CN108808671A - A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant - Google Patents
A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant Download PDFInfo
- Publication number
- CN108808671A CN108808671A CN201810716587.4A CN201810716587A CN108808671A CN 108808671 A CN108808671 A CN 108808671A CN 201810716587 A CN201810716587 A CN 201810716587A CN 108808671 A CN108808671 A CN 108808671A
- Authority
- CN
- China
- Prior art keywords
- schemes
- wind speed
- wind
- data processing
- prediction system
- 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
-
- 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
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM methods of wind power plant based on WRF patterns and random forests algorithm.The method is as follows：Based on WRF patterns, choose the meteorological elements such as wind speed, wind direction at 6 kinds of different Different Boundary Layer Parameterization Schemes forecast 70m height, again using a variety of Different Boundary Layer Parameterization Schemes come DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed, the wind speed of each single Different Boundary Layer Parameterization Schemes forecast and anemometer tower are surveyed into air speed data, DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model is established using random forests algorithm, the wind speed of wind power plant is forecast.The present invention provides a kind of science, effective method for wind power plant short-term wind speed prediction, have the characteristics that generalization ability is strong, stability is good, precision of prediction is high, wind power prediction accuracy is improved, the scheduling and operation of electric system are conducive to, there is certain practical value.
Description
Technical field
The present invention relates to a kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM methods of wind power plant, belong to wind power prediction field.
Background technology
With the fast development of global economy, it is extremely urgent to seek clean reproducible energy for fossil class A fuel A increasingly depleted.
For wind energy as clean reproducible energy, Technical comparing is ripe, and cost constantly declines, and the excessive exploitation that can not only alleviate the energy is asked
Topic, also there is outstanding advantage in terms of environmental protection.In wind-power electricity generation, the intermittence of wind energy is to restrict the most root of Wind Power Development
This reason.Wind energy stock has prodigious randomness, indirect, and the output of wind turbine and wind speed are three times in the movement of air
Side is approximate directly proportional, to which wind power output power has prodigious fluctuation and randomness, to the safe and stable operation band of power grid
To influence.Therefore the accuracy of forecasting wind speed is that wind turbine output predicts extremely important key factor, especially under complicated landform
Forecasting wind speed research have great importance.
Currently, forecasting short-term wind speed frequently with meso-scale models such as WRF.For complicated landform area, wind speed is pre-
The accuracy rate of report is always difficult point and emphasis, variant according to the influence of the factors such as landform, roughness of ground surface, barrier, meteorology
Position wind speed necessarily has certain difference.In wind-resources assessment, the turbulent phenomenon of wind field needs to pay special attention to, can be to wind turbine
The runnability of group adversely affects.Turbulent flow belongs to irregular movement, speed, direction, pressure, temperature on turbulent flow every bit etc.
The random fluctuations such as physical characteristic.And turbulent flow processes need Different Boundary Layer Parameterization Schemes to describe, different Different Boundary Layer Parameterization sides
Case has the advantage that it stresses, and often has different manifestations in different zones, different Different Boundary Layer Parameterization Schemes can be used to come more
Mend its limitation.For under complicated landform, different boundary layer has feasibility in the case that various turbulent flow processes are all likely to occur.
Therefore, in application WRF patterns carry out the analog study of wind speed forecasting, it is necessary to select suitable Different Boundary Layer Parameterization Schemes.But
When forecasting wind speed using single Different Boundary Layer Parameterization Schemes, even if being combined best Parameterization Scheme very possible with this area
It is completely not applicable in other areas.And DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM then provides to solve uncertain problem existing for single deterministic prediction
One new approach combines different forecasting models to a variety of forecast results of wind speed, is better than to obtain one
The forecast result of single alternative forecast.Therefore, a variety of Different Boundary Layer Parameterization Schemes can be used and carry out the gas such as DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed and direction
Image data obtains preferable forecast result.
Invention content
The present invention in order to solve the problems in the existing technology, provide it is a kind of being based on WRF patterns, choose 6 kinds it is different
Different Boundary Layer Parameterization Schemes carry out DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed, and by the wind speed of each single Different Boundary Layer Parameterization Schemes forecast and survey wind speed
Data establish the forecasting procedure of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model using random forests algorithm.
In order to achieve the above object, technical solution proposed by the present invention is：A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM side of wind power plant
Method includes the following steps：
Step 1: acquisition wind power plant surveys air speed data, line number of going forward side by side Data preprocess；
Step 2: carrying out WRF mode scheme designs；
Step 3: choosing a variety of different Different Boundary Layer Parameterization Schemes and corresponding ground layer Parameterization Scheme.
Step 4: being based on WRF patterns, forecast that the meteorologies such as wind speed are wanted with a variety of different boundary layer parameter schemes of selection
Element, and carry out error analysis with measured data；
Step 5: by the wind speed of each single Different Boundary Layer Parameterization Schemes forecast and surveying wind speed number using random forests algorithm
According to establishing DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model, forecast to the wind speed of wind power plant.
Above-mentioned technical proposal is further designed to：A variety of different Different Boundary Layer Parameterization Schemes are equipped with six kinds,
Respectively YSU schemes, ACM2 schemes, QNSE schemes, MYNN2.5 schemes, MYJ schemes, BouLac schemes.
The corresponding ground layer Parameterization Scheme of six kinds of different Different Boundary Layer Parameterization Schemes is MM5Monin-
Obukhov schemes, Pleim-Xiu surface layer schemes, QNSE surface layer schemes, MYNN surface
Layer schemes, Monin-Obukhov schemes and MM5Monin-Obukhov schemes.
The WRF mode schemes use triple nested grids, and grid number is respectively 50 × 60,55 × 52,67 × 64.
Compared with prior art, the beneficial effects of the invention are as follows：
1, the deterministic prediction of single alternative only provides a kind of possibility of wind speed, and randomness is larger.And it uses a variety of
Different Boundary Layer Parameterization Schemes carry out DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed, solve uncertain problem existing for the deterministic prediction of single alternative,
Different forecasting models combines to a variety of forecast results of wind speed, is better than single alternative forecasting procedure to obtain one
Forecast result.
2, compared to the wind speed of single Different Boundary Layer Parameterization Schemes forecast, using DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method, the wind speed number of forecast
According to mean absolute error (MAE), root-mean-square error (RMSE), opposite mean absolute error (rMAE) and opposite root-mean-square error
(rRMSE) it is obviously reduced, prediction effect significantly improves.
3, compared with BP neural network DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM and equal ensemble forecast, WRF patterns are based on, by each single boundary layer
Parameterization Scheme forecast wind speed and anemometer tower survey air speed data, using random forests algorithm come establish DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model into
Sector-style electric field short-term wind speed prediction, error reduce, and precision higher is more preferable to the fitting effect for surveying wind speed.
Description of the drawings
Fig. 1 .WRF pattern simulation area schematics；
Fig. 2 DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM flow charts；
Fig. 3 survey air speed data distribution map；
Fig. 4 survey wind speed diurnal variation curve figure；
Fig. 5 actual measurement wind directions and prediction wind rose map distribution；
The forecasting wind speed effect of the power such as Fig. 6, three kinds of BP neural network, random forests algorithm aggregate manners.
Specific implementation mode
Below in conjunction with the accompanying drawings and specific embodiment the present invention is described in detail.
A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant of the present embodiment, its step are as follows,
1, acquisition wind power plant surveys air speed data, and data prediction is carried out in conjunction with periphery wind field data and historical data,
Pretreatment includes rejecting abnormalities value, is filled up etc. to missing data, obtains the air speed data after denoising, passes through integrality and conjunction
Rationality is examined.
2, WRF mode schemes are arranged
The WRF mode schemes design that the present embodiment is selected is as follows：Using triple nested grids, forecast area is as shown in Figure 1.
Integration cell design, grid number is respectively 50 × 60,55 × 52,67 × 64, horizontal grid resolution ratio be respectively 27km, 9km,
3km, grid element center point are located at 29.788 ° of N, 108.227 ° of E.Using 1 ° × 1 ° of the whole world, GFS forecast fields data conducts primary 6h
The initial field and lateral boundary condition of WRF patterns.WRF mode parameter Scheme Choices are：Microphysical processes scheme is WSM6 class ice
Hail scheme, long-wave radiation are RRTM schemes, and shortwave radiation is Dudhia schemes, and land surface emissivity uses Noah land surface schemes,
First and second heavy simulated domain of cumulus parameterization scheme selects shallow convection Kain-Fritsch (new Eta) scheme, and most interior
Layer region resolution ratio can parse Cumulus Convection Process, therefore without Cumulus parameterization.
3, Different Boundary Layer Parameterization Schemes are chosen
The present embodiment uses six kinds of Different Boundary Layer Parameterization Schemes, chooses respectively as follows：YSU schemes, ACM2 schemes, the side QNSE
Case, MYNN2.5 schemes, MYJ schemes, BouLac schemes.These PBL schemes have the advantage that oneself stresses, multiple for landform
These schemes have feasibility in the case that the miscellaneous various turbulent motion processes in area are all likely to occur.In WRF patterns, each
The Different Boundary Layer Parameterization Schemes used have corresponding ground layer scheme, have certain matching relationship, PBL scheme and
6 kinds of composite test schemes setting of ground layer scheme is shown in Table 1.
1 simulation test conceptual design of table
4, DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM flow chart
It is illustrated in figure 2 storm rainfall.Using certain wind power plant under complicated landform as research object, WRF patterns are based on, are chosen
The meteorological datas such as 6 kinds of different Different Boundary Layer Parameterization Schemes forecast wind speed and directions, the wind speed of more each single alternative forecast and survey
Wind tower surveys air speed data error；Again by the wind speed of each single Different Boundary Layer Parameterization Schemes forecast, using random forests algorithm
DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model is established, the wind speed of wind power plant is forecast.Will forecast air speed data and anemometer tower survey air speed data into
DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM feasibility and advantage are analyzed in row error analysis.
The feasibility of wind power plant short-term wind speed prediction is used for for the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of the verification present invention, the present embodiment to use
Chongqing wind power plant is research object, and the landform of wind power plant anemometer tower region is more complicated.Measured data comes from survey wind
The meteorological datas such as annual wind speed, the wind direction in 2011 acquired at tower 70m height, forecast data is with 6 kinds of different boundary layer parameters
For change scheme annual WRF data in 2011 as experimental data, data time resolution ratio is 10min.Selection 2011 1,4,7,
October, data were simulated as annual representative data.By last 3 days of each month in 4 month chosen, totally 1728
Group data as test sample collection, other number of days data in each month as training sample set, by MAE, RMSE, rMAE,
RRMSE indexs carry out evaluation and foreca effect.It includes following content to verify content：
1, wind farm wind velocity characteristic is analyzed
By the analysis to data, air speed data distribution at anemometer tower 70m height is as shown in figure 3, as seen from the figure, wind speed
It is concentrated mainly on 2-9m/s, wind energy distribution is more concentrated.The wind speed diurnal variation curve that monthly average obtains is as shown in figure 4, can by figure
Know：Daytime, wind speed was less than normal, and night wind speed is bigger than normal.When 3 to 17, wind speed is on a declining curve；When 17 to next day 3, wind speed is in bright
Aobvious ascendant trend.
2, it verifies and applies WRF model predictions wind farm wind velocity wind direction feasibilities under complicated landform
Wind rose map and 6 kinds of different boundary layer parameter program prediction wind rose map such as Fig. 5 institutes are surveyed at anemometer tower
Show.Actual measurement wind speed is mainly distributed within the scope of SE-S, and prevailing wind direction is SSE or SE, and wind direction relatively concentrates on prevailing wind direction, with locality
Climate characteristic is consistent.By air speed data distribution map and actual measurement wind rose map it is found that the wind direction is relatively stable, wind energy distribution
It more concentrates, is suitble to wind-power electricity generation.The wind speed profile of 6 kinds of Different Boundary Layer Parameterization Schemes prediction slightly has difference, but all integrated distributions
Within the scope of ESE-SSE, prevailing wind direction SE.The wind direction of WRF model predictions and the wind direction of anemometer tower actual measurement also slightly have difference, but have
Preferable consistency illustrates that WRF model predictions data can preferably react the meteorological elements such as wind speed, the wind direction of institute's survey region,
Prove that under MODEL OVER COMPLEX TOPOGRAPHY be feasible using the short-term wind speed of WRF model predictions wind power plants.
3, wind speed is forecast using the single Different Boundary Layer Parameterization Schemes of WRF patterns
Table 2 is 6 kinds of different Different Boundary Layer Parameterization Schemes WRF model predictions wind speed and actual measurement wind at anemometer tower 70m height
The error analysis of fast data.As shown in Table 2, the wind speed MAE of 6 kinds of Parameterization Schemes forecast is put down within the scope of 2.70-3.19m/s
Mean value is 2.89m/s；RMSE is within the scope of 3.23-3.81m/s, average value 3.47m/s；RMAE is in 43.84%-51.67%
In range, average value 46.90%, rRMSE is within the scope of 52.46%-61.83%, average value 56.34%, relatively square
Root error rRMSE and opposite mean absolute error rMAE are larger；Error it is larger be scheme 3 and scheme 5, error it is minimum be
Scheme 4.For total analysis, 6 kinds of Parameterization Schemes slightly have difference to the value of forecasting of wind speed, and wherein scheme 4 forecasts wind speed effect
Fruit is best, when needing to forecast wind speed using single alternative, optimal modeling scheme that can be using selection scheme 4 as pattern simulation.
But known by list data analysis, even if forecasting that wind speed, forecast wind speed are compared using single optimal Different Boundary Layer Parameterization Schemes
The error that anemometer tower surveys wind speed is still larger.Therefore, it cannot meet only with WRF pattern single alternatives forecast wind speed effect and want
It asks, WRF model predictions wind speed should be improved with this using a variety of Different Boundary Layer Parameterization Schemes of WRF patterns come DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed
Accuracy rate.
The single Different Boundary Layer Parameterization Schemes forecast wind speed of table 2WRF patterns and actual measurement air speed error analysis
4, using a variety of Different Boundary Layer Parameterization Schemes DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed
On the basis of the wind speed of each single Different Boundary Layer Parameterization Schemes forecast, it is pre- to establish set using random forests algorithm
Model is reported, wind farm wind velocity is forecast.Apply 6 kinds of Different Boundary Layer Parameterization Schemes forecast of random forests algorithm pair first herein
Wind speed into row set, it is poor to choose the single alternative value of forecasting further according to 2 evaluation index of table (MAE, RMSE, rMAE, rRMSE)
Two kinds of Different Boundary Layer Parameterization Schemes (i.e. scheme 3 and scheme 5) forecast wind speed, using random forests algorithm into row set.It will
The DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed result of above-mentioned 2 kinds of situations is compared and analyzed with anemometer tower measured data, specific as shown in table 3.By table
It is found that using a variety of Different Boundary Layer Parameterization Schemes DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed methods, each error criterion is obviously reduced lattice, and MAE is reduced
About 1.1m/s, RMSE reduce about 1.2m/s, and rMAE, which reduces about 18%, rRMSE, reduces about 20%.And according to evaluation
Index selects two kinds of poor Different Boundary Layer Parameterization Schemes of the value of forecasting to carry out DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed, forecast result also than it is single most
The wind speed effect of excellent Different Boundary Layer Parameterization Schemes forecast will be got well.That is two kinds of Different Boundary Layer Parameterization Schemes of arbitrary selection are pre- to gather
Wind speed, forecast result is reported to be got well than the wind speed effect of single optimal Different Boundary Layer Parameterization Schemes forecast.Illustrate using set
Forecasting procedure can more accurately reflect the meteorological elements such as institute's survey region wind speed, wind direction, improve the precision of wind speed forecasting.Cause
This, when using WRF model predictions wind speed, should use DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method to carry out wind speed forecasting.
3 DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM of table corrects wind speed and actual measurement air speed error analysis
5, verification establishes the superiority that DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model carries out wind power plant short-term wind speed prediction using random forests algorithm
DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM is carried out using equal ensemble forecast and BP neural network DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM to the wind speed of WRF model predictions to grind
Study carefully, by random forests algorithm, BP neural network and the wind speed forecasting result of 3 kinds of aggregate manners of power and actual measurement air speed data is waited to carry out
Comparative analysis, the results are shown in Figure 6.It can be seen from the figure that using the wind of single optimal Different Boundary Layer Parameterization Schemes forecast
Speed and the wind speed effect of equal ensemble forecast are poor, and use random forests algorithm and BP neural network DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM mode,
The wind speed result of forecast surveys air speed data closer to anemometer tower, and prediction effect is preferable.Therefore, in application WRF patterns into sector-style
When electric field short-term wind speed forecasting, should wind speed be forecast using DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method, more accurate wind speed be obtained, to improve wind speed
The precision of prediction.Meanwhile compared with BP neural network and equal ensemble are forecast, using random forests algorithm come the wind of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM
The closer actual measurement wind speed of speed.
Table 4 lists the error for surveying air speed data with anemometer tower using the air speed data of different sets mode DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM
Compare.As can be seen from the table, the air speed error ratio after DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM is carried out using random forests algorithm uses BP neural network
Air speed error result after being forecast with equal ensemble is small, illustrates to be better than it using random forests algorithm DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed mode
Its DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM wind speed mode, high to the precision of prediction of wind speed, the value of forecasting is preferable.
The air speed error of 4 three kinds of aggregate manners of table forecast
Technical scheme of the present invention is not limited to the various embodiments described above, all technical solutions obtained using equivalent replacement mode
It all falls in the scope of protection of present invention.
Claims (4)
1. a kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant, which is characterized in that include the following steps：
Step 1: acquisition wind power plant surveys air speed data, line number of going forward side by side Data preprocess；
Step 2: carrying out WRF mode scheme designs；
Step 3: choosing a variety of different Different Boundary Layer Parameterization Schemes and corresponding ground layer Parameterization Scheme.
Step 4: being based on WRF patterns, the meteorological elements such as wind speed are forecast with a variety of different boundary layer parameter schemes of selection, and
Error analysis is carried out with measured data；
Step 5: by the wind speed of each single Different Boundary Layer Parameterization Schemes forecast and air speed data is surveyed using random forests algorithm,
DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model is established, the wind speed of wind power plant is forecast.
2. the short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant according to claim 1, which is characterized in that the different boundary layer
Parameterization Scheme is equipped with six kinds, respectively YSU schemes, ACM2 schemes, QNSE schemes, MYNN2.5 schemes, MYJ schemes, BouLac
Scheme.
3. the short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant according to claim 2, which is characterized in that six kinds of different sides
The corresponding ground layer Parameterization Scheme of interlayer Parameterization Scheme is MM5Monin-Obukhov schemes, Pleim-Xiu
Surface layer schemes, QNSE surface layer schemes, MYNN surface layer schemes, Monin-Obukhov
Scheme and MM5Monin-Obukhov schemes.
4. the short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant according to claim 1, which is characterized in that the WRF mode schemes
Using triple nested grids, grid number is respectively 50 × 60,55 × 52,67 × 64.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810716587.4A CN108808671A (en) | 2018-07-03 | 2018-07-03 | A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810716587.4A CN108808671A (en) | 2018-07-03 | 2018-07-03 | A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108808671A true CN108808671A (en) | 2018-11-13 |
Family
ID=64074238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810716587.4A Pending CN108808671A (en) | 2018-07-03 | 2018-07-03 | A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108808671A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110535159A (en) * | 2019-07-25 | 2019-12-03 | 中国电力科学研究院有限公司 | A kind of method and system of scale energy-accumulating power station running unit fault pre-alarming |
| CN111027223A (en) * | 2019-12-18 | 2020-04-17 | 上海眼控科技股份有限公司 | Method and system for generating ensemble forecasting result, electronic device and storage medium |
| CN111324936A (en) * | 2018-11-29 | 2020-06-23 | 北京金风慧能技术有限公司 | Fan wind speed prediction method, computer readable storage medium and computing device |
| CN111967653A (en) * | 2020-07-22 | 2020-11-20 | 易天气(北京)科技有限公司 | Method for constructing airport runway wind forecasting model, forecasting method and forecasting system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750953A (en) * | 2013-12-26 | 2015-07-01 | 中国辐射防护研究院 | Method for simulating middle-and-small-scale airborne substance atmosphere transportation ensemble diffusion |
| WO2018013148A1 (en) * | 2016-07-15 | 2018-01-18 | University Of Connecticut | Systems and methods for outage prediction |
| US20180038994A1 (en) * | 2016-08-02 | 2018-02-08 | International Business Machines Corporation | Techniques to Improve Global Weather Forecasting Using Model Blending and Historical GPS-RO Dataset |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
-
2018
- 2018-07-03 CN CN201810716587.4A patent/CN108808671A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750953A (en) * | 2013-12-26 | 2015-07-01 | 中国辐射防护研究院 | Method for simulating middle-and-small-scale airborne substance atmosphere transportation ensemble diffusion |
| WO2018013148A1 (en) * | 2016-07-15 | 2018-01-18 | University Of Connecticut | Systems and methods for outage prediction |
| US20180038994A1 (en) * | 2016-08-02 | 2018-02-08 | International Business Machines Corporation | Techniques to Improve Global Weather Forecasting Using Model Blending and Historical GPS-RO Dataset |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
Non-Patent Citations (6)
| Title |
|---|
| WEIZHOU SHEN: "An EMD-RF Based Short-term Wind Power Forecasting Method", 《2018 IEEE 7TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE》 * |
| 丁煌: "基于WRF和SVM方法的风电场功率预报技术研究", 《高原气象》 * |
| 李欣海: "随机森林模型在分类与回归分析中的应用", 《应用昆虫学报》 * |
| 蔡子颖: "基于多种边界层方案的天津PM2.5集合预报试验", 《应用气象学报》 * |
| 贵州电网有限责任公司编: "《高原山区风电功率预测技术[M].》", 30 March 2017, 贵州大学出版社社 * |
| 贵志成: "不同边界层参数化方案对东亚夏季风气候模拟的对比研究", 《气象科学》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111324936A (en) * | 2018-11-29 | 2020-06-23 | 北京金风慧能技术有限公司 | Fan wind speed prediction method, computer readable storage medium and computing device |
| CN111324936B (en) * | 2018-11-29 | 2024-02-13 | 北京金风慧能技术有限公司 | Fan wind speed prediction method, computer readable storage medium and computing device |
| CN110535159A (en) * | 2019-07-25 | 2019-12-03 | 中国电力科学研究院有限公司 | A kind of method and system of scale energy-accumulating power station running unit fault pre-alarming |
| CN111027223A (en) * | 2019-12-18 | 2020-04-17 | 上海眼控科技股份有限公司 | Method and system for generating ensemble forecasting result, electronic device and storage medium |
| CN111967653A (en) * | 2020-07-22 | 2020-11-20 | 易天气(北京)科技有限公司 | Method for constructing airport runway wind forecasting model, forecasting method and forecasting system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| de Jong et al. | Estimating the impact of climate change on wind and solar energy in Brazil using a South American regional climate model | |
| Shboul et al. | A new ANN model for hourly solar radiation and wind speed prediction: A case study over the north & south of the Arabian Peninsula | |
| Liu et al. | Wind resource potential assessment using a long term tower measurement approach: A case study of Beijing in China | |
| CN105184423B (en) | A kind of wind power plant cluster wind speed forecasting method | |
| Olaofe | Review of energy systems deployment and development of offshore wind energy resource map at the coastal regions of Africa | |
| CN108808671A (en) | A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant | |
| Hereher et al. | Exploring the potential of solar, tidal, and wind energy resources in Oman using an integrated climatic-socioeconomic approach | |
| Tiang et al. | Technical review of wind energy potential as small-scale power generation sources in Penang Island Malaysia | |
| KR101383617B1 (en) | Method and apparatus for predicting daily solar radiation level | |
| Thorsteinsson et al. | Climate Change and Energy Systems | |
| Noman et al. | Comprehensive review of wind energy in Malaysia: Past, present, and future research trends | |
| Wu et al. | Synoptic analysis of extreme hourly precipitation in Taiwan during 2003–12 | |
| Yip | Statistical characteristics and mapping of near-surface and elevated wind resources in the Middle East | |
| Satyanarayana Gubbala et al. | Assessment of wind energy potential over India using high-resolution global reanalysis data | |
| Sun et al. | GIS‐based multiregional potential evaluation and strategies selection framework for various renewable energy sources: a case study of eastern coastal regions of China | |
| CN111666725A (en) | Anemometer tower planning and site selection method and system suitable for wind power plant with non-complex terrain | |
| Shreif et al. | Wind resource assessment for southern part of Libya: Case study of Hun | |
| Wang et al. | Comparing different boundary layer schemes of WRF by simulation the low-level wind over complex terrain | |
| Elliott et al. | Wind energy resource atlas of Mongolia | |
| CN112001090A (en) | Wind field numerical simulation method | |
| Tempa et al. | Assessment of solar energy potential using GIS and AHP approach: A case study of Bumthang Valley | |
| Mialhe et al. | On the determination of coherent solar climates over a tropical island with a complex topography | |
| MALAYSIA | Forecasting and mapping of extreme wind speed for 5 to 100-years return period in Peninsula Malaysia | |
| Yu et al. | An operational application of NWP models in a wind power forecasting demonstration experiment | |
| Kim et al. | Long-term wind resource mapping of Korean west-south offshore for the 2.5 GW offshore wind power project |
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: 20181113 |