CN106650977A - Short-term power prediction method used for newly-built wind farm - Google Patents
Short-term power prediction method used for newly-built wind farm Download PDFInfo
- Publication number
- CN106650977A CN106650977A CN201510717213.0A CN201510717213A CN106650977A CN 106650977 A CN106650977 A CN 106650977A CN 201510717213 A CN201510717213 A CN 201510717213A CN 106650977 A CN106650977 A CN 106650977A
- Authority
- CN
- China
- Prior art keywords
- wind
- power
- newly
- turbine set
- energy turbine
- 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
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a short-term power prediction method used for a newly-built wind farm. The short-term power prediction method comprises steps that A: by using a BP neural network, a historical data relation between a scale value weather forecast prediction factor in the newly-built wind farm and a wind farm early-stage anemometer tower actually-measured wind speed is established, and a wind speed statistic downscaling model of an anemometer tower position draught fan hub height is generated; B: the short-term prediction wind speed of the anemometer tower position draught fan hub height is generated according to the prediction factor of the scale value weather forecast in the wind farm area and the wind speed statistic downscaling model of the anemometer tower position draught fan hub height of the step A; C: a newly-built wind farm short-term power prediction model is established according to a wind speed-power characteristic curve analysis data and a wind farm integrated factory electricity loss proportion, and newly-built wind farm short-term prediction power is calculated. Newly-built wind farm integrated output short-term prediction is realized.
Description
Technical field
The present invention relates to wind farm power prediction technical field, more particularly to one kind are applied to newly-built
The short term power Forecasting Methodology of wind energy turbine set.
Background technology
In recent years, as China's wind-power electricity generation is developed rapidly, a large amount of newly-built wind energy turbine sets in the short time
Grid-connected operation, these wind energy turbine sets lack accurately and reliably history data, it is impossible to by tradition
Statistical modeling method set up high accuracy short term power forecast model, significantly impact newly-built wind-powered electricity generation
Field short term power precision of prediction.The grid-connected fortune safe, reliable, efficient to guarantee large-scale wind power
OK, develop meet engineer applied wind power forecasting system it is very crucial.
The content of the invention
In view of this, present invention is primarily targeted at, there is provided one kind is applied to newly-built wind energy turbine set
Short term power Forecasting Methodology, including step：
A, BP neural network is utilized, set up newly-built wind-powered electricity generation field areas mesoscale Numerical Weather pre-
Historical data relation between report predictive factor and wind energy turbine set early stage anemometer tower actual measurement wind speed, generates
The wind speed statistics NO emissions reduction model of anemometer tower position axial fan hub height；
The predictive factor of B, foundation wind-powered electricity generation field areas mesoscale numerical weather forecast, and step
The axial fan hub of anemometer tower position described in A highly counts NO emissions reduction model, generates anemometer tower position
The short-term forecast wind speed of axial fan hub height；
C, foundation wind speed-power characteristic parsing data and wind energy turbine set synthesis station service consume
Ratio, sets up newly-built wind energy turbine set short term power forecast model, calculates newly-built wind energy turbine set short-term pre-
Power scale.
By upper, by carrying out statistics NO emissions reduction to mesoscale model numerical weather forecast, survey is drawn
The short-term forecast wind speed of wind tower position axial fan hub height, and then set up newly-built wind energy turbine set short-term work(
Rate forecast model, realizes short-term forecast of integrally exerting oneself to newly-built wind energy turbine set.Effectively reduce middle chi
The uncertainty that degree lack of resolution is brought, significantly improves newly-built wind energy turbine set short-term wind speed forecasting
Precision, efficiently solving newly-built wind energy turbine set cannot set up high accuracy work(due to a lack of fan operation data
A difficult problem for rate forecast model.
Optionally, in step A, the predictive factor of the mesoscale numerical weather forecast is at least wrapped
Include：500hPa geopotential units, 850hPa geopotential units, the wind speed of axial fan hub height, wind
To, pressure and relative humidity.
By upper, because above-mentioned predictor can be predicted accurately, and different prediction because
It is weak related or unrelated between son, therefore using above-mentioned predictor as the defeated of BP neural network
Enter amount, more accurately BP neural network can be trained.
Optionally, in step A, also include entering the predictive factor of mesoscale numerical weather forecast
Row normalized.
Optionally, wind speed described in step C-power characteristic parsing data include：
Using multistage Gaussian function fitting wind speed-power characteristic, wind speed-power characteristic is obtained
Analytical function P (v) of curve,
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),
V represents air speed value in formula, and ai, bi, ci (i=1～4) represent multistage Gauss curve fitting curve
Constant value coefficient.
Optionally, wind energy turbine set described in step C synthesis station service consume ratio=(generated energy-on
Net electricity)/generated energy=integrated plant power consumption/generated energy；
Integrated plant power consumption=wind energy turbine set power inside amount+main transformer and field interior lines path loss power consumption+electricity
Anti- device power consumption.
Optionally, the newly-built wind energy turbine set short term power forecast model is N*P (v) * C；
Wherein N represents wind electric field blower quantity, and P (v) represents the parsing of wind speed-power characteristic
Data, C represents wind energy turbine set synthesis station service consume ratio.
Optionally, in step A, the historical forecast data of the numerical weather forecast predictive factor,
Survey with the wind energy turbine set early stage anemometer tower of mesoscale numerical weather forecast predictive factor time match
The time span of wind speed is no less than 6 calendar months.
Optionally, also include after step C：With reference to actual power to newly-built wind energy turbine set short-term forecast
Power is verified, and the newly-built wind energy turbine set short term power forecast model is entered according to check results
The step of row amendment.
Description of the drawings
Fig. 1 is flow chart of the present invention；
Fig. 2 is the principle schematic of BP neural network of the present invention；
Genuine wind speed-power characteristic the schematic diagram of Fig. 3 blower fans.
Specific embodiment
To overcome the defect of prior art presence, the present invention to provide one kind and be applied to newly-built wind energy turbine set
Short term power Forecasting Methodology, by mesoscale model predict output carry out NO emissions reduction computing,
Draw the short-term forecast wind speed of wind energy turbine set early stage anemometer tower position hub height, and then foundation
Wind speed-power characteristic analytical function and wind energy turbine set synthesis station service consume ratio set up newly-built
Wind energy turbine set short term power forecast model, realizes the short-term forecast integrally exerted oneself to wind energy turbine set.It is above-mentioned
Forecasting Methodology effectively reduces the uncertainty that mesoscale lack of resolution is brought, and newly-built wind
Electric field lacks a large amount of history datas and leads to not set up the shortcoming of high accuracy statistical model, shows
Work improves newly-built wind power plant short-period power prediction precision.
As shown in figure 1, a kind of short term power Forecasting Methodology for being applied to newly-built wind energy turbine set includes：
Step 10：The actual measurement air speed data of anemometer tower before wind energy turbine set is set up is collected, and with when
Between match wind-powered electricity generation field areas mesoscale numerical weather forecast predictive factor historical forecast data.
The selection of mesoscale numerical weather forecast predictive factor is applied statistics NO emissions reduction method mistake
Important link in journey, the selection of predictive factor has been largely fixed the local meteorology of wind energy turbine set
The Forecast characteristic of condition.The predictive factor that selection has a significant impact to wind speed, reduces its quantity,
Can effectively reduce counting the complexity of NO emissions reduction model, reduce model amount of calculation, it is to avoid draw
Enter extra interference information.Choose predictive factor and follow following methods：
1st, predictive factor allows for accurately being predicted by mesoscale numerical weather forecast pattern,
And there is significant non-linear system between predictive factor and wind energy turbine set domestic site meteorological element
Meter relation, and this statistical relationship is stably effective；
2nd, predictive factor allows for reflecting important Mesoscale physical change process；
3rd, it is weak related or unrelated between different predictive factors.
Based on it is above-mentioned some, selected predictive factor is respectively：Mesoscale numerical weather forecast
The 500hPa geopotential units that there is provided, 850hPa geopotential units, the wind speed of axial fan hub height,
Wind direction, pressure and relative humidity.
The wind energy turbine set early stage anemometer tower historical data time span is at least half a year, preferably,
For 1 year.
Step 20：Wind energy turbine set early stage anemometer tower position axial fan hub is set up using BP neural network
The statistics NO emissions reduction model of height.
Statistics NO emissions reduction model, specifically, i.e. mesoscale number are set up using BP neural network
Statistical relationship between value weather forecast predictive factor and anemometer tower position hub height wind speed, will
This statistical relationship is applied to produce the anemometer tower position as the statistics NO emissions reduction model of anemometer tower
Axial fan hub Height Prediction wind speed.
BP neural network is a kind of Multi-layered Feedforward Networks trained by error backpropagation algorithm,
Any Nonlinear Mapping can be approached with arbitrary accuracy, its topological structure by input layer, hidden layer and
Output layer is constituted, and the model is output as：In formula, yk(t)
For the t kth Fans hub height wind speed value of model output；F is transmission function,
In the present embodiment, transmission function is tangent hyperbolic functions；wjTo connect hidden layer and output layer
Weight coefficient；xiT () is i-th predictive factor value of mode input t；vijTo connect input layer
With the weight coefficient of hidden layer；N is input layer dimension；M is the dimension of hidden layer；θjFor hidden
Threshold value containing layer；θ0For output layer threshold value.
Illustrated as a example by setting up anemometer tower position axial fan hub and highly counting NO emissions reduction model,
As shown in Fig. 2 modeling data is the mesoscale numerical value day in January, 2012 in June, 2012
Gas Forecast Mode predictive factor and anemometer tower survey air speed data, and data time resolution ratio is
15min, data length selection 0～24h of next day, the 500hPa geopotential units that pattern is exported,
850hPa geopotential units, wind speed V, wind direction D sine values, wind direction D cosine values, atmospheric pressure
Strong P, humidity RH are used as model training input quantity, axial fan hub height wind speed measured value conduct
Training output quantity, sets up three layers of BP neural network model.The BP neural network input layer
Neuron number is 6；Hidden layer neuron Number of the is crossed test and is preferentially determined；Network output layer nerve
First number is 1.During training BP neural network, to being input into and exporting layer data place is normalized
Reason, adopts be normalized with the following method here：Enter by taking pressure as an example
Row explanation, X represents prediction pressure values, XminRepresent default minimum pressure value, XmaxRepresent
Default maximum pressure value,Represent normalized pressure values.
Through screening analysis, determine hidden layer neuron number be 21 when, training sample error is most
Little (this step be BP normal flows), now each weight coefficient matrix and threshold matrix be also therewith
It is determined that.BP neural network model after weighted value and the determination of threshold matrix coefficient is used as anemometer tower
Statistics NO emissions reduction forecast model.
Step 30：NO emissions reduction model and mesoscale are highly counted according to anemometer tower position axial fan hub
The wind-powered electricity generation field areas short-term forecast wind speed that numerical weather forecast is provided, generates anemometer tower position blower fan
Hub height short-term forecast wind speed.
Complete anemometer tower position axial fan hub highly to count after NO emissions reduction modeling, by mesoscale numerical value
Weather forecast predictive factor (500hPa geopotential units, 850hPa geopotential units, axial fan hub
Height wind speed, wind direction, pressure and relative humidity) input anemometer tower statistics NO emissions reduction model, just
The short-term forecast wind speed of exportable anemometer tower position axial fan hub height.
Mesoscale numerical weather forecast counts NO emissions reduction method, using above-mentioned 6 predictive factors just
The high-resolution short-term wind speed forecasting value of anemometer tower position hub height can be calculated, amount of calculation is little
And calculating speed is fast, the requirement of wind energy turbine set short term power predictive engine, the method can be met completely
Compared to existing power NO emissions reduction technology, computational efficiency is greatly improved.
Step 40：Set up wind energy turbine set short term power forecast model.
As shown in figure 3, wind energy turbine set short term power forecast model is based on genuine wind speed-power characteristic
Curve data P (v) and wind energy turbine set synthesis station service consume ratio C build.Using high-order Gaussian function
It is several that genuine wind speed-power characteristic data are carried out with nonlinear fitting, obtain genuine wind speed-work(
Characteristic analytical function P (v) of rate；Wind energy turbine set synthesis station service consume factor includes wind energy turbine set
Internal wiring consume, transformer consume and wind energy turbine set are from electricity consumption etc..
Specifically, using multistage Gaussian function fitting genuine wind speed-power characteristic, obtain
The analytical function of genuine wind speed-power characteristic, the analytical function has 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)
V represents air speed value in formula, and ai, bi, ci (i=1～4) represent multistage Gauss curve fitting curve
Constant value coefficient.
In addition, wind energy turbine set synthesis station service consume ratio C=(generated energy-electricity volume)/generate electricity
Amount=integrated plant power consumption/generated energy；
Integrated plant power consumption=wind energy turbine set power inside amount+main transformer and field interior lines path loss power consumption+electricity
Anti- device power consumption.
By above-mentioned calculating formula, it can be deduced that the electricity consume inside wind energy turbine set occurs than row.
Newly-built wind energy turbine set short term power forecast model is adopted and is expressed as below, wind energy turbine set short-term forecast work(
Rate=N*P (v) * C, N is wind electric field blower quantity in formula.
Step 50：Wind energy turbine set short term power is predicted.
By the short-term forecast wind of the wind energy turbine set early stage anemometer tower position processed through statistics NO emissions reduction
Speed is input to newly-built wind energy turbine set short term power forecast model, obtains wind energy turbine set short-term forecast power.
Step 60：With reference to actual power, the prediction data in step S50 is verified,
And the wind energy turbine set short term power forecast model in step 40 is modified according to check results.
For newly-built wind energy turbine set, its actual power data is less, then need according to less reality
Power data carries out degree of accuracy judgement for predicted value.For example, when pre- power scale is less than real
During the power of border, then the electricity consume ratio row C reduced inside wind energy turbine set is corresponded to, recalculate prediction
Power.Conversely, when pre- power scale is more than actual power, then corresponding to increases inside wind energy turbine set
Electricity consume, until the pre- power scale for being calculated is close with actual power, is determined than row C
Closest to the electricity consume inside the wind energy turbine set of actual value than row C.So as to realize for step 40
The amendment of middle wind energy turbine set short term power forecast model.
Presently preferred embodiments of the present invention is the foregoing is only, not to limit the present invention.
In a word, all any modifications within the spirit and principles in the present invention, made, equivalent,
Improve etc., should be included within the scope of the present invention.
Claims (8)
1. a kind of short term power Forecasting Methodology for being applied to newly-built wind energy turbine set, it is characterised in that
Including step：
A, BP neural network is utilized, set up newly-built wind-powered electricity generation field areas mesoscale Numerical Weather pre-
Historical data relation between the predictive factor of report and wind energy turbine set early stage anemometer tower actual measurement wind speed, it is raw
Wind speed into anemometer tower position axial fan hub height counts NO emissions reduction model；
The predictive factor of B, foundation wind-powered electricity generation field areas mesoscale numerical weather forecast, and step
The axial fan hub of anemometer tower position described in A highly counts NO emissions reduction model, generates anemometer tower position
The short-term forecast wind speed of axial fan hub height；
C, foundation wind speed-power characteristic parsing data and wind energy turbine set synthesis station service consume
Ratio, sets up newly-built wind energy turbine set short term power forecast model, calculates newly-built wind energy turbine set short-term pre-
Power scale.
2. method according to claim 1, it is characterised in that described in step A
The predictive factor of mesoscale numerical weather forecast at least includes：500hPa geopotential units, 850hPa
Geopotential unit, the wind speed of axial fan hub height, wind direction, pressure and relative humidity.
3. method according to claim 1, it is characterised in that in step A, also wrap
The step of including the predictive factor to mesoscale numerical weather forecast and be normalized.
4. method according to claim 1, it is characterised in that wind described in step C
Speed-power characteristic parsing data include：
Using multistage Gaussian function fitting wind speed-power characteristic, wind speed-power characteristic is obtained
Analytical function P (v) of curve,
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),
V represents air speed value in formula, and ai, bi, ci (i=1～4) represent multistage Gauss curve fitting curve
Constant value coefficient.
5. method according to claim 1, it is characterised in that wind described in step C
Electric field synthesis station service consume ratio=(generated energy-electricity volume)/generated energy=synthesis station service
Amount/generated energy；
Integrated plant power consumption=wind energy turbine set power inside amount+main transformer and field interior lines path loss power consumption+electricity
Anti- device power consumption.
6. method according to claim 1, it is characterised in that the newly-built wind energy turbine set
Short term power forecast model is N*P (v) * C；
Wherein N represents wind electric field blower quantity, and P (v) represents the parsing of wind speed-power characteristic
Data, C represents wind energy turbine set synthesis station service consume ratio.
7. method according to claim 1, it is characterised in that described in step A
The historical forecast data of numerical weather forecast predictive factor and mesoscale numerical weather forecast are predicted
The time span of the wind energy turbine set early stage anemometer tower actual measurement wind speed of factor time match is no less than 6 certainly
The right moon.
8. method according to claim 1, it is characterised in that also include after step C：
Newly-built wind energy turbine set short-term forecast power is verified with reference to actual power, according to check results pair
The step of newly-built wind energy turbine set short term power forecast model is modified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510717213.0A CN106650977A (en) | 2015-10-29 | 2015-10-29 | Short-term power prediction method used for newly-built wind farm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510717213.0A CN106650977A (en) | 2015-10-29 | 2015-10-29 | Short-term power prediction method used for newly-built wind farm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106650977A true CN106650977A (en) | 2017-05-10 |
Family
ID=58831120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510717213.0A Pending CN106650977A (en) | 2015-10-29 | 2015-10-29 | Short-term power prediction method used for newly-built wind farm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106650977A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153894A (en) * | 2017-06-02 | 2017-09-12 | 北京金风科创风电设备有限公司 | Method and device for correcting predicted wind speed of wind power plant |
| CN107563547A (en) * | 2017-08-18 | 2018-01-09 | 国网天津市电力公司 | A kind of novel user side energy depth Optimum Synthesis energy management-control method |
| CN108665102A (en) * | 2018-05-11 | 2018-10-16 | 中国船舶重工集团海装风电股份有限公司 | Method based on the real-time generated energy of mesoscale data prediction wind power plant |
| CN110070223A (en) * | 2019-04-19 | 2019-07-30 | 中能电力科技开发有限公司 | A kind of short term power prediction technique applied to newly-built wind power plant |
| CN110555538A (en) * | 2018-05-31 | 2019-12-10 | 北京金风科创风电设备有限公司 | Wind power plant wind speed prediction method and prediction system |
| CN111931967A (en) * | 2019-12-20 | 2020-11-13 | 南京南瑞继保电气有限公司 | Wind power plant short-term power prediction method |
| CN113205210A (en) * | 2021-04-29 | 2021-08-03 | 西安热工研究院有限公司 | Wind speed and power prediction method, system, equipment and storage medium for wind power plant with complex terrain |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496927A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Wind power station power projection method based on error statistics modification |
| CN103473621A (en) * | 2013-09-29 | 2013-12-25 | 中能电力科技开发有限公司 | Wind power station short-term power prediction method |
| CN103489046A (en) * | 2013-09-29 | 2014-01-01 | 中能电力科技开发有限公司 | Method for predicting wind power plant short-term power |
-
2015
- 2015-10-29 CN CN201510717213.0A patent/CN106650977A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496927A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Wind power station power projection method based on error statistics modification |
| CN103473621A (en) * | 2013-09-29 | 2013-12-25 | 中能电力科技开发有限公司 | Wind power station short-term power prediction method |
| CN103489046A (en) * | 2013-09-29 | 2014-01-01 | 中能电力科技开发有限公司 | Method for predicting wind power plant short-term power |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11208985B2 (en) | 2017-06-02 | 2021-12-28 | Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd. | Correction method and apparatus for predicted wind speed of wind farm |
| CN107153894B (en) * | 2017-06-02 | 2018-11-27 | 北京金风科创风电设备有限公司 | Method and device for correcting predicted wind speed of wind power plant |
| CN107153894A (en) * | 2017-06-02 | 2017-09-12 | 北京金风科创风电设备有限公司 | Method and device for correcting predicted wind speed of wind power plant |
| CN107563547A (en) * | 2017-08-18 | 2018-01-09 | 国网天津市电力公司 | A kind of novel user side energy depth Optimum Synthesis energy management-control method |
| CN107563547B (en) * | 2017-08-18 | 2021-01-15 | 国网天津市电力公司 | Comprehensive energy management and control method for optimizing depth of energy consumption of user side |
| CN108665102A (en) * | 2018-05-11 | 2018-10-16 | 中国船舶重工集团海装风电股份有限公司 | Method based on the real-time generated energy of mesoscale data prediction wind power plant |
| CN108665102B (en) * | 2018-05-11 | 2022-08-05 | 中国船舶重工集团海装风电股份有限公司 | Method for predicting real-time power generation capacity of wind power plant based on mesoscale data |
| CN110555538A (en) * | 2018-05-31 | 2019-12-10 | 北京金风科创风电设备有限公司 | Wind power plant wind speed prediction method and prediction system |
| CN110555538B (en) * | 2018-05-31 | 2022-11-11 | 北京金风科创风电设备有限公司 | Wind power plant wind speed prediction method and prediction system |
| CN110070223A (en) * | 2019-04-19 | 2019-07-30 | 中能电力科技开发有限公司 | A kind of short term power prediction technique applied to newly-built wind power plant |
| CN111931967A (en) * | 2019-12-20 | 2020-11-13 | 南京南瑞继保电气有限公司 | Wind power plant short-term power prediction method |
| CN111931967B (en) * | 2019-12-20 | 2022-07-22 | 南京南瑞继保电气有限公司 | Short-term power prediction method for wind power plant |
| CN113205210A (en) * | 2021-04-29 | 2021-08-03 | 西安热工研究院有限公司 | Wind speed and power prediction method, system, equipment and storage medium for wind power plant with complex terrain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| Ciulla et al. | Modelling and analysis of real-world wind turbine power curves: Assessing deviations from nominal curve by neural networks | |
| CN102663251B (en) | Physical prediction method for wind power station power based on computational fluid mechanics model | |
| CN104699936B (en) | Wind power plant sector management method based on Fluid Mechanics Computation short-term wind speed forecasting | |
| Wu et al. | Economics-and reliability-based design for an offshore wind farm | |
| CN103473621A (en) | Wind power station short-term power prediction method | |
| Brusca et al. | A new design methodology to predict wind farm energy production by means of a spiking neural network–based system | |
| CN103489046A (en) | Method for predicting wind power plant short-term power | |
| CN111753893A (en) | Wind turbine generator power cluster prediction method based on clustering and deep learning | |
| CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
| CN104252649A (en) | Regional wind power output prediction method based on correlation between multiple wind power plants | |
| CN104978608A (en) | Wind power prediction apparatus and prediction method | |
| CN103996079B (en) | Wind power weighting predication method based on conditional probability | |
| CN111488896B (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN105512766A (en) | Wind power plant power predication method | |
| CN107104442A (en) | The computational methods of Probabilistic Load containing wind power plant of meter and parameter fuzzy | |
| CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
| CN108388962A (en) | A kind of wind power forecasting system and method | |
| CN106875037A (en) | Wind-force Forecasting Methodology and device | |
| CN110070223A (en) | A kind of short term power prediction technique applied to newly-built wind power plant | |
| CN105930900A (en) | Method and system for predicting hybrid wind power generation | |
| CN113627101A (en) | Wind turbine wake flow simulation method based on improved AD/RSM model | |
| CN105279384A (en) | Wind turbine cabin wind speed-based method and device for calculating wind speed of incoming flow | |
| CN112862274A (en) | WRF-LES and Deepar combined wind power prediction method | |
| CN113626990A (en) | Wind turbine generator power curve verification method based on wind power prediction anemometer tower |
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 |
Application publication date: 20170510 |
|
| RJ01 | Rejection of invention patent application after publication |