CN105389634A - Combined short-term wind power prediction system and method - Google Patents
Combined short-term wind power prediction system and method Download PDFInfo
- Publication number
- CN105389634A CN105389634A CN201510866087.5A CN201510866087A CN105389634A CN 105389634 A CN105389634 A CN 105389634A CN 201510866087 A CN201510866087 A CN 201510866087A CN 105389634 A CN105389634 A CN 105389634A
- Authority
- CN
- China
- Prior art keywords
- module
- prediction
- wind
- wind power
- power
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a combined short-term wind power prediction system and method. The system includes a meteorological application decision support module, a wind power combined prediction module, a power prediction correction module and a real-time communication module. Based on data acquired by the meteorological application decision support module, a minimum variance combined prediction method is used for combining a physical prediction module and a statistical prediction module for prediction to obtain a combined prediction value through the wind power combined prediction module, the power prediction correction module combines the acquired data for error analysis and corrects the combined prediction value, and the corrected combined prediction value is uploaded to a central control center and a dispatching department through the real-time communication module. The invention effectively integrates the advantages of the physical prediction module and the statistical prediction module, the prediction accuracy is greatly improved, and the development of wind power prediction is facilitated.
Description
Technical field
The present invention relates to wind power prediction field, more particularly, relate to a kind of combined type short-term wind-electricity power prognoses system and method.
Background technology
In recent years, the development of wind-power electricity generation is more and more rapider.According to " Development of Wind Power In China report 2014 " statistics of regenerative resource Professional Committee of Circular Economy in China association (CREIA), national installed capacity of wind-driven power is increased to 91413MW.Along with developing rapidly of wind-power electricity generation, grid-connectedly become the study hotspot making full use of wind-powered electricity generation, because the output power of wind-powered electricity generation depends on wind speed, for the undulatory property of wind speed, intermittence and randomness, serious impact will certainly be brought to the stability of electrical network, and can affect the quality of power supply of electrical network, so short-term wind power prediction is particularly important accurately.
Find by prior art documents, Chinese Patent Application No. is: 201410155445.7, name is called a kind of wind power prediction combined method and system, this application proposes to be predicted by time series method and BP artificial neural network method, then predicting the outcome of obtaining is utilized to set up new forecast model again, finally obtain the predicted value of wind power, but this system utilizes merely statistical forecast module, also do not have accurate error correction systems, precision of prediction can not meet current higher demand.Therefore, how solving the above problems, is problem demanding prompt solution.
Summary of the invention
The object of the present invention is to provide a kind of combined type short-term wind-electricity power prognoses system.
Another object of the present invention is to provide a kind of combined type short-term wind power forecast method coordinating said system.The present invention can by setting up the short-term wind-electricity power prognoses system based on numerical weather forecast, utilize minimum variance combined method that physics predicts module and statistical forecast module are carried out combined prediction, substantially increase precision of prediction, and have simple and practical, respond advantage rapidly, be conducive to the development of wind power prediction.
For realizing above-mentioned object, a kind of combined type short-term wind-electricity power prognoses system of the present invention, it comprises: meteorological application decision support module, obtains history wind power data, numerical weather forecast data, in real time Internet data and Feng Ta observatory data; Wind power combined prediction module, be connected to meteorological application decision support module, be made up of forecasting model database and prediction algorithm storehouse, physics predicts module and statistical forecast module is provided with in forecasting model database, described physics predicts module is connected with algorithms library respectively with statistical forecast module, and the predicted value obtained from physics predicts module and statistical forecast module is respectively carried out the wind power combining to predict following 72 hours by algorithms library; Power prediction correcting module, be connected to wind power combined prediction module and meteorological application decision support module, according to the wind power historical data obtained from meteorological application decision support module, predicting the outcome of wind power combined prediction module acquisition is revised; Real-time communication module, is connected to power prediction correcting module, and the correction result that power prediction correcting module obtains is real-time transmitted to control center.
System of the present invention forms whole prognoses system by meteorological application decision support module, wind power combined prediction module, power prediction correcting module and real-time communication module, wind power combined prediction module and meteorological application decision support module is connected respectively by power prediction correcting module, can according to the wind power historical data obtained from meteorological application decision support module, predicting the outcome of wind power combined prediction module acquisition is revised, predicated error is reduced, the high request of system prediction precision can be met.
For realizing above-mentioned object, a kind of combined type short-term wind power forecast method of the present invention, it comprises the following steps:
1. history wind power data, numerical weather forecast data, in real time Internet data and Feng Ta observatory data are obtained;
2. according to the data that step one obtains, adopt variance minimum combination predicted method that physics predicts module and statistical forecast module are carried out combined prediction, draw wind power prediction value;
3. according to the data that step one obtains, error analysis is carried out to wind power prediction value, final wind power prediction value is drawn to error correction.
Further improvement project, above-mentioned combined type short-term wind power forecast method, the prediction steps of physics predicts module comprises: step one: try to achieve wind speed on the corresponding axial fan hub of wind energy turbine set by wind speed altitude conversion model, wind speed space transform models and Jensen model; Step 2: the data that integrating step one obtains, draws wind power prediction value with wind speed-powertrace.
The prediction steps of above-mentioned physics predicts module, the Jensen model described in step 2 is under wake effect, and on same wind direction, distance upwind blower fan is that the blower fan actual wind speed expression formula of X is as follows:
Wherein,
represent the natural wind speed without blower fan,
represent the thrust coefficient of Wind turbines, K is wake flow descent coefficient, and X is on same wind direction, the distance between blower fan to be asked and upwind blower fan, and R is blower fan wind wheel blade radius to be asked.
The prediction steps of above-mentioned physics predicts module, described wind speed altitude conversion model is the mathematical model adopting inverse distance square to carry out space interpolation, and this mathematical model is:
Wherein,
represent the wind speed interpolation at x place,
then represent former space x
iplace's wind speed.
for
Wherein
get Euclidean distance.
The prediction steps of above-mentioned physics predicts module, described wind speed space transform models is the mathematical model adopting wind vertical trimming power law, and this mathematical model is:
Wherein,
be the i-th Fans respective heights air speed value,
with
for corresponding wind speed under known altitude in anemometer tower data and this height,
it is the i-th Fans blower fan height
for wind shear exponent.
Further improvement project, above-mentioned combined type short-term wind power forecast method, the prediction steps of described statistical forecast module comprises: step one: with the application Mean Impact Value of BP neural computing each input variable, and to sort the input item for filtering out appreciable impact on its numerical value; Step 2: utilize similar sample clustering analytical approach, to adapt to Statistical Prediction Model in the situation step 3 larger to the larger predicated error of sample changed: adopt genetic algorithm to be optimized the initial weight of neural network every layer and threshold value, reach global optimizing.
Further improvement project, above-mentioned combined type short-term wind power forecast method, adopt variance minimum combination predicted method that physics predicts module and statistical forecast module are carried out combined prediction in step 2, j moment performance number predicted, i-th model predict the outcome for
, in j moment real power value be
, the weight coefficient of i-th model is
, then
the following constraint condition of demand fulfillment:
In a jth moment, power prediction value is:
In a jth moment, the error of power prediction is:
If number of samples is n, objective function and the straint optimation of variance minimum combination predicted method are expressed as follows shown in formula:
Wherein, the δ j wind speed represented on wind indicator is transformed into the wind speed on fan blade, and j represents the δ in j moment.Z is objective function, represents the minimum value of the wind speed δ quadratic sum on fan blade.
Above-mentioned combined type short-term wind power forecast method, described objective function is unfolded as follows formula:
Wherein,
for predicting the outcome of j moment i-th model, in j moment real power value be
,
the wind speed on fan blade is transformed into for the wind speed on the wind indicator of j moment i-th model,
it is the weight coefficient of i-th model.
Above-mentioned combined type short-term wind power forecast method, variance minimum combination prediction in
tthe individual moment does not stop to upgrade, along with the carrying out in prediction moment, right
do not stop to dynamically update.
Method of the present invention adopts variance minimum combination predicted method that physics predicts module and statistical forecast module are carried out combined prediction, adopt Genetic Algorithm Optimized Neural Network initial value, dynamically update weight coefficient, and weight coefficient is retrained, select the performance that rational weight coefficient is conducive to improving model, reduce predicated error; Simultaneously can effectively comprehensive physical prediction module and the single advantage of statistical forecast module, substantially increase precision of prediction; The present invention also have simple and practical, respond advantage rapidly, be conducive to the development of wind power prediction.
Accompanying drawing explanation
Below in conjunction with the specific embodiment in accompanying drawing, the present invention is described in further detail, but does not form any limitation of the invention.
Fig. 1 is the structural representation of present system;
Fig. 2 is the process flow diagram of the inventive method;
Fig. 3 is the prediction process flow diagram of physics predicts module of the present invention;
Fig. 4 is the prediction process flow diagram of statistical forecast module of the present invention;
Fig. 5 is minimum variance combined prediction curve map of the present invention.
Embodiment
As shown in Figure 1, a kind of combined type short-term wind-electricity power prognoses system, it comprises the meteorological application decision support module that can obtain history wind power data, numerical weather forecast data, in real time Internet data and Feng Ta observatory data; Wind power combined prediction module, be connected to meteorological application decision support module, be made up of forecasting model database and prediction algorithm storehouse, physics predicts module and statistical forecast module is provided with in forecasting model database, described physics predicts module is connected with algorithms library respectively with statistical forecast module, and the predicted value obtained from physics predicts module and statistical forecast module is respectively carried out the wind power combining to predict following 72 hours by algorithms library; Power prediction correcting module, be connected to wind power combined prediction module and meteorological application decision support module, according to the wind power historical data obtained from meteorological application decision support module, predicting the outcome of wind power combined prediction module acquisition is revised; Real-time communication module, is connected to power prediction correcting module, and the correction result that power prediction correcting module obtains is real-time transmitted to control center.
As shown in Figure 2, a kind of combined type short-term wind power forecast method, it comprises the following steps: first, obtains history wind power data, numerical weather forecast data, in real time Internet data and Feng Ta observatory data; Secondly, according to the data that step one obtains, adopt variance minimum combination predicted method that physics predicts module and statistical forecast module are carried out combined prediction, draw wind power prediction value; Finally, according to real-time Internet data and predicted data, error analysis is carried out to wind power prediction value, final wind power prediction value is drawn to error correction.
As shown in Figure 3, the prediction steps of physics predicts module comprises: step one: try to achieve wind speed on the corresponding axial fan hub of wind energy turbine set by wind speed altitude conversion model, wind speed space transform models and Jensen model; Step 2: the data that integrating step one obtains, draws wind power prediction value with wind speed-powertrace.And in the prediction steps of physics predicts module, wind speed altitude conversion model, wind speed space transform models and Jensen model are as follows:
Wind speed altitude conversion model
Wherein,
represent the wind speed interpolation at x place,
then represent xi place, former space wind speed.
for
wherein
get Euclidean distance;
Wind speed space transform models
Wherein,
be the i-th Fans respective heights air speed value,
with
for corresponding wind speed under known altitude in anemometer tower data and this height,
it is the i-th Fans blower fan height
for wind shear exponent.
Jensen model is under wake effect, and on same wind direction, distance upwind blower fan is that the blower fan actual wind speed expression formula of X is as follows:
Wherein,
represent the natural wind speed without blower fan,
represent the thrust coefficient of Wind turbines, K is wake flow descent coefficient, and X is on same wind direction, the distance between blower fan to be asked and upwind blower fan, and R is blower fan wind wheel blade radius to be asked.
By Jensen model; obtain the actual numerical value of wind speed, according to the wind speed-powertrace of each blower fan self, wind speed powertrace generally: when wind speed is less than the incision wind speed of blower fan; fan parking; power is 0, and wind speed is greater than incision wind speed, when being less than cut-out wind speed; some power of fan be follow the wind speed 3 powers be directly proportional; when being greater than cut-out wind speed, fan parking, power is 0.The function that wind speed-powertrace and wind speed and power are formed, then obtain corresponding output power predicted value according to the value of wind speed.
As shown in Figure 4, the prediction steps of statistical forecast module comprises: step one: with the application Mean Impact Value of BP neural computing each input variable, and to sort the input item for filtering out appreciable impact on its numerical value; Step 2: utilize similar sample clustering analytical approach, to adapt to Statistical Prediction Model in the situation larger to the larger predicated error of sample changed; Step 3: by Genetic Algorithm Optimized Neural Network initial value, trains history wind power data, obtains wind power prediction value; Using the input variable of the data such as wind speed, wind direction in numerical weather forecast and Feng Ta observatory data as BP Net work, by the application Mean Impact Value of each input variable of BP neural computing, and its numerical value is sorted the input item for filtering out appreciable impact; And adopt that genetic algorithm is optimized the initial weight of neural network every layer and threshold value, global optimizing, the technique effect of the global optimum reached.
Refer to obtaining training pattern with training set training network to MIV, then each training sample input argument value in training set is increased respectively and reduces 10%, the sample set that formation two is new respectively, the sample set that two are newly formed is emulated in the model trained by raw data as simulation sample collection, obtain the simulation result of two data sets, the difference of two data set Output simulation results, changing value (the IV after being this independent variable of variation, Output rusults had an impact, Impactvalue), finally changing value is on average got off to draw the MIV value of this independent variable for dependent variable according to observation number of cases.To the computing that each independent variable carries out above, finally sort for each independent variable according to the MIV value of each independent variable, obtain the relative effect size of each independent variable for dependent variable, and obtain the influence value of each independent variable.
Have employed the similar sample clustering method centered by predicted data sample.By forecast sample and training data vector quantization, by vectorial similarity system design, in training data, filter out the training data composing training collection similar to forecast sample, and after obtaining model by training, predicted data sample is predicted.
And adopt variance minimum combination predicted method, physics predicts module and statistical forecast block combiner are predicted, its objective function is as follows:
Wherein,
for predicting the outcome of j moment i-th model, in j moment real power value be
,
the wind speed on fan blade is transformed into for the wind speed on the wind indicator of j moment i-th model,
it is the weight coefficient of i-th model.
Objective function and straint optimation expression formula are following formula:
Above formula asks extreme value, considers the Lagrangian function of the problems referred to above, asks partial derivative and then obtain weight coefficient.In the prediction of variance minimum combination, t moment does not stop to upgrade, and along with the carrying out in prediction moment, does not stop to dynamically update to wi.
Wait in the specific implementation in invention, for certain wind energy turbine set, the numerical weather forecast data pattern that this wind energy turbine set adopts is WRF pattern (WeatherResearchandForecastingModel); Wind energy turbine set actual go out force data provided by grid company traffic department, the field chosen is that 1# main transformer high-pressure side has work value, and data are 15 minutes points.The observation data time is the actual operating data of 2013-01-0100:00:00 to 2013-07-3123:45:00, half a year.The longitude and latitude of employing numerical weather forecast data NWP point is:
Table 1 numerical weather forecast data NWP point longitude and latitude
| Longitude | 108.42 | 108.39 | 108.37 |
| Latitude | 18.79 | 19.02 | 19.25 |
The temporal resolution of NWP data is 15min, and spatial resolution is 27km.This wind energy turbine set rectification campaign field blower fan adds up to 24, and blower fan single-machine capacity is 1500kW, and wind rating is 12m/s, and blower fan incision wind speed is 3m/s, and cut-out wind speed is 20m/s, and hub height is 70m.
By n matching of putting above, algorithm case determines that (n+1)th combining weights combines.Minimum variance combined prediction curve as shown in Figure 3.
As shown in Figure 5, minimum variance combinatorial forecast can utilize the output of wind electric field time, adjustment subsequent combination weights, and reduces follow-up error according to the information of predicated error above.This test adopts the information of front 8 time points to carry out matching to Combining weights, the namely data of the first two hour of future position, through Experimental Comparison compared with first 1 hour and first 3 hours, within first 2 hours, can adjust to follow-up error preferably, also illustrate that output of wind electric field temporal correlation is the strongest in 2 hours, by calculating, the root-mean-square error (RMSE, root-mean-squareerror) that can obtain minimum variance combined prediction is 15.26%.
In sum, the present invention, as instructions and diagramatic content, makes actual sample and through repeatedly using test, and from the effect using test, provable the present invention can reach its desired object, and practical value is unquestionable.Above illustrated embodiment is only used for conveniently illustrating the present invention, not any pro forma restriction is done to the present invention, have in any art and usually know the knowledgeable, if do not depart from the present invention carry in the scope of technical characteristic, utilize the Equivalent embodiments that the done local of disclosed technology contents is changed or modified, and do not depart from technical characteristic content of the present invention, all still belong in the scope of the technology of the present invention feature.
Claims (10)
1. a combined type short-term wind-electricity power prognoses system, is characterized in that comprising:
Meteorological application decision support module, obtains history wind power data, numerical weather forecast data, in real time Internet data and Feng Ta observatory data;
Wind power combined prediction module, be connected to meteorological application decision support module, be made up of forecasting model database and prediction algorithm storehouse, physics predicts module and statistical forecast module is provided with in forecasting model database, described physics predicts module is connected with algorithms library respectively with statistical forecast module, and the predicted value obtained from physics predicts module and statistical forecast module is respectively carried out the wind power combining to predict following 72 hours by algorithms library;
Power prediction correcting module, be connected to wind power combined prediction module and meteorological application decision support module, according to the wind power historical data obtained from meteorological application decision support module, predicting the outcome of wind power combined prediction module acquisition is revised;
Real-time communication module, is connected to power prediction correcting module, and the correction result that power prediction correcting module obtains is real-time transmitted to control center.
2. a combined type short-term wind power forecast method, is characterized in that comprising the following steps:
1. history wind power data, numerical weather forecast data, in real time Internet data and Feng Ta observatory data are obtained;
2. according to the data that step one obtains, adopt variance minimum combination predicted method that physics predicts module and statistical forecast module are carried out combined prediction, draw wind power combined prediction value;
3. according to the data that step one obtains, error analysis is carried out to wind power combined prediction value, final wind power prediction value is drawn to error correction.
3. combined type short-term wind power forecast method according to claim 2, is characterized in that: the prediction steps of described physics predicts module comprises:
Step one: try to achieve wind speed on the corresponding axial fan hub of wind energy turbine set by wind speed altitude conversion model, wind speed space transform models and Jensen model;
Step 2: the data that integrating step one obtains, draws wind power prediction value with wind speed-powertrace.
4. combined type short-term wind power forecast method according to claim 3, is characterized in that: in step 2, and described improvement Jensen model is under wake effect, and on same wind direction, distance upwind blower fan is that the blower fan actual wind speed expression formula of X is as follows:
Wherein,
represent the natural wind speed without blower fan,
represent the thrust coefficient of Wind turbines, K is wake flow descent coefficient, and X is on same wind direction, the distance between blower fan to be asked and upwind blower fan, and R is blower fan wind wheel blade radius to be asked.
5. combined type short-term wind power forecast method according to claim 3, is characterized in that: described wind speed altitude conversion model is the mathematical model adopting inverse distance square to carry out space interpolation, and this mathematical model is:
Wherein,
represent the wind speed interpolation at x place,
then represent former space x
iplace's wind speed;
for
wherein
get Euclidean distance.
6. combined type short-term wind power forecast method according to claim 3, is characterized in that: described wind speed space transform models is the mathematical model adopting wind vertical trimming power law, and this mathematical model is:
Wherein,
be the i-th Fans respective heights air speed value,
with
for corresponding wind speed under known altitude in anemometer tower data and this height,
it is the i-th Fans blower fan height
for wind shear exponent.
7. combined type short-term wind power forecast method according to claim 2, is characterized in that: the prediction steps of described statistical forecast module comprises:
Step one: with the application Mean Impact Value of BP neural computing each input variable, and its numerical value is sorted the input item for filtering out appreciable impact;
Step 2: utilize similar sample clustering analytical approach, to adapt to statistical forecast module in the situation larger to the larger predicated error of sample changed;
Step 3: adopt genetic algorithm to be optimized the initial weight of neural network every layer and threshold value, history wind power data are trained, obtains wind power prediction value.
8. according to the arbitrary described combined type short-term wind power forecast method of claim 2 to 7, it is characterized in that: adopt variance minimum combination predicted method that physics predicts module and statistical forecast module are carried out combined prediction in step 2, set up model j moment performance number being carried out to combined prediction:
Wherein, i-th model predict the outcome for
, in j moment real power value be
, the weight coefficient of i-th model is
, then
the following constraint condition of demand fulfillment:
In a jth moment, the error of power prediction is:
If number of samples is n, objective function and the straint optimation of variance minimum combination predicted method are expressed as follows shown in formula:
Wherein, the δ j wind speed represented on wind indicator is transformed into the wind speed on fan blade, and j represents the δ in j moment; Z is objective function, represents the minimum value of the wind speed δ quadratic sum on fan blade.
9. combined type short-term wind power forecast method according to claim 8, is characterized in that: described objective function is unfolded as follows formula:
Wherein,
for predicting the outcome of j moment i-th model, in j moment real power value be
,
the wind speed on fan blade is transformed into for the wind speed on the wind indicator of j moment i-th model,
it is the weight coefficient of i-th model.
10. combined type short-term wind power forecast method according to claim 8, is characterized in that: in the prediction of variance minimum combination
tthe individual moment does not stop to upgrade, along with the carrying out in prediction moment, right
do not stop to dynamically update.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510866087.5A CN105389634A (en) | 2015-12-01 | 2015-12-01 | Combined short-term wind power prediction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510866087.5A CN105389634A (en) | 2015-12-01 | 2015-12-01 | Combined short-term wind power prediction system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105389634A true CN105389634A (en) | 2016-03-09 |
Family
ID=55421900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510866087.5A Pending CN105389634A (en) | 2015-12-01 | 2015-12-01 | Combined short-term wind power prediction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105389634A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787813A (en) * | 2016-03-21 | 2016-07-20 | 广西电网有限责任公司电力科学研究院 | Short-term wind power prediction method based on covariance |
| CN105930933A (en) * | 2016-04-26 | 2016-09-07 | 华北电力科学研究院有限责任公司 | Wind power plant theoretical power curve determination method and device |
| CN105930900A (en) * | 2016-05-09 | 2016-09-07 | 华北电力大学 | Method and system for predicting hybrid wind power generation |
| CN106383932A (en) * | 2016-09-05 | 2017-02-08 | 上海电机学院 | Wind power prediction method |
| CN107017668A (en) * | 2017-03-20 | 2017-08-04 | 国网浙江省电力公司嘉兴供电公司 | A kind of virtual plant power regulating method based on wind energy and luminous energy |
| CN107069832A (en) * | 2017-03-20 | 2017-08-18 | 国网浙江省电力公司嘉兴供电公司 | A kind of virtual plant power regulating method based on tide energy and wind energy |
| CN107067099A (en) * | 2017-01-25 | 2017-08-18 | 清华大学 | Wind power probability forecasting method and device |
| CN108846499A (en) * | 2018-04-13 | 2018-11-20 | 中国电力科学研究院有限公司 | A kind of meteorological element ultra-short term prediction method and device |
| CN110489852A (en) * | 2019-08-14 | 2019-11-22 | 北京天泽智云科技有限公司 | Improve the method and device of the wind power system quality of data |
| CN110619455A (en) * | 2019-08-09 | 2019-12-27 | 南京因泰莱电器股份有限公司 | Method for realizing reusable wind power generation power prediction model |
| CN111325376A (en) * | 2018-12-14 | 2020-06-23 | 北京金风科创风电设备有限公司 | Wind speed prediction method and device |
| CN117039895A (en) * | 2023-10-09 | 2023-11-10 | 西安热工研究院有限公司 | Wind power prediction method and system for energy storage auxiliary black start |
| WO2024007840A1 (en) * | 2022-07-07 | 2024-01-11 | 中国长江三峡集团有限公司 | Method and apparatus for predicting reaming torque in horizontal directional drilling, device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
| CN201813161U (en) * | 2010-07-16 | 2011-04-27 | 北京中科伏瑞电气技术有限公司 | Wind power forecasting system |
| CN102269124A (en) * | 2011-06-30 | 2011-12-07 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
| 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 |
| CN102570453A (en) * | 2012-01-06 | 2012-07-11 | 甘肃省电力公司风电技术中心 | Short-term wind power prediction method and system based on multiple numerical weather prediction sources |
| CN105046349A (en) * | 2015-06-25 | 2015-11-11 | 广东电网有限责任公司电力科学研究院 | Wind power prediction method considering wake effect |
-
2015
- 2015-12-01 CN CN201510866087.5A patent/CN105389634A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
| CN201813161U (en) * | 2010-07-16 | 2011-04-27 | 北京中科伏瑞电气技术有限公司 | Wind power forecasting system |
| CN102269124A (en) * | 2011-06-30 | 2011-12-07 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
| 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 |
| CN102570453A (en) * | 2012-01-06 | 2012-07-11 | 甘肃省电力公司风电技术中心 | Short-term wind power prediction method and system based on multiple numerical weather prediction sources |
| CN105046349A (en) * | 2015-06-25 | 2015-11-11 | 广东电网有限责任公司电力科学研究院 | Wind power prediction method considering wake effect |
Non-Patent Citations (1)
| Title |
|---|
| 李俊豪: "《风电场风速及风电功率短期预测方法的研究》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787813A (en) * | 2016-03-21 | 2016-07-20 | 广西电网有限责任公司电力科学研究院 | Short-term wind power prediction method based on covariance |
| CN105930933B (en) * | 2016-04-26 | 2019-05-31 | 华北电力科学研究院有限责任公司 | Wind power plant theoretical power curve determines method and device |
| CN105930933A (en) * | 2016-04-26 | 2016-09-07 | 华北电力科学研究院有限责任公司 | Wind power plant theoretical power curve determination method and device |
| CN105930900A (en) * | 2016-05-09 | 2016-09-07 | 华北电力大学 | Method and system for predicting hybrid wind power generation |
| CN105930900B (en) * | 2016-05-09 | 2018-02-27 | 华北电力大学 | The Forecasting Methodology and system of a kind of hybrid wind power generation |
| CN106383932A (en) * | 2016-09-05 | 2017-02-08 | 上海电机学院 | Wind power prediction method |
| CN107067099B (en) * | 2017-01-25 | 2020-06-19 | 清华大学 | Wind power probability prediction method and device |
| CN107067099A (en) * | 2017-01-25 | 2017-08-18 | 清华大学 | Wind power probability forecasting method and device |
| CN107017668A (en) * | 2017-03-20 | 2017-08-04 | 国网浙江省电力公司嘉兴供电公司 | A kind of virtual plant power regulating method based on wind energy and luminous energy |
| CN107069832A (en) * | 2017-03-20 | 2017-08-18 | 国网浙江省电力公司嘉兴供电公司 | A kind of virtual plant power regulating method based on tide energy and wind energy |
| CN108846499A (en) * | 2018-04-13 | 2018-11-20 | 中国电力科学研究院有限公司 | A kind of meteorological element ultra-short term prediction method and device |
| CN108846499B (en) * | 2018-04-13 | 2022-10-11 | 中国电力科学研究院有限公司 | Ultra-short-term meteorological element prediction method and device |
| CN111325376A (en) * | 2018-12-14 | 2020-06-23 | 北京金风科创风电设备有限公司 | Wind speed prediction method and device |
| CN110619455A (en) * | 2019-08-09 | 2019-12-27 | 南京因泰莱电器股份有限公司 | Method for realizing reusable wind power generation power prediction model |
| CN110489852A (en) * | 2019-08-14 | 2019-11-22 | 北京天泽智云科技有限公司 | Improve the method and device of the wind power system quality of data |
| WO2024007840A1 (en) * | 2022-07-07 | 2024-01-11 | 中国长江三峡集团有限公司 | Method and apparatus for predicting reaming torque in horizontal directional drilling, device and storage medium |
| CN117039895A (en) * | 2023-10-09 | 2023-11-10 | 西安热工研究院有限公司 | Wind power prediction method and system for energy storage auxiliary black start |
| CN117039895B (en) * | 2023-10-09 | 2024-01-26 | 西安热工研究院有限公司 | Wind power prediction method and system for energy storage auxiliary black start |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105389634A (en) | Combined short-term wind power prediction system and method | |
| Shi et al. | Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features | |
| Yan et al. | Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine | |
| CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
| CN109086928A (en) | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model | |
| CN103401236B (en) | A kind of wind energy turbine set unit group technology based on flow correlation of wind power farm | |
| CN102496927A (en) | Wind power station power projection method based on error statistics modification | |
| CN104978608B (en) | A kind of wind electric powder prediction device and prediction technique | |
| CN106505631B (en) | Intelligent wind power wind power prediction system | |
| CN105447572A (en) | Wind power prediction system and method based on neural network optimized by genetic algorithm | |
| CN103942736B (en) | A kind of wind power plant multimachine equivalent modeling method | |
| CN106650784A (en) | Feature clustering comparison-based power prediction method and device for photovoltaic power station | |
| CN109523084A (en) | A kind of ultrashort-term wind power prediction method based on pivot analysis and machine learning | |
| CN109274121B (en) | Wind power plant control parameter optimization method and system | |
| CN106022538B (en) | Photovoltaic power generation prediction method based on K-means clustering improved generalized weather | |
| CN104732296A (en) | Modeling method for distributed photovoltaic output power short-term prediction model | |
| CN103117546A (en) | Ultrashort-term slide prediction method for wind power | |
| CN102184337A (en) | Dynamic combination analysis method of new energy generating capacity influenced by meteorological information | |
| CN110766200A (en) | Method for predicting generating power of wind turbine generator based on K-means mean clustering | |
| CN106875037A (en) | Wind-force Forecasting Methodology and device | |
| CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
| CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
| CN104732300A (en) | Neural network wind power short-term forecasting method based on fuzzy partition theory | |
| CN105303250A (en) | Wind power combination prediction method based on optimal weight coefficient | |
| CN103996079A (en) | Wind power weighting predication method based on conditional probability |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160309 |
|
| RJ01 | Rejection of invention patent application after publication |