CN107732962A - It is a kind of to abandon wind decrement method based on what ultra-short term abandoned wind curve prediction - Google Patents
It is a kind of to abandon wind decrement method based on what ultra-short term abandoned wind curve prediction Download PDFInfo
- Publication number
- CN107732962A CN107732962A CN201710902996.9A CN201710902996A CN107732962A CN 107732962 A CN107732962 A CN 107732962A CN 201710902996 A CN201710902996 A CN 201710902996A CN 107732962 A CN107732962 A CN 107732962A
- Authority
- CN
- China
- Prior art keywords
- wind
- ultra
- short term
- curve
- blower fan
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000007613 environmental effect Effects 0.000 claims abstract description 12
- 238000012937 correction Methods 0.000 claims description 16
- 238000005265 energy consumption Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000013316 zoning Methods 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 7
- 238000009987 spinning Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 238000004870 electrical engineering Methods 0.000 abstract description 2
- 238000000354 decomposition reaction Methods 0.000 description 5
- 230000005684 electric field Effects 0.000 description 5
- 238000007363 ring formation reaction Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 238000007664 blowing Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H02J3/386—
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- 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
- Y02E10/76—Power conversion electric or electronic aspects
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention be it is a kind of abandon wind decrement method based on what ultra-short term abandoned wind curve prediction, belong to electrical engineering active power dispatch field, wind decrement method abandoned based on what ultra-short term abandoned wind curve prediction the present invention relates to a kind of.It is monitored and records for the environmental data related to abandoning air quantity, blower fan data, load data and self-defining data, and weak relevant environment predictive index, strong correlation environmental forecasting index, strong correlation blower fan predictive index, region load amendment total amount, region load amendment five important parameters of peak-valley difference are calculated according to four class data, and then build and abandon wind curve prediction function.The curve prediction function can reach the effect of adjustment precision of prediction by improving DATA REASONING frequency and adjustment prediction calculating time interval.Accurately predicted by abandoning wind power to wind power plant, provide foundation for electric network coordination scheduling, for optimizing frequency modulation and spinning reserve capacity, on-line optimization Unit Combination and economic load dispatching, air quantity is abandoned in reduction.
Description
Technical field
Belong to electrical engineering active power dispatch field, the present invention relates to a kind of wind of abandoning that wind curve prediction is abandoned based on ultra-short term to subtract
Amount method.
Background technology
As wind power integration power network scale increasingly increases, wind-abandoning phenomenon is also increasingly apparent, causes the wave to wind energy resources
Take and the loss of power system resource, and significantly limit the further development of wind energy.Therefore, the prediction for abandoning wind curve is shown
Obtain ever more important.
Existing ultra-short term abandons the method that wind Forecasting Methodology uses wind power output curve to subtract load curve, uses similar day
Method, artificial neural network method, wavelet analysis method, SVMs.Similar day method can only be directed to existing historical data and be quantified
Analysis, flexibility are poor；Artificial neural network method is easily absorbed in local minimum, and convergence rate is slow；Wavelet analysis method uses
When highly dependent upon wavelet basis selection, extreme influence precision of prediction；With data volume increase and dimension during SVMs computing
Increase greatly improves to hardware requirement.
Prior art one《The Short-term Forecasting Model of output of wind electric field in large-scale wind power interconnected electric power system economic load dispatching》
(Proceedings of the CSEE 2010 year the 13rd phase of volume 30), in the output of wind electric field Short-term Forecasting Model pair based on neutral net
Output of wind electric field is carried out on the basis of prediction, it is contemplated that the prediction error of history and application is based on improved neural network prediction
Technology carries out error prediction to the prediction error in future, using the short-term prediction of the prediction error correction output of wind electric field, builds
The basic wind power plant that can meet large-scale wind power interconnected electric power system economic load dispatching time scale and precision scale requirement has been found to go out
Power Short-term Forecasting Model.
A pair of output of wind electric field Forecasting Methodologies based on neutral net of prior art are improved, the error correction side of proposition
Case can efficiently reduce the prediction error of forecasting system, but work as the change of the variation tendency and prediction error of error prediction
When trend is conversely or variation tendency does not have rule, its error correction scheme needs further to be studied.
Prior art two《It is pre- based on the short-term wind-electricity load for improving least square method supporting vector machine and pre- measuring error correction
Survey》(electric power system protection and control 2015 year o. 11th of volume 43) introduces Lifting Wavelet and decomposes initial data, can effectively carry
Its principal character is taken, so as to overcome the randomness of wind power plant.Then using least square method supporting vector machine to the signal after decomposition
Give a forecast, ensure that precision of prediction.Then with error correcting system amendment prediction result, the appearance of larger error dot is reduced,
Improve the stability of prediction result.
Prior art two is directed to the phenomenon for having more larger error dot to occur, and increase error prediction is repaiied to prediction result
Just, the purpose for improving precision of prediction is reached, but selection dependence of the Lifting Wavelet to wavelet basis is higher.
Prior art three《Ultra-short term wind power output forecast model based on small echo-Atomic Decomposition》(Chinese journal of scientific instrument
The 10th phase of volume 37 in 2016) propose the wind power output ultra-short term forecast model based on small echo-Atomic Decomposition.The model uses
Wavelet decomposition is as preposition link, to be divided based on atomic expression from prediction with the remnants based on least square method supporting vector machine
Amount is predicted as fundamental construction Atomic Decomposition forecast model, and the high-low frequency weight of wind power output is predicted respectively, and by result
Addition obtains final predicted value.
Hysteresis be present when wind power output occurs significantly to vibrate in prior art three.Therefore in next step to wind power output
When carrying out ultra-short term forecasting research, influence of the meteorologic factor to actual value and predicted value can be introduced, includes forecast model more
Environment and climatic information so that precision of prediction is higher.
The content of the invention
The present invention goal in research be：
A large amount of the reason for abandoning wind are that the uncertainty that power network dispatching system is predicted wind power output is held and do not use attitude,
Conventional power unit does not consider that wind-powered electricity generation generates electricity when combining, discharge wind-powered electricity generation after daily Unit Combination and include system in right amount, during non-electrical peak
Duan Zaocheng largely abandons wind.Therefore present invention proposition is a kind of abandons wind decrement method based on the ultra-short term for abandoning wind curve prediction.
Natural conditions parameter and operation of power networks parameter are combined, and proposes corrected parameter, ultra-short term wind power plant is obtained and abandons
Wind power curve function.The function curve can refine each parameter measurement time interval, reach raising by improving measurement frequency
The purpose of prediction curve precision.Natural parameter and operational factor are measured by data acquisition module first, obtained through data computation module
To wind power curve function parameters are abandoned, ultra-short term is finally drawn out by data processing module and abandons wind prediction curve, to help
Air quantity is abandoned in network optimization frequency modulation and spinning reserve capacity, on-line optimization Unit Combination and economic load dispatching, reduction.
To achieve these goals, in view of the shortcomings of the prior art, the present invention provides a kind of ultra-short term and abandons wind curve prediction
Method.
Technical scheme is as follows：
Step 1：Data acquisition module chooses the parameter being had an impact to abandoning wind curve prediction value and measures and monitor：
The parameter, including：Zone leveling temperature Tqy, zone leveling humidity Hqy, zone leveling wind speed vqy, zone leveling
Atmospheric pressure pqy, zone leveling intensity of illumination lqy, blower fan installed capacity gfj, region load total amount Wqy, region load peak-valley difference
Cqy；
Step 2：Blower fan warp-wise ascent, the monitoring of blower fan broadwise ascent and input data acquisition module, region energy consumption are repaiied
Positive coefficient, the factor that extends, abandon the calculating of wind curve die-away time parameter and input data acquisition module：
Define blower fan warp-wise ascent Afj, blower fan broadwise ascent Bfj, region energy consumption modified index αqy, extension factor-betaqy,
Abandon wind curve die-away time tsj。
Wherein ɑ is warp-wise angle, i.e., natural wind in the horizontal direction with fan blade central shaft angle；B is broadwise angle, i.e., certainly
Right wind in the vertical direction and fan blade central shaft angle；αqyFor for correcting the holiday factor of energy consumption level；βqyFor weighing apparatus
The second-order correction coefficient that energy consumption changes before and after amount festivals or holidays.
Abandon wind curve die-away time tsjFor current time and morning zero when difference absolute value, in units of hour.
Parameter acquisition frequency is higher in step 1 and step 2, by increasing data computation module calculation times, can reach
Improve the purpose of precision of prediction.
Step 3：Data computation module calculation procedure 1.It is weak relevant environment predictive index, strong correlation environmental forecasting index, strong
Phase Blowing stopper predictive index calculates：
Step 1 data measured and step 2 calculating parameter are handled, obtain weak relevant environment predictive index x1, Qiang Xiang
Cyclization border predictive index x2, strong correlation blower fan predictive index x3Totally 3 predictive indexs.Weak correlation in 3 predictive index definition of the above
Refer to that the coefficient is smaller to abandoning wind prediction curve influence degree, strong correlation is higher than weak correlation relative to weak correlation, its influence degree
More than 10 times of index.
The step 3, including：
Step 3.1：By zone leveling atmospheric pressure pqy, zone leveling intensity of illumination lqy, zone leveling humidity HqyObtain weak
Relevant environment predictive index x1, weak relevant environment predictive index x1It is as follows to calculate function：
Step 3.2：By zone leveling temperature Tqy, zone leveling wind speed vqyObtain strong correlation external prediction index x2, Qiang Xiang
Cyclization border predictive index x2It is as follows to calculate function：
Step 3.3：By blower fan installed capacity gfj, blower fan warp-wise ascent Afj, blower fan broadwise ascent BfjObtain strong correlation
Blower fan predictive index x3, strong correlation blower fan predictive index x3It is as follows to calculate function：
Step 4：Data computation module calculation procedure 2.Region load amendment total amount, region load amendment peak-valley difference calculate：
Zoning load total amount Wqy, region load peak-valley difference CqyCorrection factor, new parameter region is obtained after amendment and is born
Lotus amendment total amount W 'qyAnd region load amendment peak-valley difference C 'qy。
The step 4, including：
Step 4.1：Zoning load total amount WqyCorrection factor simultaneously obtains new parameter region load amendment total amount W 'qy：
Step 4.2：Zoning load total amount CqyCorrection factor simultaneously obtains new parameter region load amendment peak-valley difference C 'qy：
Step 5：Data computation module calculation procedure 3.Abandon the foundation of wind curve model and parameter calculates：
The weak relevant environment predictive index x obtained by step 3 and step 41, strong correlation environmental forecasting index x2, strong correlation wind
Machine predictive index x3And region load amendment total amount W 'qy, region load amendment peak-valley difference C 'qyEstablish ultra-short term and abandon wind prediction mould
Type：
P (t) is that ultra-short term abandons wind prediction curve function, and the model is applied to prediction 1 day and abandons wind song i.e. within 24 hours
Line.Wherein parameter ξ1,ξ2,ξ3,ξ4Calculating function it is as follows：
5 steps more than, obtain ultra-short term and abandon wind prediction curve function parameters.
Step 6：Data processing module draws ultra-short term according to parameters and abandons wind prediction curve, is carried for electric network coordination scheduling
For foundation.
Data at least once are gathered within a period and draw curve, and the curve is next period, i.e., after 1 hour
Abandon wind prediction curve, with this reach ultra-short term abandon wind prediction purpose.Pass through multiple data acquisition, calculating, place in a cycle
Reason, can correct and abandon wind prediction curve, improve precision of prediction.
It is credible predicted value that prediction, which is abandoned after air quantity is multiplied by reliability forecasting coefficient 0.8,.
So far the wind prediction curve of abandoning after handling carries out credible prediction, power network dispatching system base to the air quantity of abandoning after the short time
In credible predicted value, it is possible to achieve excellent when credible predicted value is more than capacity (such as 60MW) of conventional fired power generating unit in locality
Change frequency modulation and spinning reserve capacity, on-line optimization Unit Combination and economic load dispatching, air quantity is abandoned in reduction.
Beneficial effect
The present invention is supervised for the environmental data related to abandoning air quantity, blower fan data, load data and self-defining data
Survey and record, and it is pre- according to the weak relevant environment predictive index of four class data calculating, strong correlation environmental forecasting index, strong correlation blower fan
Index, region load amendment total amount, region load amendment five important parameters of peak-valley difference are surveyed, and then builds and abandons wind curve prediction letter
Number.Wind premeasuring can be abandoned in real time according to wind curve prediction function moment result of calculation is abandoned, by a large amount of Piecewise Operations
It may be monitored and wind prediction curve is continuously abandoned in data period.The curve prediction function can be by improving DATA REASONING frequency
Rate and adjustment prediction calculate the effect that time interval reaches adjustment precision of prediction.Carried out accurately by abandoning wind power to wind power plant
Prediction, foundation is provided for electric network coordination scheduling, for optimizing frequency modulation and spinning reserve capacity, on-line optimization Unit Combination and economy
Air quantity is abandoned in load scheduling, reduction.
Brief description of the drawings
Fig. 1 is that a kind of in the specific embodiment of the invention abandons wind decrement method stream based on what ultra-short term abandoned wind curve prediction
Cheng Tu.
Embodiment
The geographic range and time range for abandoning wind curve are clearly calculated, ultra-short term is built according to the following steps and abandons wind prediction song
Line：
Step 1：Data acquisition module chooses the parameter being had an impact to abandoning wind curve prediction value and measures and monitor, and counts
Precision is higher when measuring time interval below 1 hour；
By monitoring, somewhere 22 days 06 June in 2017 of mean temperature T when 07qy=23 DEG C, medial humidity Hqy=
63%RH, mean wind speed vqy=14km/h, Zenith Distance pressure pqy=102kPa, zone leveling intensity of illumination lqy=
52370lx, blower fan installed capacity gfj=180MW, load total amount Wqy=327MW, load peak-valley difference Cqy=8MW.
Step 2：Blower fan warp-wise ascent, the monitoring of blower fan broadwise ascent and input data acquisition module, region energy consumption are repaiied
Positive coefficient, the factor that extends, abandon the calculating of wind curve die-away time parameter and input data acquisition module：
Define blower fan warp-wise ascent Afj, blower fan broadwise ascent Bfj, region energy consumption modified index αqy, extension factor-betaqy,
Abandon wind curve die-away time tsj。
Wherein ɑ is warp-wise angle, i.e., natural wind in the horizontal direction with fan blade central shaft angle；B is broadwise angle, i.e., certainly
Right wind in the vertical direction and fan blade central shaft angle；αqyFor for correcting the holiday factor of energy consumption level；βqyFor weighing apparatus
The second-order correction coefficient that energy consumption changes before and after amount festivals or holidays.
Abandon wind curve die-away time tsjFor current time and morning zero when difference absolute value, in units of hour.
This area's 22 days 06 June in 2017 warp-wise angle ɑ=0 when 07,αqy=1, βqy=1, tsj=6.Calculate
A can be obtainedfj=1, Bfj=44.90.
Step 3：Data computation module calculation procedure 1.It is weak relevant environment predictive index, strong correlation environmental forecasting index, strong
Phase Blowing stopper predictive index calculates：
Step 1 data measured and step 2 calculating parameter are handled, obtain weak relevant environment predictive index x1, Qiang Xiang
Cyclization border predictive index x2, strong correlation blower fan predictive index x3Totally 3 predictive indexs.Weak correlation in 3 predictive index definition of the above
Refer to that the coefficient is smaller to abandoning wind prediction curve influence degree, strong correlation is higher than weak correlation relative to weak correlation, its influence degree
More than 10 times of index.
The step 3, including：
Step 3.1：By zone leveling atmospheric pressure pqy, zone leveling intensity of illumination lqy, zone leveling humidity HqyObtain weak
Relevant environment predictive index x1, weak relevant environment predictive index x1It is as follows to calculate function：
Step 3.2：By zone leveling temperature Tqy, zone leveling wind speed vqyObtain strong correlation external prediction index x2, Qiang Xiang
Cyclization border predictive index x2It is as follows to calculate function：
Step 3.3：By blower fan installed capacity gfj, blower fan warp-wise ascent Afj, blower fan broadwise ascent BfjObtain strong correlation
Blower fan predictive index x3, strong correlation blower fan predictive index x3It is as follows to calculate function：
Weak relevant environment predictive index x can be calculated by steps 1 and 2 the data obtained1=13.20, strong correlation environmental forecasting refers to
Number x2=465.69, strong correlation blower fan predictive index x3=8372.22.
Step 4：Data computation module calculation procedure 2.Region load amendment total amount, region load amendment peak-valley difference calculate：
Zoning load total amount Wqy, region load peak-valley difference CqyCorrection factor, new parameter region is obtained after amendment and is born
Lotus amendment total amount W 'qyAnd region load amendment peak-valley difference C 'qy。
The step 4, including：
Step 4.1：Zoning load total amount WqyCorrection factor simultaneously obtains new parameter region load amendment total amount W 'qy：
Step 4.2：Zoning load total amount CqyCorrection factor simultaneously obtains new parameter region load amendment peak-valley difference C 'qy：
W ' is calculatedqy=155.23MW, C 'qy=6.35MW.
Step 5：Data computation module calculation procedure 3.Abandon the foundation of wind curve model and parameter calculates：
The weak relevant environment predictive index x obtained by step 3 and step 41, strong correlation environmental forecasting index x2, strong correlation wind
Machine predictive index x3And region load amendment total amount W 'qy, region load amendment peak-valley difference C 'qyEstablish ultra-short term and abandon wind prediction mould
Type：
P (t) is that ultra-short term abandons wind prediction curve function, and the model is applied to prediction 1 day and abandons wind song i.e. within 24 hours
Line.Wherein parameter ξ1,ξ2,ξ3,ξ4Calculating function it is as follows：
ξ is calculated by step 3,4 gained ginsengs1=3.24, ξ2=0.55, ξ3=12.33, ξ4=0.72.
Then P (t)=arccos [- ξ1·e-t·(1-ξ3·e-t-1)·(1-ξ3·e-t+1)]+ξ2·W′qy+ξ4·C′qy
=arccos [- 3.24e-t·(1-12.33·e-t-1)·(1-12.33·e-t+1)]+89.95,6≤t≤7
Finally drawing out ultra-short term up to 07 when in this area's 22 days 06 June in 2017 by data processing module, to abandon wind prediction bent
Line.
It is 163.25MW that thus obtained subsequent time, which abandons wind premeasuring, and it is credible premeasuring that the value, which is multiplied by coefficient 0.8,
130.6MW。
So far treated credible premeasuring can reduce by two conventional 60MW fired power generating units online or reduce two in real time
Platform cost higher thermal is standby, realizes optimization frequency modulation and spinning reserve capacity, on-line optimization Unit Combination and economic load dispatching, subtracts
Air quantity is abandoned less.
By actual schedule data, for prediction curve worst error within 9%, precision of prediction is higher.
Embodiments of the invention are these are only, are not intended to limit the invention, it is therefore, all in the spirit and principles in the present invention
Within, any modification, equivalent substitution and improvements done etc., it should be included within scope of the presently claimed invention.
Claims (11)
1. a kind of ultra-short term abandons wind curve prediction method, it is characterised in that comprises the following steps：
Step 1：Data acquisition module chooses the parameter being had an impact to abandoning wind curve prediction value and measures and monitor, parameter bag
Include：Zone leveling temperature Tqy, zone leveling humidity Hqy, zone leveling wind speed vqy, zone leveling atmospheric pressure pqy, zone leveling
Intensity of illumination lqy, blower fan installed capacity gfj, region load total amount Wqy, region load peak-valley difference Cqy；
Step 2：Blower fan warp-wise ascent, the monitoring of blower fan broadwise ascent and input data acquisition module, region energy consumption amendment system
Number, the factor that extends, abandon the calculating of wind curve die-away time parameter and input data acquisition module；
Step 3：Data computation module calculation procedure 1, weak relevant environment predictive index, strong correlation environmental forecasting index, strong correlation
Blower fan predictive index calculates；
Step 4：Data computation module calculation procedure 2, region load amendment total amount, region load amendment peak-valley difference calculate；
Step 5：Data computation module calculation procedure 3, abandons the foundation of wind curve model and parameter calculates；
Step 6：Data processing module according to parameters draw ultra-short term abandon wind prediction curve, for electric network coordination dispatch provide according to
According to.
2. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 2
Define blower fan warp-wise ascent Afj, blower fan broadwise ascent Bfj, region energy consumption modified index αqy, extension factor-betaqy, abandon wind curve
Die-away time tsj
Wherein ɑ is warp-wise angle, i.e., natural wind in the horizontal direction with fan blade central shaft angle；B is broadwise angle, i.e. natural wind
In the vertical direction and fan blade central shaft angle；αqyFor for correcting the holiday factor of energy consumption level；βqySaved to weigh
The second-order correction coefficient that energy consumption changes before and after holiday；
Abandon wind curve die-away time tsjFor current time and morning zero when difference absolute value, in units of hour.
3. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that described step 3 is
Step 1 data measured and step 2 calculating parameter are handled, obtain weak relevant environment predictive index x1, strong correlation environment it is pre-
Survey index x2, strong correlation blower fan predictive index x3Totally 3 predictive indexs；Weak correlation refers to that this is in 3 predictive index definition of the above
Several smaller to abandoning wind prediction curve influence degree, strong correlation is higher than weak 10 times of the index of correlation relative to weak correlation, its influence degree
More than.
4. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 3
Including step 3.1：By zone leveling atmospheric pressure pqy, zone leveling intensity of illumination lqy, zone leveling humidity HqyObtain weak correlation
Environmental forecasting index x1, weak relevant environment predictive index x1It is as follows to calculate function：
。
5. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 3
Including step 3.2：By zone leveling temperature Tqy, zone leveling wind speed vqyObtain strong correlation external prediction index x2, strong correlation ring
Border predictive index x2It is as follows to calculate function：
。
6. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 3
Including step 3.3：By blower fan installed capacity gfj, blower fan warp-wise ascent Afj, blower fan broadwise ascent BfjObtain strong correlation blower fan
Predictive index x3, strong correlation blower fan predictive index x3It is as follows to calculate function：
。
7. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 4
Zoning load total amount Wqy, region load peak-valley difference CqyCorrection factor, it is total that new parameter region load amendment is obtained after amendment
Measure Wq′yAnd region load amendment peak-valley difference C 'qy。
8. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 4
Including step 4.1：Zoning load total amount WqyCorrection factor simultaneously obtains new parameter region load amendment total amount W 'qy：
。
9. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that in described step 4
Including step 4.2：Zoning load total amount CqyCorrection factor simultaneously obtains new parameter region load amendment peak-valley difference C 'qy：
。
10. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that described step 5
The weak relevant environment predictive index x obtained by step 3 and step 41, strong correlation environmental forecasting index x2, strong correlation blower fan prediction refer to
Number x3And region load amendment total amount W 'qy, region load amendment peak-valley difference C 'qyEstablish ultra-short term and abandon wind forecast model：
P (t) is that ultra-short term abandons wind prediction curve function, and ultra-short term refers to that the model is applied within prediction 1 day i.e. 24 hour
Abandon wind curve.Wherein parameter ξ1,ξ2,ξ3,ξ4Calculating function it is as follows：
。
11. according to claim 1, a kind of ultra-short term abandons wind curve prediction method, it is characterised in that described step 6
Ultra-short term is drawn by data processing module by step 5 gained parameters and abandons wind curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710902996.9A CN107732962B (en) | 2017-09-29 | 2017-09-29 | Abandoned wind reduction method based on ultra-short term abandoned wind curve prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710902996.9A CN107732962B (en) | 2017-09-29 | 2017-09-29 | Abandoned wind reduction method based on ultra-short term abandoned wind curve prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107732962A true CN107732962A (en) | 2018-02-23 |
| CN107732962B CN107732962B (en) | 2020-12-01 |
Family
ID=61208959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710902996.9A Active CN107732962B (en) | 2017-09-29 | 2017-09-29 | Abandoned wind reduction method based on ultra-short term abandoned wind curve prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107732962B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160653A (en) * | 2019-12-31 | 2020-05-15 | 国网内蒙古东部电力有限公司经济技术研究院 | Distributed energy storage system wind power consumption capacity monitoring method based on cloud computing |
| CN112868157A (en) * | 2018-10-15 | 2021-05-28 | 乌本产权有限公司 | Method for feeding electric power into an electric supply network and wind park |
| CN112952839A (en) * | 2021-01-29 | 2021-06-11 | 国网内蒙古东部电力有限公司 | Power distribution network economic dispatching evaluation method based on controllable load |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082172A1 (en) * | 2008-09-25 | 2010-04-01 | Korea Electric Power Corporation | Load forecasting analysis system for calculating customer baseline load |
| CN105224733A (en) * | 2015-09-19 | 2016-01-06 | 东北电力大学 | Wind power is abandoned wind data feature and is known method for distinguishing |
| CN105552970A (en) * | 2016-02-25 | 2016-05-04 | 华北电力科学研究院有限责任公司 | Method and apparatus for improving accuracy of predicting power of wind power station |
| CN106505635A (en) * | 2016-09-20 | 2017-03-15 | 北京恒泰实达科技股份有限公司 | Abandon the minimum active power dispatch model of wind and scheduling system |
| CN107194625A (en) * | 2017-07-25 | 2017-09-22 | 国家电网公司 | Wind power plant based on neutral net abandons wind-powered electricity generation amount appraisal procedure |
-
2017
- 2017-09-29 CN CN201710902996.9A patent/CN107732962B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082172A1 (en) * | 2008-09-25 | 2010-04-01 | Korea Electric Power Corporation | Load forecasting analysis system for calculating customer baseline load |
| CN105224733A (en) * | 2015-09-19 | 2016-01-06 | 东北电力大学 | Wind power is abandoned wind data feature and is known method for distinguishing |
| CN105552970A (en) * | 2016-02-25 | 2016-05-04 | 华北电力科学研究院有限责任公司 | Method and apparatus for improving accuracy of predicting power of wind power station |
| CN106505635A (en) * | 2016-09-20 | 2017-03-15 | 北京恒泰实达科技股份有限公司 | Abandon the minimum active power dispatch model of wind and scheduling system |
| CN107194625A (en) * | 2017-07-25 | 2017-09-22 | 国家电网公司 | Wind power plant based on neutral net abandons wind-powered electricity generation amount appraisal procedure |
Non-Patent Citations (1)
| Title |
|---|
| 杨茂等: "风电功率弃风数据特征识别方法研究", 《中国电力》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112868157A (en) * | 2018-10-15 | 2021-05-28 | 乌本产权有限公司 | Method for feeding electric power into an electric supply network and wind park |
| CN111160653A (en) * | 2019-12-31 | 2020-05-15 | 国网内蒙古东部电力有限公司经济技术研究院 | Distributed energy storage system wind power consumption capacity monitoring method based on cloud computing |
| CN111160653B (en) * | 2019-12-31 | 2023-06-27 | 国网内蒙古东部电力有限公司经济技术研究院 | Distributed energy storage system wind power consumption capability monitoring method based on cloud computing |
| CN112952839A (en) * | 2021-01-29 | 2021-06-11 | 国网内蒙古东部电力有限公司 | Power distribution network economic dispatching evaluation method based on controllable load |
| CN112952839B (en) * | 2021-01-29 | 2022-09-20 | 国网内蒙古东部电力有限公司 | Power distribution network economic dispatching evaluation method based on controllable load |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107732962B (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
| CN110880789B (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
| CN107732962A (en) | It is a kind of to abandon wind decrement method based on what ultra-short term abandoned wind curve prediction | |
| CN102184453A (en) | Wind power combination predicting method based on fuzzy neural network and support vector machine | |
| CN102102626A (en) | Method for forecasting short-term power in wind power station | |
| Wu et al. | Stratification-based wind power forecasting in a high-penetration wind power system using a hybrid model | |
| CN107204615A (en) | A kind of method and system for realizing power prediction | |
| WO2023216576A1 (en) | Photovoltaic power generation short-term power prediction method and system | |
| CN110705771A (en) | Method and device for predicting and optimizing power generation power of new energy of regional power grid | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| Shah et al. | A novel prediction error-based power forecasting scheme for real pv system using pvusa model: A grey box-based neural network approach | |
| CN105046349B (en) | It is a kind of meter and wake effect wind power forecasting method | |
| Han et al. | Optimal scheduling of distribution system with edge computing and data-driven modeling of demand response | |
| Saini et al. | Gated recurrent unit (gru) based short term forecasting for wind energy estimation | |
| CN115660232A (en) | Ultra-short-term prediction method, device and system for wind power | |
| CN105844350B (en) | Short-term wind power prediction system based on covariance optimal combination model | |
| Alharbi et al. | Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks | |
| CN103927598A (en) | Photovoltaic generation power prediction method based on self-learning radial basis function | |
| CN111967660B (en) | Ultra-short-term photovoltaic prediction residual error correction method based on SVR | |
| CN112580862A (en) | Method and device for predicting short-term real-time power generation power of distributed photovoltaic system | |
| Yang et al. | Day‐ahead wind power combination forecasting based on corrected numerical weather prediction and entropy method | |
| CN116667333A (en) | New energy power generation and power consumption prediction system and method | |
| CN112036672B (en) | New energy power generation ultra-short term power prediction method and system based on iterative correction | |
| CN116231749A (en) | New energy power system dispatching method based on digital twin | |
| CN110705769A (en) | New energy power generation power prediction optimization method and device |
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 |