CN106779208B - Wind power ultra-short-term power prediction method based on virtual anemometer tower technology - Google Patents
Wind power ultra-short-term power prediction method based on virtual anemometer tower technology Download PDFInfo
- Publication number
- CN106779208B CN106779208B CN201611135551.4A CN201611135551A CN106779208B CN 106779208 B CN106779208 B CN 106779208B CN 201611135551 A CN201611135551 A CN 201611135551A CN 106779208 B CN106779208 B CN 106779208B
- Authority
- CN
- China
- Prior art keywords
- wind
- wind power
- power plant
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005516 engineering process Methods 0.000 title claims abstract description 12
- 238000012706 support-vector machine Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims description 22
- 101100315388 Danio rerio tshz1 gene Proteins 0.000 claims description 15
- 238000013210 evaluation model Methods 0.000 description 3
- 230000005684 electric field Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010248 power generation 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 a wind power ultra-short-term power prediction method based on a virtual anemometer tower technology, which comprises the following steps of 1, collecting basic data, historical data and real-time data of n fans in a wind power plant; 2. simulating and calculating the wind speed and the wind direction of the hub height of the whole wind power plant at the moment xi; 3. simulating and calculating the temperature of the whole hub height of the wind power plant at the moment xi; 4. calculating the air density, humidity and air pressure of the wind power plant at the moment xi; 5. obtaining virtual anemometer tower data of the wind power plant at the xi moment; 6. obtaining a historical virtual anemometer tower data set of the wind power plant according to the steps 1-5; 7. establishing a support vector machine model for ultra-short term power prediction of a wind power plant and training by using a historical virtual anemometer tower data set of the wind power plant; 8. substituting the virtual anemometer tower data of the wind power plant at the ξ moment into the trained model to obtain an ultra-short-term power predicted value data set of the wind power plant at the ξ moment; the method solves the problems that the ultra-short-term power prediction precision of the wind power plant is low in the prior art and the like.
Description
Technical Field
The invention belongs to a wind power generation short-term power prediction technology, and particularly relates to a wind power ultra-short-term power prediction method based on a virtual anemometer tower technology.
Background
The arrangement of the fans of the wind power plant in the plateau mountain area is much more complex compared with that of the wind power plant in the plain. The wind turbines of the wind power plant in the plateau mountain area are arranged without a unified rule, and the arrangement of the wind turbines not only meets the spacing and pitch principle of the wind power plant in the plain, but also needs to be arranged in the ridge area as much as possible according to the specific conditions of landform and landform. Therefore, the distance between the fans is irregular, and is generally larger than the distance between the fans of a plain wind power plant, and the occupied area of the wind power plant in a plateau mountain area is also large. At the moment, the influence of the wake flow of the fan is not an important factor influencing the output of the wind power plant, and the micro change of the wind speed and the wind direction in the wind power plant greatly influences the output of the wind power plant.
Because the position of each wind turbine in the wind power plant in the plateau mountain area has certain particularity, the influence of turbulence and return wind is different, so that the wind speed correlation between different heights of the same wind measuring tower in the plateau mountain area is good, the wind speed correlation between the wind measuring towers in the same wind power plant is not good, so that the wind measuring towers do not have enough representativeness, any one or more wind measuring towers or wind turbine wind measuring instrument data cannot comprehensively represent the whole wind power plant in the complex terrain, the icing disaster is frequent due to the special geographic position and meteorological characteristics of the plateau mountain area, the erected wind measuring tower is damaged or inverted due to icing or long-term maintenance, or the icing causes the damage of the wind measuring instrument or short-time work failure, and the wind measuring data are obviously abnormal and untrusty. The quality of the anemometer tower data is poor easily caused by the problems, and the problems that the wind power ultra-short-term power prediction precision of a wind power plant is low and the like are caused by the fact that the anemometer tower data is still adopted for wind power ultra-short-term power prediction of the wind power plant in the plateau and mountain area in the prior art.
The invention content is as follows:
the technical problems to be solved by the invention are as follows: the method is used for solving the problems that wind power ultra-short term power prediction precision of a wind power plant is low and the like because wind power ultra-short term power prediction of the wind power plant in a plateau mountain area is still carried out by adopting wind measuring tower data in the prior art.
The technical scheme of the invention is as follows:
a wind power ultra-short-term power prediction method based on a virtual anemometer tower technology comprises the following steps:
step 1, collecting basic data and historical data of n fans of a wind power plant;
step 2, acquiring n wind turbine real-time data of the wind power plant, wherein the real-time data comprises wind speed data Wssrt and wind direction data Wdstt measured by wind turbine anemometers of all wind turbines in the region of the wind power plant, temperature data Tsrt measured by wind turbine temperature sensors of all the wind turbines, real-time output data Pwtrt of all the wind turbines and real-time output data Pwfrt of the whole wind power plant;
step 3, according to historical data and real-time data information of n fans of the wind power plant, simulating and calculating wind speed Wssrt xi and wind direction Wdstrt xi of the whole wind power plant hub height at the moment of the ξ;
step 4, according to historical data and real-time data information of n fans of the wind power plant, simulating and calculating the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi;
step 5, calculating the air density, humidity and air pressure of the wind power plant at the moment xi according to the calculation results of the steps 3 and 4;
step 6, summarizing the data obtained by calculation in the steps 3, 4 and 5 to obtain virtual anemometer tower data of the wind power plant at the ξ moment;
step 7, obtaining a historical virtual anemometer tower data set VH of the wind power plant according to the methods in the steps 1 to 6;
step 8, establishing a support vector machine model for ultra-short term power prediction of the wind power plant;
step 9, training the support vector machine model for the ultra-short term power prediction of the wind power plant established in the step 8 by using the historical virtual anemometer tower data set VH of the wind power plant obtained in the step 7;
and step 10, substituting the virtual anemometer tower data VAT of the wind power plant at the ξ moment obtained in the step 6 into the trained support vector machine model for the ultra-short term power prediction of the wind power plant in the step 9, so as to obtain the ultra-short term power prediction value data set PAT of the wind power plant at the ξ moment.
Step 1, the basic data comprise the hub heights of all fans in the wind power plant area, and the historical data comprise the hub heights of all fans in the wind power plant area
Historical wind speed data Wssh and wind direction data Wdsh of all fans in the region, historical temperature data Tsh of all fans, historical wind speed data Wssh of all fans, historical wind direction data Wdsh of all fans, historical wind speed data Tsh of all fans, historical wind speed data Wssh of all fans and historical wind direction data W,
Historical output data Pwth of all the wind turbines and historical output data Pwfh of the whole wind power plant.
And 3, the method for simulating and calculating the wind speed Wssrt xi and the wind direction Wdstrt xi of the hub height of the whole wind power plant at the moment xi according to the historical data and the real-time data information of n fans of the wind power plant comprises the following steps:
3.1, establishing a wind speed and wind direction-wind power station wind power data sample library of all wind turbine generators by utilizing the historical wind speed and wind direction data of the wind turbine generators in the wind power place and the historical output data of the whole wind power station;
3.2, establishing a wind speed and wind direction-wind power plant wind power model of all wind turbine generators;
3.3, taking the wind speed and wind direction-wind power plant wind power data sample base of all the wind generation sets established in the step 3.1 as a training set, training a wind speed and wind direction-wind power plant wind power model of the wind generation sets, and determining the weight of the wind speed and wind direction data of n wind generation sets in the model; wherein, the weight of the wind speed and direction data of the ith fan is recorded as Wqzi, and Wqz1+ Wqz2+. Wqzi +. + Wqzn is 1; and i is more than or equal to 1 and less than or equal to n;
step 3.4, calculating wind speed Wssrt xi and wind direction Wdstrt xi of the whole wind power plant hub height at the moment of the xi
The calculation formula of the wind speed Wssrt xi of the whole wind power plant hub height at the moment xi is as follows:
the expression of the wind direction Wdstrt xi of the whole wind power plant hub height at the moment xi is as follows:
the calculating method for simulating and calculating the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi according to the historical data and the real-time data information of the n fans of the wind power plant comprises the following steps:
step 4.1, establishing a temperature-wind power plant wind power data sample base of all wind turbines by utilizing historical temperature data of all wind turbines of a wind power plant, historical output data of all fans and historical output data of the whole wind power plant;
4.2, establishing a model of all wind turbine generator temperature-wind power of a wind power plant;
step 4.3, taking the database of the wind power data of all the wind turbine generator temperature-wind power plant established in step 4.1 as a training set, training a wind turbine generator temperature-wind power plant wind power model, and determining the weight of the temperature data of all the wind turbine generators in the model;
wherein, the weight of the temperature data of the ith fan is denoted as Tqzi, and Tqz1+ Tqz2+. Tqzi +. + Tqzn is 1;
and i is more than or equal to 1 and less than or equal to n;
step 4.4, simulating and calculating the temperature Tsrt xi of the whole wind power plant hub height at the moment xi
The expression of the temperature Tsrt xi of the whole wind power plant hub height at the moment xi is as follows:
step 5, the calculation method for calculating the air density, humidity and air pressure of the wind power plant at the moment xi according to the calculation results of the steps 3 and 4 comprises the following steps:
step 5.1, calculating the air density rho srt xi at the xi moment according to the output power Pwfrt xi and the wind speed Wssrt xi at the xi moment of the wind power plant
The computational expression of the air density ρ srt ξ at the ξ -th time is:
wherein F is the swept area of one rotation of the wind turbine blade;
step 5.2, according to the calculation formula of the atmospheric pressure and the air density and the air humidity formula, calculating to obtain a calculation expression of the air pressure presrt xi at the moment of humidity and air pressure xi, wherein the calculation expression is as follows:
presrtξ＝ρsrtξ×(273.15+Tsrtξ)×R
wherein R is a gas constant having a value of 287;
the computational expression of the humidity Hsrt xi at the moment xi is as follows:
and 6, the data expression of the virtual anemometer tower at the ξ moment of the wind power plant is as follows:
VAT＝{Wssrtξ、Wdsrtξ、Tsrtξ、ρsrtξ、Hsrtξ、presrtξ}。
the expression of the historical virtual anemometer tower data set VH of the wind power plant in the step 7 is as follows:
VH＝{WsH，WdH，TH，ρH，HH，preH}。
step 10, the ultra-short-term power prediction value data set PAT expression of the wind power plant at the ξ moment is as follows:
PAT＝{PAT(ξ+s)，PAT(ξ+2s)，...，PAT(ξ+16s)}
in the formula: ξ is the current moment, s is the prediction step length, the step length of ultra-short-term power prediction is 15min, and the prediction scale is 4 h. The invention has the beneficial effects that:
the invention provides a wind power ultra-short term power prediction method based on a virtual wind measuring tower technology, which mainly comprises the steps of collecting observation data of a wind turbine generator wind measuring system and a temperature measuring system of the whole field of a target wind power plant, determining a weight coefficient of each fan by utilizing an entropy weight method comprehensive evaluation model to construct a virtual wind measuring tower of the whole field, giving calculated values of all real-time physical quantities of the virtual wind measuring tower, including real-time information and historical information of wind speed, wind direction, temperature, humidity, air pressure and the like of each high layer, training a support vector machine model of ultra-short term power prediction of the wind power plant through the historical information to improve the applicability and the accuracy of the model, finally taking a virtual wind measuring tower data set at the xi moment of the wind power plant as input, substituting the trained support vector machine model of the ultra-short term power prediction of the wind power plant into the obtained ultra-short term power prediction data set PAT at the xi moment of, the wind power ultra-short-term power prediction precision of the wind power plant is improved; the method solves the problems that under the special geographic position and meteorological characteristics of the plateau mountain area, data of any one or more anemometer towers or wind turbine anemometers cannot comprehensively represent the whole wind power plant with complex terrain, and the ultra-short-term power prediction precision of the wind power plant is low due to the fact that the anemometer towers collapse, the anemometer is damaged or the short-time work fails caused by frequent disasters such as icing and the like, and the data quality of the anemometer towers is poor.
The specific implementation mode is as follows:
a method for constructing a virtual anemometer tower of a wind power plant comprises the following steps:
step 1, collecting basic data and historical data of n fans of a wind power plant; the basic data in the step 1 comprise the hub heights of all fans in a wind power plant area, and the historical data comprise historical wind speed data Wssh and wind direction data Wdsh of all fans in the area where the wind power plant is located, historical temperature data Tsh of all fans, historical output data Pwth of all fans and historical output data Pwfh of the whole wind power plant.
Step 2, acquiring n wind turbine real-time data of the wind power plant, wherein the real-time data comprises wind speed data Wssrt and wind direction data Wdstt measured by wind turbine anemometers of all wind turbines in the region of the wind power plant, temperature data Tsrt measured by wind turbine temperature sensors of all the wind turbines, real-time output data Pwtrt of all the wind turbines and real-time output data Pwfrt of the whole wind power plant;
step 3, according to historical data and real-time data information of n fans of the wind power plant, simulating and calculating wind speed Wssrt xi and wind direction Wdstrt xi of the whole wind power plant hub height at the moment of the ξ;
3.1, establishing a wind speed and wind direction-wind power station wind power data sample library of all wind turbine generators by utilizing the historical wind speed and wind direction data of the wind turbine generators in the wind power place and the historical output data of the whole wind power station;
3.2, establishing a wind speed and wind direction-wind power plant wind power model of all wind turbine generators; an entropy weight method comprehensive evaluation model can be adopted to establish a wind speed and wind direction-wind power model of a wind power plant of all wind turbine generators;
3.3, taking the wind speed and wind direction-wind power plant wind power data sample base of all the wind generation sets established in the step 3.1 as a training set, training a wind speed and wind direction-wind power plant wind power model of the wind generation sets, and determining the weight of the wind speed and wind direction data of n wind generation sets in the model; wherein, the weight of the wind speed and direction data of the ith fan is recorded as Wqzi, and Wqz1+ Wqz2+. Wqzi +. + Wqzn is 1; and i is more than or equal to 1 and less than or equal to n;
step 3.4, simulating and calculating wind speed Wssrt xi and wind direction Wdstrt xi of the whole wind power plant hub height at the moment of the ξ
The calculation formula of the wind speed Wssrt xi of the whole wind power plant hub height at the moment xi is as follows:
in the formula: wssrti xi is the wind speed at the ith turbine hub height at moment xi.
The expression of the wind direction Wdstrt xi of the whole wind power plant hub height at the moment xi is as follows:
in the formula: wdsrti xi is the wind direction of the hub height of the ith fan at the moment of the ξ.
Step 4, according to historical data and real-time data information of n fans of the wind power plant, simulating and calculating the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi;
the calculating method for simulating and calculating the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi according to the historical data and the real-time data information of the n fans of the wind power plant comprises the following steps:
step 4.1, establishing a temperature-wind power plant wind power data sample base of all wind turbines by utilizing historical temperature data of all wind turbines of a wind power plant, historical output data of all fans and historical output data of the whole wind power plant;
4.2, establishing a model of all wind turbine generator temperature-wind power of a wind power plant; the method adopts an entropy weight method comprehensive evaluation model to establish a wind power model of all wind turbine generator temperature-wind power plants;
step 4.3, taking the database of the wind power data of all the wind turbine generator temperature-wind power plant established in step 4.1 as a training set, training a wind turbine generator temperature-wind power plant wind power model, and determining the weight of the temperature data of all the wind turbine generators in the model;
wherein, the weight of the temperature data of the ith fan is denoted as Tqzi, and Tqz1+ Tqz2+. Tqzi +. + Tqzn is 1;
and i is more than or equal to 1 and less than or equal to n;
step 4.4, simulating and calculating the temperature Tsrt xi of the whole wind power plant hub height at the moment xi
The expression of the temperature Tsrt xi of the whole wind power plant hub height at the moment xi is as follows:
in the formula: tsrti xi is the temperature of the ith typhoon hub height at the moment xi.
Step 5, calculating the air density, humidity and air pressure of the wind power plant at the moment xi according to the calculation results of the steps 3 and 4;
step 5, the calculation method for calculating the air density, humidity and air pressure of the wind power plant at the moment xi according to the calculation results of the steps 3 and 4 comprises the following steps:
step 5.1, calculating the air density rho srt xi at the xi moment according to the output power Pwfrt xi and the wind speed Wssrt xi at the xi moment of the wind power plant
The computational expression of the air density ρ srt ξ at the ξ -th time is:
wherein F is the swept area of one rotation of the wind turbine blade;
step 5.2, calculating to obtain humidity and air pressure according to a calculation formula of atmospheric pressure and air density and an empirical formula of air humidity
The computational expression for air pressure presrt ξ at moment ξ is:
presrtξ＝ρsrtξ×(273.15+Tsrtξ)×R
wherein R is a gas constant having a value of 287;
the computational expression of the humidity Hsrt xi at the moment xi is as follows:
and 6, summarizing the data obtained by calculation in the steps 3, 4 and 5 to form virtual anemometer tower data of the wind power plant at the ξ moment. The expression of the virtual anemometer tower data at the ξ moment of the wind power plant is as follows:
VAT＝{Wssrtξ、Wdsrtξ、Tsrtξ、ρsrtξ、Hsrtξ、presrtξ}。
and 7: obtaining a historical virtual anemometer tower data set VH of the wind power plant according to the method for constructing the virtual anemometer tower from the step 1 to the step 6; the expression is as follows: VH ═ WsH, WdH, TH, ρ H, HH, preH }.
WsH is a wind power plant historical wind speed data set obtained by the method for constructing the virtual anemometer tower from the step 1 to the step 6;
WdH is a wind power plant historical wind direction data set obtained by the method for constructing the virtual anemometer tower from the step 1 to the step 6;
TH is a method for constructing a virtual anemometer tower through the steps 1-6 to obtain a historical temperature data set of a wind electric field;
rho H is a historical air density data set of the wind power plant obtained by the method for constructing the virtual anemometer tower in the steps 1 to 6;
HH is a wind electric field historical humidity data set obtained by the method for constructing the virtual anemometer tower in the steps 1 to 6;
preH is a wind power plant historical air pressure data set obtained by the method for constructing the virtual anemometer tower in the steps 1-6.
And 8: and establishing a support vector machine model for the ultra-short term power prediction of the wind power plant.
And step 9: and (4) training the support vector machine model for the ultra-short term power prediction of the wind power plant established in the step 8 by using the historical virtual anemometer tower data set VH of the wind power plant obtained in the step 7.
Step 10: substituting the virtual anemometer tower data VAT of the wind power plant at the ξ -th moment obtained in the step 6 into the trained support vector machine model for the ultra-short term power prediction of the wind power plant in the step 9, and obtaining the ultra-short term power prediction value data set PAT of the wind power plant at the ξ -th moment.
The expression of the ultra-short-term power prediction value data set PAT at the ξ moment of the wind power plant is as follows:
PAT＝{PAT(ξ+s)，PAT(ξ+2s)，...，PAT(ξ+16s)}。
where ξ is the current time, s is the prediction step length, the step length of ultra-short-term power prediction is generally 15min, and the prediction scale is 4 h.
Claims (5)
1. A wind power ultra-short-term power prediction method based on a virtual anemometer tower technology comprises the following steps:
step 1, collecting basic data and historical data of n wind turbines in a wind power plant;
step 1, the basic data comprise the hub heights of all wind motors in a wind power plant region, the historical data comprise historical wind speed data Wssh and wind direction data Wdsh of all wind motors in the region where the wind power plant is located, historical temperature data Tsh of all wind motors, historical output data Pwth of all wind motors and historical output data Pwfh of the whole wind power plant;
step 2, acquiring n wind motor real-time data of the wind power plant, wherein the real-time data comprises wind speed data Wssrt and wind direction data Wdstt measured by a wind motor anemometer of all wind motors in the region where the wind power plant is located, temperature data Tsrt measured by a wind motor temperature sensor of all the wind motors, real-time output data Pwtrt of all the wind motors and real-time output data Pwfrt of the whole wind power plant;
step 3, simulating and calculating wind speed Wssrt xi and wind direction Wdsrt xi of the whole wind power plant hub height at the moment xi according to historical data and real-time data of n wind power plants;
and 3, the method for simulating and calculating the wind speed Wssrt xi and the wind direction Wdstrt xi of the whole wind power plant hub height at the moment xi according to the historical data and the real-time data of the n wind power plants of the wind power plant comprises the following steps:
3.1, establishing a wind speed and wind direction-wind power station wind power data sample library of all wind motors by utilizing the historical wind speed data and wind direction data of the wind motors in the wind power station and the historical output data of the whole wind power station;
3.2, establishing a wind speed and wind direction-wind power plant wind power model of all wind motors;
3.3, taking all wind speed and wind direction-wind power plant wind power data sample libraries established in the step 3.1 as training sets, training a wind speed and wind direction-wind power plant wind power model of the wind motors, and determining the weight of wind speed data and wind direction data of n wind motors in the model; wherein, the weight of the wind speed data and the wind direction data of the ith typhoon motor is recorded as Wqzi, and Wqz1+ Wqz2+. Wqzi +. + Wqzn equals to 1; and i is more than or equal to 1 and less than or equal to n;
step 3.4, calculating the wind speed Wssrt xi and the wind direction Wdstrt xi of the whole wind power plant hub height at the xi moment
The calculation formula of the wind speed Wssrt xi of the whole wind power plant hub height at the moment xi is as follows:
the expression of the wind direction Wdstrt xi of the whole wind power plant hub height at the moment xi is as follows:
wssrti xi is the wind speed of the ith typhoon motor hub height at the moment xi; wdsrti xi is the wind direction of the hub height of the ith typhoon motor at the moment xi;
step 4, according to historical data and real-time data of n wind turbines of the wind power plant, simulating and calculating the temperature Tsrt xi of the whole wind power plant hub height at the moment xi;
the calculating method for simulating and calculating the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi according to the historical data and the real-time data of the n wind motors of the wind power plant comprises the following steps:
step 4.1, establishing a wind power data sample library of wind power plants and all wind motor temperatures by utilizing the historical temperature data of wind motors in the wind power plants, the historical output data of all the wind motors and the historical output data of the whole wind power plants;
step 4.2, establishing a model of all wind motor temperatures and wind power of a wind power plant;
step 4.3, taking all the wind motor temperature-wind power plant wind power data sample databases established in step 4.1 as training sets, training a wind motor temperature-wind power plant wind power model, and determining the weight of the temperature data of all the wind motors in the model;
wherein, the weight of the temperature data of the ith typhoon motor is recorded as Tqzi, and Tqz1+ Tqz2+. Tqzi +. + Tqzn equals 1;
and i is more than or equal to 1 and less than or equal to n;
and 4.4, simulating and calculating the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi, wherein the expression of the temperature Tsrt xi of the hub height of the whole wind power plant at the moment xi is as follows:
tsrti xi is the temperature of the hub height of the ith typhoon motor at the moment xi;
step 5, calculating the air density, humidity and air pressure of the wind power plant at the ξ moment according to the calculation results of the steps 3 and 4;
step 6, summarizing the data obtained by calculation in the steps 3, 4 and 5 to obtain virtual anemometer tower data of the wind power plant at the ξ moment;
step 7, obtaining a historical virtual anemometer tower data set VH of the wind power plant according to the methods in the steps 1 to 6;
step 8, establishing a support vector machine model for ultra-short term power prediction of the wind power plant;
step 9, training the support vector machine model for the ultra-short term power prediction of the wind power plant established in the step 8 by using the historical virtual anemometer tower data set VH of the wind power plant obtained in the step 7;
and step 10, substituting the virtual anemometer tower data VAT of the wind power plant at the ξ moment obtained in the step 6 into the trained support vector machine model for the ultra-short term power prediction of the wind power plant in the step 9, so as to obtain the ultra-short term power prediction value data set PAT of the wind power plant at the ξ moment.
2. The wind power ultra-short-term power prediction method based on the virtual anemometer tower technology as claimed in claim 1, wherein: step 5, the calculation method for calculating the air density, humidity and air pressure of the wind power plant at the ξ moment according to the calculation results of the steps 3 and 4 comprises the following steps:
step 5.1, calculating the air density rho srt xi at the xi moment according to the output power Pwfrt xi of the whole wind power plant at the xi moment and the wind speed Wssrt xi of the hub height of the whole wind power plant at the xi moment; the calculation expression of the air density ρ srt ξ at the ξ -th time is:
wherein F is the swept area of one rotation of the wind turbine blade;
step 5.2, calculating to obtain humidity and air pressure according to an atmospheric pressure and air density calculation formula and an air humidity formula
The calculated expression for air pressure presrt ξ at moment ξ is:
presrtξ＝ρsrtξ×(273.15+Tsrtξ)×R
wherein R is a gas constant having a value of 287;
the calculation expression of the humidity Hsrt xi at the xi moment is as follows:
3. the wind power ultra-short-term power prediction method based on the virtual anemometer tower technology as claimed in claim 1, wherein: and 6, the data expression of the virtual anemometer tower at the ξ moment of the wind power plant is as follows:
VAT＝{Wssrtξ、Wdsrtξ、Tsrtξ、ρsrtξ、Hsrtξ、presrtξ}。
4. the wind power ultra-short-term power prediction method based on the virtual anemometer tower technology as claimed in claim 1, wherein: the expression of the historical virtual anemometer tower data set VH of the wind power plant in the step 7 is as follows:
VH＝{WsH，WdH，TH，ρH，HH，preH}；
WsH is a wind farm historical wind speed data set;
WdH is a wind farm historical wind direction data set;
TH is a historical temperature data set of the wind power plant;
rho H is a historical air density data set of the wind power plant;
HH is a historical humidity data set of the wind power plant;
preH is a wind farm historical air pressure data set.
5. The wind power ultra-short-term power prediction method based on the virtual anemometer tower technology as claimed in claim 1, wherein: step 10, the ultra-short-term power prediction value data set PAT expression of the wind power plant at the ξ moment is as follows:
PAT＝{PAT(ξ+s)，PAT(ξ+2s)，...，PAT(ξ+16s)}
in the formula: ξ is the current moment, s is the prediction step length, the step length of ultra-short-term power prediction is 15min, and the prediction scale is 4 h.
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 CN106779208A (en) | 2017-05-31 |
| CN106779208B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10033183C2 (en) * | 2000-07-07 | 2002-08-08 | Max Planck Gesellschaft | Method and device for processing and predicting flow parameters of turbulent media |
| 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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 基于深度学习网络的风电场功率预测研究及应用;潘志刚;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20161015;第2-4章 * |
| 风电场功率超短期预测算法优化研究;史洁;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20131215;第2章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106779208A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779208B (en) | Wind power ultra-short-term power prediction method based on virtual anemometer tower technology | |
| US11408399B2 (en) | Forecasting output power of wind turbine in wind farm | |
| CN109958588B (en) | Icing prediction method, icing prediction device, storage medium, model generation method and model generation device | |
| US20160203245A1 (en) | Method for simulating wind field of extreme arid region based on wrf | |
| CN106547996B (en) | A kind of virtual anemometer tower construction method of wind power plant | |
| CN102663251B (en) | Physical prediction method for wind power station power based on computational fluid mechanics model | |
| CN106873359B (en) | Wind power noise evaluation method based on cluster analysis and neural network | |
| US10914291B2 (en) | Annual energy production of wind turbine sites | |
| CN113205210B (en) | Wind power plant wind speed and power prediction method, system and equipment for complex terrain and storage medium | |
| CN109784563B (en) | Ultra-short-term power prediction method based on virtual anemometer tower technology | |
| CN109978275B (en) | Extreme strong wind speed prediction method and system based on mixed CFD and deep learning | |
| CN103617308B (en) | A kind of construction method of wind power plant frequency domain equivalent model | |
| CN115358606B (en) | Method and system for evaluating energy efficiency of in-service wind power plant under gentle terrain | |
| CN109146192B (en) | Wind power prediction method considering operation condition of wind turbine generator | |
| CN107194141B (en) | Regional wind energy resource fine evaluation method | |
| CN108665102B (en) | Method for predicting real-time power generation capacity of wind power plant based on mesoscale data | |
| CN113051845B (en) | Method, system, equipment and storage medium for visually evaluating real-time wind resources of in-service mountain wind power plant | |
| CN106779202B (en) | Wind power prediction method considering air humidity | |
| CN113344252A (en) | Wind power prediction method based on virtual meteorological technology | |
| CN116881662A (en) | Method for predicting icing disaster of rotating wind power blade | |
| Antoniou et al. | Influence of wind characteristics on turbine performance | |
| CN114943174A (en) | Fan output loss prediction method used under cold tide small sample condition | |
| Li et al. | Wind velocity prediction at wind turbine hub height based on CFD model | |
| CN111738556A (en) | Method for evaluating power generation capacity of fan based on head microclimate | |
| CN112364300A (en) | Near-ground wind speed statistics downscaling correction method based on relative slope length |
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 |