case where reached dimensionality reduction simplify result.
In step S300, wind speed correlation analysis is carried out to the data after dimension-reduction treatment.Specifically, it will be passed through in step S200
Air speed data after crossing dimension-reduction treatment is pre-processed, and carries out wind speed correlation analysis to pretreated data.According to this
Inventive embodiments carry out correlation analysis with closest node (KNN) algorithm.
Since in general wind field area is larger, and the wind speed of not all wind power generating set all has correlation, may
Only a few have correlation due in landform on wind speed.If by establishing physical model calculating air fluid
Mechanics difficulty is larger and different wind fields can only be calculated one by one, so, in the present invention, selection uses KNN algorithm, passes through structure
It builds mathematical model and infers that the wind speed of which platform wind power generating set is relatively close together.
Specifically, training sample and test tuple will be divided by the data after PCA algorithm dimensionality reduction, then is based on Euclid
Theorem calculates separately test tuple at a distance from training tuple, wherein Euclidean distance formula is as follows:
In above formula, xjIndicate test tuple, yjIndicate training tuple.Then, taken in the distance being calculated according to above formula away from
From the smallest K trained tuple, judges the label that frequency of occurrence is most in K trained tuple, is set to the class of test tuple
Not, training sample is divided at least one region further according to the classification of test tuple.Error rate is finally calculated, minimum miss is selected
K value corresponding to rate, K value corresponding to minimal error rate indicate that the wind speed of K wind power generating set in the wind power plant has
Linear dependence.According to an embodiment of the invention, taking 16 wind power generating sets is training sample, it is numbered respectively,
And correlation analysis is carried out by closest node (KNN) algorithm.Implement according to the present invention below with reference to Fig. 2 to be described in detail
Utilization closest node (KNN) algorithm of example carries out the result of correlation analysis.
Fig. 2 is utilization closest node (KNN) the algorithm progress correlation analysis for showing embodiment according to the present invention
As a result.
As shown in Figure 2, the training sample is divided into after carrying out correlation analysis by closest node (KNN) algorithm
Four regions, wherein the wind power generating set that the number with correlation is 01,02,03,04,05,08 is classified as same area
Domain, the wind power generating set that the number with correlation is 06 and 07 are classified as the same area, number 10 with correlation, 11,
12,13 wind power generating set is classified as the same area, and the wind power generating set of the number 09,14,15,16 with correlation is classified as
The same area.Fig. 1 is returned, in step S400, linear regression model (LRM) is established according to wind speed correlation analysis result, and based on foundation
Linear regression model (LRM) predict the wind speed of the specific wind power generating set in wind power plant.Specifically, to step S300 wind speed phase
The different zones that the analysis of closing property divides carry out linear regression analysis respectively and establish linear regression model (LRM), finally, being returned based on linear
Model is returned to carry out the prediction of wind farm wind velocity.According to an embodiment of the invention, respectively to four obtained in above-mentioned Fig. 2 not same districts
Air speed data in domain carries out linear regression analysis, for example, the wind power generating set group for being 01,02,03,04,05,08 to number
At region air speed data carry out linear regression analysis.In the historical data of acquisition, each component regards a feature as
Data, as soon as at least corresponding unknown parameter of each feature, constructs a linear regression model (LRM) letter according to Regression Analysis Result
Number, vector representation are as follows:
hθ(x)=θTX
Wherein, θ is unknown parameter, and X is the historical wind speed data and history floor data after dimensionality reduction, hθ(x) wind-powered electricity generation is indicated
The prediction of wind speed of field.H function is assessed further according to linear regression model (LRM) function and historical data building loss function, is lost
Function representation is as follows:
Wherein, y(i)Historical wind speed data actual value after indicating dimensionality reduction, hθ(x(i)) indicate through the prediction of wind speed of model
Value, by adjusting θ value so that loss function J (θ) is minimized, here by least square method and or gradient decline carry out
Loss function minimum value is sought.For example, when least square method being selected to carry out solving loss function minimum value, by going through after dimensionality reduction
History air speed data and history floor data are expressed as X matrix, and the prediction of wind speed result of wind power plant is expressed as y vector, and X is sequency spectrum
Matrix obtains parameterFinally, corresponding optimal parameter θ when according to loss function minimum value
And parameter θ tax is carried out to historical wind speed data and history floor data respectively according to the factor for influencing size on wind farm wind velocity
Value, and wind farm wind velocity is predicted by linear regression model (LRM) function.
In step S500, determine whether the wind speed of prediction goes out according to the wind power curve of the specific wind power generating set
Existing deviation.Specifically, according to an embodiment of the invention, for example, certain wind power generating set breaks down in wind power plant, this hair
Bright prediction technique sends out the wind-force that anemoclinograph fails according to wind power plant wind power generating set correlation models and Wind speed model
The wind speed of motor group is resolved, while central control system monitors the wind power curve of this wind power generating set, if wind
Power curve occurs abnormal, then it is assumed that relatively large deviation occurs in wind speed resolving, and wind power generating set should be immediately controlled and shut down to prevent hair
Raw safety accident, if wind power curve does not occur exception, then it is assumed that it is accurate that central control system assert that forecasting wind speed system resolves,
Then remain operational wind power generating set in the case where anemoclinograph failure.
Fig. 3 is the forecasting wind speed result of specific wind power generating set in the wind power plant for show embodiment according to the present invention.
As shown in figure 3, the wind-power electricity generation in the wind power generating set affiliated area for being 01,02,03,04,05,08 to number
The air speed data of unit carries out linear regression analysis, wherein abscissa is time t, and ordinate indicates speed v/s, it is assumed that No. 01
The failure of wind power generating set anemoclinograph, obtains No. 01 wind with the prediction technique model of wind farm wind velocity proposed by the present invention
The prediction of wind speed of power generator group, from the figure 3, it may be seen that error is within 10% between gained prediction of wind speed and actual wind speed, error
It is relatively small.
According to an embodiment of the invention, the invention also includes carry out intensified learning to the linear regression model (LRM) of foundation.Specifically
It is constantly collected, accumulation air speed data, according to the present invention in the case where wind power generating set anemoclinograph operates normally on ground
Prediction technique wind speed persistence forecasting and compare predicted value and actual value, with being continuously increased for data volume,
The loss function value of matched curve will be reduced constantly, and making the prediction technique, constantly enhancing algorithm learns with as far as possible in the process of running
Closing to reality value.
Fig. 4 is the forecasting system block diagram for showing the wind farm wind velocity of embodiment according to the present invention.
As shown in figure 4, the forecasting system 600 of wind farm wind velocity may include data processor module 601, correlation analysis
Program module 602 and forecasting wind speed program module 603.According to an embodiment of the invention, the forecasting system 600 of wind farm wind velocity can
It is realized by various computing devices (for example, computer, server, work station etc.).Concretely, data processor module
601 for obtaining the historical data of wind power plant and carrying out dimension-reduction treatment to the historical data of acquisition.Correlation analysis program module
602 for carrying out wind speed correlation analysis to the data after dimension-reduction treatment.Forecasting wind speed program module 603 is used for according to wind speed phase
Closing property analysis result is established linear regression model (LRM) and is predicted the specific wind-force in wind power plant based on the linear regression model (LRM) of foundation
The wind speed of generating set.
Data processor module 601 according to an embodiment of the present invention is described in detail below with reference to Fig. 5.
Fig. 5 shows the block diagram of the data processor module of embodiment according to the present invention.
As shown in figure 5, data processor module 601 includes objective function program module 101, maximum eigenvalue program mould
Block 102 and dimension-reduction treatment program module 103.Wherein, the historical data that objective function program module 101 will acquire carries out centralization
It handles and objective function is sought according to centralization processing result, maximum eigenvalue program module 102 is by objective function program module
101 objective functions sought and constraint condition collectively form maximization Solve problems, and construct Lagrangian, to maximization
Solve problems are solved to obtain maximum eigenvalue；Dimension-reduction treatment program module 103 is according to the corresponding maximum of maximum eigenvalue
Feature vector obtains the result of dimension-reduction treatment.
Correlation analysis program module 602 according to an embodiment of the present invention is described in detail below with reference to Fig. 6.
Fig. 6 shows the block diagram of the correlation analysis program module of embodiment according to the present invention.
As shown in fig. 6, correlation analysis program module 602 includes data preprocessing procedures module 104, Euler apart from program
Module 105, region division program module 16 and linearly related program module 107.Wherein, data preprocessing procedures module 104 is right
Data after dimension-reduction treatment carry out data prediction, and pretreated data are divided into trained sample apart from program module 105 by Euler
Originally and tuple is tested, and calculates separately test tuple and trains Euler's distance of tuple, region division program module 106 is according to Europe
The Euler's distance being calculated apart from program module 105 is drawn, is taken apart from the smallest K trained tuple, and described K training is first
Occur the classification that most multiple label is set as test tuple in group, is divided into training sample at least according to the classification of test tuple
One region, linearly related program module 107 calculates error rate, and selects K value corresponding to minimal error rate, wherein described
The wind speed that K value corresponding to minimal error rate is expressed as K wind power generating set in the wind power plant has linear dependence.
Forecasting wind speed program module 603 according to an embodiment of the present invention is described in detail below with reference to Fig. 7.
Fig. 7 shows the block diagram of the forecasting wind speed program module of embodiment according to the present invention.
As shown in fig. 7, forecasting wind speed program module 603 includes model-builder program module 108 and forecasting wind speed program mould
Block 109.Wherein, model-builder program module 108 carries out linear regression analysis, and root to the air speed data in different zones respectively
Linear regression model (LRM) is established according to linear regression analysis result, forecasting wind speed program module 109 is according to model-builder program module 108
The linear regression model (LRM) and historical data of foundation construct loss function, solve corresponding parameter when loss function minimum value, and
The wind speed of the specific wind power generating set in wind power plant is predicted based on the parameter of solution and the linear regression model (LRM) of foundation.Its
In, the loss function minimum value by least square method and or gradient descent method seek.
According to an embodiment of the invention, the forecasting system 600 of wind farm wind velocity further include: test bias program module 604,
For determining whether the wind speed of prediction deviation occurs according to the wind power curve of the specific wind power generating set.
According to an embodiment of the invention, the forecasting system 600 of wind farm wind velocity further include: intensified learning program module 605,
Intensified learning is constantly carried out for the linear regression model (LRM) to foundation, making the forecasting system, constantly enhancing is calculated in the process of running
Calligraphy learning is with closing to reality value as far as possible.
The prediction technique and system of a kind of wind farm wind velocity of embodiment according to the present invention, the prediction technique is by going through
The analysis of history data and wind farm wind velocity modeling can be compared with using correlation analysis and the modeling of the regression analysis based on machine learning
For the wind speed for accurately predicting some specific wind power generating set, make its still can be kept after anemoclinograph failure compared with
High wind-powered electricity generation efficiency can effectively reduce downtime as emergency system, improve wind power generating set availability, increase
Wind power generating set unit output, economic benefit are obvious.
A kind of prediction technique of wind farm wind velocity of embodiment according to the present invention can be realized as computer-readable record Jie
Computer-readable code in matter, or can be sent by transmission medium.Computer readable recording medium is can to store hereafter
The arbitrary data storage device for the data that can be read by computer system.Computer-readable recording medium storage has computer journey
Sequence, when which is run by processor, processor executes the prediction technique of wind farm wind velocity shown in FIG. 1.Computer
The example of readable medium recording program performing include read-only memory (ROM), random access memory (RAM), CD (CD)-ROM, number it is more
Functional disc (DVD), tape, floppy disk, optical data storage device, but not limited to this.Transmission medium may include by network or each
The carrier wave that the communication channel of seed type is sent.Computer readable recording medium also can be distributed in the computer system of connection network,
To which computer-readable code is stored and executed in a distributed fashion.
Another embodiment of the present invention provides a kind of computer equipment, including processor and stores depositing for computer program
Reservoir, when the computer program is run by processor, processor executes the prediction technique of wind farm wind velocity shown in FIG. 1.
Although the present invention, art technology has been shown and described referring to certain exemplary embodiments of the invention
Personnel will be understood that, can be into the case where not departing from the spirit and scope of the present invention being defined by the claims and their equivalents
Various changes on row various forms and details.
Claims (18)
1. a kind of prediction technique of wind farm wind velocity, which is characterized in that the prediction technique the following steps are included:
Obtain the historical data of wind power plant；
Dimension-reduction treatment is carried out to the historical data of acquisition；
Wind speed correlation analysis is carried out to the data after dimension-reduction treatment；
Linear regression model (LRM) is established according to wind speed correlation analysis result, and wind-powered electricity generation is predicted based on the linear regression model (LRM) of foundation
The wind speed of specific wind power generating set in.
2. prediction technique as described in claim 1, which is characterized in that the historical data includes historical wind speed data and history
Floor data.
3. prediction technique as described in claim 1, which is characterized in that the historical data of described pair of acquisition carries out dimension-reduction treatment
Step includes:
The historical data that will acquire carries out centralization processing and seeks objective function according to centralization processing result；
Objective function and constraint condition are collectively formed into maximization Solve problems, and construct Lagrangian, maximization is asked
Solution problem is solved to obtain maximum eigenvalue；
The result of dimension-reduction treatment is obtained according to the corresponding maximal eigenvector of maximum eigenvalue.
4. prediction technique as described in claim 1, which is characterized in that it is related that the data to after dimension-reduction treatment carry out wind speed
Property analysis the step of include:
Data after dimension-reduction treatment are pre-processed；
By pretreated data be divided into training sample and test tuple, calculate separately test tuple and training tuple Euler away from
From；
It takes Euler apart from the smallest K trained tuple, and is set as testing by there is most multiple label in described K trained tuple
Training sample is divided at least one region according to the classification of test tuple by the classification of tuple；
Error rate is calculated, and selects K value corresponding to minimal error rate,
Wherein, the wind speed that K value corresponding to the minimal error rate is expressed as K wind power generating set in the wind power plant has line
Property correlation.
5. prediction technique as claimed in claim 4, which is characterized in that described to be established linearly according to wind speed correlation analysis result
Regression model, and the step of predicting based on the linear regression model (LRM) of foundation the wind speed of specific wind power generating set in wind power plant
Include:
Linear regression analysis is carried out to the air speed data in different zones respectively, and is established linearly according to linear regression analysis result
Regression model；
Loss function is constructed according to linear regression model (LRM) and historical data, solves corresponding parameter when loss function minimum value,
And the wind speed of the specific wind power generating set in wind power plant is predicted based on the parameter of solution and the linear regression model (LRM) of foundation.
6. prediction technique as claimed in claim 5, which is characterized in that the loss function minimum value passes through least square method
With or gradient descent method seek.
7. prediction technique as described in claim 1, which is characterized in that further include:
Determine whether the wind speed of prediction deviation occurs according to the wind power curve of the specific wind power generating set.
8. prediction technique as described in claim 1, which is characterized in that further include: the linear regression model (LRM) of foundation is carried out strong
Chemistry is practised.
9. a kind of forecasting system of wind farm wind velocity, which is characterized in that the forecasting system includes:
Data processor module, for obtaining the historical data of wind power plant and carrying out dimension-reduction treatment to the historical data of acquisition；
Correlation analysis program module, for carrying out wind speed correlation analysis to the data after dimension-reduction treatment；
Forecasting wind speed program module, for establishing linear regression model (LRM) according to wind speed correlation analysis result, and based on foundation
Linear regression model (LRM) predicts the wind speed of the specific wind power generating set in wind power plant.
10. forecasting system as claimed in claim 9, which is characterized in that historical data packet in the data processor module
Include historical wind speed data and history floor data.
11. forecasting system as claimed in claim 9, which is characterized in that the data processor module includes:
Objective function program module, the historical data that will acquire carry out centralization processing and seek mesh according to centralization processing result
Scalar functions；
Objective function and constraint condition are collectively formed maximization Solve problems, and construct glug by maximum eigenvalue program module
Bright day function is solved to obtain maximum eigenvalue to Solve problems are maximized；
Dimension-reduction treatment program module obtains the result of dimension-reduction treatment according to the corresponding maximal eigenvector of maximum eigenvalue.
12. forecasting system as claimed in claim 9, which is characterized in that the correlation analysis program module includes:
Data preprocessing procedures module pre-processes the data after dimension-reduction treatment；
Euler is divided into training sample and test tuple apart from program module, by pretreated data, calculates separately test tuple
With Euler's distance of training tuple；
Region division program module takes Euler apart from the smallest K trained tuple, and will occur most in described K trained tuple
Multiple label is set as the classification of test tuple, and training sample is divided at least one region according to the classification of test tuple；
Linearly related program module calculates error rate, and selects K value corresponding to minimal error rate,
Wherein, the wind speed that K value corresponding to the minimal error rate is expressed as K wind power generating set in the wind power plant has line
Property correlation.
13. forecasting system as claimed in claim 12, which is characterized in that the forecasting wind speed program module includes:
Model-builder program module carries out linear regression analysis to the air speed data in different zones respectively, and is returned according to linear
Analysis result is returned to establish linear regression model (LRM)；
Forecasting wind speed program module constructs loss function according to linear regression model (LRM) and historical data, it is minimum to solve loss function
Corresponding parameter when value, and predict based on the parameter of solution and the linear regression model (LRM) of foundation the specific wind-force in wind power plant
The wind speed of generating set.
14. forecasting system as claimed in claim 13, which is characterized in that the loss function minimum value passes through least square method
With or gradient descent method seek.
15. forecasting system as claimed in claim 9, which is characterized in that further include:
Test bias program module, tested according to the wind power curve of the specific wind power generating set prediction wind speed whether
There is deviation.
16. forecasting system as claimed in claim 9, which is characterized in that further include:
Intensified learning program module carries out intensified learning to the linear regression model (LRM) of foundation.
17. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the computer program is located
When managing device operation, processor perform claim requires prediction technique described in any one of 1-8.
18. a kind of computer equipment, the memory including processor and storage computer program, which is characterized in that the calculating
When machine program is run by processor, processor executes such as prediction technique of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710474284.1A CN109102101B (en) | 2017-06-21 | 2017-06-21 | Wind speed prediction method and system for wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710474284.1A CN109102101B (en) | 2017-06-21 | 2017-06-21 | Wind speed prediction method and system for wind power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109102101A true CN109102101A (en) | 2018-12-28 |
| CN109102101B CN109102101B (en) | 2021-01-26 |
Family
ID=64796014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710474284.1A Active CN109102101B (en) | 2017-06-21 | 2017-06-21 | Wind speed prediction method and system for wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109102101B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109413149A (en) * | 2018-09-19 | 2019-03-01 | 上海哔哩哔哩科技有限公司 | Information distribution control method, system, server and computer readable storage medium |
| CN110188939A (en) * | 2019-05-24 | 2019-08-30 | 上海电气风电集团有限公司 | Prediction technique, system, equipment and the storage medium of the wind power of wind power plant |
| CN110222899A (en) * | 2019-06-12 | 2019-09-10 | 哈尔滨工业大学 | A kind of cross-country skiing racing track wind speed field prediction technique |
| CN110942182A (en) * | 2019-11-14 | 2020-03-31 | 国网福建省电力有限公司建设分公司 | Method for establishing typhoon prediction model based on support vector regression |
| CN112308322A (en) * | 2020-11-03 | 2021-02-02 | 华翔翔能科技股份有限公司 | Multi-wind-field space-time wind speed prediction method and device and electronic equipment |
| CN112502899A (en) * | 2020-11-30 | 2021-03-16 | 东方电气风电有限公司 | Consumption reduction method for wind generating set |
| CN113297728A (en) * | 2021-04-30 | 2021-08-24 | 东方电气风电有限公司 | Single-fan virtual wind speed calculation method and system based on wind field wind speed correlation |
| CN114048930A (en) * | 2022-01-13 | 2022-02-15 | 广东电网有限责任公司揭阳供电局 | Ultra-short-term wind power prediction method and device |
| CN115081677A (en) * | 2022-05-12 | 2022-09-20 | 暨南大学 | Wind speed prediction method and device, electronic equipment and readable storage medium |
| CN116070471A (en) * | 2023-04-06 | 2023-05-05 | 浙江远算科技有限公司 | Wind driven generator simulation acceleration method and system based on reduced order decomposition processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120185414A1 (en) * | 2010-12-15 | 2012-07-19 | Vaisala, Inc. | Systems and methods for wind forecasting and grid management |
| CN103324980A (en) * | 2013-04-25 | 2013-09-25 | 华北电力大学（保定） | Wind power station wind speed prediction method |
| CN104239964A (en) * | 2014-08-18 | 2014-12-24 | 华北电力大学 | Ultra-short-period wind speed prediction method based on spectral clustering type and genetic optimization extreme learning machine |
| CN105320809A (en) * | 2015-09-30 | 2016-02-10 | 西安电子科技大学 | Wind speed prediction method for wind farm spatial correlation |
| CN106067073A (en) * | 2016-05-30 | 2016-11-02 | 都城绿色能源有限公司 | A kind of wind power forecasting method based on wind-resources correlation analysis |
| CN106779201A (en) * | 2016-12-08 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of wind speed modeling method of consideration plateau mountain area blower fan position |
| CN106875037A (en) * | 2016-12-30 | 2017-06-20 | 东软集团股份有限公司 | Wind-force Forecasting Methodology and device |
-
2017
- 2017-06-21 CN CN201710474284.1A patent/CN109102101B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120185414A1 (en) * | 2010-12-15 | 2012-07-19 | Vaisala, Inc. | Systems and methods for wind forecasting and grid management |
| CN103324980A (en) * | 2013-04-25 | 2013-09-25 | 华北电力大学（保定） | Wind power station wind speed prediction method |
| CN104239964A (en) * | 2014-08-18 | 2014-12-24 | 华北电力大学 | Ultra-short-period wind speed prediction method based on spectral clustering type and genetic optimization extreme learning machine |
| CN105320809A (en) * | 2015-09-30 | 2016-02-10 | 西安电子科技大学 | Wind speed prediction method for wind farm spatial correlation |
| CN106067073A (en) * | 2016-05-30 | 2016-11-02 | 都城绿色能源有限公司 | A kind of wind power forecasting method based on wind-resources correlation analysis |
| CN106779201A (en) * | 2016-12-08 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of wind speed modeling method of consideration plateau mountain area blower fan position |
| CN106875037A (en) * | 2016-12-30 | 2017-06-20 | 东软集团股份有限公司 | Wind-force Forecasting Methodology and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109413149A (en) * | 2018-09-19 | 2019-03-01 | 上海哔哩哔哩科技有限公司 | Information distribution control method, system, server and computer readable storage medium |
| CN110188939A (en) * | 2019-05-24 | 2019-08-30 | 上海电气风电集团有限公司 | Prediction technique, system, equipment and the storage medium of the wind power of wind power plant |
| CN110188939B (en) * | 2019-05-24 | 2023-12-12 | 上海电气风电集团股份有限公司 | Wind power prediction method, system, equipment and storage medium of wind power plant |
| CN110222899A (en) * | 2019-06-12 | 2019-09-10 | 哈尔滨工业大学 | A kind of cross-country skiing racing track wind speed field prediction technique |
| CN110222899B (en) * | 2019-06-12 | 2022-04-22 | 哈尔滨工业大学 | Cross-country skiing track wind speed field prediction method |
| CN110942182A (en) * | 2019-11-14 | 2020-03-31 | 国网福建省电力有限公司建设分公司 | Method for establishing typhoon prediction model based on support vector regression |
| CN112308322B (en) * | 2020-11-03 | 2023-11-24 | 华翔翔能科技股份有限公司 | Multi-wind-field space-time wind speed prediction method and device and electronic equipment |
| CN112308322A (en) * | 2020-11-03 | 2021-02-02 | 华翔翔能科技股份有限公司 | Multi-wind-field space-time wind speed prediction method and device and electronic equipment |
| CN112502899A (en) * | 2020-11-30 | 2021-03-16 | 东方电气风电有限公司 | Consumption reduction method for wind generating set |
| CN113297728A (en) * | 2021-04-30 | 2021-08-24 | 东方电气风电有限公司 | Single-fan virtual wind speed calculation method and system based on wind field wind speed correlation |
| CN114048930A (en) * | 2022-01-13 | 2022-02-15 | 广东电网有限责任公司揭阳供电局 | Ultra-short-term wind power prediction method and device |
| CN115081677A (en) * | 2022-05-12 | 2022-09-20 | 暨南大学 | Wind speed prediction method and device, electronic equipment and readable storage medium |
| CN116070471A (en) * | 2023-04-06 | 2023-05-05 | 浙江远算科技有限公司 | Wind driven generator simulation acceleration method and system based on reduced order decomposition processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109102101B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109102101A (en) | Wind speed prediction method and system for wind power plant | |
| US8606418B1 (en) | Wind prediction for wind farms through the use of weather radar | |
| KR102226687B1 (en) | Apparatus and method of remaining maintenance cycle prediction based on times series prediction using deep learning | |
| US8489247B1 (en) | Agent-based chaotic control of wind turbines | |
| Tesfaye et al. | Short-term wind power forecasting using artificial neural networks for resource scheduling in microgrids | |
| Labati et al. | A decision support system for wind power production | |
| CN108092319A (en) | A kind of Uncertainty Analysis Method and device of short-term wind-electricity power prediction | |
| CN112116160B (en) | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network | |
| US20230214703A1 (en) | Predicting energy production for energy generating assets | |
| CN110210641A (en) | Wind direction prediction method and device for wind power plant | |
| Khan et al. | AI based real-time signal reconstruction for wind farm with SCADA sensor failure | |
| CN114742363A (en) | Energy efficiency state evaluation method, system and medium for wind turbine generator | |
| Zhong et al. | Airrl: A reinforcement learning approach to urban air quality inference | |
| Li et al. | Separate wind power and ramp predictions based on meteorological variables and clustering method | |
| Bouazzi et al. | Deep recurrent neural networks based Bayesian optimization for fault diagnosis of uncertain GCPV systems depending on outdoor condition variation | |
| CN117387617A (en) | Ship track analysis system | |
| CN116680567A (en) | Missing state variable filling method and device for wind driven generator | |
| US12066472B2 (en) | Calculating energy loss during an outage | |
| CN116451608A (en) | Mixed wind power prediction method and device for complex terrain | |
| Sudhakar et al. | Faulty diagnostics model for wind power plant application using AI | |
| Gawali et al. | Fault prediction model in wind turbines using deep learning structure with enhanced optimisation algorithm | |
| Indhumathi et al. | IoT-Enabled Weather Monitoring and Rainfall Prediction using Machine Learning Algorithm | |
| CN117494026B (en) | Method, system and storage medium for positioning icing fault of power transmission line under cold and tidal weather | |
| Li | Improving Wind Ramp Predictions Using Gabor Filtering and Statistical Scenarios | |
| Rama et al. | Predictive Maintenance and Anomaly Detection of Wind Turbines Based on Bladed Simulator Models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |