CN106779208A - A kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology - Google Patents
A kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology Download PDFInfo
- Publication number
- CN106779208A CN106779208A CN201611135551.4A CN201611135551A CN106779208A CN 106779208 A CN106779208 A CN 106779208A CN 201611135551 A CN201611135551 A CN 201611135551A CN 106779208 A CN106779208 A CN 106779208A
- Authority
- CN
- China
- Prior art keywords
- wind
- power plant
- wind power
- data
- moment
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 25
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 238000013277 forecasting method Methods 0.000 title claims abstract description 14
- 238000004088 simulation Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000013480 data collection Methods 0.000 claims abstract description 5
- 101100315388 Danio rerio tshz1 gene Proteins 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 13
- 238000000205 computational method Methods 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 3
- 230000005684 electric field Effects 0.000 description 8
- 238000013210 evaluation model Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006467 substitution reaction 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)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses the wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology, it includes the 1, basic data of collection wind power plant n Fans, historical data and real time data；2nd, simulation calculates the ξ wind speed and direction of moment whole wind power plant hub height；3rd, simulation calculates the ξ temperature of moment whole wind power plant hub height；4th, the ξ moment wind power plant atmospheric density, humidity and air pressure are calculated；5th, the virtual anemometer tower data at wind power plant ξ moment are obtained；6th, the virtual anemometer tower data set of wind power plant history is obtained according to step 1-5；7th, set up the supporting vector machine model of wind power plant ultra-short term power prediction and trained with the virtual anemometer tower data set of wind power plant history；The 8th, the virtual anemometer tower data at wind power plant ξ moment are substituted into the model for training, the ultra-short term power prediction Value Data collection at wind power plant ξ moment is obtained；Solve prior art wind power plant ultra-short term power prediction precision it is relatively low the problems such as.
Description
Technical field
The invention belongs to wind-power electricity generation short term power Predicting Technique, more particularly to a kind of wind based on virtual anemometer tower technology
Electric ultra-short term power forecasting method.
Background technology
The blower fan arrangement of plateau mountain area wind power plant, it is more complex compared to Plain wind power plant.The wind of plateau mountain area wind power plant
Machine is arranged, and does not have unified rule, and its arrangement will not only meet the spacing and array pitch principle of Plain wind power plant, in addition it is also necessary to base area
The concrete condition of shape landforms, is arranged in ridge region as far as possible.Then, the distance between blower fan typically all compares Plain without rule
The blower fan spacing of wind power plant is big, and the wind power plant occupied area in plateau mountain area is also big.Now, the influence of blower fan wake flow is frequently not shadow
Ring output of wind electric field important factor, and in wind power plant wind speed and direction micro-variations, on output of wind electric field influence it is very big.
Because the location of plateau mountain area wind power plant each Wind turbines have certain particularity, its turbulent flow with return
The influence of wind is all different, and wind speed correlation is good between causing the same anemometer tower different height in plateau mountain area, and same wind power plant is each
Wind speed correlation between anemometer tower is bad so that anemometer tower does not have enough representativenesses, any one or several anemometer towers or
Blower fan anemometer data all cannot comprehensively represent the whole mountain region wind power plant of complicated landform, and due to plateau mountain area distinguishingly
Reason position and Meteorological Characteristics cause that icing disaster takes place frequently, the anemometer tower for having stood because of icing or long neglected and in disrepair and damage or tower, or
Person's icing causes instrument for wind measurement to damage or short time work failure, surveys wind data substantially abnormal, insincere.Due to problem above pole
Easily cause the anemometer tower quality of data poor, and prior art for plateau mountain area wind power plant ultrashort-term wind power power prediction still
Carried out using anemometer tower data, thus cause wind power plant wind-powered electricity generation ultra-short term power prediction precision it is relatively low the problems such as.
The content of the invention：
The technical problem to be solved in the present invention：A kind of wind-powered electricity generation ultra-short term power prediction based on virtual anemometer tower technology is provided
Method, anemometer tower data are still used to solve prior art for plateau mountain area wind power plant ultrashort-term wind power power prediction
To carry out, thus cause wind power plant wind-powered electricity generation ultra-short term power prediction precision it is relatively low the problems such as.
Technical solution of the present invention：
A kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology, it includes：
The basic data and historical data of step 1, collection wind power plant n Fans；
Step 2, collection wind power plant n Fans real time datas, real time data include all blower fans in wind power plant region
Blower fan anemometer measure air speed data Wssrt and wind direction data Wdsrt, the blower fan temperature sensor of all blower fans measures temperature
Data Tsrt, all blower fans in real time go out force data Pwtrt, whole wind power plant in real time go out force data Pwfrt；
Step 3, historical data and real time data information according to wind power plant n Fans, it is whole that simulation calculates the ξ moment
Wind speed Wssrt ξ and wind direction the Wdsrt ξ of wind power plant hub height；
Step 4, historical data and real time data information according to wind power plant n Fans, it is whole that simulation calculates the ξ moment
The temperature Tsrt ξ of wind power plant hub height；
Step 5, according to step 3,4 result of calculation, calculate the ξ moment wind power plant atmospheric density, humidity and air pressure；
The data that step 6, aggregation step 3,4,5 are calculated, obtain the virtual anemometer tower data at wind power plant ξ moment；
Step 7, the method according to step 1- steps 6, obtain the virtual anemometer tower data set VH of wind power plant history；
Step 8, the supporting vector machine model for setting up wind power plant ultra-short term power prediction；
Step 9, the virtual anemometer tower data set VH of wind power plant history obtained using step 7, carry out the wind of the foundation of training step 8
The supporting vector machine model of electric field ultra-short term power prediction；
Step 10, the virtual anemometer tower data VAT at the wind power plant ξ moment for obtaining step 6 substitute into what step 9 was trained
The supporting vector machine model of wind power plant ultra-short term power prediction, you can obtain the ultra-short term power prediction value at wind power plant ξ moment
Data set PAT.
Basic data described in step 1 includes that the hub height of all blower fans, historical data include wind-powered electricity generation in wind-powered electricity generation field areas
Place exists
Historical wind speed data Wssh and wind direction data Wdsh, the historical temperature data of all blower fans of all blower fans in region
Tsh、
The history of all blower fans goes out force data Pwth and the history of whole wind power plant goes out force data Pwfh.
According to the historical data and real time data information of wind power plant n Fans described in step 3, simulation calculates the ξ moment
The method of wind speed Wssrt ξ and wind direction the Wdsrt ξ of whole wind power plant hub height includes：
Step 3.1, the historical wind speed wind direction data using all Wind turbines of wind power plant, and the entirely history of wind power plant
Go out force data, set up all Wind turbines wind speed and directions-wind power plant wind power data sample storehouse；
Step 3.2, set up all Wind turbines wind speed and directions-wind power plant wind power model；
Step 3.3, using 3.1 set up all Wind turbines wind speed and directions-wind power plant wind power data sample storehouse as
Training set, is trained to Wind turbines wind speed and direction-wind power plant wind power model, determines n typhoon group of motors in model
The weights of wind speed and direction data；Wherein, the weights of the wind speed and direction data of the i-th Fans are denoted as Wqzi, then have Wqz1+Wqz2
+ ... Wqzi+...+Wqzn=1；And have 1≤i≤n；
Step 3.4, the ξ wind speed Wssrt ξ and wind direction the Wdsrt ξ of moment whole wind power plant hub height of calculating
The computing formula of the ξ wind speed Wssrt ξ of moment whole wind power plant hub height is：
The expression formula of the ξ wind direction Wdsrt ξ of moment whole wind power plant hub height is：
Historical data and real time data information according to wind power plant n Fans described in step 4, when simulation calculates the ξ
The computational methods for carving the temperature Tsrt ξ of whole wind power plant hub height include：
Step 4.1, the historical temperature data using all Wind turbines of wind power plant, and the history of all blower fans are exerted oneself number
Go out force data according to the history with whole wind power plant, set up all Wind turbines temperature-wind power plant wind power data sample storehouse；
Step 4.2, set up all Wind turbines temperature-wind power plant wind power model；
Step 4.3, all Wind turbines temperature-wind power plant wind power data sample storehouse set up 4.1 are used as training
Collection, is trained to Wind turbines temperature-wind power plant wind power model, determines the temperature data of all Wind turbines in model
Weights；
Wherein, the weights of the temperature data of the i-th Fans are denoted as Tqzi, then have Tqz1+Tqz2+...Tqzi+...+Tqzn
=1；
And have 1≤i≤n；
Step 4.4, simulation calculate the ξ temperature Tsrt ξ of moment whole wind power plant hub height
The expression formula of the ξ temperature Tsrt ξ of moment whole wind power plant hub height is：
According to step 3,4 result of calculation described in step 5, the ξ moment wind power plant atmospheric density, humidity and air pressure are calculated
Computational methods include：
Step 5.1, according to wind power plant the ξ the power output Pwfrt ξ and wind speed Wssrt ξ at moment, calculate the ξ moment
Atmospheric density ρ srt ξ
The calculation expression of the ξ atmospheric density ρ srt ξ at moment is：
The swept area that wherein F rotates a circle for wind wheel blade；
Step 5.2, according to atmospheric pressure and atmospheric density computing formula, and air humidity formula, be calculated humidity
Calculation expression with the ξ air pressure presrt ξ at moment of air pressure is：
Presrt ξ=ρ srt ξ × (273.15+Tsrt ξ) × R
In formula, R is gas constant, and its value is 287；
The calculation expression of the ξ humidity Hsrt ξ at moment is：
The virtual anemometer tower date expression at the wind power plant ξ moment described in step 6 is：
VAT={ Wssrt ξ, Wdsrt ξ, Tsrt ξ, ρ srt ξ, Hsrt ξ, presrt ξ }.
The virtual anemometer tower data set VH expression formulas of wind power plant history described in step 7 are：
VH={ WsH, WdH, TH, ρ H, HH, preH }.
The ultra-short term power prediction Value Data collection pat table at wind power plant ξ moment described in step 10 is up to formula：
PAT={ PAT (ξ+s), PAT (ξ+2s) ..., PAT (ξ+16s) }
In formula：ξ is current time, and s is prediction step, and the step-length of ultra-short term power prediction is 15min, and prediction yardstick is
4h.Beneficial effects of the present invention：
The present invention proposes the wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology, and it is mainly collection mesh
The Wind turbines wind measuring system of the whole field of mark wind power plant and the observation data of temp measuring system, it is true using entropy assessment comprehensive evaluation model
Determine the weight coefficient of wind turbine to build the virtual anemometer tower of the whole audience, and provide all real-time physical amounts of virtual anemometer tower
Calculated value, including real time information and historical informations such as each high-rise wind speed and direction, temperature humidity and air pressure, by historical information come
The supporting vector machine model of wind power plant ultra-short term power prediction is trained, to improve the applicability and accuracy of model, finally by wind
The support of the wind power plant ultra-short term power prediction that the virtual anemometer tower data set at electric field ξ moment is trained as input, substitution
Vector machine model, obtains the ultra-short term power prediction Value Data collection PAT at wind power plant ξ moment, ultrashort to improve wind power plant wind-powered electricity generation
Phase power prediction precision；Solve under the Special geographical position and Meteorological Characteristics in plateau mountain area, any one or several survey wind
Tower or blower fan anemometer data all cannot comprehensively represent the whole wind power plant of complicated landform, and the disaster such as icing takes place frequently and causes to survey
Wind tower is collapsed, instrument for wind measurement is damaged or short time work failure, causes the ultrashort of the caused wind power plant of anemometer tower quality of data difference
The problems such as phase power prediction precision is relatively low.
Specific embodiment：
A kind of virtual anemometer tower construction method of wind power plant, it includes：
The basic data and historical data of step 1, collection wind power plant n Fans；Basic data described in step 1 includes wind-powered electricity generation
The hub height of all blower fans, historical data include the historical wind speed data of all blower fans in wind power plant region in field areas
Wssh and wind direction data Wdsh, the historical temperature data Tsh of all blower fans, the history of all blower fans go out force data Pwth and whole
The history of wind power plant goes out force data Pwfh.
Step 2, collection wind power plant n Fans real time datas, real time data include all blower fans in wind power plant region
Blower fan anemometer measure air speed data Wssrt and wind direction data Wdsrt, the blower fan temperature sensor of all blower fans measures temperature
Data Tsrt, all blower fans in real time go out force data Pwtrt, whole wind power plant in real time go out force data Pwfrt；
Step 3, historical data and real time data information according to wind power plant n Fans, it is whole that simulation calculates the ξ moment
Wind speed Wssrt ξ and wind direction the Wdsrt ξ of wind power plant hub height；
Step 3.1, the historical wind speed wind direction data using all Wind turbines of wind power plant, and the entirely history of wind power plant
Go out force data, set up all Wind turbines wind speed and directions-wind power plant wind power data sample storehouse；
Step 3.2, set up all Wind turbines wind speed and directions-wind power plant wind power model；Entropy assessment synthesis can be used
Evaluation model, sets up all Wind turbines wind speed and directions-wind power plant wind power model；
Step 3.3, using 3.1 set up all Wind turbines wind speed and directions-wind power plant wind power data sample storehouse as
Training set, is trained to Wind turbines wind speed and direction-wind power plant wind power model, determines n typhoon group of motors in model
The weights of wind speed and direction data；Wherein, the weights of the wind speed and direction data of the i-th Fans are denoted as Wqzi, then have Wqz1+Wqz2
+ ... Wqzi+...+Wqzn=1；And have 1≤i≤n；
Step 3.4, simulation calculate the ξ wind speed Wssrt ξ and wind direction the Wdsrt ξ of moment whole wind power plant hub height
The computing formula of the ξ wind speed Wssrt ξ of moment whole wind power plant hub height is：
In formula：Wssrti ξ are the ξ wind speed of moment the i-th Fans hub height.
The expression formula of the ξ wind direction Wdsrt ξ of moment whole wind power plant hub height is：
In formula：Wdsrti ξ are the ξ wind direction of the hub height of the Fans of moment i-th.
Step 4, historical data and real time data information according to wind power plant n Fans, it is whole that simulation calculates the ξ moment
The temperature Tsrt ξ of wind power plant hub height；
Historical data and real time data information according to wind power plant n Fans described in step 4, when simulation calculates the ξ
The computational methods for carving the temperature Tsrt ξ of whole wind power plant hub height include：
Step 4.1, the historical temperature data using all Wind turbines of wind power plant, and the history of all blower fans are exerted oneself number
Go out force data according to the history with whole wind power plant, set up all Wind turbines temperature-wind power plant wind power data sample storehouse；
Step 4.2, set up all Wind turbines temperature-wind power plant wind power model；The present invention uses entropy assessment synthesis
Evaluation model, sets up all Wind turbines temperature-wind power plant wind power model；
Step 4.3, all Wind turbines temperature-wind power plant wind power data sample storehouse set up 4.1 are used as training
Collection, is trained to Wind turbines temperature-wind power plant wind power model, determines the temperature data of all Wind turbines in model
Weights；
Wherein, the weights of the temperature data of the i-th Fans are denoted as Tqzi, then have Tqz1+Tqz2+...Tqzi+...+Tqzn
=1；
And have 1≤i≤n；
Step 4.4, simulation calculate the ξ temperature Tsrt ξ of moment whole wind power plant hub height
The expression formula of the ξ temperature Tsrt ξ of moment whole wind power plant hub height is：
In formula：Tsrti ξ are the ξ temperature of moment the i-th Fans hub height.
Step 5, according to step 3,4 result of calculation, calculate the ξ moment wind power plant atmospheric density, humidity and air pressure；
According to step 3,4 result of calculation described in step 5, the ξ moment wind power plant atmospheric density, humidity and air pressure are calculated
Computational methods include：
Step 5.1, according to wind power plant the ξ the power output Pwfrt ξ and wind speed Wssrt ξ at moment, calculate the ξ moment
Atmospheric density ρ srt ξ
The calculation expression of the ξ atmospheric density ρ srt ξ at moment is：
The swept area that wherein F rotates a circle for wind wheel blade；
Step 5.2, according to atmospheric pressure and atmospheric density computing formula, and air humidity empirical equation, be calculated
Humidity and air pressure
The calculation expression of the ξ air pressure presrt ξ at moment is：
Presrt ξ=ρ srt ξ × (273.15+Tsrt ξ) × R
In formula, R is gas constant, and its value is 287；
The calculation expression of the ξ humidity Hsrt ξ at moment is：
The data that step 6, aggregation step 3,4,5 are calculated, form the virtual anemometer tower data at wind power plant ξ moment.
The expression formula of the wherein virtual anemometer tower data at wind power plant ξ moment is：
VAT={ Wssrt ξ, Wdsrt ξ, Tsrt ξ, ρ srt ξ, Hsrt ξ, presrt ξ }.
Step 7：The virtual anemometer tower method of structure according to step 1- steps 6, obtains the virtual anemometer tower number of wind power plant history
According to collection VH；Its expression formula is：VH={ WsH, WdH, TH, ρ H, HH, preH }.
WsH is through the virtual anemometer tower method of structure of step 1- steps 6, the wind power plant historical wind speed data acquisition system for obtaining；
WdH is the wind power plant history wind direction data set for obtaining through the virtual anemometer tower method of structure of step 1- steps 6；
TH is, through the virtual anemometer tower method of structure of step 1- steps 6, to obtain the electric field historical temperature data set of wind；
ρ H are the electric field history atmospheric density data set that wind is obtained through the virtual anemometer tower method of structure of step 1- steps 6
Close；
HH is the electric field history humidity data set that wind is obtained through the virtual anemometer tower method of structure of step 1- steps 6；
PreH is through the virtual anemometer tower method of structure of step 1- steps 6, the wind power plant historical barometric data acquisition system for obtaining.
Step 8：Set up the supporting vector machine model of wind power plant ultra-short term power prediction.
Step 9：The virtual anemometer tower data set VH of wind power plant history obtained using step 7, carrys out the wind of the foundation of training step 8
The supporting vector machine model of electric field ultra-short term power prediction.
Step 10：The virtual anemometer tower data VAT at the wind power plant ξ moment that step 6 is obtained substitutes into what step 9 was trained
The supporting vector machine model of wind power plant ultra-short term power prediction, you can obtain the ultra-short term power prediction value at wind power plant ξ moment
Data set PAT.
The expression formula of the wherein ultra-short term power prediction Value Data collection PAT at wind power plant ξ moment is：
PAT={ PAT (ξ+s), PAT (ξ+2s) ..., PAT (ξ+16s) }.
Wherein, ξ is current time, and s is prediction step, and the step-length of ultra-short term power prediction is generally 15min, predicts yardstick
It is 4h.
Claims (8)
1. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology, it includes：
The basic data and historical data of step 1, collection wind power plant n Fans；
Step 2, collection wind power plant n Fans real time datas, real time data include the wind of all blower fans in wind power plant region
Machine anemometer measures air speed data Wssrt and wind direction data Wdsrt, the blower fan temperature sensor of all blower fans measures temperature data
Tsrt, all blower fans in real time go out force data Pwtrt, whole wind power plant in real time go out force data Pwfrt；
Step 3, historical data and real time data information according to wind power plant n Fans, simulation calculate the ξ moment whole wind-powered electricity generation
Wind speed Wssrt ξ and wind direction the Wdsrt ξ of field hub height；
Step 4, historical data and real time data information according to wind power plant n Fans, simulation calculate the ξ moment whole wind-powered electricity generation
The temperature Tsrt ξ of field hub height；
Step 5, according to step 3,4 result of calculation, calculate the ξ moment wind power plant atmospheric density, humidity and air pressure；
The data that step 6, aggregation step 3,4,5 are calculated, obtain the virtual anemometer tower data at wind power plant ξ moment；
Step 7, the method according to step 1- steps 6, obtain the virtual anemometer tower data set VH of wind power plant history；
Step 8, the supporting vector machine model for setting up wind power plant ultra-short term power prediction；
Step 9, the virtual anemometer tower data set VH of wind power plant history obtained using step 7, carry out the wind power plant of the foundation of training step 8
The supporting vector machine model of ultra-short term power prediction；
Step 10, the virtual anemometer tower data VAT at the wind power plant ξ moment for obtaining step 6 substitute into the wind-powered electricity generation that step 9 is trained
The supporting vector machine model of field ultra-short term power prediction, you can obtain the ultra-short term power prediction Value Data at wind power plant ξ moment
Collection PAT.
2. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：Basic data described in step 1 includes that the hub height of all blower fans, historical data include wind power plant in wind-powered electricity generation field areas
The historical wind speed data Wssh and wind direction data Wdsh of all blower fans in region, the historical temperature data Tsh of all blower fans,
The history of all blower fans goes out force data Pwth and the history of whole wind power plant goes out force data Pwfh.
3. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：According to the historical data and real time data information of wind power plant n Fans described in step 3, it is whole that simulation calculates the ξ moment
The method of wind speed Wssrt ξ and wind direction the Wdsrt ξ of individual wind power plant hub height includes：
Step 3.1, the historical wind speed wind direction data using all Wind turbines of wind power plant, and the history of whole wind power plant are exerted oneself
Data, set up all Wind turbines wind speed and directions-wind power plant wind power data sample storehouse；
Step 3.2, set up all Wind turbines wind speed and directions-wind power plant wind power model；
Step 3.3, all Wind turbines wind speed and directions-wind power plant wind power data sample storehouse set up 3.1 are used as training
Collection, is trained to Wind turbines wind speed and direction-wind power plant wind power model, determines the wind speed of n typhoon group of motors in model
The weights of wind direction data；Wherein, the weights of the wind speed and direction data of the i-th Fans are denoted as Wqzi, then have Wqz1+Wqz2+
... Wqzi+...+Wqzn=1；And have 1≤i≤n；
Step 3.4, the ξ wind speed Wssrt ξ and wind direction the Wdsrt ξ of moment whole wind power plant hub height of calculating
The computing formula of the ξ wind speed Wssrt ξ of moment whole wind power plant hub height is：
The expression formula of the ξ wind direction Wdsrt ξ of moment whole wind power plant hub height is：
4. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：Historical data and real time data information according to wind power plant n Fans described in step 4, simulation calculate the ξ moment
The computational methods of the temperature Tsrt ξ of whole wind power plant hub height include：
Step 4.1, the historical temperature data using all Wind turbines of wind power plant, and all blower fans history go out force data and
The history of whole wind power plant goes out force data, sets up all Wind turbines temperature-wind power plant wind power data sample storehouse；
Step 4.2, set up all Wind turbines temperature-wind power plant wind power model；
Step 4.3, all Wind turbines temperature-wind power plant wind power data sample storehouse set up 4.1 are right as training set
Wind turbines temperature-wind power plant wind power model is trained, and determines the power of the temperature data of all Wind turbines in model
Value；
Wherein, the weights of the temperature data of the i-th Fans are denoted as Tqzi, then have Tqz1+Tqz2+...Tqzi+...+Tqzn=1；
And have 1≤i≤n；
Step 4.4, simulation calculate the ξ temperature Tsrt ξ of moment whole wind power plant hub height
The expression formula of the ξ temperature Tsrt ξ of moment whole wind power plant hub height is：
5. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：According to step 3,4 result of calculation described in step 5, the ξ moment wind power plant atmospheric density, humidity and air pressure are calculated
Computational methods include：
Step 5.1, according to wind power plant the ξ the power output Pwfrt ξ and wind speed Wssrt ξ at moment, calculate the ξ sky at moment
The calculation expression of the ξ atmospheric density ρ srt ξ at moment of air tightness ρ srt ξ is：
The swept area that wherein F rotates a circle for wind wheel blade；
Step 5.2, according to atmospheric pressure and atmospheric density computing formula, and air humidity formula, be calculated humidity gentle
The calculation expression for pressing the ξ air pressure presrt ξ at moment is：
Presrt ξ=ρ srt ξ × (273.15+Tsrt ξ) × R
In formula, R is gas constant, and its value is 287；
The calculation expression of the ξ humidity Hsrt ξ at moment is：
6. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：The virtual anemometer tower date expression at the wind power plant ξ moment described in step 6 is：
VAT={ Wssrt ξ, Wdsrt ξ, Tsrt ξ, ρ srt ξ, Hsrt ξ, presrt ξ }.
7. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：The virtual anemometer tower data set VH expression formulas of wind power plant history described in step 7 are：
VH={ WsH, WdH, TH, ρ H, HH, preH }.
8. a kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology according to claim 1, it is special
Levy and be：The ultra-short term power prediction Value Data collection pat table at wind power plant ξ moment described in step 10 is up to formula：
PAT={ PAT (ξ+s), PAT (ξ+2s) ..., PAT (ξ+16s) }
In formula：ξ is current time, and s is prediction step, and the step-length of ultra-short term power prediction is 15min, and prediction yardstick is 4h.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611135551.4A CN106779208B (en) | 2016-12-08 | 2016-12-08 | Wind power ultra-short-term power prediction method based on virtual anemometer tower technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611135551.4A CN106779208B (en) | 2016-12-08 | 2016-12-08 | Wind power ultra-short-term power prediction method based on virtual anemometer tower technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106779208A true CN106779208A (en) | 2017-05-31 |
| CN106779208B CN106779208B (en) | 2020-09-29 |
Family
ID=58875311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611135551.4A Active CN106779208B (en) | 2016-12-08 | 2016-12-08 | Wind power ultra-short-term power prediction method based on virtual anemometer tower technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779208B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491860A (en) * | 2017-07-12 | 2017-12-19 | 中国农业大学 | One kind weighs regional wind power generating capacity and refers to calibration method |
| CN108062722A (en) * | 2017-12-13 | 2018-05-22 | 贵州大学 | Mountainous region farm model wind turbine mechanical output based on the wind speed coefficient of variation calculates method |
| 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 |
| CN109784563A (en) * | 2019-01-18 | 2019-05-21 | 南方电网科学研究院有限责任公司 | Ultra-short-term power prediction method based on virtual anemometer tower technology |
| CN112270439A (en) * | 2020-10-28 | 2021-01-26 | 国能日新科技股份有限公司 | Ultra-short-term wind power prediction method and device, electronic equipment and storage medium |
| CN114139775A (en) * | 2021-11-15 | 2022-03-04 | 明阳智慧能源集团股份公司 | Wind power prediction system based on virtual anemometer tower |
| CN115081742A (en) * | 2022-07-22 | 2022-09-20 | 北京东润环能科技股份有限公司 | Ultra-short-term power prediction method for distributed wind power plant and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030160457A1 (en) * | 2000-07-07 | 2003-08-28 | Mario Ragwitz | Method and device for processing and predicting the flow parameters of turbulent media |
| CN102102626A (en) * | 2011-01-30 | 2011-06-22 | 华北电力大学 | Method for forecasting short-term power in wind power station |
| CN102170130A (en) * | 2011-04-26 | 2011-08-31 | 华北电力大学 | Short-term wind power prediction method |
| CN102269124A (en) * | 2011-06-30 | 2011-12-07 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
| CN103440405A (en) * | 2013-08-08 | 2013-12-11 | 广东电网公司电力科学研究院 | Method and system for steady-state modeling of wind power plant based on measured data |
-
2016
- 2016-12-08 CN CN201611135551.4A patent/CN106779208B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030160457A1 (en) * | 2000-07-07 | 2003-08-28 | Mario Ragwitz | Method and device for processing and predicting the flow parameters of turbulent media |
| CN102102626A (en) * | 2011-01-30 | 2011-06-22 | 华北电力大学 | Method for forecasting short-term power in wind power station |
| CN102170130A (en) * | 2011-04-26 | 2011-08-31 | 华北电力大学 | Short-term wind power prediction method |
| CN102269124A (en) * | 2011-06-30 | 2011-12-07 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
| CN103440405A (en) * | 2013-08-08 | 2013-12-11 | 广东电网公司电力科学研究院 | Method and system for steady-state modeling of wind power plant based on measured data |
Non-Patent Citations (2)
| Title |
|---|
| 史洁: "风电场功率超短期预测算法优化研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 潘志刚: "基于深度学习网络的风电场功率预测研究及应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491860A (en) * | 2017-07-12 | 2017-12-19 | 中国农业大学 | One kind weighs regional wind power generating capacity and refers to calibration method |
| CN107491860B (en) * | 2017-07-12 | 2020-04-24 | 中国农业大学 | Method for measuring power generation capacity index of regional wind power plant |
| CN108062722A (en) * | 2017-12-13 | 2018-05-22 | 贵州大学 | Mountainous region farm model wind turbine mechanical output based on the wind speed coefficient of variation calculates method |
| CN108062722B (en) * | 2017-12-13 | 2021-08-17 | 贵州大学 | Mechanical power calculation method of mountain wind power plant model fan based on wind speed variation coefficient |
| 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 |
| CN108665102B (en) * | 2018-05-11 | 2022-08-05 | 中国船舶重工集团海装风电股份有限公司 | Method for predicting real-time power generation capacity of wind power plant based on mesoscale data |
| CN109784563A (en) * | 2019-01-18 | 2019-05-21 | 南方电网科学研究院有限责任公司 | Ultra-short-term power prediction method based on virtual anemometer tower technology |
| CN109784563B (en) * | 2019-01-18 | 2023-05-23 | 南方电网科学研究院有限责任公司 | Ultra-short-term power prediction method based on virtual anemometer tower technology |
| CN112270439A (en) * | 2020-10-28 | 2021-01-26 | 国能日新科技股份有限公司 | Ultra-short-term wind power prediction method and device, electronic equipment and storage medium |
| CN112270439B (en) * | 2020-10-28 | 2024-03-08 | 国能日新科技股份有限公司 | Ultra-short-term wind power prediction method and device, electronic equipment and storage medium |
| CN114139775A (en) * | 2021-11-15 | 2022-03-04 | 明阳智慧能源集团股份公司 | Wind power prediction system based on virtual anemometer tower |
| CN115081742A (en) * | 2022-07-22 | 2022-09-20 | 北京东润环能科技股份有限公司 | Ultra-short-term power prediction method for distributed wind power plant and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106779208B (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779208A (en) | A kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology | |
| Wagner et al. | The influence of the wind speed profile on wind turbine performance measurements | |
| Bodini et al. | Three-dimensional structure of wind turbine wakes as measured by scanning lidar | |
| CN106547996B (en) | A kind of virtual anemometer tower construction method of wind power plant | |
| Aitken et al. | Quantifying wind turbine wake characteristics from scanning remote sensor data | |
| Li et al. | LiDAR technology for wind energy potential assessment: Demonstration and validation at a site around Lake Erie | |
| CN107390298A (en) | A kind of analogy method and device of Complex Mountain underlying surface strong wind | |
| CN108536881A (en) | Method and apparatus for calculating wind power plant generated energy | |
| CN106815456A (en) | A kind of Wind turbines power characteristic evaluation method | |
| KR101332559B1 (en) | Numerical simulation system and method for atmospheric wind flow by computational fluid dynamics | |
| CN109784563B (en) | Ultra-short-term power prediction method based on virtual anemometer tower technology | |
| Wharton et al. | Measuring turbine inflow with vertically-profiling lidar in complex terrain | |
| CN103617308B (en) | A kind of construction method of wind power plant frequency domain equivalent model | |
| CN106548414A (en) | A kind of marine wind electric field generated energy computational methods | |
| CN105335617B (en) | Method and device for evaluating wake effect of wind power plant | |
| CN115358606B (en) | Method and system for evaluating energy efficiency of in-service wind power plant under gentle terrain | |
| CN105279576A (en) | Wind speed forecasting method | |
| Vincent et al. | Cross-spectra over the sea from observations and mesoscale modelling | |
| CN104217260B (en) | A kind of wind field measures the combination fill system of wind speed defect value adjacent to many typhoon motors | |
| CN108665102A (en) | Method based on the real-time generated energy of mesoscale data prediction wind power plant | |
| Alland et al. | Effects of surface fluxes on ventilation pathways and the intensification of Hurricane Michael (2018) | |
| Beljaars et al. | Diabatic wind speed profiles in coastal regions: comparison of an internal boundary layer (IBL) model with observations | |
| Aspliden et al. | Resource assessment methods, siting and performance evaluation | |
| Antoniou et al. | Influence of wind characteristics on turbine performance | |
| Essandoh et al. | Wind data collection and analysis in Kumasi |
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 |