CN109784563B - Ultra-short-term power prediction method based on virtual anemometer tower technology - Google Patents
Ultra-short-term power prediction method based on virtual anemometer tower technology Download PDFInfo
- Publication number
- CN109784563B CN109784563B CN201910048584.2A CN201910048584A CN109784563B CN 109784563 B CN109784563 B CN 109784563B CN 201910048584 A CN201910048584 A CN 201910048584A CN 109784563 B CN109784563 B CN 109784563B
- Authority
- CN
- China
- Prior art keywords
- wind
- historical
- data
- power
- virtual
- 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
Images
Landscapes
- Wind Motors (AREA)
Abstract
The invention discloses an ultra-short-term power prediction method, device and equipment based on a virtual anemometer tower technology and a computer readable storage medium, wherein the method comprises the following steps: acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant; according to the historical data and the historical power output value, determining the weight of each wind turbine generator set, and obtaining a historical virtual wind tower data vector; acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and acquiring a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the future NWP data; and calculating the output power of the wind power plant in the future ultra-short period according to the data vector of the virtual wind measuring tower and the power curve of the wind power plant. According to the technical scheme, ultra-short-term power prediction of the mountain wind farm on the plateau can be achieved under the condition that wind tower data are not relied on.
Description
Technical Field
The invention relates to the technical field of wind power prediction, in particular to an ultra-short-term power prediction method, device and equipment based on a virtual anemometer tower technology and a computer readable storage medium.
Background
The grid-connected wind power plant has short-term and ultra-short-term power prediction capability, short-term prediction precision is not lower than 80%, and ultra-short-term prediction precision is not lower than 85%, which are clearly required in national standard technical provision for wind power plant access to electric power system (GB/T19963-2011) and energy industry standard functional Specification for wind power prediction systems (NB/T31046-2013). The ultra-short-term power prediction is the output prediction of the wind power plant in 15 minutes to 4 hours in the future, and the time resolution is not less than 15 minutes. The ultra-short term power prediction of wind power generation generally adopts a statistical method combined with NWP (Numerical Weather Prediction, numerical weather forecast), and possible data sources include NWP data, anemometer tower wind speed data and actual power data generated by a wind power station.
For European countries, the wind power plant actual power can better represent wind conditions because of no wind-abandoning limit electricity problem, so that the actual power of the past few points (such as the last hour) can be compared with the short-term predicted power calculated based on the NWP data and used for the past few points, and the short-term predicted power calculated based on the NWP data and used for the future few points can be directly corrected. For domestic purposes, the existing large-scale wind power base is mainly concentrated in plain areas of three north (northwest, north China and northeast China), and the actual power of the wind power plant cannot reflect the corresponding wind power and the available power because the wind power cut-off condition is more prominent, so that the current common ultra-short-term prediction method generally does not adopt the actual power of the wind power plant, adopts wind speed data acquired by a wind measuring tower, corrects the wind speed prediction result of the NWP in the future ultra-short-term time scale by calculating the deviation of the wind speed data to the NWP data, and converts the wind speed prediction result into the ultra-short-term wind power plant output prediction through an algorithm, that is, the existing ultra-short-term prediction method very depends on the measurement accuracy of the wind speed by the wind measuring tower. However, for the wind farm in the mountain area of the plateau built in Guizhou and other areas, because the position of each wind turbine unit has certain specificity, the turbulence and the return air influence are different, and the data of any one or a plurality of wind towers cannot comprehensively represent the whole mountain wind farm in the complex terrain, the data of the wind towers cannot be used for prediction. In addition, the wind power plants can also have the conditions that the wind power plants are not provided with the wind measuring towers, the wind measuring towers are provided with the wind measuring towers, but the wind measuring towers are not accurately measured or cannot work normally due to climate or long-term maintenance, and the like, so that the prediction of the power of the wind power plants cannot be realized.
In summary, how to implement ultra-short-term power prediction of a mountain wind farm on the premise of not depending on wind tower data is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention aims to provide an ultra-short-term power prediction method, device, equipment and computer readable storage medium based on a virtual anemometer tower technology, so as to implement ultra-short-term power prediction for a mountain wind farm on the premise of not depending on anemometer tower data.
In order to achieve the above object, the present invention provides the following technical solutions:
an ultra-short term power prediction method based on a virtual anemometer tower technology comprises the following steps:
acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speed and wind direction measured by an anemometer of the wind turbines and temperature measured by a temperature measuring system of the wind turbines;
according to the historical data and the historical power output value, determining the weight of each wind turbine generator by a mathematical statistics method, and obtaining a historical virtual wind measuring tower data vector according to the historical data and the weight of each wind turbine generator, wherein the historical virtual wind measuring tower data vector comprises high wind speed, wind direction, temperature, humidity and air pressure of each layer;
acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data;
and calculating the output power of the wind power plant in the ultra-short future period according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
Preferably, determining the weight of each wind turbine generator set according to the historical data and the historical power output value through a mathematical statistics method includes:
establishing a sample library by utilizing the historical data and the historical power output value;
establishing a wind turbine generator data-wind power plant power output value model based on the fuzzy comprehensive judgment model;
and training the training set by using the historical data and the historical power output value in the preset time period acquired from the sample library as the training set and utilizing the wind turbine generator data-wind turbine farm power output value model to determine the weight of each wind turbine generator.
Preferably, according to the historical data and the weight of each wind turbine, a historical virtual wind tower data vector is obtained, including:
according to the historical data and the weight of each wind turbine, historical data of the wind turbine hub height are obtained, wherein the historical data of the wind turbine hub height comprise wind speed, wind direction and temperature;
calculating the high wind speed of each layer according to the wind speed profile and the wind speed of the hub height of the wind turbine generator;
and calculating air density according to the wind speed of the hub height of the wind turbine generator set and the historical power output value of the wind power plant, and calculating humidity and air pressure according to the calculated air density to obtain the historical virtual anemometer tower data vector.
Preferably, when obtaining a power curve of the wind farm according to the historical virtual wind tower data vector and the historical power output value, the method further comprises:
and setting redundancy of a preset threshold value for the power curve of the wind power plant.
An ultra-short term power prediction device based on a virtual anemometer tower technology, comprising:
an acquisition module for: acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speed and wind direction measured by an anemometer of the wind turbines and temperature measured by a temperature measuring system of the wind turbines;
a determining module for: according to the historical data and the historical power output value, determining the weight of each wind turbine generator by a mathematical statistics method, and obtaining a historical virtual wind measuring tower data vector according to the historical data and the weight of each wind turbine generator, wherein the historical virtual wind measuring tower data vector comprises high wind speed, wind direction, temperature, humidity and air pressure of each layer;
a first calculation module for: acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data;
a second calculation module for: and calculating the output power of the wind power plant in the ultra-short future period according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
Preferably, the determining module includes:
a first establishing unit for: establishing a sample library by utilizing the historical data and the historical power output value;
a second establishing unit for: establishing a wind turbine generator data-wind power plant power output value model based on the fuzzy comprehensive judgment model;
training unit for: and training the training set by using the historical data and the historical power output value in the preset time period acquired from the sample library as the training set and utilizing the wind turbine generator data-wind turbine farm power output value model to determine the weight of each wind turbine generator.
An ultra-short term power preset device based on virtual anemometer tower technology, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the virtual anemometer tower technology-based ultrashort-term power prediction method as described in any one of the above when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the virtual anemometer tower technology based ultrashort term power prediction method as described in any of the above.
The invention provides an ultra-short-term power prediction method, device and equipment based on a virtual anemometer tower technology and a computer readable storage medium, wherein the method comprises the following steps: acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speed and wind direction measured by a wind anemometer of the wind turbines and temperature measured by a temperature measuring system of the wind turbines; according to the historical data and the historical power output value, determining the weight of each wind turbine generator set by a mathematical statistics method, and obtaining a historical virtual wind measuring tower data vector according to the historical data and the weight of each wind turbine generator set, wherein the historical virtual wind measuring tower data vector comprises high wind speed, wind direction, temperature, humidity and air pressure of each layer; acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data; and calculating the output power of the wind power plant in the ultra-short term in the future according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
According to the technical scheme, the historical data obtained by measuring the wind turbines in the whole wind power plant and the historical power output value of the whole wind power plant are utilized, the weight of each wind turbine is determined by adopting a mathematical statistics method to construct a virtual wind measuring tower, the historical virtual wind measuring tower data vector is obtained by calculation according to the historical data of each wind turbine and the weight of each wind turbine, then the future virtual wind measuring tower data vector is calculated according to the relation between the historical NWP data and the historical virtual wind measuring tower data vector and the future NWP data, and the output power of the wind power plant in the future ultra-short period is calculated according to the future virtual wind measuring tower data and the wind power plant power curve.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an ultra-short-term power prediction method based on a virtual anemometer tower technique according to an embodiment of the present invention;
FIG. 2 is a flowchart of determining a weight of each wind turbine according to wind direction and wind speed according to an embodiment of the present invention;
FIG. 3 is a flowchart of determining a weight of each wind turbine according to a temperature according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the prediction accuracy of a wind farm of Wujiang origin for 83 days;
FIG. 5 is a graph of predictive accuracy of a four grid wind farm for 68 days;
FIG. 6 is a schematic diagram of the prediction accuracy of a cloud top wind farm for 123 days;
fig. 7 is a schematic structural diagram of an ultra-short-term power prediction device based on a virtual anemometer tower technology according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an ultra-short-term power prediction device based on a virtual anemometer tower technology according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of an ultra-short-term power prediction method based on a virtual anemometer tower technology according to an embodiment of the present invention may include:
s11: the method comprises the steps of obtaining historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speed and wind direction measured by an anemometer of the wind turbines and temperature measured by a temperature measuring system of the wind turbines.
In consideration of the fact that the position of each wind turbine in the mountain wind farm in the highland has certain specificity, the data measured by any one or more wind towers and anemometers cannot comprehensively and accurately represent the data of all wind turbines in the whole wind farm in complex terrain, and therefore, in order to improve the accuracy and the accuracy of ultra-short-term power prediction of the wind farm, the historical data of all wind turbines in the whole wind farm can be utilized to construct a virtual wind tower.
Specifically, the wind speed and the wind direction of the position of each wind turbine are measured by using an anemometer of each wind turbine in the wind power plant, and the temperature of the position of each wind turbine is measured by using a temperature measurement system of each wind turbine, so that historical data of all wind turbines are obtained. And acquiring the historical data of each wind turbine generator set, and simultaneously acquiring the historical power output value of the whole wind power plant to construct a time sequence consisting of the historical data of the wind turbine generator set and the historical power output value of the wind power plant.
S12: according to the historical data and the historical power output value, the weight of each wind turbine generator is determined through a mathematical statistics method, and according to the historical data and the weight of each wind turbine generator, a historical virtual wind measuring tower data vector is obtained, wherein the historical virtual wind measuring tower data vector comprises high wind speed, wind direction, temperature, humidity and air pressure of each layer.
After the historical data of all the wind turbines and the historical output value of the whole wind power plant are obtained, namely, a time sequence formed by the historical data and the historical power output value is obtained, the weight of each wind turbine in the whole wind power plant can be determined according to the historical data of the wind turbines and the historical power output value of the whole wind power plant by a mathematical statistics method, namely, the contribution of each wind turbine to the output power of the wind power plant is determined, so that a virtual wind measuring tower is constructed.
After the weight of each wind turbine is determined, a historical virtual wind measuring tower data vector of the wind power plant is obtained according to the obtained historical data of each wind turbine and the weight of each wind turbine, wherein the historical virtual wind measuring tower data vector comprises high wind speed, wind direction, temperature, humidity and air pressure of each layer.
S13: and acquiring a power curve of the wind power plant according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data.
After the historical virtual anemometer tower data vector is obtained, a wind power plant power curve can be obtained by fitting according to the historical virtual anemometer tower data vector and the historical power output value of the whole wind power plant, and then a relation curve between the output power of the wind power plant and the virtual anemometer tower data vector is obtained.
In addition, after the historical virtual wind tower data vector is obtained, historical NWP data may also be obtained, and a relationship between the historical NWP data and the historical virtual wind tower data vector may be determined. Then, a future virtual wind tower data vector may be determined based on the relationship between the historical NWP data and the historical virtual wind tower data vector, and the acquired future NWP data.
S14: and calculating the output power of the wind power plant in the ultra-short term in the future according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
After the power curve of the wind power plant and the future virtual wind measuring tower data vector are obtained, the output power of the wind power plant in the future ultra-short period can be predicted and calculated according to the two known quantities, namely the ultra-short period power prediction is carried out on the wind power plant. Here, the ultra-short term power prediction refers to power of 4 hours in future per 15min roller prediction, that is, the prediction step length is 15min, and the predicted value within 4 hours is 16, that is, the time length of the above mentioned future virtual anemometer tower data vector is 15min. Therefore, when the output power is predicted in a rolling manner, each prediction time is predicted 16 times, and the prediction result with 15min advance is higher in accuracy than the prediction result with 4h advance. In addition, after each prediction time is predicted 16 times, the accuracy of the 16 times of prediction results at each time can be averaged to obtain average accuracy, and the accuracy of the ultra-short-term power prediction results is judged by using the average accuracy.
Because the wind speed and the wind direction do not need to be acquired through the anemometer tower in the process, the dependence on the anemometer tower data can be reduced. In addition, the process does not depend on actual power data of the wind farm to predict the output power of the wind farm, so the process can be suitable for the situations that the wind abandoning electricity limit exists and wind tower data is absent or unreliable. Moreover, as all the wind turbines in the process participate in prediction, the accuracy of prediction can be improved.
According to the technical scheme, the historical data obtained by measuring the wind turbines in the whole wind power plant and the historical power output value of the whole wind power plant are utilized, the weight of each wind turbine is determined by adopting a mathematical statistics method to construct a virtual wind measuring tower, the historical virtual wind measuring tower data vector is obtained by calculating according to the historical data of each wind turbine and the weight of each wind turbine, then the future virtual wind measuring tower data vector is calculated according to the relation between the historical NWP data and the historical virtual wind measuring tower data vector and the future NWP data, and the output power of the wind power plant in the future ultra-short period is calculated according to the future virtual wind measuring tower data and the wind power plant power curve.
The ultra-short-term power prediction method based on the virtual wind measuring tower technology provided by the invention can be used for determining the weight of each wind turbine generator set by a mathematical statistics method according to historical data and historical power output values, and can comprise the following steps:
establishing a sample library by utilizing the historical data and the historical power output value;
establishing a wind turbine generator data-wind power plant power output value model based on the fuzzy comprehensive judgment model;
and taking the historical data and the historical power output value in the preset time period obtained from the sample library as a training set, and training the training set by using a wind turbine generator data-wind power plant power output value model so as to determine the weight of each wind turbine generator.
When the weight of each wind turbine generator is determined, the weight can be determined by adopting a modeling mode of a fuzzy comprehensive judgment model so as to construct a virtual wind measuring tower.
Specifically, for wind direction and wind speed data, a wind direction and wind speed-wind power plant power output value sample library of the wind turbine is built by using the obtained historical wind direction and wind speed of the wind turbine and the obtained historical power output value, a wind direction and wind speed-wind power plant power output value model of the wind turbine is built by using a fuzzy comprehensive judgment model, then the historical wind direction and wind speed and the historical power output value in a preset time period traversed in the sample library are used as training sets, and the selected training sets are trained through the wind direction and wind speed-wind power plant power output value model of the wind turbine so as to determine the weight of each wind turbine. The specific process may correspondingly refer to fig. 2, which shows a flowchart for determining the weight of each wind turbine according to the wind direction and the wind speed according to the embodiment of the present invention.
For the temperature, the method for determining the weight of the wind turbine is similar to that described above, a wind turbine temperature-wind power plant power output value sample library is established by using the historical temperature and the historical power output value, a wind turbine temperature-wind power plant power output value model is established by using a fuzzy comprehensive judgment model, then the historical temperature and the historical power output value of a preset time period traversed in the sample library are used as training sets, and training is performed through the wind turbine temperature-wind power plant power output value model to determine the weight of each wind turbine. The specific process may correspondingly refer to fig. 3, which shows a flowchart for determining the weight of each wind turbine according to the temperature according to the embodiment of the present invention.
It should be noted that, the above mentioned preset time period may be determined according to the size of the established wind turbine generator set historical data-wind turbine farm historical power output value sample library, where the longer the preset time period is, the more accurate the weight of each wind turbine generator set is obtained, but considering the training speed, the calculated amount and the like, the traversed preset time period cannot be too long, and may be one year or other time periods generally, and the preset time period is not limited in any way.
The ultra-short-term power prediction method based on the virtual anemometer tower technology provided by the invention obtains a historical virtual anemometer tower data vector according to historical data and the weight of each wind turbine generator, and can comprise the following steps:
according to the historical data and the weight of each wind turbine, historical data of the wind turbine hub height is obtained, wherein the historical data of the wind turbine hub height comprises wind speed, wind direction and temperature;
calculating the high wind speed of each layer according to the wind speed profile and the wind speed of the hub height of the wind turbine generator;
and calculating the air density according to the wind speed of the hub height of the wind turbine generator and the historical power output value of the wind power plant, and calculating the humidity and the air pressure according to the calculated air density to obtain the historical virtual wind tower data vector.
After training is performed according to the wind direction and wind speed of the wind turbines and the power output value model of the wind farm to obtain the weight of each wind turbine, the wind direction and the wind speed of the hub height of the wind turbine of the whole wind farm can be calculated according to the historical wind direction and the wind speed and the weight of each wind turbine. Similarly, after training is performed according to the wind turbine temperature-wind power plant power output value model to obtain the weight of each wind turbine, the temperature of the hub height of the wind turbine of the whole wind power plant can be calculated according to the historical temperature and the corresponding weight of each wind turbine.
Then, the wind speeds of other high layers (namely, the high wind speeds of all layers) can be calculated through the wind speed profile and the wind speed of the hub height of the wind turbine generator. The air density can be calculated according to the wind speed of the hub height of the wind turbine generator and the historical power output value of the wind power plant, and then the humidity and the air pressure can be calculated according to the empirical formula of the air humidity and the calculation formula of the atmospheric pressure and the air density. Finally, the historical virtual anemometer tower data vector comprising the high wind speed, the wind direction, the temperature, the humidity and the air pressure of each layer can be obtained.
The ultra-short-term power prediction method based on the virtual wind measuring tower technology provided by the invention can further comprise the following steps when obtaining a power curve of a wind power plant according to a historical virtual wind measuring tower data vector and a historical power output value:
and setting redundancy of a preset threshold value for the power curve of the wind power plant.
When the wind power plant power curve is obtained according to the historical virtual wind power tower data vector and the historical power output value, the redundancy of a preset threshold value can be set for the wind power plant power curve, namely, the wind power plant power curve is allowed to have certain redundancy, so that the wind power plant can be subjected to ultra-short-term output power prediction even if the future virtual wind power tower data vector has partial loss, and the predicted result is not greatly influenced. That is, setting a certain redundancy for the wind farm power curve may increase the inclusion of future virtual wind tower data vectors such that ultra-short term power predictions are not affected if there is a partial loss of future virtual wind tower data vectors.
In order to more clearly explain the technical scheme, the technical scheme can be applied to the Guizhou mountain wind farm to perform ultra-short-term power prediction on the Guizhou mountain wind farm. As shown in Table 1, it shows a Guizhou mountain area wind farm data collection statistics.
TABLE 1 wind farm data collection statistics
As can be seen from table 1, only three wind farms, i.e. the wujiang source wind farm, the four grids and the cloud top wind farm, have fan anemometer data of partial time periods, so the above technical scheme is used for ultra-short term power prediction by taking the wujiang source wind farm as an example, and verification is performed by using the four grids wind farm and the cloud top wind farm.
1. Data preparation
The data used in the method comprise measured data of a wind meter of a wind turbine generator in a Guizhou Wujiang source wind power plant and NWP numerical weather forecast, and the sampling intervals are 15 minutes. The wind power plant is located in a mountain area of a plateau, 132 wind power units are provided, so that 132 wind power units are provided, the actual measurement data of wind meters of the wind power units are provided, the numerical weather forecast adopts T639 data, the spatial resolution is 110km, and the time resolution is 3h. And selecting data of the whole year in 2013 as a training set to perform ultra-short-term power prediction modeling, and selecting 83 days of data from 1 month, 1 day to 3 months, 24 days in 2014 to perform prediction effect verification.
2. Calculation case analysis and conclusion
By utilizing the technical scheme, ultra-short-term power prediction is carried out on the Wujiang source wind power plant, the accuracy of each period of each day is calculated respectively, and then the average value of the daily accuracy is calculated, and the ultra-short-term power prediction is particularly shown as fig. 4, which shows a schematic diagram of the prediction accuracy of the Wujiang source wind power plant for 83 days, wherein the abscissa represents days and the ordinate represents accuracy. The graph shows that the accuracy rate of ultra-short-term power prediction of the wind power plant of the Wujiang source for 83 days is 95.61% at the highest, 84.23% at the lowest, the average accuracy rate is 90.25%, and the prediction error is not more than 10%.
3. Verification and conclusion of algorithm
(1) Four-grid wind farm
By utilizing the technical scheme, ultra-short-term power prediction is carried out on the four-grid wind power plant, the accuracy and the qualification rate of each period of each day are respectively calculated, and then the average value of the accuracy of each day is calculated, and the method is particularly shown in fig. 5, which shows a schematic diagram of the prediction accuracy of the four-grid wind power plant for 68 days. The graph shows that the accuracy rate of ultra-short-term power prediction of the four-grid wind power plant for 68 days is 96.82% at the highest, 84.62% at the lowest, the average accuracy rate is 90.09%, and the prediction error is not more than 10%.
(2) Cloud top wind power plant
By utilizing the technical scheme, ultra-short-term power prediction is carried out on the cloud top wind power plant, the accuracy and the qualification rate of each period of each day are respectively calculated, and then the average value of the accuracy of each day is calculated, and the method is particularly shown in fig. 6, which shows a schematic diagram of the prediction accuracy of the cloud top wind power plant for 123 days. The graph shows that the accuracy rate of ultra-short-term power prediction of the cloud top wind power plant for 123 days is 96.97% at the highest, 84.63% at the lowest, the average accuracy rate is 91.17%, and the prediction error is not more than 10%.
According to experimental results of the Wujiang source wind power plant, the four grid wind power plant and the cloud top wind power plant, the technical scheme is effective and feasible to be applied to the Guizhou plateau mountain wind power plant, good results can be obtained, and the method has good popularization.
The embodiment of the invention also provides an ultra-short-term power prediction device based on the virtual anemometer tower technology, and particularly can be seen from fig. 7, which shows a schematic structural diagram of the ultra-short-term power prediction device based on the virtual anemometer tower technology, which can include:
an acquisition module 11 for: acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speed and wind direction measured by a wind anemometer of the wind turbines and temperature measured by a temperature measuring system of the wind turbines;
a determining module 12 for: according to the historical data and the historical power output value, determining the weight of each wind turbine generator set by a mathematical statistics method, and obtaining a historical virtual wind measuring tower data vector according to the historical data and the weight of each wind turbine generator set, wherein the historical virtual wind measuring tower data vector comprises high wind speed, wind direction, temperature, humidity and air pressure of each layer;
a first calculation module 13 for: acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data;
a second calculation module 14 for: and calculating the output power of the wind power plant in the ultra-short term in the future according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
The embodiment of the invention provides an ultra-short-term power prediction device based on a virtual anemometer tower technology, and the determining module 12 may include:
a first establishing unit for: establishing a sample library by utilizing the historical data and the historical power output value;
a second establishing unit for: establishing a wind turbine generator data-wind power plant power output value model based on the fuzzy comprehensive judgment model;
training unit for: and taking the historical data and the historical power output value in the preset time period obtained from the sample library as a training set, and training the training set by using a wind turbine generator data-wind power plant power output value model so as to determine the weight of each wind turbine generator.
The embodiment of the invention also provides ultra-short-term power prediction equipment based on the virtual anemometer tower technology, and particularly can be seen from fig. 8, which shows a schematic structural diagram of the ultra-short-term power prediction equipment based on the virtual anemometer tower technology, which can include:
a memory 21 for storing a computer program;
a processor 22 for implementing any of the above-described ultra-short term power prediction methods based on virtual anemometer tower technology when executing a computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of any ultra-short-term power prediction method based on the virtual anemometer tower technology are realized.
The description of the relevant parts in the ultra-short-term power prediction device, the device and the computer readable storage medium based on the virtual wind measuring tower technology provided by the embodiment of the invention is referred to in the detailed description of the corresponding parts in the ultra-short-term power prediction method based on the virtual wind measuring tower technology provided by the embodiment of the invention, and is not repeated here.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements is inherent to. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. In addition, the parts of the above technical solutions provided in the embodiments of the present invention, which are consistent with the implementation principles of the corresponding technical solutions in the prior art, are not described in detail, so that redundant descriptions are avoided.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The ultra-short-term power prediction method based on the virtual anemometer tower technology is characterized by comprising the following steps of:
acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speeds and wind directions measured by an anemometer of the wind turbines and temperatures measured by a temperature measuring system of the wind turbines;
according to the historical data and the historical power output value, determining the weight of each wind turbine generator by a mathematical statistics method, and obtaining a historical virtual wind measuring tower data vector according to the historical data and the weight of each wind turbine generator, wherein the historical virtual wind measuring tower data vector comprises wind speeds of all layers of heights, wind directions of all layers of heights, temperatures of all layers of heights, humidity of all layers of heights and air pressures of all layers of heights;
acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data;
and calculating the output power of the wind power plant in the ultra-short future period according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
2. The ultra-short term power prediction method based on the virtual anemometer tower technology according to claim 1, wherein determining the weight of each wind turbine generator by a mathematical statistics method according to the historical data and the historical power output value comprises:
establishing a sample library by utilizing the historical data and the historical power output value;
establishing a wind turbine generator data-wind power plant power output value model based on the fuzzy comprehensive judgment model;
and training the training set by using the historical data and the historical power output value in the preset time period acquired from the sample library as the training set and utilizing the wind turbine generator data-wind turbine farm power output value model to determine the weight of each wind turbine generator.
3. The ultra-short term power prediction method based on the virtual anemometer tower technology according to claim 2, wherein obtaining a historical virtual anemometer tower data vector according to the historical data and the weight of each wind turbine generator set comprises:
according to the historical data and the weight of each wind turbine, historical data of the wind turbine hub height are obtained, wherein the historical data of the wind turbine hub height comprise wind speed, wind direction and temperature;
calculating the wind speed of each layer of height according to the wind speed profile and the wind speed of the hub height of the wind turbine generator;
and calculating air density according to the wind speed of the hub height of the wind turbine generator set and the historical power output value of the wind power plant, and calculating humidity and air pressure according to the calculated air density to obtain the historical virtual anemometer tower data vector.
4. The method for ultra-short term power prediction based on virtual anemometer tower technology according to claim 1, wherein when obtaining a wind farm power curve according to the historical virtual anemometer tower data vector and the historical power output value, further comprising:
and setting redundancy of a preset threshold value for the power curve of the wind power plant.
5. An ultra-short term power prediction device based on a virtual anemometer tower technology is characterized by comprising:
an acquisition module for: acquiring historical data of all wind turbines in a wind power plant and historical power output values of the whole wind power plant, wherein the historical data comprise wind speeds and wind directions measured by an anemometer of the wind turbines and temperatures measured by a temperature measuring system of the wind turbines;
a determining module for: according to the historical data and the historical power output value, determining the weight of each wind turbine generator by a mathematical statistics method, and obtaining a historical virtual wind measuring tower data vector according to the historical data and the weight of each wind turbine generator, wherein the historical virtual wind measuring tower data vector comprises wind speeds of all layers of heights, wind directions of all layers of heights, temperatures of all layers of heights, humidity of all layers of heights and air pressures of all layers of heights;
a first calculation module for: acquiring a wind power plant power curve according to the historical virtual wind tower data vector and the historical power output value, and calculating to obtain a future virtual wind tower data vector according to the relation between the historical NWP data and the historical virtual wind tower data vector and the acquired future NWP data;
a second calculation module for: and calculating the output power of the wind power plant in the ultra-short future period according to the data vector of the virtual wind measuring tower in the future and the power curve of the wind power plant.
6. The virtual anemometer tower technology based ultrashort term power prediction apparatus of claim 5, wherein the determination module comprises:
a first establishing unit for: establishing a sample library by utilizing the historical data and the historical power output value;
a second establishing unit for: establishing a wind turbine generator data-wind power plant power output value model based on the fuzzy comprehensive judgment model;
training unit for: and training the training set by using the historical data and the historical power output value in the preset time period acquired from the sample library as the training set and utilizing the wind turbine generator data-wind turbine farm power output value model to determine the weight of each wind turbine generator.
7. Ultra-short-term power preset equipment based on virtual anemometer tower technology is characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the virtual anemometer tower technology based ultrashort term power prediction method as claimed in any one of claims 1 to 4 when executing the computer program.
8. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the ultra short term power prediction method based on virtual anemometer tower technology according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910048584.2A CN109784563B (en) | 2019-01-18 | 2019-01-18 | Ultra-short-term power prediction method based on virtual anemometer tower technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910048584.2A CN109784563B (en) | 2019-01-18 | 2019-01-18 | Ultra-short-term power prediction method based on virtual anemometer tower technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109784563A CN109784563A (en) | 2019-05-21 |
| CN109784563B true CN109784563B (en) | 2023-05-23 |
Family
ID=66501578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910048584.2A Active CN109784563B (en) | 2019-01-18 | 2019-01-18 | Ultra-short-term power prediction method based on virtual anemometer tower technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109784563B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112260276A (en) * | 2020-11-04 | 2021-01-22 | 中能电力科技开发有限公司 | Virtual anemometer tower device of wind power plant power prediction system |
| CN112215305A (en) * | 2020-11-16 | 2021-01-12 | 远景能源有限公司 | Virtual laser radar system and method based on mutual early warning of fans |
| CN112651560B (en) * | 2020-12-28 | 2023-04-25 | 华润电力技术研究院有限公司 | Ultra-short-term wind power prediction method, device and equipment |
| CN113610285A (en) * | 2021-07-26 | 2021-11-05 | 华能定边新能源发电有限公司 | Power prediction method for distributed wind power |
| 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 |
| CN116187559B (en) * | 2023-02-21 | 2024-03-15 | 华润电力技术研究院有限公司 | Centralized wind power ultra-short-term power prediction method, system and cloud platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810542A (en) * | 2014-03-07 | 2014-05-21 | 北京动力京工科技有限公司 | Wind power prediction system for wind power plant, and realization method |
| CN104699936A (en) * | 2014-08-18 | 2015-06-10 | 沈阳工业大学 | Sector management method based on CFD short-term wind speed forecasting wind power plant |
| CN106779208A (en) * | 2016-12-08 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology |
| EP3343300A1 (en) * | 2017-01-03 | 2018-07-04 | General Electric Company | Digital twin interface for operating wind farms |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021424B (en) * | 2013-02-28 | 2018-12-07 | 乌托巴斯洞察公司 | Method and apparatus for predicting the output power of the blower in wind field |
| CN103279804B (en) * | 2013-04-29 | 2016-08-17 | 清华大学 | The Forecasting Methodology of super short-period wind power |
| CN106547996B (en) * | 2016-12-08 | 2019-10-29 | 贵州电网有限责任公司电力科学研究院 | A kind of virtual anemometer tower construction method of wind power plant |
| CN107067099B (en) * | 2017-01-25 | 2020-06-19 | 清华大学 | Wind power probability prediction method and device |
| CN108536881B (en) * | 2017-03-06 | 2020-10-16 | 新疆金风科技股份有限公司 | Method and device for calculating the power generation of a wind farm |
| CN107169612A (en) * | 2017-06-21 | 2017-09-15 | 南京信息工程大学 | The prediction of wind turbine active power and error revising method based on neutral net |
-
2019
- 2019-01-18 CN CN201910048584.2A patent/CN109784563B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810542A (en) * | 2014-03-07 | 2014-05-21 | 北京动力京工科技有限公司 | Wind power prediction system for wind power plant, and realization method |
| CN104699936A (en) * | 2014-08-18 | 2015-06-10 | 沈阳工业大学 | Sector management method based on CFD short-term wind speed forecasting wind power plant |
| CN106779208A (en) * | 2016-12-08 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of wind-powered electricity generation ultra-short term power forecasting method based on virtual anemometer tower technology |
| EP3343300A1 (en) * | 2017-01-03 | 2018-07-04 | General Electric Company | Digital twin interface for operating wind farms |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109784563A (en) | 2019-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784563B (en) | Ultra-short-term power prediction method based on virtual anemometer tower technology | |
| CN105046374B (en) | A kind of power interval prediction technique based on core extreme learning machine model | |
| CN102945508B (en) | Model correction based wind power forecasting method | |
| Deppe et al. | A WRF ensemble for improved wind speed forecasts at turbine height | |
| Wan et al. | Development of an equivalent wind plant power-curve | |
| US10215162B2 (en) | Forecasting output power of wind turbine in wind farm | |
| CN105160060B (en) | A kind of wind power plant theoretical power (horse-power) based on actual power curve matching determines method | |
| CN102914969B (en) | Comprehensive error correction method of short-period wind power prediction system | |
| CN103778572A (en) | Sea wind resource evaluation method based on WRF mode | |
| CN104036121B (en) | Wind measurement data wind speed correction method based on probability distribution transfer | |
| CN111488896B (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN110601250B (en) | Method for evaluating stability of static voltage of access point based on new energy power station | |
| CN109167387A (en) | Wind field wind power forecasting method | |
| CN102562469A (en) | Short-term wind driven generator output power predicting method based on correction algorithm | |
| Saeed et al. | Wind energy potential and economic analysis with a comparison of different methods for determining the optimal distribution parameters | |
| CN115358606B (en) | Method and system for evaluating energy efficiency of in-service wind power plant under gentle terrain | |
| CN108665102B (en) | Method for predicting real-time power generation capacity of wind power plant based on mesoscale data | |
| CN103996079A (en) | Wind power weighting predication method based on conditional probability | |
| CN108062722B (en) | Mechanical power calculation method of mountain wind power plant model fan based on wind speed variation coefficient | |
| CN113379142A (en) | Short-term wind power prediction method based on wind speed correction and fusion model | |
| Yan et al. | A robust probabilistic wind power forecasting method considering wind scenarios | |
| CN110348175B (en) | Effective irradiation calculation method and device for photovoltaic power station | |
| CN105046349A (en) | Wind power prediction method considering wake effect | |
| CN117117819A (en) | Photovoltaic power generation short-term power prediction method, system, equipment and medium | |
| CN117060407A (en) | Wind power cluster power prediction method and system based on similar day division |
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 |