CN105512766A - Wind power plant power predication method - Google Patents
Wind power plant power predication method Download PDFInfo
- Publication number
- CN105512766A CN105512766A CN201510919659.1A CN201510919659A CN105512766A CN 105512766 A CN105512766 A CN 105512766A CN 201510919659 A CN201510919659 A CN 201510919659A CN 105512766 A CN105512766 A CN 105512766A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- weather forecast
- historical data
- numerical weather
- wind
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005259 measurement Methods 0.000 claims abstract description 19
- 230000005684 electric field Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 4
- 210000005036 nerve Anatomy 0.000 abstract 1
- 230000009467 reduction Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 13
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 239000012634 fragment Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 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
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer 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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (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 provides a wind power plant power predication method. The method comprises the following steps: step A, collecting wind speed historical data of mesoscale numerical weather forecast and actually measured wind speed historical data matching the wind speed historical data in terms of time; B, matching wind speed historical data of mesoscale numerical weather forecast of a prediction day with the wind speed historical data of the mesoscale numerical weather forecast to obtain historical data with greatest similarity; C, determining a wind measurement tower actually measured wind speed matching the historical data with the greatest similarity in terms of time, and replacing the wind speed historical data of the mesoscale numerical weather forecast of the prediction day with the wind measurement tower actually measured wind speed; and D, establishing a fitting wind speed-power feature curve of a wind power plant area, and through combination with the wind measurement tower actually measured wind speed after replacement in the step C, obtaining predicted power of the wind power plant area at the predication day. According to the invention, compared to a conventional statistical scale-reducing method applying a nerve network, the wind power plant power predication method has the following advantages: the logic structure is optimized, and besides, a curve matching model also has the advantage of high execution efficiency.
Description
Technical field
The present invention relates to Wind turbines control technology field, particularly a kind of wind electric field power prediction method.
Background technology
In recent years, along with the adjustment of China energy policy, grid connected wind power installed capacity increases fast, and large-scale wind power is concentrated and grid-connectedly brought impact to electric power netting safe running.Improve the predictability of output of wind electric field, effectively can reduce the impact that wind-powered electricity generation causes electrical network, alleviate dispatching of power netwoks peak regulation pressure, this is for making full use of wind energy resources, and improving grid connected wind power installation ratio further has positive effect.
According to the domestic wind farm power prediction technical manual issued and implemented, wind energy turbine set must every day according to the rules the time to power dispatching station upload next day 0 ~ 24h exert oneself prediction curve and accept precision of prediction examination.In order to accurately reflect air motion state next day, mesoscale numerical weather forecast pattern (NWP must be used, NumericalWeatherPrediction) export the input data as wind energy turbine set short term power prognoses system, therefore mesoscale numerical weather forecast model prediction output accuracy determines the precision of wind energy turbine set short term power prediction to a great extent.
But, mesoscale model atmospheric physical processes Parameterization Scheme effectively can not simulate sub grid scale (being less than 1km) atmospheric physical processes, there is error in its synoptic process described and truth, this error can increase along with the growth of mode integral operation time.Therefore, the not enough and atmospheric physical processes Parameterization Scheme relevant with resolution of grid resolution describes inaccurate meeting and mesoscale model is predicted the outcome exist uncertain.Directly apply to power prediction and can bring larger uncertainty, NO emissions reduction pre-service must be carried out to it.
At present mesoscale numerical weather forecast is exported and carries out the main employing of NO emissions reduction research two kinds of methods:
1, physical model is used to solve the impact of wind energy turbine set Local factor on air-flow.This method calculation cost is less, but physical model constructs and implementation procedure is comparatively complicated, and precision improves limited.
2, adopt power NO emissions reduction method, such as Fluid Mechanics Computation (CFD, ComputationalFluidDynamics) wind energy turbine set interior flow field evolution process is simulated, this method can obtain comparatively accurately wind speed profile, but need when setting up prediction of wind speed Query Database or direct prediction of wind speed to use CFD method to solve Na Weiye-RANS (Navier-Stokes), this equation is the equation describing viscous Newtonian fluid in fluid mechanics, so far not yet by the equation solved completely, only have about more than 100 particular solutions at present by solution out, it is one of the most complicated equation, its Project Realization is complicated and calculation cost is huge, high to hardware requirement.
Summary of the invention
2, in view of this, fundamental purpose of the present invention is, provides a kind of wind electric field power prediction method, comprises step:
The wind speed historical data of A, collection mesoscale numerical weather forecast, and survey wind speed historical data with its anemometer tower mated in time;
B, by prediction day the air speed data of mesoscale numerical weather forecast mate with the wind speed historical data of described mesoscale numerical weather forecast, obtain the historical data that similarity is the highest;
C, determine that wind speed surveyed by the anemometer tower that the historical data the highest with described similarity is mated in time, replace the air speed data of the mesoscale numerical weather forecast of prediction day with described anemometer tower actual measurement wind speed;
D, set up the matching wind speed-power characteristic in wind energy turbine set region, the anemometer tower actual measurement wind speed after replacing described in integrating step C, obtains the wind energy turbine set regional prediction power predicting day.
By upper, use above-mentioned mesoscale numerical weather forecast prediction of wind speed just can calculate the forecasting wind speed value of wind energy turbine set, calculated amount is little and computing velocity fast, can meet the requirement of wind energy turbine set short term power predictive engine completely, the method, compared to existing power NO emissions reduction technology, improves counting yield greatly.Compared to the statistics NO emissions reduction method adopting neural network, because neural network is equivalent to " black box ", be difficult to its model structure of adjustment, and there is the lower problem of execution efficiency.The whole flow process of Curve Matching model is succinct, and there is not the logical organization of that complexity of neural network, Curve Matching model also exists the high advantage of execution efficiency in addition.
Optionally, step B comprises:
The air speed data curve of the mesoscale numerical weather forecast of generation forecast day, and the wind speed historical data curve of mesoscale numerical weather forecast;
Utilize the Euclidean distance of the air speed data curve of the mesoscale numerical weather forecast of Curve Matching model computational prediction day and the wind speed historical data curve of mesoscale numerical weather forecast, the shortest then similarity of described Euclidean distance is higher.
By upper, can be implemented in historical data, find out and forecast that immediate historical wind speed is forecast with current wind speed.
Optionally, also comprise, the described prediction air speed data curve of mesoscale numerical weather forecast of day, the wind speed historical data curve of mesoscale numerical weather forecast are disassembled step into several sequences by same time node, and
For each sequence of the air speed data curve of prediction day mesoscale numerical weather forecast, in each sequence of the wind speed historical data curve of mesoscale numerical weather forecast, obtain the highest sequence of similarity.
By upper, by the prediction of wind speed of current predictive day is split into multistage, compared to whole section of prediction, the precision of prediction of every section can be improved.
Optionally, also comprise before step C, described anemometer tower actual measurement wind speed historical data is disassembled step into several sequences by described same time node.
By upper, actual measurement wind speed correspondence split into multistage, the precision of prediction of every section can be improved, in the replacement process of subsequent step C, prediction of wind speed can be replaced with history actual measurement wind speed respectively according to different sequence.
Optionally, described timing node is 15 minutes.
Optionally, also comprise after step C: judge in each sequence of the wind speed historical data curve of described mesoscale numerical weather forecast, whether the sequence the highest with the air speed data curve current sequence similarity of prediction day mesoscale numerical weather forecast be unique, also comprise time not unique: the anemometer tower actual measurement wind speed each the highest for similarity historical data sequence mated in time carries out being averaging calculating, result of calculation is replaced the air speed data of prediction day mesoscale numerical weather forecast.
By upper, for the not unique situation of the sequence that similarity is high, by the mode of computation of mean values, the precision that wind speed is optimized can be improved.
Optionally, described Curve Matching model is
in formula || NWP
t'h
t'|| represent Euclidean distance; σ represents the standard deviation of the wind speed historical data sequence of mesoscale numerical weather forecast; f
t+jrepresent the i-th+j sequence of the air speed data curve of prediction day mesoscale numerical weather forecast; H
t '+jrepresent the i-th '+j sequence of the wind speed historical data curve of mesoscale numerical weather forecast;
get 1.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention;
Fig. 2 is Curve Matching principle schematic;
Fig. 3 is the genuine wind speed-power characteristic schematic diagram of separate unit blower fan;
Fig. 4 is genuine wind speed-power characteristic and the matching wind speed-power characteristic schematic diagram of separate unit blower fan of the present invention.
Embodiment
For overcoming the defect that prior art exists, the invention provides a kind of wind electric field power prediction method, the larger problem of mesoscale numerical weather forecast air speed error is solved according to statistics NO emissions reduction, effectively reduce the uncertainty that mesoscale lack of resolution is brought, drastically increase mesoscale numerical weather forecast mode computation efficiency, significantly improve wind farm power prediction precision, and without the need to relying on high precision hardware.
As shown in Figure 1, method for forecasting short-term power in wind power station of the present invention comprises the following steps:
S10: collect mesoscale numerical weather forecast prediction of wind speed historical data, and the anemometer tower actual measurement wind speed historical data of mating in time with it.
Wind energy turbine set is equipped with anemometer tower, and height consistent with wind generator unit wheel hub height on anemometer tower is equipped with air velocity transducer, and this air velocity transducer can the actual measurement wind speed of Real-time Obtaining present position hub height.Described historical data is at least half a year, preferably, is 1 year.
Step 20: based on Curve Matching principle, sets up the statistics NO emissions reduction model of wind energy turbine set hub height prediction of wind speed, is optimized mesoscale numerical weather forecast prediction of wind speed.
Use curve matching process sets up statistics NO emissions reduction model, specifically, namely tracing pattern matching algorithm is set up, the formula of definition tracing pattern coupling, by mesoscale numerical weather forecast prediction of wind speed, mesoscale numerical weather forecast prediction of wind speed historical data, and the anemometer tower actual measurement wind speed historical data of mating in time is with it disassembled as several little sequences by same time node.
For each prediction of wind speed sequence, mate in several little sequences of mesoscale numerical weather forecast prediction of wind speed historical data according to tracing pattern matching formula, to draw the best match sequence in mesoscale numerical weather forecast prediction of wind speed historical data.The actual measurement wind speed of the same time predicted with it is determined again, using the optimum results of this actual measurement wind speed as mesoscale numerical weather forecast prediction of wind speed according to best match sequence.
Further, because the best match sequence of each sequence may not uniquely, then by each sequence averaged of optimum matching, as optimum results.
Curve Matching model is
in formula || NWP
t'h
t'|| be expressed as the Euclidean distance D of certain sequence in the mesoscale numerical weather forecast prediction of wind speed sequence disassembling certain prediction of wind speed sequence and the history obtained from mesoscale numerical weather forecast prediction of wind speed; σ represents the standard deviation of the mesoscale numerical weather forecast prediction of wind speed sequence of history; f
t+jrepresent mesoscale numerical weather forecast prediction of wind speed sometime; H
t '+jto represent in historical series mesoscale numerical weather forecast prediction of wind speed sometime;
get 1, when representing each match query, each sequence represents the prediction of wind speed data in 3 moment of continuous print.When D is less than or equal to given threshold value, can think that history curve mates with prediction curve, in the present embodiment, D value is 0.05.
Illustrate based on the statistics NO emissions reduction model of Curve Matching principle to set up wind energy turbine set, historical data is the mesoscale numerical weather forecast prediction of wind speed data in year Dec in January, 2012 to 2012, data time resolution is 15min, and data length chooses 0 ~ 24h next day; The mesoscale numerical weather forecast prediction of wind speed time is on January 1st, 2013, and data time resolution is 15min, and data length chooses 0 ~ 24h next day, is prediction day this day.
First, according to time order and function, prediction day data are divided into 32 sequences, often group comprises 3 data.
Secondly, by the mesoscale numerical weather forecast prediction of wind speed data march lines matching in first group of data traversal year Dec in January, 2012 to 2012, the single history fragment that Euclidean distance is minimum is obtained.Survey wind speed historical data by with the anemometer tower that its single history fragment is mated in time again, be the statistics NO emissions reduction wind speed of this group prediction of wind speed, the wind speed after namely optimizing.
Again, by 32 sequence curve matching results, namely the statistics NO emissions reduction wind speed in 32 groups of 96 moment, couples together according to time order and function, just obtains the statistics NO emissions reduction wind series predicting January 1 2013 day.
When the history fragment minimum with the Euclidean distance of certain sequence is not unique, then asks for the average of anemometer tower actual measurement of each history fragment corresponding time wind speed historical data, be the statistics NO emissions reduction wind speed of this group prediction of wind speed, the wind speed after namely optimizing.
As shown in Figure 2, t '-1, t ', t '+1 represent the prediction of wind speed data in 3 moment of current predictive day certain sequence of mesoscale numerical weather forecast prediction of wind speed respectively; T-1, t, t+1 represent the prediction of wind speed data in 3 moment of certain sequence of mesoscale numerical weather forecast prediction of wind speed year one day in Dec in January, 2012 to 2012 respectively.D1 is expressed as the Euclidean distance of t '-1 and t-1; D2 is expressed as the Euclidean distance of t ' and t; D3 is expressed as the Euclidean distance of t '+1 and t+1.
Based on the mesoscale numerical weather forecast statistics NO emissions reduction method of Curve Matching, use above-mentioned mesoscale numerical weather forecast prediction of wind speed just can calculate the forecasting wind speed value of wind energy turbine set position hub height, calculated amount is little and computing velocity is fast, the requirement of wind energy turbine set short term power predictive engine can be met completely, the method, compared to existing power NO emissions reduction technology, improves counting yield greatly.Compared to the statistics NO emissions reduction method adopting neural network, because neural network is equivalent to " black box ", be difficult to its model structure of adjustment, and there is the lower problem of execution efficiency.The whole flow process of Curve Matching model is succinct, and there is not the logical organization of that complexity of neural network, Curve Matching model also exists the high advantage of execution efficiency in addition.
Step 30: the matching wind speed-power characteristic setting up wind energy turbine set.
Prediction of wind speed is converted into predicted power and must be based upon wind speed – power mapping relations under actual condition, Figure 3 shows that genuine wind speed-power characteristic that blower fan producer provides, by more known with historical data, its genuine wind speed-power characteristic can not describe the input/output relation of wind energy turbine set under actual condition well, and the wind speed-power of the wind energy turbine set that is incorporated into the power networks falls apart, point correspondence is distributed in a wider region, in order to hold the relation of wind speed and power on the whole, this step sets up the matching wind speed-power characteristic of wind energy turbine set.
In the present embodiment, the threshold wind velocity of wind electric field blower is 3m/s, and cut-out wind speed is 25m/s, take 0.1m/s as wind speed interval step-length, namely wind speed interval is [3-3.1], [3.1-3.2], [3.2-3.3] ... [24.8-24.9], [24.9-25], totally 41 wind speed interval.
Illustrate for [3-3.1] wind speed interval, first need to carry out the process of rejecting bad point to misoperation data point in wind speed and power coordinate system.Due to blower fan group maintenance shut-downs, blower fan group operation exception, the reasons such as air velocity transducer is malfunctioning, make to contain a large amount of misoperation data points in wind speed and power coordinate system, are namely scattered in the discrete data point being distributed in Fig. 3 wind speed-power characteristic edge.These abnormity point can have a strong impact on blower fan actual wind speed-power characteristic fitting effect usually.The process rejecting bad point comprises: sort from small to large to all active power values of [3-3.1] wind speed interval, calculate the mean value of active power, as the power typical value of this wind speed interval, choose a certain performance number that comes below as power upper limit, come a certain performance number above as lower limit.The upper and lower bound of rejecting bad point in each wind speed interval is revised, the active power value predicted in each wind speed interval is rejected lower than lower limit with higher than the data point of the upper limit, to complete rejecting bad point.Such as, choose in wind speed interval be positioned at 99% (be 100% to the maximum, minimum is 1%) place active power value as power upper limit, be positioned at the active power value at 1% (be 100% to the maximum, minimum is 1%) place as lower limit.All aforesaid operations is done for each wind speed interval, determines the power upper limit in each wind speed interval and lower limit.
Secondly, statistical calculation is carried out to the performance number in different wind speed interval, chooses the maximum active power value of occurrence number as power features value, and the power features value in all wind speed interval is connected, set up matching wind speed-power characteristic as shown in Figure 4.
Finally, carry out multistage Gauss curve fitting to the power features value in all wind speed interval, result obtains a smooth continuous print matching wind speed-power characteristic, and this Curve Resolution expression formula is as follows:
GeneralmodelGauss4:
P(v)＝a1*exp(-((v-b1)/c1)^2)+a2*exp(-((v-b2)/c2)^2)+
a3*exp(-((v-b3)/c3)^2)+a4*exp(-((v-b4)/c4)^2)
a1＝1470(1359,1581)
b1＝29.55(27.79,31.32)
c1＝10.54(-0.1442,21.23)
a2＝445.1(297.2,593)
b2＝10.23(10.09,10.37)
c2＝2.286(1.929,2.644)
a3＝-2.993e+006(-1.611e+013,1.611e+013)
b3＝16.29(-1160,1193)
c3＝5.815(-2379,2391)
a4＝2.994e+006(-1.611e+013,1.611e+013)
b4＝16.29(-1159,1192)
c4＝5.816(-2378,2390)
Above a
i, b
i, c
ibe matched curve constant value coefficient, the RMSE:15.07 of matched curve.
The short-term forecasting wind speed of wind energy turbine set position hub height is substituted into above fit curve equation, just can obtain the short-term forecasting power of this wind energy turbine set.
Step 40: wind energy turbine set short term power is predicted.
The Gauss's analytical expression blower fan position hub height prediction of wind speed that statistics NO emissions reduction method obtains being substituted into this curve just can obtain the short-term forecasting power of wind energy turbine set
Using the input value of wind energy turbine set statistics NO emissions reduction air speed value matching wind speed-power characteristic in step 30 in step 20, draw the short-term forecasting power of this wind energy turbine set.Further, lose owing to producing electricity consumption in running of wind generating set process, therefore the predicted power-electricity consumption of Wind turbines output power=all blower fans is lost.
Preferably, also comprise step 50 (not shown), namely Wind turbines control end is according to the output power of each wind energy turbine set predicted in step 40, regulates its online power.For example, when wind energy turbine set Wind turbines run into limit exert oneself state time, wind energy turbine set control end controls the higher several Fans of output power and stops power online to export, then is that electric energy stores by power transfer.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention.In a word, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (7)
1. a wind electric field power prediction method, is characterized in that, comprises step:
The wind speed historical data of A, collection mesoscale numerical weather forecast, and survey wind speed historical data with its anemometer tower mated in time;
B, by prediction day the air speed data of mesoscale numerical weather forecast mate with the wind speed historical data of described mesoscale numerical weather forecast, obtain the historical data that similarity is the highest;
C, determine that wind speed surveyed by the anemometer tower that the historical data the highest with described similarity is mated in time, replace the air speed data of the mesoscale numerical weather forecast of prediction day with described anemometer tower actual measurement wind speed;
D, set up the matching wind speed-power characteristic in wind energy turbine set region, the anemometer tower actual measurement wind speed after replacing described in integrating step C, obtains the wind energy turbine set regional prediction power predicting day.
2. method according to claim 1, is characterized in that, step B comprises:
The air speed data curve of the mesoscale numerical weather forecast of generation forecast day, and the wind speed historical data curve of mesoscale numerical weather forecast;
Utilize the Euclidean distance of the air speed data curve of the mesoscale numerical weather forecast of Curve Matching model computational prediction day and the wind speed historical data curve of mesoscale numerical weather forecast, the shortest then similarity of described Euclidean distance is higher.
3. method according to claim 2, it is characterized in that, also comprise, the described prediction air speed data curve of mesoscale numerical weather forecast of day, the wind speed historical data curve of mesoscale numerical weather forecast are disassembled step into several sequences by same time node, and
For each sequence of the air speed data curve of prediction day mesoscale numerical weather forecast, in each sequence of the wind speed historical data curve of mesoscale numerical weather forecast, obtain the highest sequence of similarity.
4. method according to claim 3, is characterized in that, also comprises before step C, and described anemometer tower actual measurement wind speed historical data is disassembled step into several sequences by described same time node.
5. the method according to claim 3 or 4, is characterized in that, described timing node is 15 minutes.
6. method according to claim 4, it is characterized in that, also comprise after step C: judge in each sequence of the wind speed historical data curve of described mesoscale numerical weather forecast, whether the sequence the highest with the air speed data curve current sequence similarity of prediction day mesoscale numerical weather forecast be unique, also comprise time not unique: the anemometer tower actual measurement wind speed each the highest for similarity historical data sequence mated in time carries out being averaging calculating, result of calculation is replaced the air speed data of prediction day mesoscale numerical weather forecast.
7., according to Claims 1 to 4 or 6 arbitrary described methods, it is characterized in that, described Curve Matching model is
in formula || NWP
t'h
t'|| represent Euclidean distance; σ represents the standard deviation of the wind speed historical data sequence of mesoscale numerical weather forecast; f
t+jrepresent the i-th+j sequence of the air speed data curve of prediction day mesoscale numerical weather forecast; H
t '+jrepresent the i-th '+j sequence of the wind speed historical data curve of mesoscale numerical weather forecast;
get 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510919659.1A CN105512766A (en) | 2015-12-11 | 2015-12-11 | Wind power plant power predication method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510919659.1A CN105512766A (en) | 2015-12-11 | 2015-12-11 | Wind power plant power predication method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105512766A true CN105512766A (en) | 2016-04-20 |
Family
ID=55720728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510919659.1A Pending CN105512766A (en) | 2015-12-11 | 2015-12-11 | Wind power plant power predication method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105512766A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106505631A (en) * | 2016-10-29 | 2017-03-15 | 塞壬智能科技（北京）有限公司 | Intelligent wind power wind power prediction system |
| CN106640547A (en) * | 2016-11-24 | 2017-05-10 | 东北电力大学 | Method and system for monitoring state of wind generating set |
| CN106875038A (en) * | 2017-01-03 | 2017-06-20 | 北京国能日新系统控制技术有限公司 | Based on the wind power prediction method and device for gathering local multiple spot Different climate feature |
| CN108536881A (en) * | 2017-03-06 | 2018-09-14 | 新疆金风科技股份有限公司 | Method and apparatus for calculating wind power plant generated energy |
| CN108665102A (en) * | 2018-05-11 | 2018-10-16 | 中国船舶重工集团海装风电股份有限公司 | Method based on the real-time generated energy of mesoscale data prediction wind power plant |
| CN109948824A (en) * | 2018-11-09 | 2019-06-28 | 北京华源热力管网有限公司 | A method of thermal substation thermic load is predicted using mode identification technology |
| CN110956333A (en) * | 2019-12-09 | 2020-04-03 | 国网湖南省电力有限公司 | Power grid galloping long-term prediction method and system based on climate power downscaling |
| CN112465194A (en) * | 2020-11-09 | 2021-03-09 | 王博妮 | Intelligent meteorological service system and method for offshore wind farm based on meteorological big data |
| CN112561149A (en) * | 2020-12-10 | 2021-03-26 | 江苏冰象智气信息技术有限公司 | Wind power prediction method based on power downscaling data fusion and statistical model |
| CN112613632A (en) * | 2020-03-31 | 2021-04-06 | 北京金风慧能技术有限公司 | Power prediction model establishing method, prediction method and device and electronic equipment |
| CN112685977A (en) * | 2021-01-14 | 2021-04-20 | 国家气候中心 | Wind power plant wind resource unsteady numerical simulation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496926A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Method for judging and processing wind farm power prediction input data |
| CN102588210A (en) * | 2011-12-21 | 2012-07-18 | 中能电力科技开发有限公司 | Filtering method for preprocessing fitting data of power curve |
| CN103473438A (en) * | 2013-08-15 | 2013-12-25 | 国家电网公司 | Method for optimizing and correcting wind power prediction models |
| 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 |
| CN104299044A (en) * | 2014-07-01 | 2015-01-21 | 沈阳工程学院 | Clustering-analysis-based wind power short-term prediction system and prediction method |
| CN105006846A (en) * | 2015-09-02 | 2015-10-28 | 国家电网公司 | Station level active power optimization method of wind power station |
-
2015
- 2015-12-11 CN CN201510919659.1A patent/CN105512766A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496926A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Method for judging and processing wind farm power prediction input data |
| CN102588210A (en) * | 2011-12-21 | 2012-07-18 | 中能电力科技开发有限公司 | Filtering method for preprocessing fitting data of power curve |
| CN103473438A (en) * | 2013-08-15 | 2013-12-25 | 国家电网公司 | Method for optimizing and correcting wind power prediction models |
| 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 |
| CN104299044A (en) * | 2014-07-01 | 2015-01-21 | 沈阳工程学院 | Clustering-analysis-based wind power short-term prediction system and prediction method |
| CN105006846A (en) * | 2015-09-02 | 2015-10-28 | 国家电网公司 | Station level active power optimization method of wind power station |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106505631A (en) * | 2016-10-29 | 2017-03-15 | 塞壬智能科技（北京）有限公司 | Intelligent wind power wind power prediction system |
| CN106505631B (en) * | 2016-10-29 | 2019-02-01 | 塞壬智能科技（北京）有限公司 | Intelligent wind power wind power prediction system |
| CN106640547B (en) * | 2016-11-24 | 2020-08-18 | 东北电力大学 | Method and system for monitoring state of wind turbine generator |
| CN106640547A (en) * | 2016-11-24 | 2017-05-10 | 东北电力大学 | Method and system for monitoring state of wind generating set |
| CN106875038A (en) * | 2017-01-03 | 2017-06-20 | 北京国能日新系统控制技术有限公司 | Based on the wind power prediction method and device for gathering local multiple spot Different climate feature |
| CN108536881A (en) * | 2017-03-06 | 2018-09-14 | 新疆金风科技股份有限公司 | Method and apparatus for calculating wind power plant generated energy |
| US11168667B2 (en) | 2017-03-06 | 2021-11-09 | Xinjiang Goldwind Science & Technology Co., Ltd. | Method and device for calculating power generation of wind farm |
| CN108536881B (en) * | 2017-03-06 | 2020-10-16 | 新疆金风科技股份有限公司 | Method and device for calculating the power generation of a wind farm |
| CN108665102A (en) * | 2018-05-11 | 2018-10-16 | 中国船舶重工集团海装风电股份有限公司 | Method based on the real-time generated energy of mesoscale data prediction wind power plant |
| CN109948824B (en) * | 2018-11-09 | 2021-09-07 | 北京华源热力管网有限公司 | Method for predicting heat load of heating power station by using pattern recognition technology |
| CN109948824A (en) * | 2018-11-09 | 2019-06-28 | 北京华源热力管网有限公司 | A method of thermal substation thermic load is predicted using mode identification technology |
| CN110956333A (en) * | 2019-12-09 | 2020-04-03 | 国网湖南省电力有限公司 | Power grid galloping long-term prediction method and system based on climate power downscaling |
| CN112613632A (en) * | 2020-03-31 | 2021-04-06 | 北京金风慧能技术有限公司 | Power prediction model establishing method, prediction method and device and electronic equipment |
| CN112465194A (en) * | 2020-11-09 | 2021-03-09 | 王博妮 | Intelligent meteorological service system and method for offshore wind farm based on meteorological big data |
| CN112561149A (en) * | 2020-12-10 | 2021-03-26 | 江苏冰象智气信息技术有限公司 | Wind power prediction method based on power downscaling data fusion and statistical model |
| CN112561149B (en) * | 2020-12-10 | 2024-08-09 | 江苏冰象智气信息技术有限公司 | Wind power prediction method based on dynamic downscaling data fusion and statistical model |
| CN112685977A (en) * | 2021-01-14 | 2021-04-20 | 国家气候中心 | Wind power plant wind resource unsteady numerical simulation method and device |
| CN112685977B (en) * | 2021-01-14 | 2023-12-08 | 国家气候中心 | Wind power plant wind resource unsteady value simulation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512766A (en) | Wind power plant power predication method | |
| CN107766990B (en) | Method for predicting power generation power of photovoltaic power station | |
| CN103401236B (en) | A kind of wind energy turbine set unit group technology based on flow correlation of wind power farm | |
| CN103473621A (en) | Wind power station short-term power prediction method | |
| CN105069521A (en) | Photovoltaic power plant output power prediction method based on weighted FCM clustering algorithm | |
| Yang et al. | Day-ahead forecasting of photovoltaic output power with similar cloud space fusion based on incomplete historical data mining | |
| CN104978608B (en) | A kind of wind electric powder prediction device and prediction technique | |
| CN106505631B (en) | Intelligent wind power wind power prediction system | |
| CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
| CN103489046A (en) | Method for predicting wind power plant short-term power | |
| CN105654207A (en) | Wind power prediction method based on wind speed information and wind direction information | |
| CN105305488B (en) | A kind of evaluation method for considering new-energy grid-connected and power transmission network utilization rate being influenced | |
| CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
| CN109272258B (en) | Regional wind and solar power generation resource evaluation method based on K-means clustering | |
| CN112819238A (en) | Short-term wind power prediction method based on chaotic chicken flock optimization algorithm | |
| Wu et al. | Deterministic and probabilistic wind power forecasts by considering various atmospheric models and feature engineering approaches | |
| CN108985490A (en) | Wind-driven generator power curve modification method based on the fitting of sliding window characteristic | |
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| CN114021483A (en) | Ultra-short-term wind power prediction method based on time domain characteristics and XGboost | |
| Chen et al. | Research on wind power prediction method based on convolutional neural network and genetic algorithm | |
| CN105825002A (en) | Method for modeling dynamic equivalence of wind power farm based on dynamic grey-relevancy analysis method | |
| CN111008725B (en) | Meteorological factor fluctuation feature extraction method for short-term wind power prediction | |
| CN113988421A (en) | Wind turbine generator power intelligent prediction method based on deep learning | |
| CN105741192B (en) | Short-term wind speed combined forecasting method for wind turbine engine room of wind power plant | |
| CN117910668A (en) | Power system evolution path planning method considering multiple uncertainty factors |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160420 |