CN112561149B - Wind power prediction method based on dynamic downscaling data fusion and statistical model - Google Patents
Wind power prediction method based on dynamic downscaling data fusion and statistical model Download PDFInfo
- Publication number
- CN112561149B CN112561149B CN202011435153.0A CN202011435153A CN112561149B CN 112561149 B CN112561149 B CN 112561149B CN 202011435153 A CN202011435153 A CN 202011435153A CN 112561149 B CN112561149 B CN 112561149B
- Authority
- CN
- China
- Prior art keywords
- wind
- wind speed
- historical
- data fusion
- speed
- 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.)
- Active
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000013179 statistical model Methods 0.000 title claims abstract description 22
- 238000010248 power generation Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 22
- 238000000053 physical method Methods 0.000 description 6
- 238000007619 statistical method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011985 exploratory data analysis Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Fluid Mechanics (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a wind power prediction method based on dynamic downscaling data fusion and a statistical model, which specifically comprises the following steps: step 1, dynamically downscaling the historical return wind speed of the NWP through a regional climate mode RegCM to obtain a fine-scale wind speed; step 2, comparing the dynamic downscaling with historical observation data, determining credibility weight factors of the historical wind speed data before and after dynamic downscaling, and establishing a data fusion function model; step 3, obtaining a historical wind speed according to the data fusion function model established in the step 2, and establishing an S-like curve model by combining historical wind power generation power data; and 4, obtaining a predicted wind speed according to the data fusion function model established in the step 2, and predicting the future power generation by combining the S-shaped curve model established in the step 3.
Description
Technical Field
The invention belongs to the technical field of wind power, and particularly relates to a wind power prediction method based on dynamic downscaling data fusion and a statistical model.
Background
With the rapid development of global economy, the demand for energy is also increasing. The development of renewable green energy has become a necessary direction for future human energy strategies. Wind energy is now considered as a basic alternative to fossil energy combustion and is beginning to be widely used in our daily lives. However, the fluctuation of wind energy is large in comparison to fossil energy. When large-scale wind power is connected into a power grid, the safety scheduling of the power grid is greatly influenced. Wind power prediction is thus crucial for the reliability of the power system.
The current wind power prediction method can be divided into a physical method and a statistical method.
The principle of the physical method is to use numerical weather forecast (NWP) and physical information around the wind turbines to predict the wind. Generating physical system generating methods based on incremental self-organizing neural networks and exploratory data analysis techniques, for example; or predicting meteorological parameters by using an NWP model and an artificial neural network. However, physical methods require a deeper understanding of the meteorological knowledge and physical characteristics of the wind farm, and the complexity of designing for a particular wind farm is very high. Thus, most wind farms use statistical learning methods to predict wind power. According to historical data and NWP, wind power of a wind field is predicted by adopting a statistical learning method, and a statistical model is generally measured on line, so that a better prediction method is provided for wind forecast. Various prediction models applied to the field of wind power generation have advantages and disadvantages, and the prediction performance obtained by a single prediction model is often difficult to reach the best. The method combines the advantages of a plurality of models, establishes a combined prediction model, improves the prediction performance, and is an important research direction of wind power prediction research.
At present, the mixed methods can integrate the advantages of each method and establish a more accurate prediction model. However, most of the current prediction methods depend on a single NWP, and the grid resolution of the meteorological information which can be provided in China is rough, so that a certain uncertainty exists in the predicted wind speed, and the uncertainty of wind power prediction is increased. Therefore, the accuracy of wind speed forecasting is improved by combining a dynamic downscaling and data fusion technology, and the wind speed forecasting is coupled to a statistical model to find out a wind power forecasting method with more credible forecasting results so as to better provide effective guidance for safe dispatching of a power system.
Disclosure of Invention
The invention aims to provide a wind power prediction method based on dynamic downscaling data fusion and a statistical model, so as to solve the problems that the accuracy is low when the wind speed is predicted by NWP (numerical weather forecast), the corresponding relation is inaccurate when the wind speed and the electric power are predicted by coupling physical and statistical methods, and the like.
In order to achieve the above purpose, the present invention provides the following technical solutions: the wind power prediction method based on dynamic downscaling data fusion and statistical model comprises the following steps:
step 1, dynamically downscaling the historical return wind speed of the NWP through a regional climate mode RegCM to obtain a fine-scale wind speed;
Step 2, comparing the dynamic downscaling with historical observation data, determining credibility weight factors of the historical wind speed data before and after dynamic downscaling, and establishing a data fusion function model;
step 3, obtaining a historical wind speed according to the data fusion function model established in the step 2, and establishing an S-like curve model by combining historical wind power generation power data;
And 4, obtaining a predicted wind speed according to the data fusion function model established in the step 2, and predicting the future power generation by combining the S-shaped curve model established in the step 3.
Preferably, in the step 1, the method specifically includes the following steps:
Step 11, collecting a historical report wind speed field, an air temperature field, an air pressure field and a relative humidity field which are output by the numerical forecast NWP;
Step 12, using the NWP output field as the input field of the regional climate mode RegCM, operating the mode by using the supercomputer, and outputting a wind speed field with higher resolution;
And 13, determining the position of the wind motor, interpolating the wind speed fields before and after the dynamic downscaling by utilizing bilinear interpolation, and giving the wind speed values before and after the dynamic downscaling at the wind motor.
Preferably, in the step 2, the method specifically includes the following steps:
step 21, recording a historical return wind speed of a single power generation fan which is not downscaled as V h1, wherein the corresponding credibility weight factor is w1, the downscaled historical return wind speed is V h2, and the corresponding credibility weight factor is w2, and if w1+w2=1 (1);
Step 22, recording the historical observation wind speed at a single power generation fan as V h, and determining a credibility weight factor according to the similarity degree of V h1, V h2 and V h, wherein the similarity degree is,
Step 23, according to the similarity between the two historical return wind speeds obtained in step 22 and the historical observation wind speed, the weight factor w1 is,
Solving a credibility weight factor by combining the formula (1) and the formula (4);
Step 24, setting the wind speed after the fusion of the two historical return wind speeds as V, if the wind speed is V,
V＝w1×Vh1+w2×Vh2(5)，
And (3) establishing a data fusion function model according to the formula (5), and performing data fusion on future forecast wind speeds before and after downscaling.
Preferably, in the step 3, the method specifically includes the following steps:
Step 31, according to the property of the wind turbine generator, the calculation relation between the output power at any moment and the wind speed at the corresponding moment is that,
Step 32, obtaining a historical wind speed according to the data fusion function model established in the step2, and training a class S-shaped curve by combining the historical wind power generation power data, wherein the class S-shaped curve is set as,
Step 33, fitting the class S-shaped curve by MATLAB software, solving out undetermined coefficients, obtaining a function expression of the class S-shaped curve, substituting the function expression into the expression obtained in the step 31 to obtain a P-V statistical prediction model,
Preferably, in the step 4, the method specifically includes the following steps:
Step 41, performing dynamic downscaling on the wind speed predicted by the NWP by using a regional climate mode RegCM, and fusing data before and after the dynamic downscaling to obtain a future predicted wind speed v at the wind motor;
And 42, carrying the predicted wind speed V into a P-V statistical prediction model to obtain the power generation P of the wind motor at the future moment.
Preferably, in the step 22, R1 and R2 are the similarity between the two historical return wind speeds and the historical observed wind speed; Respectively represent two historical return wind speeds, and Representing the average observed wind speed.
Preferably, in the step 31, P (V) is the output power of the wind turbine when the wind speed is V, and S is the output power of the S-like curve model to be constructed; v Cutting in is the wind turbine cut-in speed, V Rated for is the rated speed, V cutting out is the cut-out speed, and Pmax is the maximum power output by the wind turbine.
Preferably, in the step 32, e is a natural exponent, and a, b, c, and d are undetermined coefficients; v is the input wind speed, the numerical value of the input wind speed is between the cut-in wind speed and the rated wind speed of the wind turbine, and S is the output power.
The wind power prediction method based on the dynamic downscaling data fusion and the statistical model has the technical effects and advantages that:
1. When data fusion is carried out on wind speeds before and after dynamic downscaling, finer wind field data with finer resolution is obtained through downscaling, and credibility weighting factors are larger, so that the wind speed after data fusion is closer to the real wind speed, the influence of the original predicted wind speed is considered, and the wind speed at the wind outlet electric field can be predicted better;
2. The constructed S-shaped curve function is an S-shaped curve function, and the function obtained by fitting MATLAB software is more in accordance with the one-to-one correspondence of wind speed and power than the S-shaped curve function;
3. The dynamic downscaling data fusion and the statistical model are combined, so that uncertainty of a numerical weather forecast wind speed is avoided, and meanwhile, the corresponding relation between the wind speed and the generated power in the constructed prediction model is more accurate.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to fig. 1 of the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a wind power prediction method based on dynamic downscaling data fusion and a statistical model, which is shown in figure 1, and comprises the following steps:
step 1, dynamically downscaling the historical return wind speed of the NWP through a regional climate mode RegCM to obtain a wind speed with finer scale, and better simulating important climate events in the east Asia season wind region, particularly the space-time evolution characteristics of the east Asia season rain belt, through application of the regional climate mode RegCM, so that the method has prediction capability on the climate in the middle country region.
And step 2, determining credibility weight factors of the historical wind speed data before and after dynamic downscaling through comparison with the historical observation data, and establishing a data fusion function model.
And step 3, obtaining a historical wind speed according to the data fusion function model in the step 2, and establishing an S-like curve model by combining historical wind power generation power data.
And 4, obtaining a predicted wind speed according to the data fusion function model in the step 2, and predicting the future generated power by combining the S-shaped curve model established in the step 3.
In the step 1 of the wind power prediction method based on the dynamic downscaling data fusion and the statistical model, the dynamic downscaling is performed on the historical return wind speed of the NWP through the regional climate mode RegCM to obtain the wind speed with finer scale, and the specific steps are as follows:
Step 11, collecting a historical report wind speed field, an air temperature field, an air pressure field and a relative humidity field which are output by the numerical forecast NWP;
Step 12, using the NWP output field as the input field of the regional climate mode RegCM, operating the mode by using the supercomputer, and outputting a wind speed field with higher resolution;
And 13, determining the position of the wind motor, interpolating the wind speed fields before and after the dynamic downscaling by utilizing bilinear interpolation, and giving the wind speed values before and after the dynamic downscaling at the wind motor.
In the step 2 of the wind power prediction method based on the dynamic downscaling data fusion and the statistical model, the credibility weight factors of the historical wind speed data before and after the dynamic downscaling are determined by comparing with the historical observation data, and the specific steps of establishing the data fusion function model are as follows:
Step 21, recording that the historical return wind speed of a single power generation fan which is not downscaled is V h1, the corresponding credibility weight factor is w1, the downscaled historical return wind speed is V h2, the corresponding credibility weight factor is w2, and if w1+w2=1 (1).
Step 22, recording the historical observation wind speed at a single power generation fan as V h, determining a credibility weight factor according to the similarity degree of V h1, V h2 and V h, and if the similarity degree is,
In the formula (2) and the formula (3): r1 and R2 are the similarity degree of the two historical return wind speeds and the historical observation wind speed respectively; Respectively represent two historical return wind speeds, and Representing the average observed wind speed.
Step 23, according to the similarity between the two historical return wind speeds and the historical observed wind speed obtained in step 22, and continuously determining a weight factor w1 according to the following formula, wherein the weight factor w1 is:
Solving a credibility weight factor by the combined formula (1) and the formula (4);
Step 24, setting the wind speed after the fusion of the two historical return wind speeds as V, if the wind speed is V,
V＝w1×Vh1+w2×Vh2(5)，
And (3) establishing a data fusion function model according to the formula (5), wherein the data fusion function model can be used for data fusion of future forecast wind speeds before and after the downscaling, and the reliability weight is relatively larger due to finer wind speed field scale after the downscaling.
In the step 3 of the wind power prediction method based on the dynamic downscaling data fusion and the statistical model, the historical wind speed is obtained according to the data fusion function model in the step 2, and the specific steps of establishing an S-like curve model by combining the historical wind power generation power data are as follows:
step 31, in the wind power prediction of the wind power plant, according to the property of the wind turbine generator, the calculation relation between the output power at any moment and the wind speed at the corresponding moment is that,
In the formula (6), P (V) is the output power of the wind motor when the wind speed is V, and S is the output power of an S-like curve model to be constructed; v Cutting in is the cut-in speed of the wind motor, V Rated for is the rated speed of the wind motor, V cutting out is the cut-out speed of the wind motor, pmax is the maximum power output by the wind motor, and the values are constant values related to the properties of the wind motor.
Step 32, utilizing the historical wind speed obtained by the data fusion function model established in the step 2, and combining the power generation power data of the historical wind motor to train an S-shaped like curve, wherein the S-shaped like curve is set as,
In the formula (7), e is a natural index, a, b, c and d are undetermined coefficients, V is an input wind speed, the magnitude of the input wind speed is between the cut-in wind speed and the rated wind speed of the wind turbine, and S is output power.
Step 33, fitting the class S-shaped curve by MATLAB software, solving out undetermined coefficients, obtaining a function expression of the class S-shaped curve, substituting the function expression into the expression (6) to obtain a P-V statistical prediction model,
And the equation (8) is a P-V statistical prediction model.
In the step4 of the wind power prediction method based on the dynamic downscaling data fusion and the statistical model, the predicted wind speed is obtained according to the data fusion function model in the step 2, and the specific steps of predicting the future generated power by combining the S-shaped curve model established in the step 3 are as follows:
Step 41, performing dynamic downscaling on the wind speed predicted by the NWP by using a regional climate mode RegCM, and fusing data before and after the dynamic downscaling to obtain a future predicted wind speed v at the wind motor;
Step 42, the obtained predicted wind speed v is carried into expression (8), and the power P generated by the wind turbine at the future time is obtained.
The invention mainly solves the defects of low accuracy when the NWP predicts the wind speed in numerical weather forecast, inaccurate corresponding relation when the physical and statistical method is coupled to predict the corresponding relation between the wind speed and the electric power, and the like, and provides the wind power prediction method based on dynamic downscaling data fusion and the statistical model, so that the wind speed at the wind motor can be predicted more accurately, and the relationship between the wind speed and the electric power can be predicted more accurately in the physical and statistical method.
Finally, it should be noted that: the foregoing description is only illustrative of the preferred embodiments of the present invention, and although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements or changes may be made without departing from the spirit and principles of the present invention.
Claims (6)
1. The wind power prediction method based on dynamic downscaling data fusion and statistical model is characterized by comprising the following steps:
step 1, dynamically downscaling the historical return wind speed of the NWP through a regional climate mode RegCM to obtain a fine-scale wind speed;
Step 2, comparing the dynamic downscaling with historical observation data, determining credibility weight factors of the historical wind speed data before and after dynamic downscaling, and establishing a data fusion function model;
step 3, obtaining a historical wind speed according to the data fusion function model established in the step 2, and establishing an S-like curve model by combining historical wind power generation power data;
the step2 specifically includes the following steps:
step 21, recording a historical return wind speed of a single power generation fan which is not downscaled as V h1, wherein the corresponding credibility weight factor is w1, the downscaled historical return wind speed is V h2, and the corresponding credibility weight factor is w2, and if w1+w2=1 (1);
Step 22, recording the historical observation wind speed at a single power generation fan as V h, and determining a credibility weight factor according to the similarity degree of V h1, V h2 and V h, wherein the similarity degree is,
Step 23, according to the similarity between the two historical return wind speeds obtained in step 22 and the historical observation wind speed, the weight factor w1 is,
Solving a credibility weight factor by combining the formula (1) and the formula (4);
Step 24, setting the wind speed after the fusion of the two historical return wind speeds as V, if the wind speed is V,
V＝w1×Vh1+w2×Vh2(5)，
Establishing a data fusion function model according to the formula (5), and performing data fusion on future forecast wind speeds before and after downscaling;
Wherein:
r1 and R2 are the similarity degree of the two historical return wind speeds and the historical observation wind speed respectively;
respectively representing two historical return wind speeds;
Representing the average value of the observed wind speed;
And 4, obtaining a predicted wind speed according to the data fusion function model established in the step 2, and predicting the future power generation by combining the S-shaped curve model established in the step 3.
2. The wind power prediction method based on dynamic downscaling data fusion and statistical model according to claim 1, wherein in step 1, the method specifically comprises the following steps:
Step 11, collecting a historical report wind speed field, an air temperature field, an air pressure field and a relative humidity field which are output by the numerical forecast NWP;
Step 12, using the NWP output field as the input field of the regional climate mode RegCM, operating the mode by using the supercomputer, and outputting a wind speed field with higher resolution;
And 13, determining the position of the wind motor, interpolating the wind speed fields before and after the dynamic downscaling by utilizing bilinear interpolation, and giving the wind speed values before and after the dynamic downscaling at the wind motor.
3. The wind power prediction method based on dynamic downscaling data fusion and statistical model according to claim 1, wherein the step 3 specifically comprises the following steps:
Step 31, according to the property of the wind turbine generator, the calculation relation between the output power at any moment and the wind speed at the corresponding moment is that,
Step 32, obtaining a historical wind speed according to the data fusion function model established in the step2, and training a class S-shaped curve by combining the historical wind power generation power data, wherein the class S-shaped curve is set as,
Step 33, fitting the class S-shaped curve by MATLAB software, solving out undetermined coefficients, obtaining a function expression of the class S-shaped curve, substituting the function expression into the expression obtained in the step 31 to obtain a P-V statistical prediction model,
Wherein:
P (V) is the output work of the wind motor when the wind speed is V;
V Cutting in is the cut-in speed of the wind motor;
V Rated for is the rated speed;
V cutting out is the cut-out speed;
Pmax is the maximum power output by the wind turbine;
a. b, c and d are undetermined coefficients;
V is the input wind speed;
s is the output power.
4. The wind power prediction method based on dynamic downscaling data fusion and statistical model according to claim 1, wherein the step 4 specifically comprises the following steps:
Step 41, performing dynamic downscaling on the wind speed predicted by the NWP by using a regional climate mode RegCM, and fusing data before and after the dynamic downscaling to obtain a future predicted wind speed v at the wind motor;
And 42, carrying the predicted wind speed V into a P-V statistical prediction model to obtain the power generation P of the wind motor at the future moment.
5. A method for predicting wind power based on dynamic downscaling data fusion and statistical model according to claim 3, wherein: in the step 31, P (V) is the output power of the wind turbine when the wind speed is V, and S is the output power of the S-like curve model to be constructed;
V Cutting in is the wind turbine cut-in speed, V Rated for is the rated speed, V cutting out is the cut-out speed, and Pmax is the maximum power output by the wind turbine.
6. A method for predicting wind power based on dynamic downscaling data fusion and statistical model according to claim 3, wherein: in the step 32, e is a natural exponent, and a, b, c and d are undetermined coefficients;
v is the input wind speed, the numerical value of the input wind speed is between the cut-in wind speed and the rated wind speed of the wind turbine, and S is the output power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011435153.0A CN112561149B (en) | 2020-12-10 | 2020-12-10 | Wind power prediction method based on dynamic downscaling data fusion and statistical model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011435153.0A CN112561149B (en) | 2020-12-10 | 2020-12-10 | Wind power prediction method based on dynamic downscaling data fusion and statistical model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112561149A CN112561149A (en) | 2021-03-26 |
| CN112561149B true CN112561149B (en) | 2024-08-09 |
Family
ID=75060498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011435153.0A Active CN112561149B (en) | 2020-12-10 | 2020-12-10 | Wind power prediction method based on dynamic downscaling data fusion and statistical model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561149B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657662B (en) * | 2021-08-13 | 2022-06-28 | 浙江大学 | Downscaling wind power prediction method based on data fusion |
| CN113849979B (en) * | 2021-09-26 | 2024-07-23 | 北京师范大学 | Wind speed downscaling method based on climate model and joint distribution function |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105512766A (en) * | 2015-12-11 | 2016-04-20 | 中能电力科技开发有限公司 | Wind power plant power predication method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10330081B2 (en) * | 2017-02-07 | 2019-06-25 | International Business Machines Corporation | Reducing curtailment of wind power generation |
| 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 |
-
2020
- 2020-12-10 CN CN202011435153.0A patent/CN112561149B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105512766A (en) * | 2015-12-11 | 2016-04-20 | 中能电力科技开发有限公司 | Wind power plant power predication method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112561149A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sedaghat et al. | Determination of rated wind speed for maximum annual energy production of variable speed wind turbines | |
| Shi et al. | Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features | |
| CN104978608B (en) | A kind of wind electric powder prediction device and prediction technique | |
| TWI476430B (en) | A wind energy forecasting method with extreme wind speed prediction function | |
| CN104299044A (en) | Clustering-analysis-based wind power short-term prediction system and prediction method | |
| CN106505631B (en) | Intelligent wind power wind power prediction system | |
| CN113657662B (en) | Downscaling wind power prediction method based on data fusion | |
| CN112561149B (en) | Wind power prediction method based on dynamic downscaling data fusion and statistical model | |
| CN101727538A (en) | Wind turbines input wind speed equivalent method taking into account influence of wind direction | |
| CN102479347B (en) | Method and system for forecasting short-term wind speed of wind farm based on data driving | |
| CN110365041B (en) | Wind power multi-scene robust scheduling method based on gan scene simulation | |
| CN103996079B (en) | Wind power weighting predication method based on conditional probability | |
| Bashaer et al. | Investigation and analysis of wind turbines optimal locations and performance in Iraq | |
| CN108062722B (en) | Mechanical power calculation method of mountain wind power plant model fan based on wind speed variation coefficient | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| Efe et al. | 72hr forecast of wind power in Manisa, Turkey by using the WRF model coupled to WindSim | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| Zhang et al. | Joint forecasting of regional wind and solar power based on attention neural network | |
| CN103557117A (en) | Power curve acquisition device for wind turbine generator system | |
| CN105844350A (en) | Short period wind power prediction system based on covariance preferable combination model | |
| Chenhong et al. | Wind speed prediction research based on time series model with residual correction | |
| CN105787813A (en) | Short-term wind power prediction method based on covariance | |
| Soe et al. | Assessment of Economic feasibility on promising wind energy sites in Myanmar | |
| Ayar et al. | Harvesting the Wind: A Study on the Feasibility and Advancements of Wind Energy in Turkey | |
| Wang et al. | Short-term wind power forecasting based on BOMLS K-means similar hours Clustering method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |