CN117833227A - Wind farm power prediction method and device, computer equipment and storage medium - Google Patents
Wind farm power prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117833227A CN117833227A CN202410007163.6A CN202410007163A CN117833227A CN 117833227 A CN117833227 A CN 117833227A CN 202410007163 A CN202410007163 A CN 202410007163A CN 117833227 A CN117833227 A CN 117833227A
- Authority
- CN
- China
- Prior art keywords
- power
- data
- wind
- historical
- power prediction
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000006870 function Effects 0.000 claims description 47
- 238000012876 topography Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Abstract
The invention discloses a wind farm power prediction method, a wind farm power prediction device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring historical power data, historical wind speed data, historical wind power data and weather forecast data of a wind farm; inputting wind speed forecast data into a first power prediction model, and calculating a first power prediction result of the wind power plant according to a relation function of power and wind speed in the first power prediction model; inputting wind power forecast data and wind speed forecast data into a second power forecast model, and calculating a second power forecast result of the wind power plant according to a relation function of power and wind speed in the second power forecast model; and combining the first power prediction result and the second power prediction result to obtain a final power prediction result. According to the method, the weather forecast data are input into the two prediction models to obtain the prediction result, so that the final power prediction result with higher accuracy is obtained, and the prediction accuracy of the power of the wind power plant is improved.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a wind power plant power prediction method, a wind power plant power prediction device, computer equipment and a storage medium.
Background
Wind power generation technology has been developed more and more widely in recent years as an important form of new energy technology. The wind power generation technology converts wind energy into electric energy by utilizing a wind power field, and the wind energy has the characteristics of intermittence, randomness and fluctuation, so that the change of wind speed can directly influence the change of active power and reactive power of the wind power field, thereby leading the output power of the wind power field to be unstable, further influencing the power grid dispatching capability and the wind power access capability of a power system, and therefore, it is important for the wind power generation technology to establish a more effective prediction mechanism to accurately predict the power of the wind power field.
The prediction model and the prediction method adopted by the existing wind power plant power prediction algorithm are generally single, and the prediction accuracy is poor due to the fact that the historical data and weather data of the wind power plant are not utilized sufficiently in the prediction process, so that the prediction accuracy of the wind power plant power is improved, and the problem to be solved by the person skilled in the art is solved.
Disclosure of Invention
The embodiment of the invention provides a wind power plant power prediction method, a device, computer equipment and a storage medium, aiming at improving the prediction accuracy of wind power plant power.
In a first aspect, an embodiment of the present invention provides a wind farm power prediction method, including:
acquiring historical power data, historical wind speed data, historical wind power data and weather forecast data of a wind farm; the weather forecast data comprises wind forecast data and wind speed forecast data;
inputting the wind speed forecast data into a first power prediction model, and calculating to obtain a first power prediction result of the wind power plant according to a relation function of power and wind speed in the first power prediction model; wherein the first power prediction model is constructed based on the historical power data and historical wind speed data;
inputting the wind power forecast data and the wind speed forecast data into a second power forecast model, and calculating a second power forecast result of the wind power plant according to a relation function of power and wind speed in the second power forecast model; wherein the second power prediction model is constructed based on the historical power data, the historical wind speed data, and the historical wind power data;
and combining the first power prediction result and the second power prediction result to obtain a final power prediction result.
In a second aspect, an embodiment of the present invention provides a wind farm power prediction apparatus, including:
the data acquisition unit is used for acquiring historical power data, historical wind speed data, historical wind power data and weather forecast data of the wind power plant; the weather forecast data comprises wind forecast data and wind speed forecast data;
the first prediction unit is used for inputting the wind speed prediction data into a first power prediction model, and calculating a first power prediction result of the wind power plant according to a relation function of power and wind speed in the first power prediction model; wherein the first power prediction model is constructed based on the historical power data and historical wind speed data;
the second prediction unit is used for inputting the wind power prediction data and the wind speed prediction data into a second power prediction model, and calculating a second power prediction result of the wind power plant according to a relation function of power, wind speed and wind power in the second power prediction model; wherein the second power prediction model is constructed based on the historical power data, the historical wind speed data, and the historical wind power data;
and the combination prediction unit is used for combining the first power prediction result and the second power prediction result to obtain a final power prediction result.
In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the wind farm power prediction method according to the first aspect when executing the computer program.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a wind farm power prediction method according to the first aspect.
According to the embodiment of the invention, firstly, the historical power data, the historical wind speed data, the historical wind power data and the weather forecast data of the wind power plant are obtained, then the wind speed forecast data are input into a first power forecast model constructed according to the historical power data and the historical wind speed data, a first power forecast result of the wind power plant is calculated according to a relation function of power and wind speed in the first power forecast model, the wind forecast data and the wind speed forecast data are input into a second power forecast model constructed according to the historical power data, the historical wind speed data and the historical wind power data, a second power forecast result is calculated according to a relation function of power, wind speed and wind power in the second power forecast model, and then the two power forecast results are combined, so that a final power forecast result with higher accuracy can be obtained, and the effect of forecasting the wind power of the wind power plant by combining the historical data and the weather data is achieved, so that the forecasting accuracy of the wind power plant is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a wind farm power prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic sub-flowchart of a method for predicting power of a wind farm according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another sub-flowchart of a method for predicting power of a wind farm according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a wind farm power prediction apparatus according to an embodiment of the present invention;
FIG. 5 is a sub-schematic block diagram of a wind farm power prediction apparatus provided by an embodiment of the present invention;
fig. 6 is another sub-schematic block diagram of a wind farm power prediction apparatus 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 fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. 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.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1, fig. 1 is a schematic flow chart of a wind farm power prediction method according to an embodiment of the present invention, which specifically includes: steps S101 to S104.
S101, acquiring historical power data, historical wind speed data, historical wind power data and weather forecast data of a wind farm; the weather forecast data comprises wind forecast data and wind speed forecast data;
s102, inputting the wind speed forecast data into a first power prediction model, and calculating to obtain a first power prediction result of the wind power plant according to a relation function of power and wind speed in the first power prediction model; wherein the first power prediction model is constructed based on the historical power data and historical wind speed data;
s103, inputting the wind power forecast data and the wind speed forecast data into a second power forecast model, and calculating to obtain a second power forecast result of the wind power plant according to a relation function of power, wind speed and wind power in the second power forecast model; wherein the second power prediction model is constructed based on the historical power data, the historical wind speed data, and the historical wind power data;
and S104, combining the first power prediction result and the second power prediction result to obtain a final power prediction result.
In this embodiment, firstly, historical power data, historical wind speed data, historical wind power data and weather forecast data of a wind power plant are obtained, secondly, the wind speed forecast data are input into a first power forecast model constructed according to the historical power data and the historical wind speed data, a first power forecast result of the wind power plant is calculated according to a relation function of power and wind speed in the first power forecast model, then the wind speed forecast data and the wind speed forecast data are input into a second power forecast model constructed according to the historical power data, the historical wind speed data and the historical wind power data, a second power forecast result is calculated according to a relation function of power, wind speed and wind power in the second power forecast model, and finally the first power forecast result and the second power forecast result are combined to obtain a final power forecast result.
According to the embodiment, a first power prediction model is built according to historical power data and historical wind speed data, a second power prediction model is built according to the historical power data, the historical wind speed data and the historical wind speed data, weather forecast data are input into the two power prediction models to conduct power prediction, a more accurate power prediction result is obtained, and the power prediction results output by the two power prediction models are combined, so that the accuracy of a final power prediction result is further improved, the problem that the power of a wind power plant is unstable through a single algorithm is solved, the stability of the power prediction of the wind power plant is improved, the probability that the prediction error and the extreme abnormal value of the power of the wind power plant occur at the future time is reduced, the power grid scheduling capability and the wind power access capability of a power system are improved, and the running cost of the system is reduced.
In a specific embodiment, historical power data, historical wind speed data, historical wind power data and weather forecast data of the wind farm can be obtained through a centralized control system of the wind farm. The centralized control system of the wind power plant is a control system or a control module for acquiring, collecting and managing relevant data of the wind power plant, for example, the centralized control system of the wind power plant can monitor and control the running state of each wind turbine in the wind power plant, and meanwhile, weather forecast data of the wind power plant can be acquired through a networking function.
In one embodiment, as shown in fig. 2, the step of constructing the first power prediction model includes: steps S201 to S203.
S201, constructing a first relation function of power and wind speed according to the following formula:
wherein X is t The wind speed at time t, X t-i The wind speed at the time t-i is represented by a, the topography influencing factor is represented by b t Represents the power at time t, b t-j Representing the power at time t-j, c i Represents the i first parameter, d j The j power error is represented, p represents the total data amount of wind speed, and q represents the total data amount of power;
s202, inputting the historical power data and the historical wind speed data into the first relation function for fitting to obtain a value of a first parameter and a value of a power error;
s203, substituting the value of the first parameter and the value of the power error into the first relation function to obtain the first power prediction model.
In this embodiment, a first relation function about power and wind speed is first constructed, then historical power data and historical wind speed data are input into the first relation function, first parameters and power errors in the first relation function are obtained through fitting, and finally the first parameters and the power errors are substituted into the first relation function, so that a first power prediction model is obtained. According to the method, the first power prediction model is constructed through fitting time sequence data related to power and wind speed to conduct power prediction, and the prediction accuracy of wind power plant power is improved.
In one embodiment, as shown in connection with fig. 3, the step of constructing the second power prediction model includes: steps S301 to S303.
S301, constructing a second relation function of power, wind speed and wind power according to the following formula:
P＝kZY+a
wherein P represents power, k represents a second parameter, Z represents wind power, Y represents wind speed, and a represents a topography influencing factor;
s302, inputting the historical power data, the historical wind speed data and the historical wind power data into the second relation function for fitting to obtain a value of a second parameter;
s303, substituting the value of the second parameter into the second relation function to obtain the second power prediction model.
In this embodiment, a second relation function about power, wind speed and wind power is first constructed, then historical power data, historical wind speed data and historical wind power data are input into the second relation function, second parameters in the second relation function are obtained through fitting, and the second parameters are substituted into the second relation function, so that a second power prediction model is obtained.
In the prior art, the power is usually calculated by adopting a mode of p=fv, that is, the power is equal to the product of force and speed, but the prior art does not consider the influence of influence factors such as topography and the like on the power of the wind power plant, but in practical application, the calculated wind power plant power may have errors due to the calculation mode, so that the embodiment considers the factors of topography and the topography, introduces the topography factors into a model for power prediction, and selects the wind power and the wind speed to a certain degree of duty ratio through a second parameter (model parameter), thereby improving the accuracy of power prediction.
In one embodiment, before the step S104, the method includes:
calculating a difference between the first power prediction result and the second power prediction result;
when the difference value is smaller than or equal to a preset difference value threshold value, calculating an error between the first power prediction result and the historical average power to obtain a first error, and calculating an error between the second power prediction result and the historical average power to obtain a second error;
and when the first error is smaller than or equal to a preset error threshold value and the second error is smaller than or equal to the preset error threshold value, a step of combining the first power prediction result and the second power prediction result to obtain a final power prediction result is performed.
In this embodiment, firstly, a difference between a first power prediction result and a second power prediction result is calculated, secondly, when a condition that the difference is smaller than or equal to a preset difference threshold is met, an error between the first power prediction result and a historical average power is calculated as a first error, an error between the second power prediction result and the historical average power is calculated as a second error, finally, the first error and the second error are respectively combined with a preset error threshold to judge, and when the condition that the first error and the second error are smaller than or equal to the preset error threshold is met, a step of combining the first power prediction result and the second power prediction result to obtain a final power prediction result is entered. According to the embodiment, the prediction result is compared with the historical average power, so that the power prediction is performed by combining the time correlation of the data, and the prediction accuracy of the power of the wind power plant is improved.
In a specific application scenario, the historical average power corresponding to each wind speed can be obtained through a historical power meter, and the first power prediction result and the second power prediction result are obtained through calculation based on wind speeds, so that the historical average power corresponding to the specified wind speed can be obtained under the condition of the specified wind speed, meanwhile, the corresponding first power prediction result is output to the specified wind speed through a first power prediction model, and then the first power prediction result is compared with the historical average power, so that the first error of the first power prediction model can be obtained. Similarly, a second power prediction result corresponding to the designated wind speed is output through a second power prediction model, and then the second power prediction result is compared with the historical average power, so that a second error of the second power prediction model can be obtained.
Further, the first error is compared with a preset error threshold, and the second error is compared with the preset error threshold. If the first error and the second error are not larger than the preset error threshold, the first power prediction result and the second power prediction result which respectively correspond to the first error and the second error are accurate, and therefore the first power prediction result and the second power prediction result can be used for carrying out the next step. If the first error is greater than the preset error threshold and/or the second error is greater than the preset error threshold, it is determined that the first error and/or the second error is too large, i.e., the first power prediction result and/or the second power prediction result are inaccurate, it is understood that whether the first power prediction result and the second power prediction result are both inaccurate or only one of the first power prediction result and the second power prediction result is inaccurate, the final power prediction result is inaccurate, and therefore the corresponding first power prediction result and second power prediction result are discarded simultaneously.
In a specific embodiment, the preset difference threshold and the preset error threshold are not limited explicitly, and may be set to be the same or different according to different practical applications.
For example, the preset difference threshold and the preset error threshold may be set to be 5W (watts), that is, when the difference between the first power prediction result and the second power prediction result is less than or equal to 5W, the step of calculating the error is performed, and then when the first error and the second error are both less than or equal to 5W, it is indicated that the first power prediction result and the second power prediction result corresponding to the first error and the second error respectively are more accurate, so that the first power prediction result and the second power prediction result may be used for performing the next step, and vice versa.
In some alternative embodiments, the preset error threshold may also be set as a percentage, i.e. compared in terms of a percentage error, i.e. when comparing the first error with the preset error threshold, it is first necessary to calculate a percentage error between the first power prediction result and the historical average power, then take this percentage error as the first error, and then compare the first error with the preset error threshold. Similarly, when comparing the second error with the preset error threshold, it is first necessary to calculate a percentage error between the second power prediction result and the historical average power, then use the percentage error as the second error, and then compare the second error with the preset error threshold. For example, the preset error threshold is ±5%, and when the first error and the second error are not greater than the preset error threshold, that is, when the first error and the second error are not greater than ±5%, it is indicated that the first power prediction result and the second power prediction result corresponding to the first error and the second error respectively are relatively accurate, so that the first power prediction result and the second power prediction result can be used for performing the next step.
Specifically, the percentage error between the power prediction result (first power prediction result and second power prediction result) and the historical average power may be calculated according to the following formula:
wherein E represents a percentage error, P x The result of the power prediction is indicated,representing the historical average power.
In one embodiment, the step S102 includes:
and calculating an average value of the first power prediction result and the second power prediction result, and taking the average value as the final power prediction result.
In the embodiment, the average value of the first power prediction result and the second power prediction result is calculated, the average value is used as a final power prediction result, and the accuracy of wind power plant power prediction is improved by combining the prediction results of the two prediction models, so that the problem that the wind power plant is unstable in predicting power through a single algorithm is solved.
In one embodiment, the topography influencing factor is obtained as follows:
obtaining the topography data of a wind power plant;
cutting the topographic and geomorphic data, and carrying out data denoising and data splicing on the topographic and geomorphic data after cutting to obtain the topographic and geomorphic influence factor.
In this embodiment, firstly, the obtained topographic and geomorphic data of the wind farm is cut, then the cut topographic and geomorphic data is subjected to data denoising to remove invalid data, and finally the cut and denoised topographic and geomorphic data is subjected to data splicing to obtain the topographic and geomorphic influence factor.
In a specific application scene, the topography factors can influence the climate of the wind power plant, the climate determines the wind power and the wind speed of the wind power plant, and the wind power and the wind speed influence the power of the wind power plant, so that the topography factors need to be considered in the power prediction of the wind power plant, in the specific prediction, the influence of various factors such as the temperature, the air pressure, the topography, the altitude, the latitude and the like of the wind power plant needs to be considered, and meanwhile, the influence of the wind speed and the wind direction of the hub height of the wind turbine generator set under the actual topography condition of the wind power plant needs to be considered.
In a specific embodiment, when the topography data of the wind power plant are acquired, the real-time air temperature of the wind power plant is acquired, the real-time impeller rotating speed and the real-time output power of the wind power plant are acquired, the real-time air temperature, the real-time impeller rotating speed and the real-time output power are combined to judge, when the real-time air temperature is smaller than or equal to 0 DEG, the real-time impeller rotating speed and the real-time output power are obviously reduced in a period of time, and when the wind power plant has no problems such as abnormal pitching, the wind power plant is judged to have blade icing, and feedback early warning is carried out.
Specifically, because the influence of different seasons and climates on the wind turbine is different, for example, abnormal phenomena such as icing of the blades of the wind turbine and the existence of attachments in ice during winter can occur, the abnormal phenomena can influence the rotating speed of the blades of the wind turbine, the blades of the wind turbine are important parts for capturing wind energy of the wind turbine, the icing phenomenon can directly influence the running parameters such as the rotating speed and the output power of the impeller, when the icing is serious, the pneumatic torque of the wind turbine is reduced, the rotating speed of the impeller is reduced, the measurement of wind power and wind speed of a wind farm can be influenced, the output power of the wind turbine is obviously reduced, and the more serious the icing degree is, the rotating speed of the impeller and the output power are obviously reduced, so that feedback early warning is needed when the icing phenomenon of the blades of the wind turbine occurs.
In a specific embodiment, the data cutting needs to layer the geomorphic elements of the wind farm, for example, data in a space 20 meters above the ground of the wind farm is set as an acquisition object, and the geomorphic data in the range is subjected to layer cutting.
In an embodiment, after the step S104, the method further includes:
and when the final power prediction result exceeds a preset power threshold range, judging that the power of the wind power plant is abnormal, and feeding back.
In this embodiment, the final power prediction result is compared with a preset power threshold range, if the final power prediction result exceeds the preset power threshold range, the power abnormality of the wind power plant is determined, and feedback early warning is performed to remind a manager to perform inspection so as to ensure the operation safety of the wind power plant.
Fig. 4 is a schematic block diagram of a wind farm power prediction apparatus 400 according to the present embodiment, where the apparatus 400 includes:
a data acquisition unit 401, configured to acquire historical power data, historical wind speed data, historical wind power data, and weather forecast data of a wind farm; the weather forecast data comprises wind forecast data and wind speed forecast data;
the first prediction unit 402 is configured to input the wind speed prediction data into a first power prediction model, and calculate a first power prediction result of the wind farm according to a relationship function between power and wind speed in the first power prediction model; wherein the first power prediction model is constructed based on the historical power data and historical wind speed data;
the second prediction unit 403 is configured to input the wind power prediction data and the wind speed prediction data into a second power prediction model, and calculate a second power prediction result of the wind farm according to a relationship function between power, wind speed and wind power in the second power prediction model; wherein the second power prediction model is constructed based on the historical power data, the historical wind speed data, and the historical wind power data;
and a combination prediction unit 404, configured to combine the first power prediction result and the second power prediction result to obtain a final power prediction result.
In one embodiment, as shown in connection with fig. 5, the wind farm power prediction apparatus 400 further includes:
a first function construction unit 501, configured to construct a first relation function of power and wind speed according to the following formula:
wherein X is t The wind speed at time t, X t-i The wind speed at the time t-i is represented by a, the topography influencing factor is represented by b t Represents the power at time t, b t-j Representing the power at time t-j, c i Represents the i first parameter, d j The j power error is represented, p represents the total data amount of wind speed, and q represents the total data amount of power;
a first function fitting unit 502, configured to input the historical power data and the historical wind speed data into the first relation function to perform fitting, so as to obtain a value of a first parameter and a value of a power error;
a first parameter substituting unit 503 is configured to substitute the value of the first parameter and the value of the power error into the first relation function, so as to obtain the first power prediction model.
In one embodiment, as shown in connection with fig. 6, the wind farm power prediction apparatus 400 further includes:
a second function construction unit 601, configured to construct a second relation function of power, wind speed, and wind power according to the following formula:
P＝kZY+a
wherein P represents power, k represents a second parameter, Z represents wind power, Y represents wind speed, and a represents a topography influencing factor;
a second function fitting unit 602, configured to input the historical power data, the historical wind speed data, and the historical wind power data into the second relation function to perform fitting, so as to obtain a value of a second parameter;
a second parameter substituting unit 603 is configured to substitute a value of the second parameter into the second relation function to obtain the second power prediction model.
In an embodiment, the wind farm power prediction apparatus 400 further comprises:
a difference calculating unit for calculating a difference between the first power prediction result and the second power prediction result;
an error calculation unit, configured to calculate an error between the first power prediction result and the historical average power to obtain a first error, and calculate an error between the second power prediction result and the historical average power to obtain a second error when the difference is less than or equal to a preset difference threshold;
and the power combining unit is used for combining the first power prediction result and the second power prediction result to obtain a final power prediction result when the first error is smaller than or equal to a preset error threshold value and the second error is smaller than or equal to the preset error threshold value.
In an embodiment, the combined prediction unit 404 includes:
and the average value calculation unit is used for calculating an average value of the first power prediction result and the second power prediction result and taking the average value as the final power prediction result.
In an embodiment, the wind farm power prediction apparatus 400 further comprises:
the system comprises a landform data acquisition unit, a wind power plant data acquisition unit and a wind power plant data acquisition unit, wherein the landform data acquisition unit is used for acquiring the landform data of the wind power plant;
and the data processing unit is used for cutting the topographic and geomorphic data, denoising and splicing the cut topographic and geomorphic data to obtain the topographic and geomorphic influence factor.
In an embodiment, the wind farm power prediction apparatus 400 further comprises:
and the abnormality feedback unit is used for judging that the power of the wind power plant is abnormal and feeding back when the final power prediction result exceeds a preset power threshold range.
Since the embodiments of the apparatus portion and the embodiments of the method portion correspond to each other, the embodiments of the apparatus portion are referred to the description of the embodiments of the method portion, and are not repeated herein.
The embodiment of the present invention also provides a computer readable storage medium having a computer program stored thereon, which when executed can implement the steps provided in the above embodiment. The storage medium may include: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RandomAccess Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The embodiment of the invention also provides a computer device, which can comprise a memory and a processor, wherein the memory stores a computer program, and the processor can realize the steps provided by the embodiment when calling the computer program in the memory. Of course, the computer device may also include various network interfaces, power supplies, and the like.
In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present application without departing from the principles of the present application, and such improvements and modifications fall within the scope of the claims of the present application.
It should also be noted that in this specification, 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 does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. 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.
Claims (10)
1. A method of wind farm power prediction, comprising:
acquiring historical power data, historical wind speed data, historical wind power data and weather forecast data of a wind farm; the weather forecast data comprises wind forecast data and wind speed forecast data;
inputting the wind speed forecast data into a first power prediction model, and calculating to obtain a first power prediction result of the wind power plant according to a relation function of power and wind speed in the first power prediction model; wherein the first power prediction model is constructed based on the historical power data and historical wind speed data;
inputting the wind power forecast data and the wind speed forecast data into a second power forecast model, and calculating a second power forecast result of the wind power plant according to a relation function of power and wind speed in the second power forecast model; wherein the second power prediction model is constructed based on the historical power data, the historical wind speed data, and the historical wind power data;
and combining the first power prediction result and the second power prediction result to obtain a final power prediction result.
2. The method for predicting power of a wind farm according to claim 1, wherein the constructing of the first power prediction model comprises:
a first relationship function of power and wind speed is constructed according to the following formula:
wherein X is t The wind speed at time t, X t-i The wind speed at time t-i is indicated,a represents a topography influencing factor, b t Represents the power at time t, b t-j Representing the power at time t-j, c i Represents the i first parameter, d j The j power error is represented, p represents the total data amount of wind speed, and q represents the total data amount of power;
inputting the historical power data and the historical wind speed data into the first relation function for fitting to obtain a value of a first parameter and a value of a power error;
substituting the value of the first parameter and the value of the power error into the first relation function to obtain the first power prediction model.
3. The method for predicting power of a wind farm according to claim 1, wherein the constructing of the second power prediction model comprises:
constructing a second relation function of power, wind speed and wind power according to the following formula:
P＝kZY+a
wherein P represents power, k represents a second parameter, Z represents wind power, Y represents wind speed, and a represents a topography influencing factor;
inputting the historical power data, the historical wind speed data and the historical wind power data into the second relation function for fitting to obtain a value of a second parameter;
substituting the value of the second parameter into the second relation function to obtain the second power prediction model.
4. A method of predicting power in a wind farm according to any of claims 1-3, wherein prior to the step of combining the first power prediction result and the second power prediction result to obtain a final power prediction result, comprising:
calculating a difference between the first power prediction result and the second power prediction result;
when the difference value is smaller than or equal to a preset difference value threshold value, calculating an error between the first power prediction result and the historical average power to obtain a first error, and calculating an error between the second power prediction result and the historical average power to obtain a second error;
and when the first error is smaller than or equal to a preset error threshold value and the second error is smaller than or equal to the preset error threshold value, a step of combining the first power prediction result and the second power prediction result to obtain a final power prediction result is performed.
5. A method of predicting power of a wind farm according to any of claims 1-3, wherein combining the first power prediction result and the second power prediction result to obtain a final power prediction result comprises:
and calculating an average value of the first power prediction result and the second power prediction result, and taking the average value as the final power prediction result.
6. A method of predicting power in a wind farm according to any of claims 2 to 3, wherein the topographical influencing factor is obtained by:
obtaining the topography data of a wind power plant;
cutting the topographic and geomorphic data, and carrying out data denoising and data splicing on the topographic and geomorphic data after cutting to obtain the topographic and geomorphic influence factor.
7. The method of claim 1, wherein after the step of combining the first power prediction result and the second power prediction result to obtain a final power prediction result, further comprising:
and when the final power prediction result exceeds a preset power threshold range, judging that the power of the wind power plant is abnormal, and feeding back.
8. A wind farm power prediction apparatus, comprising:
the data acquisition unit is used for acquiring historical power data, historical wind speed data, historical wind power data and weather forecast data of the wind power plant; the weather forecast data comprises wind forecast data and wind speed forecast data;
the first prediction unit is used for inputting the wind speed prediction data into a first power prediction model, and calculating a first power prediction result of the wind power plant according to a relation function of power and wind speed in the first power prediction model; wherein the first power prediction model is constructed based on the historical power data and historical wind speed data;
the second prediction unit is used for inputting the wind power prediction data and the wind speed prediction data into a second power prediction model, and calculating a second power prediction result of the wind power plant according to a relation function of power, wind speed and wind power in the second power prediction model; wherein the second power prediction model is constructed based on the historical power data, the historical wind speed data, and the historical wind power data;
and the combination prediction unit is used for combining the first power prediction result and the second power prediction result to obtain a final power prediction result.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the wind farm power prediction method according to any of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements a wind farm power prediction method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410007163.6A CN117833227A (en) | 2024-01-03 | 2024-01-03 | Wind farm power prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410007163.6A CN117833227A (en) | 2024-01-03 | 2024-01-03 | Wind farm power prediction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117833227A true CN117833227A (en) | 2024-04-05 |
Family
ID=90511311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410007163.6A Pending CN117833227A (en) | 2024-01-03 | 2024-01-03 | Wind farm power prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117833227A (en) |
-
2024
- 2024-01-03 CN CN202410007163.6A patent/CN117833227A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Seo et al. | Wind turbine power curve modeling using maximum likelihood estimation method | |
| EP3394436B1 (en) | Controlling wind turbines according to reliability estimates | |
| CN110761958B (en) | Blade stall diagnosis method and device of wind generating set | |
| CN111340307B (en) | Method for predicting wind power generation power of fan and related device | |
| CN108062722B (en) | Mechanical power calculation method of mountain wind power plant model fan based on wind speed variation coefficient | |
| US20220026599A1 (en) | Calculating a return period wind speed | |
| CN111159640A (en) | Small rain emptying method, system, electronic equipment and storage medium suitable for grid forecast | |
| Roberge et al. | Towards standards in the analysis of wind turbines operating in cold climate–Part A: Power curve modeling and rotor icing detection | |
| CN117590027A (en) | Deficiency correction method and system for wind meter of wind turbine generator and electronic equipment | |
| CN117833227A (en) | Wind farm power prediction method and device, computer equipment and storage medium | |
| CN110188939B (en) | Wind power prediction method, system, equipment and storage medium of wind power plant | |
| CN117251995A (en) | Double-fed fan inertia evaluation method based on variable forgetting factor least square method | |
| US11920562B2 (en) | Temperature estimation in a wind turbine | |
| Bao et al. | Iterative modeling of wind turbine power curve based on least‐square B‐spline approximation | |
| Lu | Multi-step ahead ultra-short-term wind power forecasting based on time series analysis | |
| CN112613155B (en) | Method, device and equipment for determining theoretical power of wind generating set | |
| EP3406897B1 (en) | System and method for determining wind farm wake loss | |
| CN110594106A (en) | Wind turbine load online prediction method, device, equipment and medium | |
| CN115358495B (en) | Calculation method for wind power prediction comprehensive deviation rate | |
| CN113468767B (en) | Method and system for evaluating generating capacity of offshore wind turbine | |
| Noppe et al. | High frequent scada-based thrust load modeling of wind turbines | |
| CN115355142B (en) | Wind vane fault detection method, system, equipment and medium for wind turbine generator | |
| CN117635367A (en) | Method, device and equipment for determining loss electric quantity of fan | |
| CN115478990A (en) | Wind turbine wind speed time parameter determination method based on aerodynamic coefficient | |
| CN116937538A (en) | ARIMA-BP-LSTM multi-feature fusion-based ultra-short-term wind power prediction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |