CN114819385A - Wind power prediction method and device, electronic equipment and storage medium - Google Patents
Wind power prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114819385A CN114819385A CN202210530757.6A CN202210530757A CN114819385A CN 114819385 A CN114819385 A CN 114819385A CN 202210530757 A CN202210530757 A CN 202210530757A CN 114819385 A CN114819385 A CN 114819385A
- Authority
- CN
- China
- Prior art keywords
- wind power
- data
- model
- loss function
- training sample
- 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 58
- 238000012549 training Methods 0.000 claims abstract description 98
- 230000006870 function Effects 0.000 claims description 78
- 238000012545 processing Methods 0.000 claims description 26
- 238000010248 power generation Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000003062 neural network model Methods 0.000 description 13
- 238000013508 migration Methods 0.000 description 12
- 230000005012 migration Effects 0.000 description 12
- 238000005259 measurement Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000001537 neural effect Effects 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
- 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
- G06N3/045—Combinations of 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Hardware Design (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
Abstract
The invention discloses a wind power prediction method, a wind power prediction device, electronic equipment and a storage medium, wherein the method comprises the following steps: obtaining historical operating data of a target wind turbine generator in a first preset time period, and constructing a training sample data set according to the historical operating data; training a model to be trained according to a training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, wherein the pre-constructed model loss function is determined according to a maximum mean difference loss function and a mean square error loss function; target operation data of the wind turbine generator to be predicted in the time period to be predicted are obtained, and wind power of the wind turbine generator to be trained is predicted based on the wind power prediction model and the target operation data. According to the technical scheme of the embodiment of the invention, the transfer capability and the generalization capability of the wind power prediction model are improved, and the accurate prediction of the wind power of different wind turbine generators is realized.
Description
Technical Field
The invention relates to the technical field of power engineering, in particular to a wind power prediction method and device, electronic equipment and a storage medium.
Background
Wind energy, as a renewable energy source, has recently been regarded and widely used by countries around the world. The wind power generation is different from the traditional energy power generation, the environmental pollution can be reduced by utilizing the wind power generation, and the sustainable development strategy is met. However, wind energy has extremely strong volatility, intermittence, disorder and instability, and the application characteristics of the wind energy bring great challenges to grid connection. Therefore, in order to fully utilize the electric energy and reasonably plan the dispatching of the electric power system, the method has very important practical value for predicting the output power of the wind generating set.
At present, the output power of the wind generating set is mainly predicted by a physical method, a statistical method or a machine learning method. However, most wind power plants are built in remote areas with complex and severe environments, the distances among wind generating sets are long, and the working environments are different, so that the fluctuation of data acquired by the wind generating sets is large, and the prediction of the wind power is difficult.
Disclosure of Invention
The invention provides a wind power prediction method, a wind power prediction device, electronic equipment and a storage medium, and aims to solve the problem that the wind power prediction of a wind power generation unit under variable working conditions is inaccurate.
According to an aspect of the present invention, there is provided a wind power prediction method, including:
obtaining historical operating data of a target wind turbine generator in a first preset time period, and constructing a training sample data set according to the historical operating data;
training a model to be trained according to a training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, wherein the pre-constructed model loss function is determined according to a maximum mean difference loss function and a mean square error loss function;
target operation data of the wind turbine generator to be predicted in the time period to be predicted are obtained, and wind power of the wind turbine generator to be trained is predicted based on the wind power prediction model and the target operation data.
According to another aspect of the present invention, there is provided a wind power prediction apparatus, including:
the data acquisition module is used for acquiring historical operating data of the target wind turbine generator in a first preset time period and constructing a training sample data set according to the historical operating data;
the model training module is used for training a model to be trained according to a training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, wherein the pre-constructed model loss function is determined according to a maximum mean difference loss function and a mean square error loss function;
and the wind power prediction module is used for acquiring target operation data of the wind turbine generator to be predicted in a time period to be predicted and predicting the wind power of the wind turbine generator to be trained based on the wind power prediction model and the target operation data.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the wind power prediction method according to any of the embodiments of the present invention.
According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to implement the wind power prediction method according to any one of the embodiments of the present invention when executed.
The technical scheme of the embodiment of the invention comprises the steps of acquiring historical operating data of a target wind turbine generator in a first preset time period, constructing a training sample data set according to the historical operating data, then training a model to be trained according to the training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, further acquiring target operating data of the wind turbine generator to be predicted in the time period to be predicted, and predicting the wind power of the wind turbine generator to be trained on the basis of the wind power prediction model and the target operating data, thereby solving the problems that in the prior art, most wind power plants are built in remote areas with complicated and severe environments, the distances among the wind turbine generators are far, the working environments are different, so that the fluctuation of data acquired by the wind turbine generator is high, therefore, the wind power is predicted by a method of combining the maximum mean difference in measurement learning and the neural network model, so that migratable features in wind power operation data of different wind turbines can be extracted, the migration capability of the model is improved, the generalization capability of the model can be improved, the method can be applied to different wind turbines, the wind power can be accurately predicted, the electric energy quality is ensured, and the safe operation of the wind turbines is maintained.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a wind power prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic wind speed-power diagram before and after data cleaning according to an embodiment of the present invention;
FIG. 3 is a schematic wind speed-power diagram before and after data cleaning according to an embodiment of the present invention;
FIG. 4 is a flowchart of a wind power prediction method according to a second embodiment of the present invention;
fig. 5 is a wind power prediction result diagram of a wind power prediction method according to a second embodiment of the present invention;
fig. 6 is a wind power prediction result diagram of a wind power prediction method according to a second embodiment of the present invention;
fig. 7 is a schematic structural diagram of a wind power prediction device according to a third embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device implementing the wind power prediction method according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a wind power prediction method according to an embodiment of the present invention, where the present embodiment is applicable to a situation of predicting wind power of a wind turbine generator under a complex working condition, and the method may be executed by a wind power prediction device, where the wind power prediction device may be implemented in a form of hardware and/or software, and the wind power prediction device may be configured in a terminal and/or a server.
As shown in fig. 1, the method includes:
s110, historical operating data of the target wind turbine generator in a first preset time period are obtained, and a training sample data set is constructed according to the historical operating data.
In this embodiment, the target wind turbine may be a wind turbine used for model training in a process of predicting wind power. Illustratively, the first preset time period may be 1 month, 2 months, or 6 months, etc. The historical operating data may be operating data of the wind power plant over a past period of time, and the data characteristics may include, but are not limited to, wind speed, yaw angle, rotational speed, yaw versus wind error, and wind direction. The training sample data set may be a sample composed of several pieces of training data and used for model training.
Optionally, constructing a training sample data set according to the sample operation data includes: dividing historical operating data according to a time sequence to obtain sub-sample operating data sets of a plurality of time periods, taking each sub-sample operating data set as a training sample, and constructing a training sample data set according to the training sample. Illustratively, historical operating data of the target wind turbine generator are arranged according to time sequence, then, 50 groups of data are continuously taken from the 1 st group of data backward as the 1 st training sample, further, 50 groups of data are continuously taken from the 51 st group of data as the 2 nd training sample, and so on, 50 training samples are constructed altogether, and the 50 training samples are taken as a training sample data set for model training.
Specifically, when the wind power of the wind turbine generator is predicted, firstly, historical operation data of a target wind turbine generator for model training in a first preset time period is obtained, and a training sample data set is constructed according to the time sequence of the historical operation data, so that model training can be carried out by adopting the constructed training sample data set.
And S120, training the model to be trained according to the training sample data set, the label data corresponding to the training sample data set and the pre-constructed model loss function to obtain the wind power prediction model.
In this embodiment, the tag data may be wind power data corresponding to historical operating data in the training sample data set. It should be noted that, because the model to be trained needs to be trained according to the historical operating data of the wind turbine and the wind power data corresponding to the historical operating data, when the historical operating data of the target wind turbine is obtained, the wind power data corresponding to the historical operating data is obtained at the same time.
In this embodiment, the pre-constructed model loss function may be a function for evaluating the degree of difference between the predicted value and the true value of the model to be trained. The pre-constructed model loss function is determined according to the maximum mean difference loss function and the mean square error loss function.
Optionally, the specific manner of determining the pre-constructed model loss function according to the maximum mean difference loss function and the mean square error loss function is as follows:
Loss＝MSE+MMD
wherein Loss represents a model Loss function, MSE represents a mean square error Loss function, and MMD represents a maximum mean difference Loss function.
In this embodiment, the Mean Square Error (MSE) loss function is the most commonly used Error in the regression loss function. The mean square error is the sum of the squares of the differences between the predicted values and the target values. In practical applications, the calculation formula of MSE may be:
where n represents the number of training sample data sets, y i Representing the real value of the wind power corresponding to the historical operating data in the training sample data set,
and representing the predicted value of the wind power.
In this embodiment, the Maximum Mean Difference (MMD) loss function is a migration learning, especially one of the most widely used loss functions in domain adaptation, and is mainly used to measure the distance between two different but related distributions.
Optionally, the maximum mean difference loss function is determined according to first wind power operation data of the target wind power generation set in a second preset time period and second wind power operation data of the wind power generation set to be predicted in the second preset time period.
The first wind power operation data may be historical operation data of the target wind turbine in a certain past time period. The second wind power operation data can be historical operation data of the wind power generation set to be predicted in the same time period.
In practical application, the maximum mean difference loss function can be determined according to historical operating data of the target wind turbine generator and the wind turbine generator to be predicted in the same time period. The benefit of this arrangement is: the probability distribution difference between the target wind turbine generator and the wind turbine generator to be predicted can be measured by calculating the maximum mean difference measurement distance, so that the characteristic transfer capability of the model can be improved, and the trained model can be matched with the probability distribution among the operation data.
Optionally, the specific manner of determining the maximum mean difference loss function according to the first wind power operation data of the target wind power generation set in the second preset time period and the second wind power operation data of the wind power generation set to be predicted in the second preset time period is as follows:
wherein n represents the number of first wind power operation data, m represents the number of second wind power operation data, k represents a kernel function,
representing the first wind power operational data and,
representing second wind power operational data.
The model to be trained may be a neural network model that needs to be trained. Optionally, the model to be trained may be formed by at least one of a convolutional neural network, a deep neural network, or a cyclic neural network, which is not limited in this embodiment. For example, the model to be trained may be a Back Propagation Neural Network (BPNN) model, which includes an input layer, a hidden layer, and an output layer, where the activation function used by the hidden layer and the output layer is a hyperbolic tangent (tanh) activation function, the number of Neural units of the hidden layer is 40, and the number of Neural units of the output layer is 1. It should be noted that the number of the neural units in the hidden layer and the output layer may be adjusted according to actual situations, which is not limited in this embodiment.
The activation function is a function operated on a neural unit of the artificial neural network and is responsible for mapping the input of the neural unit to the output. In practical application, the activation function is introduced to increase the non-linear characteristic of the neural network model so as to make the fitting performance of the neural network model better.
Optionally, training the model to be trained according to the training sample data set, the label data corresponding to the training sample data set, and the pre-constructed model loss function to obtain the wind power prediction model, including: adjusting model parameters of a model to be trained through the following formula to obtain a wind power prediction model:
wherein eta represents the learning rate, theta represents the model parameter of the model to be trained, theta' represents the model parameter after the theta is updated by one iteration,
the derivative of the model loss function is represented,. the product is represented.
Specifically, after historical operating data of the target wind turbine generator set in a first preset time period are obtained, the historical operating data are divided according to a time sequence, a training sample data set is constructed, and further, model parameters of a model to be trained are adjusted according to the training sample data set, label data corresponding to each historical operating data in the training sample data set and a pre-constructed model loss function until a training ending condition is met, and a trained wind power prediction model is obtained.
It should be noted that the training end condition of the model to be trained is that the model loss function tends to be in a convergence state in the training process, and may also be that a difference between the training result output by the model to be trained and the label data corresponding to the training sample reaches a preset threshold, and the like, which is not limited in this embodiment.
S130, target operation data of the wind turbine generator to be predicted in the time period to be predicted are obtained, and wind power of the wind turbine generator to be trained is predicted based on the wind power prediction model and the target operation data.
In this embodiment, the wind turbine to be predicted may be a wind turbine that needs to perform wind power prediction. The time period to be predicted may be a certain time period for which the wind power generation unit is prepared to perform wind power prediction. For example, the time period to be predicted may be 1 day, 1 week, 1 month, or the like. The target operation data can be wind power operation data of the wind turbine generator to be predicted in the time period.
It should be noted that the historical operating data of the target wind turbine generator and the target operating data of the wind turbine generator to be predicted may be obtained from a wind turbine generator operating data acquisition system, may also be obtained from a local database, may also be obtained in other data obtaining manners, and the like, which is not limited in this embodiment. For example, various operation Data of the wind turbine generator can be acquired through a Supervisory Control And Data Acquisition (SCADA) system.
Specifically, after a trained wind power prediction model is obtained, the model is also required to be applied to predict the wind power of the wind turbine generator, firstly, target operation data of the wind turbine generator to be predicted within a period of time are obtained, then, the target operation data are input into the wind power prediction model, a wind power value predicted by the wind power prediction model is obtained, further, in order to evaluate the performance and the prediction effect of the model, the predicted value of the wind power can be compared with the true value of the wind power, and model evaluation is carried out according to the comparison result.
On the basis of the above technical solution, before constructing a training sample data set according to historical operating data, the method further includes: and carrying out data processing on the historical operating data according to a preset data processing mode.
The preset data processing mode can be a preset data processing mode for performing data cleaning on the wind power operation data. Optionally, the preset data processing mode may include abnormal data cleaning, stray data cleaning, and the like. In this embodiment, the abnormal data may be operation data of the historical operation data during the shutdown of the wind turbine generator due to maintenance, failure, or the like, operation data of the historical operation data below the cut-in wind speed or above the cut-out wind speed, operation data recorded with an abnormal power value in the historical operation data, or the like, for example, operation data corresponding to a power value that is a negative value or exceeds the maximum power. The outlier data may be operational data collected when an anomaly occurs with a sensor in the data collection system.
Specifically, before a training sample data set is constructed according to historical operating data, data cleaning processing needs to be performed on the acquired historical operating data according to a preset data processing mode. The advantages of such an arrangement are: in order to avoid negative influence of abnormal data or deviation data recorded in the running process of the wind turbine generator on the model analysis result, the wind power is accurately predicted.
It should be noted that when the maximum mean difference loss function is determined according to the first wind power operation data of the target wind power generation unit in the second preset time period and the second wind power operation data of the wind power generation unit to be predicted in the second preset time period, not only the first wind power operation data of the target wind power generation unit but also the second wind power operation data of the wind power generation unit to be predicted need to be subjected to data cleaning processing.
For more clearly verifying the processing result of the preset data processing mode on the operation data of the wind turbine generator, a specific example can be used to illustrate, for example, the historical operation data of the wind turbine generator 1 in 2021, 5 months and 1 day to 31 days is used as the first wind turbine operation data, the historical operation data of the wind turbine generator 10 in 2021, 5 months and 1 day to 31 days is used as the second wind turbine operation data, the time interval of data sampling is 1 minute, the data feature dimensions in each operation data are 5, which are the wind speed, the yaw angle, the rotating speed, the yaw wind alignment error and the wind direction, the cut-in wind speeds of the two wind turbine generators are 2.5 m/s, and the cut-out wind speeds are 20 m/s. Fig. 2 is a schematic diagram of wind speed-power of the operation data of the wind turbine No. 1 before data processing (left side of the figure) and after data processing (right side of the figure), and fig. 3 is a schematic diagram of wind speed-power of the operation data of the wind turbine No. 10 before data processing (left side of the figure) and after data processing (right side of the figure).
The technical scheme of the embodiment of the invention obtains the historical operating data of the target wind turbine generator in a first preset time period, constructs a training sample data set according to the historical operating data, then trains the model to be trained according to the training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, further obtains the target operating data of the wind turbine generator to be predicted in the time period to be predicted, and predicts the wind power of the wind turbine generator to be trained on the basis of the wind power prediction model and the target operating data, thereby solving the problems that in the prior art, as most wind power plants are built in remote areas with complicated and severe environments, the distances among the wind turbine generators are far, the working environments are different, so that the data fluctuation of the wind turbine generator is very high, therefore, the wind power is predicted by a method of combining the maximum mean difference in measurement learning and the neural network model, so that migratable features in wind power operation data of different wind turbines can be extracted, the migration capability of the model is improved, the generalization capability of the model can be improved, the method can be applied to different wind turbines, the wind power can be accurately predicted, the electric energy quality is ensured, and the safe operation of the wind turbines is maintained.
Example two
Fig. 4 is a flowchart of a wind power prediction method according to an embodiment of the present invention. Taking the wind power prediction model as a BP neural network model as an example, as shown in fig. 4, the method may specifically include the following steps:
1. acquiring historical operating data of two wind turbine generators in the same time period;
2. performing data cleaning on the acquired historical operating data;
3. calculating the MMD distance according to historical operation data of the two wind turbine generators, adding the calculated MMD distance into a loss function of a BP neural network model to be trained, and building a measurement BP neural network model;
4. taking historical operation data of one wind turbine generator as model training data, acquiring historical operation data of another wind turbine generator in another time period, and taking the historical operation data as model test data;
5. training the built measurement BP neural network model according to model training data to obtain a trained measurement BP neural network model;
6. and inputting the model test data into the trained measurement BP neural network model to predict the wind power, so as to obtain a wind power prediction result.
In order to verify the technical effect of the embodiment of the invention, the description can be given through a specific example, for example, historical operation data of two wind turbine generators is obtained, wherein one wind turbine generator is the wind turbine generator No. 1, the other wind turbine generator is the wind turbine generator No. 10, two migration tasks are constructed according to the two wind turbine generators, one migration task takes the historical operation data of the wind turbine generator No. 1 as training data, model training is carried out, and the wind power of the wind turbine generator No. 10 is predicted according to a trained model; and the other migration task is to take the historical operating data of the No. 10 wind turbine generator as training data to perform model training and predict the wind power of the No. 1 wind turbine generator. Fig. 5 is a wind power prediction result diagram of the migration of the wind turbine No. 1 to the wind turbine No. 10, and fig. 6 is a wind power prediction result diagram of the migration of the wind turbine No. 10 to the wind turbine No. 1. As can be seen from fig. 5 and 6, in the two migration tasks, the predicted power value and the actual power value of the model are relatively close, and the power predicted values and the power actual values at the multiple data points are very small in difference and almost coincide, which indicates that the migration effect of the model is relatively good, and the wind power prediction with higher accuracy can be realized.
The technical scheme of the embodiment of the invention obtains the historical operating data of the target wind turbine generator in a first preset time period, constructs a training sample data set according to the historical operating data, then trains the model to be trained according to the training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, further obtains the target operating data of the wind turbine generator to be predicted in the time period to be predicted, and predicts the wind power of the wind turbine generator to be trained on the basis of the wind power prediction model and the target operating data, thereby solving the problems that in the prior art, as most wind power plants are built in remote areas with complicated and severe environments, the distances among the wind turbine generators are far, the working environments are different, so that the data fluctuation of the wind turbine generator is very high, therefore, the wind power is predicted by a method of combining the maximum mean difference in measurement learning and the neural network model, so that migratable features in wind power operation data of different wind turbines can be extracted, the migration capability of the model is improved, the generalization capability of the model can be improved, the method can be applied to different wind turbines, the wind power can be accurately predicted, the electric energy quality is ensured, and the safe operation of the wind turbines is maintained.
EXAMPLE III
Fig. 7 is a schematic structural diagram of a wind power prediction apparatus provided in the third embodiment of the present invention. As shown in fig. 7, the apparatus includes: a data acquisition module 210, a model training module 220, and a wind power prediction module 230.
The data acquisition module 210 is configured to acquire historical operating data of the target wind turbine generator in a first preset time period, and construct a training sample data set according to the historical operating data;
the model training module 220 is configured to train the model to be trained according to the training sample data set, the label data corresponding to the training sample data set, and a pre-constructed model loss function to obtain a wind power prediction model, where the pre-constructed model loss function is determined according to a maximum mean difference loss function and a mean square error loss function;
the wind power prediction module 230 is configured to obtain target operation data of the wind turbine to be predicted in a time period to be predicted, and predict wind power of the wind turbine to be trained based on the wind power prediction model and the target operation data.
The technical scheme of the embodiment of the invention obtains the historical operating data of the target wind turbine generator in a first preset time period, constructs a training sample data set according to the historical operating data, then trains the model to be trained according to the training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, further obtains the target operating data of the wind turbine generator to be predicted in the time period to be predicted, and predicts the wind power of the wind turbine generator to be trained on the basis of the wind power prediction model and the target operating data, thereby solving the problems that in the prior art, as most wind power plants are built in remote areas with complicated and severe environments, the distances among the wind turbine generators are far, the working environments are different, so that the data fluctuation of the wind turbine generator is very high, therefore, the wind power is predicted by a method of combining the maximum mean difference in measurement learning and the neural network model, so that migratable features in wind power operation data of different wind turbines can be extracted, the migration capability of the model is improved, the generalization capability of the model can be improved, the method can be applied to different wind turbines, the wind power can be accurately predicted, the electric energy quality is ensured, and the safe operation of the wind turbines is maintained.
Optionally, the data obtaining module 210 is further configured to divide the historical operating data according to a time sequence to obtain sub-sample operating data sets of multiple time periods, use each sub-sample operating data set as a training sample, and construct the training sample data set according to the training sample.
Optionally, the specific manner of determining the pre-constructed model loss function according to the maximum mean difference loss function and the mean square error loss function is as follows:
Loss＝MSE+MMD
wherein, Loss represents a model Loss function, MSE represents a mean square error Loss function, and MMD represents a maximum mean difference Loss function.
Optionally, the maximum mean difference loss function is determined according to first wind power operation data of the target wind power generation set in a second preset time period and second wind power operation data of the wind power generation set to be predicted in the second preset time period.
Optionally, a specific manner of determining the maximum mean difference loss function according to the first wind power operation data of the target wind power generation set in the second preset time period and the second wind power operation data of the wind power generation set to be predicted in the second preset time period is as follows:
wherein n represents the number of first wind power operation data, m represents the number of second wind power operation data, k represents a kernel function,
representing the first wind power operational data and,
representing second wind power operational data.
Optionally, the model training module 220 is further configured to adjust model parameters of the model to be trained through the following formula to obtain a wind power prediction model:
wherein eta represents the learning rate, theta represents the model parameter of the model to be trained, theta' represents the model parameter after the theta is updated by one iteration,
the derivative of the model loss function is represented,. the product is represented.
Optionally, before constructing the training sample data set according to the historical operating data, the apparatus further includes: and the data processing module is used for carrying out data processing on the historical operating data according to a preset data processing mode, wherein the preset data processing mode comprises abnormal data cleaning and outlier data cleaning.
The wind power prediction device provided by the embodiment of the invention can execute the wind power prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
FIG. 8 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as a wind power prediction method.
In some embodiments, the wind power prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the wind power prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the wind power prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A wind power prediction method is characterized by comprising the following steps:
obtaining historical operating data of a target wind turbine generator in a first preset time period, and constructing a training sample data set according to the historical operating data;
training a model to be trained according to the training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, wherein the pre-constructed model loss function is determined according to a maximum mean difference loss function and a mean square error loss function;
and acquiring target operation data of the wind turbine generator to be predicted in a time period to be predicted, and predicting the wind power of the wind turbine generator to be trained on the basis of the wind power prediction model and the target operation data.
2. The method of claim 1, wherein constructing a training sample data set from the sample run data comprises:
and dividing the historical operating data according to a time sequence to obtain sub-sample operating data sets of a plurality of time periods, taking each sub-sample operating data set as a training sample, and constructing the training sample data set according to the training sample.
3. The method of claim 1, wherein the pre-constructed model loss function is determined from the maximum mean difference loss function and the mean square error loss function in the following manner:
Loss＝MSE+MMD
wherein Loss represents a model Loss function, MSE represents a mean square error Loss function, and MMD represents a maximum mean difference Loss function.
4. The method of claim 3, wherein the maximum mean difference loss function is determined according to first wind power operation data of the target wind power generation set in a second preset time period and second wind power operation data of the wind power generation set to be predicted in the second preset time period.
5. The method according to claim 4, wherein the maximum mean difference loss function is determined according to the first wind power operation data of the target wind power generation set in the second preset time period and the second wind power operation data of the wind power generation set to be predicted in the second preset time period in the following specific manner:
wherein n represents the number of the first wind power operation data, m represents the number of the second wind power operation data, k represents a kernel function,
representing the first wind power operational data and,
representing second wind power operational data.
6. The method according to claim 1, wherein the training a model to be trained according to the training sample data set, the label data corresponding to the training sample data set, and a pre-constructed model loss function to obtain a wind power prediction model comprises:
adjusting model parameters of the model to be trained through the following formula to obtain a wind power prediction model:
wherein eta represents the learning rate, theta represents the model parameter of the model to be trained, theta' represents the model parameter after the theta is updated by one iteration,
the derivative of the model loss function is represented,. the product is represented.
7. The method of claim 1, further comprising, prior to constructing a set of training sample data from the historical operating data:
and performing data processing on the historical operating data according to a preset data processing mode, wherein the preset data processing mode comprises abnormal data cleaning and outlier data cleaning.
8. A wind power prediction device, comprising:
the data acquisition module is used for acquiring historical operating data of the target wind turbine generator in a first preset time period and constructing a training sample data set according to the historical operating data;
the model training module is used for training a model to be trained according to the training sample data set, label data corresponding to the training sample data set and a pre-constructed model loss function to obtain a wind power prediction model, wherein the pre-constructed model loss function is determined according to a maximum mean difference loss function and a mean square error loss function;
the wind power prediction module is used for obtaining target operation data of the wind turbine generator to be predicted in a time period to be predicted and predicting the wind power of the wind turbine generator to be trained on the basis of the wind power prediction model and the target operation data.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the wind power prediction method as recited in any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the wind power prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210530757.6A CN114819385A (en) | 2022-05-16 | 2022-05-16 | Wind power prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210530757.6A CN114819385A (en) | 2022-05-16 | 2022-05-16 | Wind power prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114819385A true CN114819385A (en) | 2022-07-29 |
Family
ID=82515602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210530757.6A Pending CN114819385A (en) | 2022-05-16 | 2022-05-16 | Wind power prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114819385A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050030A (en) * | 2023-04-03 | 2023-05-02 | 亿昇(天津)科技有限公司 | Method, device and equipment for determining axial center position of blower rotor |
| CN116581756A (en) * | 2023-07-13 | 2023-08-11 | 华北电力大学 | Wind power prediction method, model training method, device, equipment and medium |
-
2022
- 2022-05-16 CN CN202210530757.6A patent/CN114819385A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050030A (en) * | 2023-04-03 | 2023-05-02 | 亿昇(天津)科技有限公司 | Method, device and equipment for determining axial center position of blower rotor |
| CN116050030B (en) * | 2023-04-03 | 2023-07-28 | 亿昇(天津)科技有限公司 | Method, device and equipment for determining axial center position of blower rotor |
| CN116581756A (en) * | 2023-07-13 | 2023-08-11 | 华北电力大学 | Wind power prediction method, model training method, device, equipment and medium |
| CN116581756B (en) * | 2023-07-13 | 2023-12-12 | 华北电力大学 | Wind power prediction method, model training method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105631483B (en) | A kind of short-term electro-load forecast method and device | |
| CN114819385A (en) | Wind power prediction method and device, electronic equipment and storage medium | |
| CN110705772B (en) | Regional power grid wind power generation power prediction optimization method and device | |
| CN110705771B (en) | Method and device for predicting and optimizing generation power of new energy of regional power grid | |
| CN104573876A (en) | Wind power plant short-period wind speed prediction method based on time sequence long memory model | |
| CN104252649A (en) | Regional wind power output prediction method based on correlation between multiple wind power plants | |
| CN109787295B (en) | Wind power ultra-short term prediction calculation method considering wind power plant state | |
| Xiyun et al. | Wind power probability interval prediction based on bootstrap quantile regression method | |
| CN103984986B (en) | The self study arma modeling ultrashort-term wind power prediction method of real time correction | |
| CN115660232A (en) | Ultra-short-term prediction method, device and system for wind power | |
| CN110705768A (en) | Wind power generation power prediction optimization method and device for wind power plant | |
| Aguilar et al. | Predicting probabilistic wind power generation using nonparametric techniques | |
| CN117473384A (en) | Power grid line safety constraint identification method, device, equipment and storage medium | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| CN102539823A (en) | Method for forecasting wind speed distribution of WTG (wind turbine generator) | |
| CN115597872B (en) | Load shedding test method, device, equipment and medium for pumped storage unit | |
| CN116484554A (en) | Topology identification method, device, equipment and medium for power distribution network | |
| CN116032020A (en) | Intelligent monitoring method and system for new energy power station | |
| CN115577854A (en) | Quantile regression wind speed interval prediction method based on EEMD-RBF combination | |
| CN115952921A (en) | Photovoltaic energy power prediction method and device, electronic equipment and storage medium | |
| CN115788797A (en) | Health state detection method and model training method and device for wind driven generator | |
| CN110705769B (en) | New energy power generation power prediction optimization method and device | |
| Bramm et al. | Effect of data preprocessing on the forecasting accuracy of solar power plant | |
| CN113779892A (en) | Wind speed and wind direction prediction method | |
| CN114757444A (en) | Wind power prediction method and device, electronic equipment and storage medium |
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 |