CN114841077A - Wind power prediction method, device and medium - Google Patents

Wind power prediction method, device and medium Download PDF

Info

Publication number
CN114841077A
CN114841077A CN202210568482.5A CN202210568482A CN114841077A CN 114841077 A CN114841077 A CN 114841077A CN 202210568482 A CN202210568482 A CN 202210568482A CN 114841077 A CN114841077 A CN 114841077A
Authority
CN
China
Prior art keywords
data
wind power
power prediction
wind
forecast data
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
Application number
CN202210568482.5A
Other languages
Chinese (zh)
Inventor
徐思达
张勇铭
赵章乐
张伟
卢成志
吕渤林
潘彬彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huadian Electric Power Research Institute Co Ltd
Original Assignee
Huadian Electric Power Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huadian Electric Power Research Institute Co Ltd filed Critical Huadian Electric Power Research Institute Co Ltd
Priority to CN202210568482.5A priority Critical patent/CN114841077A/en
Publication of CN114841077A publication Critical patent/CN114841077A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/06—Wind turbines or wind farms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Computing Systems (AREA)
  • Evolutionary Biology (AREA)
  • Human Resources & Organizations (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Biophysics (AREA)
  • Geometry (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Computer Hardware Design (AREA)
  • Medical Informatics (AREA)
  • Fluid Mechanics (AREA)
  • Wind Motors (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)

Abstract

The application relates to the field of wind power generation, and discloses a wind power prediction method, a device and a medium, which comprise the following steps: and acquiring measurement data required by wind power prediction, and providing data support for wind power prediction. Performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub; and performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data with higher time resolution, so that the time-space accuracy of wind power prediction is improved. And processing the second weather forecast data by using the power prediction model to determine a wind power prediction value. Therefore, according to the technical scheme provided by the application, the resolution of the data is improved by performing time scale reduction and space scale reduction on the measured data, so that the output power of each wind driven generator under complex terrain and complex wind conditions is accurately predicted, and the accuracy and reliability of wind power prediction of a wind power plant are improved.

Description

Wind power prediction method, device and medium
Technical Field
The application relates to the field of wind power generation, in particular to a wind power prediction method, a wind power prediction device and a wind power prediction medium.
Background
Wind power generation is one of the main technical approaches for constructing a clean low-carbon energy system and realizing a double-carbon target in China. Because the fluctuation and the randomness of wind are strong, the output power of wind power generation is unstable and irregular, and the safety and the stability of a power system can be influenced. And wind power generation capacity cannot be predicted, and wind power participation in market trading can also be influenced.
Because the wind speed in each time period is nonlinear time sequence data, in order to accurately describe the nonlinear characteristics of the data, an artificial neural network model is generally used for predicting the wind speed on the basis of a statistical method, a neural network is trained through a large amount of historical time sequence data, the nonlinear relation between input data and the predicted wind speed is found, and the prediction of the medium-time-scale wind power output power can be realized by combining with the established meteorological physical model. However, the existing medium-time scale wind power output power prediction resolution is low, and more accurate and shorter meteorological changes cannot be determined, so that the wind power output power of a single-fan level cannot be predicted accurately.
Therefore, how to provide a wind power prediction method with higher resolution is a problem that needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
The application aims to provide a wind power prediction method, a wind power prediction device and a wind power prediction medium so as to improve the prediction precision of the output power of a wind generating set.
In order to solve the technical problem, the application provides a wind power prediction method, which comprises the steps of
Acquiring measurement data required by predicting wind power;
performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub;
performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data, wherein the data time interval of the second meteorological forecast data is smaller than that of the first meteorological forecast data;
and processing the second meteorological forecast data by using a power prediction model to determine a wind power prediction value.
Preferably, the acquiring of the measurement data required for predicting the wind power includes:
acquiring mesoscale numerical weather forecast data, position information of a wind turbine generator, wind power site shape data and wind power site shape roughness data of a target area;
the target area is an area with a distance from the wind turbine generator smaller than a distance threshold value.
Preferably, the performing spatial downscaling processing on the measurement data includes:
and carrying out spatial downscaling processing on the measurement data by using a computational fluid dynamics model.
Preferably, before the step of processing the second weather forecast data by using the power prediction model, the method further includes:
carrying out error correction processing on the second meteorological forecast data by utilizing a random forest neural network model;
the random forest neural network model is a network model obtained by training according to historical measurement data.
Preferably, before the step of processing the second weather forecast data by using the power prediction model, the method further includes:
and carrying out data dimension reduction and denoising treatment on the measurement data.
Preferably, the time-downscaling the first weather forecast data includes:
and performing time scale reduction processing on the first meteorological forecast data by adopting a differential autoregressive moving average model.
Preferably, the first weather forecast data includes:
wind speed data, wind direction data, temperature data, and barometric pressure data.
In order to solve the above technical problem, the present application further provides a wind power prediction apparatus, including:
the acquisition module is used for acquiring measurement data required by predicting wind power;
the spatial downscaling module is used for performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub;
the time scale reduction module is used for performing time scale reduction processing on the first meteorological forecast data to acquire second meteorological forecast data, and the data time interval of the second meteorological forecast data is smaller than that of the first meteorological forecast data;
and the determining module is used for processing the second weather forecast data by using a power prediction model so as to determine a wind power prediction value.
In order to solve the above technical problem, the present application further provides a wind power prediction apparatus, which includes a memory for storing a computer program;
and the processor is used for realizing the steps of the wind power prediction method when the computer program is executed.
In order to solve the above technical problem, the present application further provides a computer readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the wind power prediction method.
The application provides a wind power prediction method, which comprises the following steps: and acquiring measurement data required by wind power prediction to provide data support for wind power prediction. Carrying out spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub; and performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data so as to obtain meteorological measurement data with higher time resolution, thereby improving the time-space accuracy of wind power prediction. And processing the second meteorological forecast data by using the power prediction model to determine a wind power prediction value. Therefore, according to the technical scheme provided by the application, the resolution of the data is improved by performing time scale reduction and space scale reduction on the measured data, so that the output power of each wind driven generator under complex terrain and complex wind conditions is accurately predicted, and the accuracy and reliability of wind power prediction of a wind power plant are improved.
In addition, the application also provides a wind power prediction device and medium, which correspond to the method and have the same effects as the method.
Drawings
In order to more clearly illustrate the embodiments of the present application, the drawings needed for the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a flowchart of a wind power prediction method according to an embodiment of the present disclosure;
fig. 2 is a structural diagram of a wind power prediction apparatus provided in an embodiment of the present application;
fig. 3 is a structural diagram of another wind power prediction apparatus provided in the embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
The core of the application is to provide a wind power prediction method, a wind power prediction device and a wind power prediction medium so as to improve the prediction precision of the output power of the wind generating set.
In order that those skilled in the art will better understand the disclosure, the following detailed description will be given with reference to the accompanying drawings.
In a wind power generation scene, the output power of a wind power generation device is unstable and irregular due to the fact that the intensity of wind and the direction of the wind constantly change, and the safety of a power system is affected. In order to predict the output power of the wind power generation device more accurately, the method for predicting the medium-long term wind power includes the steps of obtaining meteorological data of an area where a wind power plant is located and equipment information of a wind power generator, conducting time scale reduction processing and space scale reduction processing on the measured data to obtain meteorological measured data with higher time resolution of a specified area, and inputting the meteorological measured data into a power prediction model to predict the output power of the wind power generation device, so that the time-space accuracy of wind power prediction is improved. In addition, the measurement data are preprocessed through the neural network model before the downscaling processing, and the acquired meteorological measurement data are subjected to error correction, so that the accuracy and the reliability of the wind power prediction system are improved.
Fig. 1 is a flowchart of a wind power prediction method provided in an embodiment of the present application, and as shown in fig. 1, the method includes
S10: and acquiring measurement data required by predicting the wind power.
The acquiring of the measurement data required for predicting the wind power includes: collecting mesoscale numerical meteorological forecast data, wind turbine generator position information, wind power plant topographic data, wind power plant topographic roughness data and other information of a target area, wherein the mesoscale numerical meteorological forecast data comprises wind speed data, wind direction data, temperature data, air pressure data and the like. In specific implementation, the measurement data can be collected on site through a data collection device, and the measurement data can also directly access a GRAPES-Meso mesoscale numerical service forecasting system developed by a national weather center to inquire weather data. The horizontal resolution of the system is 3km multiplied by 3km, the system has 50 vertical layers, the time resolution is 3h, and the forecast time efficiency is 10 days at most. And the topographic map later-stage wind power plant topographic related data is formed by splicing the public DEM digital elevation data (10m precision) and the high-precision elevation data (2m precision) drawn in the wind power plant exploration and design stage.
It can be understood that, because the wind direction and the intensity of the wind are random data, in order to improve the accuracy of the subsequent prediction result, the acquired measurement data can be preprocessed to achieve the purpose of noise reduction.
S11: performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub;
s12: and performing time scale reduction processing on the first meteorological forecast data to acquire second meteorological forecast data, wherein the data time interval of the second meteorological forecast data is smaller than that of the first meteorological forecast data.
It can be understood that the weather system can be divided into a planet scale, a large scale, a medium scale and a small scale according to the time scale and the space scale; the scale concerned by the mesoscale meteorological data is several kilometers to hundreds of kilometers, and the duration is several days. The reliability and the accuracy of the mesoscale meteorological forecast are high, but the resolution ratio is low, the meteorological process with short duration cannot be captured, and the power prediction result cannot be accurate to the single-fan level.
In the specific implementation, because the height of the fan hub is higher and the distance from the ground of the wind field is longer, and the difference between the wind data (including the strength of wind, the wind direction and the like) of the area where the fan hub and the ground of the wind field is larger, in order to improve the accuracy of wind power prediction, the first meteorological forecast data with higher spatial resolution is obtained by performing spatial downscaling processing on the measured data in the scheme, so that the wind data of the area where the fan hub is located is determined.
The common scale reduction method comprises three modes of statistical scale reduction, dynamic scale reduction and dynamic-statistical scale reduction. The method comprises the steps of realizing space downscaling and time downscaling in a Computer Fluid Dynamics (CFD) mode, specifically, providing a CFD model by adopting Metadyn WT commercial wind resource measurement and calculation software, solving a Navier-Stokes equation and a continuity equation of boundary conditions by using a Fluid constant incompressible model through the CFD model, taking 10 atmospheric thermal stabilities of different levels as boundary conditions, fusing the most advanced turbulence model and a wake flow model, rapidly calculating by adopting a coupling multi-grid solver to obtain a whole wind energy grid map, and carrying out grid encryption on a target point to obtain a calculation result which is accurate to the height of a fan hub. Compared with the WAsP using a linear model and other software developed based on the WAsP at present, the Meteodyn WT is more fit with the actual situation for wind resource evaluation of the complex terrain, and the accuracy of the calculation result under the complex terrain condition is improved.
Furthermore, in order to improve the computing capability of the CFD model, an open source OpenFOAM module can be nested in the Meteodyn WT software to construct a 'double CFD engine', so that other advanced CFD models are supplemented to calculate the complex condition, and the subsequent upgrading and extension of the system are facilitated.
In particular, because the wind data changes rapidly, the common mesoscale data cannot reflect the wind strength and wind direction at each moment and some meteorological data with short duration. Therefore, it is desirable to perform a time-downscaling process on the first meteorological forecast data that is capable of reflecting the wind data at the wind turbine hub. It can be understood that, since the meteorological data are nonlinear data, in order to obtain more accurate second meteorological forecast data, the first meteorological forecast data is downscaled by using a differential autoregressive moving average model.
S13: and processing the second meteorological forecast data by using the power prediction model to determine a wind power prediction value.
In specific implementation, the measured data is input into a power prediction model, so that a wind power prediction value is obtained. Since the input data set has more dimensionality than the output data set, and the historical power data of the wind turbine derived from the SCADA system may contain a large amount of noise, the SDAE-NARX artificial neural network model is used as a power prediction model for the wind turbine power. The SDAE is a stack type denoising self-encoder, is used as a data preprocessor which is good at learning complex internal characteristics in high-dimensional data to obtain dimensionality reduction representation of the data, and can denoise the data to improve the robustness of a power prediction model. The NARX is a nonlinear regression neural network with exogenous input, has rich historical state information and excellent dynamic characteristics, can use more information corresponding to expected data due to the exogenous input, and is suitable for describing the nonlinear relation between multi-dimensional input data consisting of weather forecast and historical power and predicted power data.
It can be understood that the SDAE-NARX artificial neural network model provided in this embodiment is a model trained from a historical meteorological data set, where the historical meteorological data set at least includes: historical meteorological forecast measurement data and historical wind turbine generator output power data at the height of the wind hub, specifically, the training process of the SDAE comprises the following steps:
(1) normalizing the data, adding Gaussian noise and inputting the data into a first DAE;
(2) iteratively calculating characteristic quantities, cost functions and gradients of a hidden layer and an output layer;
(3) and (4) removing the output layer after the convergence is judged, taking the hidden layer output of the first DAE as the input of the second DAE, and repeating the step (2). By analogy, training layer by layer to obtain a weight matrix and an offset item of each DAE, and establishing an SDAE model.
The training process of NARX includes:
(4) and dividing the historical power data of the fan into data at the t moment and the power data of the fan 10 days before the occurrence of the t moment. the power data of the fan at the time t is a target value, weather forecast data which is synchronous with the power data of the fan at the time t is an input variable, and n fan power data which are 10 days before the time t occurs are exogenous input variables;
(5) constructing a training set and a testing set by using the data in the last step;
(6) setting NARX initial parameters, iteratively calculating a hidden layer and an output layer, optimizing the parameters by adopting a random gradient descent algorithm, and establishing an NARX model.
In this embodiment, a wind power prediction method is provided, and the method includes: and acquiring measurement data required by wind power prediction to provide data support for wind power prediction. Performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub; and performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data so as to obtain meteorological measurement data with higher time resolution, thereby improving the time-space accuracy of wind power prediction. And processing the second meteorological forecast data by using the power prediction model to determine a wind power prediction value. Therefore, according to the technical scheme provided by the application, the resolution of the data is improved by performing time scale reduction and space scale reduction on the measured data, so that the output power of each wind driven generator under complex terrain and complex wind conditions is accurately predicted, and the accuracy and reliability of wind power prediction of a wind power plant are improved.
In specific implementation, wind power data is usually selected to predict wind power of a wind driven generator, but the prediction result is easily affected by other environmental factors (such as terrain factors, roughness factors and the like) and wind power equipment factors, so that the prediction result is inaccurate.
In order to solve the problem, thereby improving the accuracy of the measurement result and reducing the influence of the complex terrain factors on the wind power prediction result, on the basis of the above embodiment, the obtaining of the measurement data required for predicting the wind power includes:
acquiring mesoscale numerical weather forecast data, position information of a wind turbine generator, wind power site shape data and wind power site shape roughness data of a target area;
the target area is an area with a distance from the wind turbine generator smaller than a distance threshold value.
It can be understood that, in order to reduce interference caused by factors such as errors, in addition to the related measurement data in the wind farm, the measurement data required for predicting the wind power needs to be acquired, an area with a distance from the wind turbine set smaller than a distance threshold is also included.
Further, the first weather forecast data includes: wind speed data, wind direction data, temperature data, and barometric pressure data. In the embodiment, the output power of the wind turbine generator is predicted through wind speed data, wind direction data, temperature data, air pressure data and the like, and the output power of the wind turbine generator in different environments can be predicted more accurately.
In the embodiment, the mesoscale numerical weather forecast data, the position information of the wind turbine generator, the wind power field shape data and the wind power field terrain roughness data of the target area are used as the measurement data, so that the influence of terrain factors on the wind power prediction result is reduced, and the prediction accuracy is improved.
In the process of time scale reduction and space scale reduction processing of the measurement data, the method collects numerical weather forecast data of the past four years of grid points in the wind power field and nearby grid points, and screens out weather information closely related to wind power: wind speed, wind direction, temperature and air pressure, and numerical weather forecast data come from a GRAPES-Meso scale numerical service forecasting system, the forecast time is 10 days, the grid horizontal resolution is 3km multiplied by 3km, and the time resolution is 3 h. And collecting geographic position information (earth 2000 coordinate system) of the wind turbine generator, DEM digital elevation data (10m precision) of the wind power plant and a peripheral certain range, and a surveying and mapping topographic map (2m precision) of the wind power plant, and downloading roughness data of the wind power plant in a WT database. The method comprises the steps of taking weather forecast grid points in and near a wind power plant as virtual wind measuring points, taking position points of a wind power unit as target result points, loading a digital topographic map formed by splicing DEM digital elevation data and surveying and mapping topographic data into a Meteodyn WT 5.0 for calculation, dividing a directional calculation quadrant into 16 sectors, setting the step length to be 10m, and obtaining wind speed, wind direction, temperature and air pressure forecast data of the last four years at the height position of each fan hub of the wind power plant by utilizing the Meteodyn WT to perform a grid self-encryption function on the target result points.
Further, a differential autoregressive moving average model needs to be established, which specifically includes:
(1) carrying out differential operation on weather forecast data to obtain a stable data sequence;
(2) calculating an autocorrelation coefficient and a partial autocorrelation coefficient, and performing model identification;
(3) for the identified model, model parameters are determined.
And fitting the first meteorological forecast data with the time resolution of 3h by using the established differential autoregressive moving average model to obtain second meteorological forecast data with the time resolution of 15 min.
It can be understood that, in order to further improve the accuracy of the wind power prediction result, on the basis of the foregoing embodiment, before the step of processing the second weather forecast data by using the power prediction model, the method further includes:
and carrying out error correction processing on the second meteorological forecast data by utilizing a random forest neural network model, wherein the random forest neural network model is a network model obtained by training according to historical measurement data.
In specific implementation, besides the random forest neural network model, the countermeasure neural network model with higher convergence rate can be used for carrying out error correction processing on the second meteorological forecast data, but considering the influence of all influence factors on the output power of the wind turbine generator set, which needs to be comprehensively calculated, in the application scene of the wind power prediction method, the random forest neural network has stronger processing capability on high-dimensional data, feature selection is not needed, and meanwhile, when nonlinear discrete data are processed, normalization processing on a data set is not needed, so that the random forest neural network model is selected.
Specifically, training and testing a random forest neural network model according to historical measurement data and historical meteorological measurement data at the height of the fan hub, optimizing model parameters by adopting an improved particle swarm optimization, constructing a meteorological forecast data error correction model, and performing error correction on the obtained second meteorological forecast data to improve data reliability.
Furthermore, data dimension reduction and denoising processing can be performed on the obtained measurement data, so that the reliability of the data is improved. In specific implementation, the data dimension reduction method can be divided into linear dimension reduction and nonlinear dimension reduction, the linear dimension reduction method includes principal component analysis, independent component analysis, linear decision analysis, local feature analysis and the like, and the nonlinear dimension reduction method includes kernel function-based methods (for example, kernel function-based principal component analysis, kernel function-based independent component analysis, kernel function-based decision analysis) and feature value-based methods (for example, equidistant feature mapping, local linear embedding algorithm and the like). In the embodiment, the principal component analysis method is selected to perform the dimension reduction processing on the measurement data required by predicting the wind power, so that the loss of information can be reduced as much as possible, thereby removing noise and reducing the calculation resources required by the dimension reduction operation on the measurement data. In the embodiment, the accuracy and the reliability of the measurement data and the second weather forecast data are improved by preprocessing the measurement data and correcting the error of the second weather forecast data, so that a more accurate wind power prediction value is provided.
In the above embodiments, the wind power prediction method is described in detail, and the application also provides an embodiment corresponding to the wind power prediction device. It should be noted that the present application describes the embodiments of the apparatus portion from two perspectives, one from the perspective of the function module and the other from the perspective of the hardware.
Fig. 2 is a structural diagram of a wind power prediction apparatus provided in an embodiment of the present application, and as shown in fig. 2, the apparatus includes:
the acquisition module 10 is used for acquiring measurement data required by predicting wind power;
the spatial downscaling module 11 is configured to perform spatial downscaling processing on the measurement data to obtain first weather forecast data at the height of each fan hub;
a time downscaling module 12, configured to perform time downscaling on the first weather forecast data to obtain second weather forecast data, where a data time interval of the second weather forecast data is smaller than a data time interval of the first weather forecast data;
and the determining module 13 is configured to process the second weather forecast data by using the power prediction model to determine a wind power prediction value.
Since the embodiments of the apparatus portion and the method portion correspond to each other, please refer to the description of the embodiments of the method portion for the embodiments of the apparatus portion, which is not repeated here.
The embodiment provides a wind power prediction device, and the device includes: and acquiring measurement data required by predicting the wind power to provide data support for wind power prediction. Performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub; and performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data so as to obtain meteorological measurement data with higher time resolution, thereby improving the time-space accuracy of wind power prediction. And processing the second weather forecast data by using the power prediction model to determine a wind power prediction value. Therefore, according to the technical scheme provided by the application, the resolution ratio of the data is improved by performing time scale reduction and space scale reduction on the measured data, so that the output power of each wind driven generator under complex terrain and complex wind conditions is accurately predicted, and the accuracy and reliability of wind power prediction of the wind power plant are improved
Fig. 3 is a structural diagram of another wind power prediction apparatus provided in an embodiment of the present application, and as shown in fig. 3, the wind power prediction apparatus includes: a memory 20 for storing a computer program;
and the processor 21 is configured to implement the steps of the method for obtaining the predicted value of the wind turbine output power according to the above embodiment when executing the computer program.
The terminal device provided by the embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, or a desktop computer.
The processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The Processor 21 may be implemented in hardware using at least one of a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), and a Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a Graphics Processing Unit (GPU) which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 21 may further include an Artificial Intelligence (AI) processor for processing computing operations related to machine learning.
The memory 20 may include one or more computer-readable storage media, which may be non-transitory. Memory 20 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used for storing the following computer program 201, wherein after being loaded and executed by the processor 21, the computer program can implement the relevant steps of the wind power prediction method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202, data 203, and the like, and the storage manner may be a transient storage manner or a permanent storage manner. Operating system 202 may include, among others, Windows, Unix, Linux, and the like. The data 203 may include, but is not limited to, measurement data, first weather forecast data, second weather forecast data, and the like.
In some embodiments, the wind power prediction device may further include a display 22, an input/output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.
Those skilled in the art will appreciate that the configuration shown in FIG. 3 does not constitute a limitation of the wind power prediction apparatus and may include more or fewer components than those shown.
The wind power prediction device provided by the embodiment of the application comprises a memory and a processor, wherein when the processor executes a program stored in the memory, the following method can be realized:
acquiring measurement data required by predicting wind power;
carrying out spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub;
performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data, wherein the data time interval of the second meteorological forecast data is smaller than that of the first meteorological forecast data;
and processing the second meteorological forecast data by using the power prediction model to determine a wind power prediction value.
Finally, the application also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps as set forth in the above-mentioned method embodiments.
It is to be understood that if the method in the above embodiments is implemented in the form of software functional units and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and executes all or part of the steps of the methods described in the embodiments of the present application, or all or part of the technical solutions. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The wind power prediction method, the wind power prediction device and the wind power prediction medium provided by the application are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present 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. Also, 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Claims (10)

1. A wind power prediction method is characterized by comprising
Acquiring measurement data required by predicting wind power;
performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub;
performing time scale reduction processing on the first meteorological forecast data to obtain second meteorological forecast data, wherein the data time interval of the second meteorological forecast data is smaller than that of the first meteorological forecast data;
and processing the second meteorological forecast data by using a power prediction model to determine a wind power prediction value.
2. The wind power prediction method of claim 1, wherein the obtaining measurement data required for predicting wind power comprises:
acquiring mesoscale numerical weather forecast data, position information of a wind turbine generator, wind power site shape data and wind power site shape roughness data of a target area;
the target area is an area with a distance from the wind turbine generator smaller than a distance threshold value.
3. The wind power prediction method of claim 1, wherein the spatially downscaling the measurement data comprises:
and carrying out spatial downscaling processing on the measurement data by using a computational fluid dynamics model.
4. The wind power prediction method of claim 1, wherein before the step of processing the second weather forecast data using the power prediction model, the method further comprises:
carrying out error correction processing on the second meteorological forecast data by utilizing a random forest neural network model;
the random forest neural network model is a network model obtained by training according to historical measurement data.
5. The method for predicting wind power according to claim 1, wherein before the step of performing spatial downscaling processing on the measurement data, the method further comprises:
and carrying out data dimension reduction and denoising treatment on the measurement data.
6. The wind power prediction method of claim 1, wherein the time downscaling the first meteorological forecast data comprises:
and performing time scale reduction processing on the first meteorological forecast data by adopting a differential autoregressive moving average model.
7. The wind power prediction method of claim 1, wherein the first weather forecast data comprises:
wind speed data, wind direction data, temperature data, and barometric pressure data.
8. A wind power prediction device, comprising:
the acquisition module is used for acquiring measurement data required by predicting wind power;
the spatial downscaling module is used for performing spatial downscaling processing on the measurement data to obtain first meteorological forecast data at the height of each fan hub;
the time scale reduction module is used for performing time scale reduction processing on the first meteorological forecast data to acquire second meteorological forecast data, and the data time interval of the second meteorological forecast data is smaller than that of the first meteorological forecast data;
and the determining module is used for processing the second meteorological forecast data by using a power prediction model so as to determine a wind power prediction value.
9. A wind power prediction device comprising a memory for storing a computer program;
a processor for implementing the steps of the wind power prediction method according to any of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the wind power prediction method according to any one of claims 1 to 7.
CN202210568482.5A 2022-05-24 2022-05-24 Wind power prediction method, device and medium Pending CN114841077A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210568482.5A CN114841077A (en) 2022-05-24 2022-05-24 Wind power prediction method, device and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210568482.5A CN114841077A (en) 2022-05-24 2022-05-24 Wind power prediction method, device and medium

Publications (1)

Publication Number Publication Date
CN114841077A true CN114841077A (en) 2022-08-02

Family

ID=82572064

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210568482.5A Pending CN114841077A (en) 2022-05-24 2022-05-24 Wind power prediction method, device and medium

Country Status (1)

Country Link
CN (1) CN114841077A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117175585A (en) * 2023-11-02 2023-12-05 深圳航天科创泛在电气有限公司 Wind power prediction method, device, equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117175585A (en) * 2023-11-02 2023-12-05 深圳航天科创泛在电气有限公司 Wind power prediction method, device, equipment and storage medium
CN117175585B (en) * 2023-11-02 2024-03-08 深圳航天科创泛在电气有限公司 Wind power prediction method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
US9310517B2 (en) Method and system for determining accuracy of a weather prediction model
US20130144565A1 (en) Accuracy-based significant point derivation from dense 3d point clouds for terrain modeling
CN110705115B (en) Weather forecast method and system based on deep belief network
CN108763825B (en) Numerical simulation method for simulating wind field of complex terrain
CN109543907B (en) Complex terrain wind resource assessment method and device
CN108664705B (en) OpenFOAM-based method for simulating surface roughness of complex terrain
CN110134907B (en) Rainfall missing data filling method and system and electronic equipment
CN108269197B (en) Wind turbine generator set power characteristic evaluation method and device
Zagouras et al. Clustering the solar resource for grid management in island mode
CN115455793A (en) High-rise structure complex component stress analysis method based on multi-scale model correction
CN114841077A (en) Wind power prediction method, device and medium
CN115239105A (en) Method and device for evaluating wind resources of in-service wind power plant
CN112700349A (en) Anemometer tower site selection method and device
CN117252863A (en) Quick detection and analysis method for geographic information abnormal data
CN116796649A (en) SPEI coarse resolution data space downscaling method and device based on machine learning
CN111489063A (en) Method and system for evaluating influence of wind driven generator on surrounding environment
CN108764602B (en) Building group natural ventilation potential evaluation method and system
Khokhlov et al. Data security and quality evaluation framework: Implementation empirical study on android devices
CN115545295A (en) Method, device, equipment and medium for determining annual energy production of wind power plant
CN115081742A (en) Ultra-short-term power prediction method for distributed wind power plant and related equipment
CN112700134A (en) Method, system and equipment for wind measuring tower representativeness analysis
CN109100102B (en) Fan modal analysis method, device, terminal and computer readable storage medium based on strain continuous monitoring
CN112163331A (en) Distribution network line vulnerability calculation method and related device
CN113553754A (en) Memory, fire risk prediction model construction method, system and device
CN112950784B (en) Foundation optical astronomical station observation environment analysis method

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