CN102945318B - A kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan - Google Patents
A kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan Download PDFInfo
- Publication number
- CN102945318B CN102945318B CN201210418541.7A CN201210418541A CN102945318B CN 102945318 B CN102945318 B CN 102945318B CN 201210418541 A CN201210418541 A CN 201210418541A CN 102945318 B CN102945318 B CN 102945318B
- Authority
- CN
- China
- Prior art keywords
- wind
- fans
- wind speed
- blower fan
- attenuation rate
- 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.)
- Expired - Fee Related
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/50—Manufacturing or production processes characterised by the final manufactured product
Landscapes
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The present invention relates to a kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan, wind energy turbine set set up by cascade blower fan, measure the distance of adjacent two Fans, before and after gathering, two Fans are at instantaneous wind speed and instantaneous wind angle, calculate the time that front Fans propagates into rear Fans, set up according to sea land distribution rate formula and wind direction attenuation rate formula the attenuation rate that prognoses system obtains wind speed and direction.By the attenuation rate data system of the wind speed and direction of foundation, convert out the wind speed and direction of rear Fans, make full use of the energy transferring relation between blower fan and blower fan, set up cascade blower fan system, realize the performance prediction of ultra-short term wind speed.Generally can apply for wind energy and provide technical foundation.
Description
Technical field
The present invention relates to a kind of forecasting wind speed technology, particularly a kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan.
Background technology
Along with the appearance of global energy crisis, countries in the world are all to the strong interest that renewable resource causes, and the advantages such as wind energy is clean with it, cheap, potentiality to be exploited is large are generally applied, and its ratio is also rapidly increasing year by year.But wind-power electricity generation also also exists deficiency.The complexity that the uncertainty of wind makes the prediction of wind speed and wind power become, predicated error is large, precision is low.At present, mostly concentrate on both at home and abroad and the short-term forecasting of wind speed is studied, study very few to ultra-short term prediction and even performance prediction.
The ultra-short term prediction of wind speed is often referred to the prediction within 30min, simultaneously all based on static prediction, by historical wind speed and correlated condition as input, the wind speed of following a period of time is predicted, and the acquisition interval of data is large, real-time and the continuity of sequence suffer restraints.In addition, the wind speed input that this blower fan is surveyed only is depended in the predicted data source for separate unit blower fan.Although, on the basis that measuring accuracy raising, computer disposal speed improve, select appropriate method can improve to the prediction of wind speed, but often kind of prediction algorithm has the defect of himself, make the probability distribution of stochastic error unequal, and maximum error may be very large, and the stability of prediction cannot ensure, therefore precision of prediction is not fundamentally improved.
From general knowledge, wind speed has size, and wind direction is angled, and the wind speed that wind-powered electricity generation place is surveyed is usually in units of m/s.Investigate through reality and find, wind propagates into another one place from the three unities needs the regular hour, when blower fan changes at wind speed and direction angle, the change of blade also needs the regular hour, in reality, often after blower fan measures current wind energy signal, corresponding action just made by blower fan, the relation that between this, life period is delayed.From wind energy formula (1), the change of wind speed and wind energy change in three cubed relation, therefore, within this delayed time, abundant not to the absorption of wind energy,
（1）
Therefore, in order to make full use of the time of energy transferring between blower fan, the wind of last Fans number is made to be delivered to blower fan in advance, blower fan is allowed to make corresponding action in advance, wind energy can not only be utilized fully, when wind speed is in cut-out wind speed and incision wind speed edge, can also allows its advancement, add the maintenance approach of a blower fan.
Summary of the invention
The problem that the precision that the present invention be directed to forecasting wind speed now is not fundamentally improved, propose a kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan, make full use of the energy transferring relation between blower fan and blower fan, set up cascade blower fan system, realize the performance prediction of ultra-short term wind speed.
Technical scheme of the present invention is: a kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan, specifically comprises the steps:
1) wind energy turbine set set up by cascade blower fan, and the distance measuring adjacent two Fans is H, and before gathering, Fans at instantaneous wind speed is
, instantaneous wind angle is
, rear Fans at instantaneous wind speed is
, instantaneous wind angle is
, the time that front Fans propagates into rear Fans is
, i is the dynamic acquisition moment, then
computing formula is as follows:
；
2) wind speed passing time is tried to achieve in step 1) poor
after, after actual, Fans wind speed is input as
, ask the sea land distribution rate of two Fans
, try to achieve sea land distribution rate according to sea land distribution rate formula, sea land distribution rate
formula is as follows:
，
Obtain sea land distribution rate sequence data, recording foreground wind speed, predict the attenuation rate of corresponding foreground wind speed to backstage wind speed, can convert and obtain backstage wind speed;
3) wind speed passing time is tried to achieve in step 1) poor
after, after actual, Fans wind angle is input as
, ask the wind direction attenuation rate of two Fans
dg (i), try to achieve wind direction attenuation rate according to wind direction attenuation rate formula, wind direction attenuation rate formula is as follows:
，
Obtain wind direction attenuation rate sequence data, recording foreground wind direction, predict the attenuation rate of corresponding foreground wind direction to backstage wind direction, can convert and obtain backstage wind direction.
Beneficial effect of the present invention is: the ultra-short term wind speed dynamic prediction method that the present invention is based on cascade blower fan, realizes the performance prediction of ultra-short term wind speed, generally can apply provide technical foundation for wind energy.
Accompanying drawing explanation
Fig. 1 is the wind energy turbine set model schematic of the ultra-short term wind speed dynamic prediction method cascade blower fan that the present invention is based on cascade blower fan;
Fig. 2 is the ultra-short term wind speed dynamic prediction method cascade prognoses system block diagram that the present invention is based on cascade blower fan.
Embodiment
Wind speed is when being greater than cut-out wind speed, and blower fan will stall, and cut-out wind speed is generally at about 25m/s.For the wind energy turbine set of reality, the distance between two Fans is generally hundreds of rice, and in several power plant of actual investigation, minor increment is 500m.Being delivered to another typhoon in wind energy from a Fans, to there is the regular hour in time poor, and in this time period, signal handling equipment can fully by this data processing, is conveyed to next Fans, using the reference data as this time period rear fan as feed-forward signal.Because blower fan needs to absorb wind energy, the friction of the earth also can cause certain obstruction to the propagation of wind speed, therefore, in communication process, must consider the decay of wind energy.
Fig. 1 is the wind energy turbine set model schematic containing two Fans, and be designated as No.1 and No.2 respectively, fore-and-aft clearance is 500m.For the blower fan used in order reality, it cuts wind speed
general at about 3m/s, and cut-out wind speed
general at about 25m/s, therefore,
with
in scope, ideally, the wind energy transmission between two Fans at least needs 20s.
If No. 1 blower fan at the wind speed of t is
, wind angle is
, No. 2 blower fans at the wind speed of t are
, wind angle is
.The time that No. 1 blower fan propagates into No. 2 blower fans is
, as the formula (2).
（2）
Namely in theory, in the time
afterwards, the instantaneous wind speed value of No. 2 blower fans
, wind angle
but, for actual wind energy turbine set, the absorption of wind energy to be carried out when wind speed to 1 blower fan, and because No. 1 blower fan is within the time period that wind energy is delivered to No. 2 blower fans, absorption containing other peripheral obstacles, therefore, in this transmittance process, wind energy has a certain amount of decay, simultaneously, wind angle also has corresponding change, if sea land distribution rate is
, wind direction attenuation rate is
, calculate such as formula shown in (3), (4).
（3）
（4）
When fan operation, actual parameter is real-time change, general wind energy turbine set, and the memory cycle of data is 5 ~ 10min, as everyone knows, measured collection period is shorter, and precision of prediction can be higher, therefore, by improving the performance of measuring equipment and the capacity of memory element, shorten collection period as far as possible, making data closer to requirement of real-time, just can realize the performance prediction to wind speed and wind angle.
For a series of dynamic data sequence, if No. 1 blower fan instantaneous wind speed sequence that computing machine gathers is
, deflection sequence is
, No. 2 blower fan instantaneous wind speed sequences are
, deflection sequence is
, wherein
, try to achieve according to formula (2)
, the wind energy passing time be between two blower fans is poor.Using blower fan No.1 and No.2 as cascade system, set up its relation, predict the wind speed of No.2 blower fan and wind angle, cascade prognoses system block diagram as shown in Figure 2.
In Fig. 2, for historical wind speed sequence
and
, after trying to achieve wind speed passing time difference, No. 2 actual blower fan wind speed are input as
.Asking the attenuation rate of two Fans
time, due to input wind speed and wind angle signal be positive number, therefore passing ratio link realize right
negate, and then carry out subtraction, obtain attenuation rate sequence
.Wherein Proportional coefficient K=-1, and ask
function
shown in formula (3), (4).
Input signal in Fig. 2 is changed to wind angle signal, is the wind angle performance prediction of No. 2 blower fans.
Such as in a certain wind energy turbine set, have No. 1 blower fan and No. 2 blower fans (being designated as No.1 and No.2 respectively), arranging distance is 500m, is to ensure the real-time of data and synchronism, with the instantaneous wind speed of ccd video camera shooting SCADA supervisory system screen (
with
) and wind angle angle value (
with
), wherein, shooting time is spaced apart 4.5s.To survey wind speed part as shown in table 1.
Table 1
In the 67 groups of data gathered 2 Fans, due in ultra-short term, there is not large sudden change in instantaneous wind speed and wind direction, the wind speed of No. 1 blower fan near 11s, wind angle near 40 °, when distance 500m, when this wind speed propagates into No. 2 blower fans, at least need: 500/11=45s.Again because acquisition time is 4.5s, therefore, in above-mentioned data, i-th group of data of No. 1 blower fan correspond to the i-th+10 group data of No. 2 blower fans.The like, draw 57 groups of data between 1,2 liang of Fans, the attenuation rate of calculation of wind speed and wind direction is such as formula shown in (5), (6) respectively;
Sea land distribution rate:
(5)
Wind angle attenuation rate:
(6)
So, the attenuation rate vector at wind speed and direction angle is drawn
with
.Choose wherein a kind of prediction algorithm, because support vector machine (SVM) generalization ability is strong, have good effect to Small Sample Database prediction, select SVM herein.Respectively to 57 groups
with
predict, getting 52 groups of data is training sample, and predict the wind speed of (namely 5 groups) in following 22.5s and wind direction, the data obtained is respectively
with
.According to attenuation rate formula (5) and (6), computational prediction data are such as formula shown in (7), (8).
Forecasting wind speed data:
(7)
Wind angle predicted data:
(8)
With root mean square relative error (
) and mean absolute percentage error () as weigh prediction precision index, shown in (9), (10).
（9）
（10）
For ease of comparing, 67 groups of data sources are predicted separately the wind speed of No. 2 blower fans and wind angle by this case, use SVM algorithm equally, identical in input vector number, when training parameter is identical, draw prediction root mean square relative error (
) and mean absolute percentage error (
) value, as shown in table 2.
Table 2
Project in comparison sheet 2, the cascade precision of prediction of blower fan comparatively unit prediction effect promotes to some extent.
Claims (1)
1., based on a ultra-short term wind speed dynamic prediction method for cascade blower fan, it is characterized in that, specifically comprise the steps:
1) wind energy turbine set set up by cascade blower fan, and the distance measuring adjacent two Fans is H, and before gathering, Fans at instantaneous wind speed is
, instantaneous wind angle is
, rear Fans at instantaneous wind speed is
, instantaneous wind angle is
, the time that wind energy the past Fans propagates into rear Fans is
, i is the dynamic acquisition moment, then
computing formula is as follows:
；
2) step 1) try to achieve wind energy in the past Fans propagate into after time of Fans
after, after actual, Fans wind speed is input as
, ask the sea land distribution rate of two Fans
, try to achieve sea land distribution rate according to sea land distribution rate formula, sea land distribution rate
formula is as follows:
，
Obtain sea land distribution rate sequence data, recording foreground wind speed, predict the attenuation rate of corresponding foreground wind speed to backstage wind speed, can convert and obtain backstage wind speed;
3) step 1) try to achieve wind energy in the past Fans propagate into after time of Fans
after, after actual, Fans wind angle is input as
, ask the wind direction attenuation rate of two Fans
dg (i), try to achieve wind direction attenuation rate according to wind direction attenuation rate formula, wind direction attenuation rate formula is as follows:
，
Obtain wind direction attenuation rate sequence data, recording foreground wind direction, predict the attenuation rate of corresponding foreground wind direction to backstage wind direction, can convert and obtain backstage wind direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210418541.7A CN102945318B (en) | 2012-10-29 | 2012-10-29 | A kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210418541.7A CN102945318B (en) | 2012-10-29 | 2012-10-29 | A kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102945318A CN102945318A (en) | 2013-02-27 |
| CN102945318B true CN102945318B (en) | 2015-10-28 |
Family
ID=47728261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210418541.7A Expired - Fee Related CN102945318B (en) | 2012-10-29 | 2012-10-29 | A kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102945318B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675355B (en) * | 2013-11-19 | 2016-06-08 | 中国大唐集团科学技术研究院有限公司 | Anemoscope monitoring method and system |
| AT15428U1 (en) * | 2016-03-16 | 2017-08-15 | Uptime Holding Gmbh | Method for determining the wind speed and installation for carrying it out |
| CN107304746B (en) * | 2016-04-20 | 2020-07-17 | 北京天诚同创电气有限公司 | Wind generating set and operation control method and device thereof |
| CN107895058B (en) * | 2017-07-19 | 2018-08-31 | 厦门理工学院 | A kind of method of quick identification wind speed Optimal Distribution rule |
| EP3533997A1 (en) * | 2018-02-28 | 2019-09-04 | Siemens Gamesa Renewable Energy A/S | Estimating free-stream inflow at a wind turbine |
| CN111652431B (en) * | 2020-05-29 | 2023-04-18 | 华润电力投资有限公司北方分公司 | Wind power plant power prediction method, device, equipment and storage medium |
| CN112163259B (en) * | 2020-09-27 | 2021-11-02 | 西南交通大学 | Method for determining equivalent wind speed ratio of wind profile of typical railway infrastructure |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727538A (en) * | 2009-09-26 | 2010-06-09 | 山东科技大学 | Wind turbines input wind speed equivalent method taking into account influence of wind direction |
| CN102682207A (en) * | 2012-04-28 | 2012-09-19 | 中国科学院电工研究所 | Ultrashort combined predicting method for wind speed of wind power plant |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005030988A (en) * | 2003-07-09 | 2005-02-03 | East Japan Railway Co | Wind speed predicting system and wind speed prediction method |
-
2012
- 2012-10-29 CN CN201210418541.7A patent/CN102945318B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727538A (en) * | 2009-09-26 | 2010-06-09 | 山东科技大学 | Wind turbines input wind speed equivalent method taking into account influence of wind direction |
| CN102682207A (en) * | 2012-04-28 | 2012-09-19 | 中国科学院电工研究所 | Ultrashort combined predicting method for wind speed of wind power plant |
Non-Patent Citations (2)
| Title |
|---|
| The Research and Application of Wavelet-Support Vector Machine on Short-term Wind Power Prediction;Jie Shi等;《Proceedings of the 8th World Congress on Intelligent Control and Automation》;20100709;第4927-4931页 * |
| 短期负荷预测的支持向量机方法研究;李元诚等;《中国电机工程学报》;20030630;第23卷(第6期);第55-59页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102945318A (en) | 2013-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102945318B (en) | A kind of ultra-short term wind speed dynamic prediction method based on cascade blower fan | |
| Shi et al. | Forecasting power output of photovoltaic systems based on weather classification and support vector machines | |
| CN102930175B (en) | Assessment method for vulnerability of smart distribution network based on dynamic probability trend | |
| CN109492315B (en) | Spatio-temporal correlation wind-solar sequence simulation method based on Copula function | |
| CN102545707B (en) | Take generator unit as the generated power forecasting method and system of fundamental forecasting unit | |
| Fang et al. | Application of gray relational analysis to k-means clustering for dynamic equivalent modeling of wind farm | |
| CN103473393B (en) | A kind of transmission of electricity nargin Controlling model modeling method considering random chance | |
| CN103106314B (en) | The sequential modelling method of probabilistic of solar photovoltaic power output power | |
| CN108667005B (en) | Power grid static and dynamic combination vulnerability assessment method considering new energy influence | |
| CN105243516A (en) | Distributed photovoltaic power generation maximum consumption capability calculation system based on active power distribution network | |
| CN104463697A (en) | Risk assessment method for power system including large-scale wind power | |
| Wang et al. | Short-term wind speed forecasting combined time series method and arch model | |
| Yurtseven et al. | Sensorless fault detection method for photovoltaic systems through mapping the inherent characteristics of PV plant site: Simple and practical | |
| CN103996079A (en) | Wind power weighting predication method based on conditional probability | |
| CN108549999A (en) | Offshore wind farm power quality data analysis method based on wind speed interval and system | |
| CN107403015A (en) | A kind of short-term luminous power Forecasting Methodology based on Time Series Similarity | |
| Dellosa et al. | Resource assessment of a floating solar photovoltaic (FSPV) system with artificial intelligence applications in Lake Mainit, Philippines | |
| Sun et al. | A powerful Bio-Inspired optimization algorithm based PV cells diode models parameter estimation | |
| CN104346659A (en) | Short-term power generation prediction method applied to high-concentration-ratio photovoltaic power generation system | |
| CN106126934A (en) | A kind of photovoltaic generation correlation metric acquisition methods | |
| CN105574619A (en) | Solar photovoltaic power generation output prediction system, and prediction method thereof | |
| CN111488553B (en) | Solar irradiance calculating method and device | |
| CN103530508B (en) | Method for establishing wind speed-power conversion probability model | |
| CN103268416A (en) | Wind speed prediction method based on STCP-BP | |
| CN106651163A (en) | Capacity confidence level evaluation method for multiple wind power plants on the basis of Copula function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151028 Termination date: 20181029 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |