CN110070223A - A kind of short term power prediction technique applied to newly-built wind power plant - Google Patents
A kind of short term power prediction technique applied to newly-built wind power plant Download PDFInfo
- Publication number
- CN110070223A CN110070223A CN201910318073.8A CN201910318073A CN110070223A CN 110070223 A CN110070223 A CN 110070223A CN 201910318073 A CN201910318073 A CN 201910318073A CN 110070223 A CN110070223 A CN 110070223A
- Authority
- CN
- China
- Prior art keywords
- power plant
- wind
- power
- wind power
- newly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000009467 reduction Effects 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 claims description 30
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 230000005684 electric field Effects 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000010248 power generation Methods 0.000 claims 1
- 241001269238 Data Species 0.000 abstract description 3
- 238000013179 statistical model Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- 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
Abstract
The invention discloses a kind of short term power prediction techniques applied to newly-built wind power plant, by predicting that output carries out NO emissions reduction operation to mesoscale model, obtain the short-term forecast wind speed of wind power plant anemometer tower early period position hub height, and then newly-built wind power plant short term power prediction model is established according to wind speed-power characteristic analytical function and the comprehensive station service consume ratio of wind power plant, realize the short-term forecast integrally contributed to wind power plant.The prediction technique effectively reduces mesoscale lack of resolution bring uncertainty and newly-built wind power plant lacks a large amount of history datas and leads to not the shortcomings that establishing high-precision statistical model, significantly improves newly-built wind power plant short-period power prediction precision.
Description
Technical field
The present invention relates to wind farm power prediction technical fields, more particularly to a kind of applied to the short-term of newly-built wind power plant
Power forecasting method.
Background technique
In recent years, as China's wind-power electricity generation rapidly develops, wind farm grid-connected operation is largely created in the short time, these wind
Electric field lacks accurately and reliably history data, and it is pre- can not to establish high-precision short term power by traditional statistical modeling method
Model is surveyed, newly-built wind power plant short-period power prediction precision is significantly impacted.To ensure that large-scale wind power is safe, reliable, efficient
It is incorporated into the power networks, a kind of wind power forecasting system meeting engineer application is provided, be those skilled in the art's skill urgently to be solved
Art problem.
Summary of the invention
The present invention provides a kind of short term power prediction techniques applied to newly-built wind power plant.
The present invention provides following schemes:
A kind of short term power prediction technique applied to newly-built wind power plant, comprising the following steps:
Collect the actual measurement air speed data of anemometer tower before wind power plant is established, and ruler in the wind-powered electricity generation field areas of time match therewith
Spend the historical forecast data of numerical weather forecast predictive factor；
Using BP neural network, the history number of the predictive factor of newly-built wind-powered electricity generation field areas mesoscale numerical weather forecast is established
According to the historical data relationship between wind power plant anemometer tower early period actual measurement wind speed, the wind of anemometer tower position axial fan hub height is generated
Speed statistics NO emissions reduction model；
Predictive factor and anemometer tower position blower according to the wind-powered electricity generation field areas mesoscale numerical weather forecast
Hub height counts NO emissions reduction model, generates the short-term forecast wind speed of anemometer tower position axial fan hub height；
Ratio is consumed according to wind speed-power characteristic parsing data and the comprehensive station service of wind power plant, establishes newly-built wind
Electric field short term power prediction model calculates and obtains newly-built wind power plant short-term forecast power.
Preferred: the predictive factor of the mesoscale numerical weather forecast includes at least: 500hPa geopotential unit, 850hPa
Geopotential unit, the wind speed of axial fan hub height, wind direction, pressure, relative humidity.
It is preferred: the historical forecast data of the numerical weather forecast predictive factor, pre- with mesoscale numerical weather forecast
The time span for surveying the wind power plant anemometer tower early period actual measurement wind speed of factor time match is no less than 6 calendar months.
It is preferred: to further include the steps that the predictive factor of mesoscale numerical weather forecast is normalized.
It is preferred: the output model of the BP neural network are as follows:
In formula, yk (t) is the t moment kth Fans hub height wind speed value of model output；F is transmission function, this
In embodiment, transmission function is tangent hyperbolic functions；wjFor the weight coefficient for connecting hidden layer and output layer；Xi (t) is model
Input i-th of predictive factor value of t moment；vijFor the weight coefficient for connecting input layer and hidden layer；N is input layer dimension；M is hidden
Dimension containing layer；θjFor hidden layer threshold value；θ0For output layer threshold value.
Preferred: the wind speed-power characteristic parsing data include:
Using multistage Gaussian function fitting wind speed-power characteristic, wind speed-power characteristic analytical function is obtained
P (v),
P (v)=a1*exp (- ((v-b1)/c1) ^2)+a2*exp (- ((v-b2)/c2) ^2)+a3*exp (- ((v-b3)/
C3) ^2)+a4*exp (- ((v-b4)/c4) ^2),
In formula, v indicates air speed value, ai, bi, and ci (i=1~4) indicates the constant value coefficient of multistage Gauss curve fitting curve.
Preferred: the comprehensive station service of the wind power plant consumes ratio=(generated energy-electricity volume)/generated energy=integrated plant
Electricity consumption/generated energy；
Integrated plant electricity consumption=wind power plant power inside amount+main transformer and field interior lines path loss power consumption+reactor electricity consumption.
Preferred: the newly-built wind power plant short term power prediction model is N*P (v) * C；
Wherein, N indicates wind electric field blower quantity, and P (v) indicates wind speed-power characteristic parsing data, and C indicates wind
The comprehensive station service of electric field consumes ratio.
It is preferred: to further include that actual power is combined to verify newly-built wind power plant short-term forecast power, according to verification knot
The step of fruit is modified the newly-built wind power plant short term power prediction model.
Preferred: the amendment step includes that prediction power is less than actual power, then the corresponding electricity reduced inside wind power plant
Amount consume recalculates prediction power than column, with the amendment of wind power plant short term power prediction model in completion；
Or, prediction power is greater than actual power, then the corresponding electricity consume increased inside wind power plant is than column, until being calculated
Prediction power out is close with actual power, determines closest to the electricity consume inside the wind power plant of true value than column, again
Prediction power is calculated, with the amendment of wind power plant short term power prediction model in completion.
The specific embodiment provided according to the present invention, the invention discloses following technical effects:
By the invention it is possible to a kind of short term power prediction technique applied to newly-built wind power plant be realized, in a kind of realization
Under mode, this method may include collecting the actual measurement air speed data of anemometer tower before wind power plant is established, and time match therewith
The historical forecast data of wind-powered electricity generation field areas mesoscale numerical weather forecast predictive factor；Using BP neural network, newly-built wind is established
Between historical data and wind power plant anemometer tower early period the actual measurement wind speed of the predictive factor of electric field region mesoscale numerical weather forecast
Historical data relationship, generate anemometer tower position axial fan hub height wind speed count NO emissions reduction model；According to the wind power plant
The predictive factor of region mesoscale numerical weather forecast and the anemometer tower position axial fan hub height count NO emissions reduction mould
Type generates the short-term forecast wind speed of anemometer tower position axial fan hub height；According to wind speed-power characteristic parsing data and
The comprehensive station service of wind power plant consumes ratio, establishes newly-built wind power plant short term power prediction model, it is short that calculating obtains newly-built wind power plant
Phase prediction power.The application provides a kind of short term power prediction technique applied to newly-built wind power plant, by mesoscale model
Prediction output carries out NO emissions reduction operation, obtains the short-term forecast wind speed of wind power plant anemometer tower early period position hub height, into
And the newly-built short-term function of wind power plant is established according to wind speed-power characteristic analytical function and the comprehensive station service consume ratio of wind power plant
Rate prediction model realizes the short-term forecast integrally contributed to wind power plant.Above-mentioned prediction technique effectively reduces mesoscale resolution ratio
Insufficient bring uncertainty and newly-built wind power plant lack a large amount of history datas and lead to not establish high-precision statistics mould
The shortcomings that type, significantly improves newly-built wind power plant short-period power prediction precision.
Certainly, it implements any of the products of the present invention and does not necessarily require achieving all the advantages described above at the same time.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of process of short term power prediction technique applied to newly-built wind power plant provided in an embodiment of the present invention
Figure；
Fig. 2 is the schematic illustration of BP neural network provided in an embodiment of the present invention；
Fig. 3 is genuine wind speed-power characteristic schematic diagram of blower provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art's every other embodiment obtained belong to what the present invention protected
Range.
Embodiment
It is a kind of short term power prediction technique applied to newly-built wind power plant provided in an embodiment of the present invention, such as referring to Fig. 1
Shown in Fig. 1, method includes the following steps:
S101, the actual measurement air speed data for collecting anemometer tower before wind power plant is established, and the wind-powered electricity generation place of time match therewith
The historical forecast data of domain mesoscale numerical weather forecast predictive factor；The selection of mesoscale numerical weather forecast predictive factor is
Important link during applied statistics NO emissions reduction method, the selection of predictive factor have been largely fixed the local gas of wind power plant
As the Forecast characteristic of condition.The predictive factor having a significant impact to wind speed is chosen, its quantity is reduced, statistics drop can be effectively reduced
The complexity of Scale Model reduces model calculation amount, avoids introducing extra interference information.Selection predictive factor follows following
Method:
1, predictive factor allows for accurately being predicted by mesoscale numerical weather forecast mode, and predictive factor with
There is significant Nonlinear Statistical relationship, and this statistical relationship is to stablize and have between wind power plant domestic site meteorological element
Effect；
2, predictive factor allows for reflecting important Mesoscale physical change process；
It 3, is weak related or unrelated between different predictive factors.
Based on above-mentioned several points, selected predictive factor is respectively as follows: 500hPa provided by mesoscale numerical weather forecast
Geopotential unit, 850hPa geopotential unit, the wind speed of axial fan hub height, wind direction, pressure and relative humidity.The wind power plant early period
Anemometer tower historical data time span is at least six calendar months (half a year), preferably, being 1 year.
By upper, since above-mentioned predictor can be predicted accurately, and between different predictive factor be it is weak related or
It is unrelated, therefore using above-mentioned predictor as the input quantity of BP neural network, can more accurately to BP neural network into
Row training.
S102, using BP neural network, establish the predictive factor of newly-built wind-powered electricity generation field areas mesoscale numerical weather forecast
Historical data relationship between historical data and wind power plant anemometer tower early period actual measurement wind speed, it is high to generate anemometer tower position axial fan hub
The wind speed of degree counts NO emissions reduction model；
Using BP neural network establish statistics NO emissions reduction model, specifically, i.e., mesoscale numerical weather forecast prediction because
Statistical relationship between son and anemometer tower position hub height wind speed, using this statistical relationship as the statistics NO emissions reduction mould of anemometer tower
Type is applied to generate the anemometer tower position axial fan hub Height Prediction wind speed.
Referring to fig. 2, BP neural network is a kind of Multi-layered Feedforward Networks by the training of error backpropagation algorithm, can be with any
Precision approaches any Nonlinear Mapping, and topological structure is made of input layer, hidden layer and output layer, model output are as follows:In formula, yk (t) is the t moment kth Fans hub height of model output
Wind speed value；F is transmission function, and in the present embodiment, transmission function is tangent hyperbolic functions；wjFor connection hidden layer and output
The weight coefficient of layer；Xi (t) is i-th of predictive factor value of mode input t moment；vijFor the power for connecting input layer and hidden layer
Weight coefficient；N is input layer dimension；M is the dimension of hidden layer；θjFor hidden layer threshold value；θ0For output layer threshold value.
It is illustrated for establishing anemometer tower position axial fan hub height statistics NO emissions reduction model, as shown in Fig. 2, modeling
Data are that the mesoscale numerical weather forecast model prediction factor and anemometer tower in January, 2012 in June, 2012 survey wind speed number
Be 15min according to, data time resolution ratio, data length chooses next day 0~for 24 hours, by the 500hPa geopotential unit of mode output,
850hPa geopotential unit, wind speed V, wind direction D sine value, wind direction D cosine value, atmospheric pressure P, humidity RH are inputted as model training
Amount, axial fan hub height wind speed measured value establish three layers of BP neural network model as training output quantity.The BP neural network
Input layer number is 6；Hidden layer neuron number is preferentially determined by test；Network output layer neuron number is 1.Training BP
When neural network, it is normalized to layer data is output and input, is normalized with the following method here:It is illustrated by taking pressure as an example, X indicates prediction pressure values, XminIndicate preset minimum pressure value, XmaxTable
Show preset maximum pressure value,Indicate normalized pressure values.
It is analyzed by screening, when determining that hidden layer neuron number is 21, training sample error is minimum, and (this step is that BP is normal
Process), each weight coefficient matrix and threshold matrix also determine therewith at this time.BP after weighted value and threshold matrix coefficient determine is refreshing
Statistics NO emissions reduction prediction model through network model as anemometer tower.
S103, the predictive factor according to the wind-powered electricity generation field areas mesoscale numerical weather forecast and the anemometer tower position
Axial fan hub height statistics NO emissions reduction model is set, the short-term forecast wind speed of anemometer tower position axial fan hub height is generated；
The wind provided according to anemometer tower position axial fan hub height statistics NO emissions reduction model and mesoscale numerical weather forecast
Electric field region short-term forecast wind speed generates anemometer tower position axial fan hub height short-term forecast wind speed.
Complete anemometer tower position axial fan hub height statistics NO emissions reduction modeling after, by mesoscale numerical weather forecast predict because
Sub (500hPa geopotential unit, 850hPa geopotential unit, axial fan hub height wind speed, wind direction, pressure and relative humidity) input is surveyed
Wind tower counts NO emissions reduction model, can export the short-term forecast wind speed of anemometer tower position axial fan hub height.
Mesoscale numerical weather forecast counts NO emissions reduction method, can calculate anemometer tower using above-mentioned 6 predictive factors
The high-resolution short-term wind speed forecasting value of position hub height, calculation amount is small and calculating speed is fast, can satisfy wind power plant completely
The requirement of short term power predictive engine, this method greatly improve computational efficiency compared to existing power NO emissions reduction technology.
S104, ratio is consumed according to wind speed-power characteristic parsing data and the comprehensive station service of wind power plant, established new
Wind power plant short term power prediction model is built, calculates and obtains newly-built wind power plant short-term forecast power.
As shown in figure 3, wind power plant short term power prediction model is based on genuine wind speed-power characteristic data P (v) and wind
The comprehensive station service consume ratio C building of electric field.Genuine wind speed-power characteristic data are carried out using high-order Gaussian function non-
Linear fit obtains genuine wind speed-power characteristic analytical function P (v)；The comprehensive station service of wind power plant consumes factor and includes
The consume of wind power plant internal wiring, transformer consume and wind power plant are from electricity consumption etc..
Specifically, it is special to obtain genuine wind speed-power using multistage Gaussian function fitting genuine wind speed-power characteristic
The analytical function of linearity curve, the analytical function have following expression formula:
P (v)=a1*exp (- ((v-b1)/c1) ^2)+a2*exp (- ((v-b2)/c2) ^2)+a3*exp (- ((v-b3)/
c3)^2)+a4*exp(-((v-b4)/c4)^2)；
In formula, v indicates air speed value, ai, bi, and ci (i=1~4) indicates the constant value coefficient of multistage Gauss curve fitting curve.
In addition, the comprehensive station service of wind power plant consumes ratio C=(generated energy-electricity volume)/generated energy=synthesis station service
Amount/generated energy；
Integrated plant electricity consumption=wind power plant power inside amount+main transformer and field interior lines path loss power consumption+reactor electricity consumption.
Pass through above-mentioned calculating formula, it can be deduced that the electricity consume inside wind power plant occurs than column.
Newly-built wind power plant short term power prediction model is expressed using following, wind power plant short-term forecast power=N*P (v) * C,
N is wind electric field blower quantity in formula.
Wind power plant short term power is predicted.
The short-term forecast wind speed of wind power plant anemometer tower early period position by statistics NO emissions reduction processing is input to newly-built wind
Electric field short term power prediction model obtains wind power plant short-term forecast power.
In conjunction with actual power, the prediction data in step S50 is verified, and according to check results in step 40
Wind power plant short term power prediction model is modified.
For creating wind power plant, practical power data is less, then needs according to less actual power data for pre-
Measured value carries out accuracy judgement.For example, when prediction power is less than actual power, then the electricity reduced inside wind power plant is corresponded to
Amount consume recalculates prediction power than column C.Conversely, when prediction power is greater than actual power, then it is corresponding to increase in wind power plant
The electricity consume in portion determines the wind closest to true value until the calculated prediction power of institute is close with actual power than column C
Electricity consume inside electric field is than column C.To realize the amendment for wind power plant short term power prediction model in step 40.
In short, the application provides a kind of short term power prediction technique applied to newly-built wind power plant, by mesoscale mould
Formula prediction output carries out NO emissions reduction operation, obtains the short-term forecast wind speed of wind power plant anemometer tower early period position hub height,
And then it is short-term according to wind speed-power characteristic analytical function and the newly-built wind power plant of the comprehensive station service consume ratio foundation of wind power plant
Power prediction model realizes the short-term forecast integrally contributed to wind power plant.Above-mentioned prediction technique effectively reduces mesoscale resolution
Rate deficiency bring uncertainty and newly-built wind power plant lack a large amount of history datas and lead to not establish high-precision statistics
The shortcomings that model, significantly improves newly-built wind power plant short-period power prediction precision.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of short term power prediction technique applied to newly-built wind power plant, which is characterized in that the described method includes:
Collect the actual measurement air speed data of anemometer tower before wind power plant is established, and the wind-powered electricity generation field areas mesoscale number of time match therewith
It is worth the historical forecast data of weather forecast predictive factor；
Using BP neural network, establish the historical data of the predictive factor of newly-built wind-powered electricity generation field areas mesoscale numerical weather forecast with
Wind power plant anemometer tower early period surveys the historical data relationship between wind speed, generates the wind speed system of anemometer tower position axial fan hub height
Count NO emissions reduction model；
Predictive factor and anemometer tower position axial fan hub according to the wind-powered electricity generation field areas mesoscale numerical weather forecast
Height statistics NO emissions reduction model, generates the short-term forecast wind speed of anemometer tower position axial fan hub height；
Ratio is consumed according to wind speed-power characteristic parsing data and the comprehensive station service of wind power plant, establishes newly-built wind power plant
Short term power prediction model calculates and obtains newly-built wind power plant short-term forecast power.
2. the method according to claim 1, wherein the predictive factor of the mesoscale numerical weather forecast is at least
It include: 500hPa geopotential unit, 850hPa geopotential unit, the wind speed of axial fan hub height, wind direction, pressure, relative humidity.
3. the method according to claim 1, wherein the historical forecast number of the numerical weather forecast predictive factor
According to, it is equal with the time span of wind power plant anemometer tower early period of mesoscale numerical weather forecast predictive factor time match actual measurement wind speed
No less than 6 calendar months.
4. the method according to claim 1, wherein further including the predictive factor to mesoscale numerical weather forecast
The step of being normalized.
5. the method according to claim 1, wherein the output model of the BP neural network are as follows:
In formula, ykIt (t) is the t moment kth Fans hub height wind speed value of model output；F is transmission function, this implementation
In example, transmission function is tangent hyperbolic functions；wjFor the weight coefficient for connecting hidden layer and output layer；xiIt (t) is mode input t
I-th of predictive factor value of moment；vijFor the weight coefficient for connecting input layer and hidden layer；N is input layer dimension；M is hidden layer
Dimension；θjFor hidden layer threshold value；θ0For output layer threshold value.
6. the method according to claim 1, wherein the wind speed-power characteristic parsing data include:
Using multistage Gaussian function fitting wind speed-power characteristic, wind speed-power characteristic analytical function P is obtained
(v),
P (v)=a1*exp (- ((v-b1)/c1) ^2)+a2*exp (- ((v-b2)/c2) ^2)+a3*exp (- ((v-b3)/c3) ^
2)+a4*exp (- ((v-b4)/c4) ^2),
In formula, v indicates air speed value, ai, bi, and ci (i=1~4) indicates the constant value coefficient of multistage Gauss curve fitting curve.
7. the method according to claim 1, wherein the comprehensive station service consume ratio=(power generation of the wind power plant
Amount-electricity volume)/generated energy=integrated plant electricity consumption/generated energy；
Integrated plant electricity consumption=wind power plant power inside amount+main transformer and field interior lines path loss power consumption+reactor electricity consumption.
8. the method according to claim 1, wherein the newly-built wind power plant short term power prediction model is N*P
(v)*C；
Wherein, N indicates wind electric field blower quantity, and P (v) indicates wind speed-power characteristic parsing data, and C indicates wind power plant
Comprehensive station service consumes ratio.
9. according to claim 1 to method described in 8 any one, which is characterized in that further include combining actual power to newly-built
Wind power plant short-term forecast power is verified, and is repaired according to check results to the newly-built wind power plant short term power prediction model
Positive step.
10. according to the method described in claim 9, it is characterized in that, the amendment step includes that prediction power is less than practical function
Rate then corresponds to the electricity consume ratio column reduced inside wind power plant, prediction power is recalculated, with wind power plant short term power in completion
The amendment of prediction model；
Or, prediction power is greater than actual power, then the corresponding electricity consume increased inside wind power plant is than column, until institute is calculated
Prediction power is close with actual power, determines to recalculate closest to the electricity consume inside the wind power plant of true value than column
Prediction power, with the amendment of wind power plant short term power prediction model in completion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910318073.8A CN110070223A (en) | 2019-04-19 | 2019-04-19 | A kind of short term power prediction technique applied to newly-built wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910318073.8A CN110070223A (en) | 2019-04-19 | 2019-04-19 | A kind of short term power prediction technique applied to newly-built wind power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110070223A true CN110070223A (en) | 2019-07-30 |
Family
ID=67368054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910318073.8A Pending CN110070223A (en) | 2019-04-19 | 2019-04-19 | A kind of short term power prediction technique applied to newly-built wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070223A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814345A (en) * | 2020-07-17 | 2020-10-23 | 中国船舶重工集团海装风电股份有限公司 | Method for interpolating and observing missing wind speed data by utilizing various mesoscale wind speed data |
| CN113343562A (en) * | 2021-05-26 | 2021-09-03 | 国网天津市电力公司电力科学研究院 | Fan power prediction method and system based on hybrid modeling strategy |
| CN113553782A (en) * | 2021-02-04 | 2021-10-26 | 华风气象传媒集团有限责任公司 | Downscaling method for forecasting wind speed |
| CN115219853A (en) * | 2022-09-20 | 2022-10-21 | 北京智盟信通科技有限公司 | Fault early warning processing method and system for current collection line of wind power plant |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389388A (en) * | 2012-05-08 | 2013-11-13 | 华锐风电科技(集团)股份有限公司 | Method and device for predicting wind speed in wind power plant and method and system for predicting power in wind power plant |
| US20160169202A1 (en) * | 2013-05-03 | 2016-06-16 | State Grid Corporation Of China | Short-term operation optimization method of electric power system including large-scale wind power |
| CN106650977A (en) * | 2015-10-29 | 2017-05-10 | 中能电力科技开发有限公司 | Short-term power prediction method used for newly-built wind farm |
-
2019
- 2019-04-19 CN CN201910318073.8A patent/CN110070223A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389388A (en) * | 2012-05-08 | 2013-11-13 | 华锐风电科技(集团)股份有限公司 | Method and device for predicting wind speed in wind power plant and method and system for predicting power in wind power plant |
| US20160169202A1 (en) * | 2013-05-03 | 2016-06-16 | State Grid Corporation Of China | Short-term operation optimization method of electric power system including large-scale wind power |
| CN106650977A (en) * | 2015-10-29 | 2017-05-10 | 中能电力科技开发有限公司 | Short-term power prediction method used for newly-built wind farm |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814345A (en) * | 2020-07-17 | 2020-10-23 | 中国船舶重工集团海装风电股份有限公司 | Method for interpolating and observing missing wind speed data by utilizing various mesoscale wind speed data |
| CN111814345B (en) * | 2020-07-17 | 2022-08-02 | 中国船舶重工集团海装风电股份有限公司 | Method for interpolating and observing missing wind speed data by utilizing various mesoscale wind speed data |
| CN113553782A (en) * | 2021-02-04 | 2021-10-26 | 华风气象传媒集团有限责任公司 | Downscaling method for forecasting wind speed |
| CN113553782B (en) * | 2021-02-04 | 2024-03-26 | 华风气象传媒集团有限责任公司 | Downscaling method for forecasting wind speed |
| CN113343562A (en) * | 2021-05-26 | 2021-09-03 | 国网天津市电力公司电力科学研究院 | Fan power prediction method and system based on hybrid modeling strategy |
| CN115219853A (en) * | 2022-09-20 | 2022-10-21 | 北京智盟信通科技有限公司 | Fault early warning processing method and system for current collection line of wind power plant |
| CN115219853B (en) * | 2022-09-20 | 2023-01-20 | 北京智盟信通科技有限公司 | Fault early warning processing method and system for current collection line of wind power plant |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070223A (en) | A kind of short term power prediction technique applied to newly-built wind power plant | |
| Wu et al. | Economics-and reliability-based design for an offshore wind farm | |
| CN106228278A (en) | Photovoltaic power prognoses system | |
| CN110471024A (en) | A kind of online remote checking method of intelligent electric meter based on metric data analysis | |
| CN108388962B (en) | Wind power prediction system and method | |
| CN104978608B (en) | A kind of wind electric powder prediction device and prediction technique | |
| CN108983320A (en) | A kind of numerical weather forecast-artificial intelligence coupling prediction method of coastal typhoon Maximum wind speed | |
| CN103268366A (en) | Combined wind power prediction method suitable for distributed wind power plant | |
| CN109617134A (en) | The robust Unit Combination method of meter and Uncertainty prediction error temporal correlation | |
| CN103473621A (en) | Wind power station short-term power prediction method | |
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| KR20070119285A (en) | Forecasting method of wind power generation by classification of wind speed patterns | |
| CN103489046A (en) | Method for predicting wind power plant short-term power | |
| CN102945508A (en) | Model correction based wind power forecasting system and method | |
| CN104252649A (en) | Regional wind power output prediction method based on correlation between multiple wind power plants | |
| CN110110912A (en) | A kind of photovoltaic power multi-model interval prediction method | |
| CN109167387A (en) | Wind field wind power forecasting method | |
| CN111488896B (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN106407627A (en) | Wind speed probability distribution modeling method and system | |
| CN106875037A (en) | Wind-force Forecasting Methodology and device | |
| CN106548256A (en) | A kind of method and system of wind energy turbine set space-time dynamic correlation modeling | |
| CN108694479A (en) | Consider the distribution network reliability prediction technique that weather influences time between overhaul | |
| CN108269197A (en) | Wind turbines power characteristic appraisal procedure and device | |
| CN109858668B (en) | Coordination prediction method for power load region in thunder and lightning climate | |
| CN105279384A (en) | Wind turbine cabin wind speed-based method and device for calculating wind speed of incoming flow |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190730 |