CN117893362A - Multi-time-space-scale offshore wind power characteristic screening and enhanced power prediction method - Google Patents
Multi-time-space-scale offshore wind power characteristic screening and enhanced power prediction method Download PDFInfo
- Publication number
- CN117893362A CN117893362A CN202410303869.7A CN202410303869A CN117893362A CN 117893362 A CN117893362 A CN 117893362A CN 202410303869 A CN202410303869 A CN 202410303869A CN 117893362 A CN117893362 A CN 117893362A
- Authority
- CN
- China
- Prior art keywords
- feature
- offshore wind
- matrix
- time
- attention
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012216 screening Methods 0.000 title claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 132
- 230000007246 mechanism Effects 0.000 claims abstract description 35
- 230000004927 fusion Effects 0.000 claims abstract description 18
- 230000008878 coupling Effects 0.000 claims abstract description 13
- 238000010168 coupling process Methods 0.000 claims abstract description 13
- 238000005859 coupling reaction Methods 0.000 claims abstract description 13
- 238000001228 spectrum Methods 0.000 claims abstract description 9
- 238000011176 pooling Methods 0.000 claims description 51
- 230000004913 activation Effects 0.000 claims description 42
- 230000002457 bidirectional effect Effects 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 17
- 230000009467 reduction Effects 0.000 claims description 13
- 238000001556 precipitation Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 11
- 230000035945 sensitivity Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 210000004205 output neuron Anatomy 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000002347 injection Methods 0.000 claims description 4
- 239000007924 injection Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 125000004122 cyclic group Chemical group 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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"
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-time space-scale offshore wind power characteristic screening and enhanced power prediction method, which comprises the steps of firstly acquiring a multi-source data set of a target offshore wind power plant, screening a motif spectrum cluster expansion optimal sensitive factor according to acquired ocean current data, and reducing the dimension of the data; the characteristics of the offshore wind power are enhanced by taking the internal and external relations of the characteristics into consideration through a multidimensional attention mechanism, a multi-attention depth fusion mechanism is developed from different dimensions, deep coupling relations on time, space and characteristics are mined, and corresponding weights are given to different characteristics in a self-adaptive mode. According to different influence degrees of geographic positions on the output of the offshore wind turbine, the implicit correlation of different areas is excavated, different weights are self-adaptively given by using the graph annotation force, a new feature matrix is finally obtained, a prediction model is transmitted, prediction is carried out from a plurality of time scales, and the power time sequence of the corresponding offshore wind turbine at different time scales is obtained. The method effectively improves the precision of offshore wind power prediction.
Description
Technical Field
The invention relates to the technical field of multi-time-space scale prediction of offshore wind power, in particular to a multi-time-space scale offshore wind power feature screening and enhanced power prediction method.
Background
Large-scale development, deep sea floating type high-power offshore equipment and intelligent operation and maintenance are injecting strong power for offshore wind power development. Wind energy has randomness, so that instability of offshore wind power is directly caused. Therefore, accurate prediction of offshore wind power must be performed in advance, so that a basis can be provided for reliable operation and electricity reserve planning of the power grid. The accurate offshore wind power prediction has important significance on the power system.
The offshore wind power is used as a time sequence with strong randomness and volatility, and the prediction accuracy has a great relationship with the quality, time and space scale of meteorological characteristic data. Because of the greater complexity of the influencing factors and meteorological features of offshore wind power, and the inclusion of a large number of complex data features, efficient feature screening and enhancement is necessary. To date, the existing offshore wind power correlation prediction power method cannot fully consider a processing method under a large number of data characteristics, so that the prediction accuracy of offshore wind power is low.
Aiming at the characteristic screening and enhancement of a large number of complex data characteristics of the offshore wind farm, an ultra-short-term power prediction model considering the space-time characteristics of offshore wind power multi-unit is provided in the prior art, firstly, a dynamic time bending distance algorithm is adopted, an abstract and de-abstract idea is added to improve a DTW algorithm, and meanwhile, unit clustering is carried out by taking bus and geographic information into consideration to form a unit group so as to quantify and measure the time sequence similarity among units; then, using a transducer model based on an attention mechanism and carrying out probabilistic improvement on an attention module to reduce power prediction time; finally, the sequence of the space-time characteristics and the position information is comprehensively considered for prediction analysis. However, because the influence factors and the meteorological features of the offshore wind power are more complicated, the offshore wind power plant power prediction accuracy can be improved by carrying out regional division in consideration of multiple time-space scales and carrying out effective feature screening and enhancement by fusing multiple attentions from different dimensions.
Disclosure of Invention
The invention provides a multi-time space-scale offshore wind power feature screening and enhancing power prediction method and system for overcoming the defects in the prior art, so that feature screening and enhancing under different space scales are realized, prediction is performed under different time scales, and the prediction precision of offshore wind power is improved.
In order to solve the technical problems, the invention adopts the following technical scheme:
A multi-time space-scale offshore wind power feature screening and enhanced power prediction method comprises the following steps:
S1, acquiring a multi-source data set of a target and an adjacent offshore wind farm, wherein the multi-source data set comprises power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage and ocean current data of the target offshore wind farm, and performing primary processing;
S2, dividing the preprocessed historical meteorological record data of the offshore wind farm to obtain a training sample and a testing sample;
S3, carrying out motif spectrum clustering according to the acquired ocean current data, utilizing Laplace feature mapping to develop optimal sensitivity factor screening, carrying out dimension reduction on the data, and dividing the feature data into three areas of offshore, shallow and deep sea; the processed power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage quantity and ocean current data of the offshore wind farm form a feature matrix ,/>,/>;
S4, constructing a multidimensional attention fusion mechanism and a prediction model of a bidirectional gating circulation unit network;
S5, inputting a feature matrix ,/>,/> into a prediction model, taking the internal and external relations of the features into consideration through a multidimensional attention mechanism in the prediction model, developing the offshore wind power feature enhancement of a multi-attention depth fusion mechanism from different dimensions, excavating deep coupling relations on time, space and features, and giving corresponding weights to different features in a self-adaptive manner;
S6, further excavating implicit correlations of different areas according to different degrees of influence of geographical positions on the offshore wind turbine output on three feature matrixes of offshore, shallow sea and deep sea, giving different weights by using self-adaption of the schematic injection force, and finally obtaining a new feature matrix ;
S7, transmitting the feature matrix with the given weight and the enhanced features to a bidirectional gating circulation unit network, and mining hidden relations in the feature matrix by the bidirectional gating circulation unit network;
And S8, predicting the power of the target offshore wind power plant from a plurality of time scales by using the trained prediction model, and obtaining a power time sequence of the corresponding offshore wind power plant under different time scales so as to realize offshore wind power prediction under a plurality of time scales.
According to the technical means, the invention provides a marine wind power prediction method based on motif spectral clustering and a multidimensional attention mechanism, which comprises the steps of firstly acquiring a multisource data set of a target marine wind power plant, carrying out motif spectral clustering expansion optimal sensitivity factor screening according to the acquired ocean current data after preliminary processing, carrying out dimension reduction on the data, and dividing characteristic data into three areas of offshore, shallow and deep sea; the characteristics of the offshore wind power are enhanced by taking the internal and external relations of the characteristics into consideration through a multidimensional attention mechanism, a multi-attention depth fusion mechanism is developed from different dimensions, deep coupling relations on time, space and characteristics are mined, and corresponding weights are given to different characteristics in a self-adaptive mode. And further excavating implicit correlations of different areas according to different degrees of influence of geographical positions on offshore wind turbine output of offshore, shallow and deep sea three feature matrixes, endowing different weights with self-adaption by using the graph annotation force, finally obtaining a new feature matrix, transmitting the new feature matrix to a bidirectional gating circulation unit network, predicting from a plurality of time scales by using a trained prediction model, and obtaining power time sequences of corresponding offshore wind power fields under different time scales to realize offshore wind power prediction under multiple time-space scales. The method can effectively improve the precision of offshore wind power prediction.
Further, in step S1, the specific process of performing the preliminary processing on the data is as follows: and correcting background field systems such as a global forecast system (Global Forecasting System, GFS), a weather forecast mode system (WEATHER RESEARCH Forecast, WRF) and the like according to actual measurement meteorological data near the offshore wind farm area to obtain the grid NWP data with the horizontal resolution of 3km multiplied by 3 km. Filling up the missing data in the historical meteorological record data of the offshore wind farm to obtain complete historical meteorological record data of the wind farm; and carrying out min-max normalization processing on the power sequence, the wind speed sequence, the temperature sequence, the air pressure sequence, the cloud amount sequence and the ocean current sequence to obtain a processed power sequence P, a processed wind speed sequence WS, a processed temperature sequence T, a processed humidity sequence H, a processed precipitation amount sequence PRECIP, a processed air pressure sequence PA, a processed cloud amount sequence CU and a processed ocean current sequence OC, wherein the wind direction sequence adopts sine and cosine processing to obtain a wind direction sine WDS and a wind direction cosine WDC.
Further, in step S2, the preprocessed historical meteorological record data of the offshore wind farm is divided according to 8:2 and obtaining training samples and test samples.
Further, in step S3, motif spectral clustering is used for the processed sample features, and the best sensitivity factor screening is performed by using laplace feature mapping, so that the data is subjected to dimension reduction, which specifically comprises the following steps:
S31, constructing a similarity matrix , and calculating the similarity between samples according to the distance between the data samples;
S32, constructing an adjacent matrix , and constructing by using a Gaussian distance method:
wherein 、/> is the i-th and j-th points (i, j=1,., n) in the n samples, s is the standard deviation, and e is an exponential function;
S33, calculating an order moment D and a Laplacian matrix L:
Wherein is an order moment matrix of i rows and j columns, and/() is a Laplacian matrix of i rows and j columns;
S34, carrying out feature decomposition on the Laplace matrix to obtain feature vectors and feature values; selecting the first k eigenvectors as new data representations according to the magnitude of the eigenvalues; generating a feature matrix under a low dimension;
S35, carrying out K-Means clustering in the new feature space after dimension reduction, and dividing the new feature space into offshore, shallow and deep sea types to obtain a feature matrix ,/>,/>;
＝［M1,M2,...,Mn］,/> Wherein M n represents a matrix of features at times t-1 to t-M of the nth wind farm.
Further, in step S4, the specific steps for constructing the multidimensional attention fusion mechanism are as follows:
The time attention module and the feature attention module are connected in series, input into a matrix of H multiplied by W multiplied by C, the feature diagram obtained after the processing of the two attention sub-modules is subjected to element addition operation, so that the two features are fused together, and output results are processed through a ReLU activation function and used as the input of the channel attention module and the space attention module, and the two modules are connected together by adopting a serial structure; in both attention modules, different feature information is acquired from different perspectives using both the average pooling and the maximum pooling operations.
Further, the time attention module comprises a convolution layer, an FC layer, a softmax layer, a sigmoid activation function and a global average pooling layer; in the time attention module, global spatial average pooling GAP is applied to the feature matrix to ensure that the time attention module has low computational cost; then generating a position-sensitive importance map using a plurality of 1D convolutions with non-linearities over the entire time domain to enhance the frame-by-frame feature; generating a channel self-adaptive kernel based on global time information in each channel through the FC layer, and obtaining a time attention module weight coefficient Mt through the softmax layer; finally, multiplying the characteristic matrix by a weight coefficient to obtain a new zoomed characteristic matrix;
In the formula, GAP is global space average pooling, conv1D is one-dimensional convolution, X is an input sample, is a sigmoid activation function, FC is a full-connection layer, mt is a time attention module weight coefficient, and/() is a new feature matrix; delta represents the attention weight,/> is the vector product.
Further, the feature attention module comprises a convolution layer, relu activation functions, sigmoid activation functions and a pooling layer; in the feature attention module, features are input first, pass through a pooling layer, then pass through two convolution layers, an activation function is Relu, and then the obtained features are fed back to self-adaptive weight coefficients of the features in different environments through a Sigmoid activation function to obtain weight coefficients ; finally, multiplying the original characteristic matrix/> by a weight coefficient to obtain a new zoomed characteristic matrix;
Where Conv is convolution, is Relu activation function, and/> is the new feature matrix.
Further, the spatial attention module comprises a convolution layer, a maximum pooling layer, an average pooling layer and a sigmoid activation function; in the space attention module, firstly, carrying out average pooling and maximum pooling of one channel dimension respectively to obtain two H multiplied by W multiplied by 1 channels, and splicing the channels together; then, through a C×C convolution layer, the activation function is Sigmoid, and the weight coefficient Ms is obtained; finally, multiplying the characteristic matrix by a weight coefficient to obtain a new zoomed characteristic matrix;
Where is mean pooling,/> is maximum pooling and/> is the new feature matrix.
Further, the channel attention module comprises a convolution layer, a maximum pooling layer, an average pooling layer and a sigmoid activation function; in the channel attention module, firstly, carrying out global average pooling and maximum pooling on space to obtain two channels of 1 multiplied by C, respectively sending the channels into a two-layer shared neural network, wherein the number of neurons in the first layer is C/r, the activation function is Relu, and the number of neurons in the second layer is C; adding the obtained two features, and then obtaining a weight coefficient Mc through a Sigmoid activation function; finally, multiplying the original feature matrix by the weight coefficient to obtain a new zoomed feature matrix;
wherein, MLP is a multi-layer perceptron and is a new feature matrix.
Further, in step S5, the feature matrix ,/>,/> is input into the prediction model, the internal and external relationships of the features are considered through the multidimensional attention mechanism in the prediction model, the offshore wind power feature enhancement of the multi-attention depth fusion mechanism is developed from different dimensions, the deep coupling relationship on time, space and features is mined, and the corresponding weights are given to the different features in a self-adaptive manner; feature enhancement is developed deeply based on time attention/> , feature attention/> , spatial attention/> , channel attention ;
Wherein is a weight matrix calculated by attention, wherein/() is a neural network corresponding to the attention, and/() is a characteristic value corresponding to the calculated dimension;
Multiplying the obtained weights with the characteristics of the corresponding offshore wind farm respectively to obtain a weighted characteristic matrix ,/>,/>;
。
further, the step S6 specifically includes:
S61, defining a weight matrix W, and converting the feature matrix into adjacent nodes: ,/> For the j-th input sample (h=h1, … hn);
S62, splicing and mapping adjacent nodes i and j into scalar quantities, wherein is an attention calculating function: in the formula,/> , wherein/> is the original attention contribution degree obtained by calculating a certain node and is used for carrying out the normalization of the next step;
s63, passing the adjacent node matrix through leakyRelu layers and then through a softmax layer, calculating the contribution degree of each adjacent node j of the node i to the i and normalizing the contribution degree of each adjacent node j;
S64, after the contribution degree of each adjacent node of the i node is calculated, carrying out feature summation update on all the adjacent nodes of the i node according to the weight; as the final output of the i-node, is obtained;
The number of the output neurons is 3, the weights of the offshore, shallow and deep sea areas are respectively corresponding to the output neurons, and finally a new feature matrix is obtained;
Wherein ;
。
Further, in step S7, the bi-directional gating cycle cell network is constructed as follows: taking a feature matrix as input, constructing a multi-layer cascade bidirectional gating circulation unit network, wherein the multi-layer cascade bidirectional gating circulation unit network consists of a forward GRU and a backward GRU, and the activation function is tanh;
Wherein 、/>、/>、/>、/>、/> is a weight parameter matrix,/> 、/>、/> is a bias parameter matrix,/> is a matrix multiplication,/> is a Sigmoid function,/> is a reset gate,/> is an update gate,/> is a candidate state of an hidden layer at the current moment,/> is a current hidden state,/> is a hidden state at the previous moment,/> is an input state at the current moment,/> is a reverse transfer calculation/> and/> are hidden states of a forward GRU and a backward GRU, and F is an output merging method of two directions.
Further, in step S8, the time scale is n, where n is an integer, and n is 2.
Setting the time scale of the current prediction system as i, and inputting the running data of the previous moment with ,/> as the time scale i; the output of the prediction system is/> ,/> which is the prediction data of the current time scale; predicting power of a target offshore wind farm from a plurality of time scales by using a trained prediction model, obtaining power time sequences of the corresponding offshore wind farms under different time scales, respectively completing ultra-short-term prediction and short-term prediction of the offshore wind farm, and realizing offshore wind power prediction under the plurality of time scales;
Where is the predicted output load result on the i-th scale and/() is the input matrix for the i-n-1 to i-1 time scale.
The invention also provides a multi-time space-scale offshore wind power characteristic screening and enhanced power prediction system, which comprises the following components:
the data acquisition unit is used for acquiring multisource data sets of a target and an adjacent offshore wind farm, and comprises power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud accumulation and ocean current data of the target offshore wind farm;
The preprocessing unit is used for preprocessing the characteristic sequences obtained by the data acquisition unit to obtain characteristic vectors, taking the offshore wind power time sequences as prediction target samples, and dividing the characteristic vectors and the offshore wind power time sequences into training sets and verification sets respectively;
The multi-space scale feature screening unit is used for carrying out motif spectrum clustering according to the ocean current data acquired by the data acquisition unit, utilizing Laplace feature mapping to develop optimal sensitivity factor screening, carrying out dimension reduction on the data, and dividing the feature data into three areas of offshore, shallow and deep sea to respectively form three feature matrixes;
The feature enhancement unit is used for carrying out offshore wind power feature enhancement of a multi-attention depth fusion mechanism from different dimensions by taking the internal and external relations of the features into consideration through a multi-dimensional attention mechanism in the prediction model, excavating deep coupling relations on time, space and features, and self-adaptively giving corresponding weights to the different features; based on time attention, feature attention, space attention, channel attention and depth development feature enhancement, multiplying attention weight by input feature map to obtain weighted feature matrix, and sending the feature matrix to a multi-time scale prediction unit;
The multi-time scale prediction unit is used for inputting the feature matrix given with the weight into the bidirectional gating circulation unit network, predicting the power of the target offshore wind power plant from a plurality of time scales by using the trained prediction model, obtaining the power time sequences of the corresponding offshore wind power plant at different time scales, and completing the offshore wind power prediction at the multi-time-space scale.
Compared with the prior art, the beneficial effects are that: the multi-time-space-scale offshore wind power feature screening and enhanced power prediction method is realized based on a motif spectrum cluster and a multidimensional attention mechanism, wherein the motif spectrum cluster is used for screening the optimal sensitivity factor, reducing the dimension of data and effectively enhancing the deep coupling time-space feature from the space scale; the multi-dimensional attention mechanism considers the internal and external relations of the features, the deep coupling relation on the time, space and features is excavated by developing the offshore wind power feature enhancement of the multi-attention depth fusion mechanism from different dimensions, the influence degree of the drawing attention force on offshore, shallow and deep sea three feature matrixes on the output of the offshore wind turbine is different according to the geographic position, the implicit correlation of different areas is further excavated, and the method has a certain help for improving the prediction precision of the offshore wind power; prediction is carried out from a plurality of time scales, so that offshore wind power prediction under a plurality of time scales is realized, and the future long-term trend can be captured and the reliability is improved. The method has a certain practical significance for offshore wind power prediction. The method can effectively improve the precision of offshore wind power prediction.
Drawings
FIG. 1 is a flow diagram of a multi-time-space scale offshore wind feature screening and enhanced power prediction method of the present invention.
FIG. 2 is a schematic diagram of a predictive model.
FIG. 3 is a graph of weights given to different areas of a wind farm by multiple attentiveness mechanisms.
FIG. 4 is a diagram of the multi-time-space scale offshore wind power feature screening and enhanced power prediction effect of the invention.
FIG. 5 is a schematic flow diagram of a multi-time-space scale offshore wind feature screening and enhanced power prediction system.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. The invention is described in one of its examples in connection with the following detailed description. Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to be limiting of the present patent; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
In the description of the present invention, it should be understood that, if there is an azimuth or positional relationship indicated by terms such as "upper", "lower", "left", "right", etc., based on the azimuth or positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but it is not indicated or implied that the apparatus or element referred to must have a specific azimuth, be constructed and operated in a specific azimuth, and thus terms describing the positional relationship in the drawings are merely illustrative and should not be construed as limitations of the present patent, and specific meanings of the terms described above may be understood by those skilled in the art according to specific circumstances. In addition, if there is a description of "first", "second", etc. in the embodiments of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and/or" as it appears throughout is meant to include three side-by-side schemes, for example, "A and/or B", including the A scheme, or the B scheme, or the scheme where A and B meet at the same time.
Example 1:
As shown in fig. 1, the multi-time space-scale offshore wind power feature screening and enhanced power prediction method comprises the following steps:
S1, acquiring a multi-source data set of a target and an adjacent offshore wind farm, wherein the multi-source data set comprises power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage and ocean current data of the target offshore wind farm, and performing primary processing;
S2, dividing the preprocessed historical meteorological record data of the offshore wind farm to obtain a training sample and a testing sample;
s3, carrying out motif spectrum clustering according to the acquired ocean current data, utilizing Laplace feature mapping to develop optimal sensitivity factor screening, carrying out dimension reduction on the data, and dividing the feature data into three areas of offshore, shallow and deep sea; the processed power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage quantity and ocean current data of the offshore wind farm form a feature matrix ,/>,/>;
S4, constructing a multidimensional attention fusion mechanism and a prediction model of a bidirectional gating circulation unit network;
S5, inputting a feature matrix ,/>,/> into a prediction model, taking the internal and external relations of the features into consideration through a multidimensional attention mechanism in the prediction model, developing the offshore wind power feature enhancement of a multi-attention depth fusion mechanism from different dimensions, excavating deep coupling relations on time, space and features, and giving corresponding weights to different features in a self-adaptive manner;
S6, further excavating implicit correlations of different areas according to different degrees of influence of geographical positions on the offshore wind turbine output on three feature matrixes of offshore, shallow sea and deep sea, giving different weights by using self-adaption of the schematic injection force, and finally obtaining a new feature matrix ;
s7, transmitting the feature matrix with the given weight and the enhanced features to a bidirectional gating circulation unit network, and mining hidden relations in the feature matrix by the bidirectional gating circulation unit network;
And S8, predicting the power of the target offshore wind power plant from a plurality of time scales by using the trained prediction model, and obtaining a power time sequence of the corresponding offshore wind power plant under different time scales so as to realize offshore wind power prediction under a plurality of time scales.
According to the technical means, the invention provides a marine wind power prediction method based on motif spectral clustering and a multidimensional attention mechanism, which comprises the steps of firstly acquiring a multisource data set of a target marine wind power plant, carrying out motif spectral clustering expansion optimal sensitivity factor screening according to the acquired ocean current data after preliminary processing, carrying out dimension reduction on the data, and dividing characteristic data into three areas of offshore, shallow and deep sea; the characteristics of the offshore wind power are enhanced by taking the internal and external relations of the characteristics into consideration through a multidimensional attention mechanism, a multi-attention depth fusion mechanism is developed from different dimensions, deep coupling relations on time, space and characteristics are mined, and corresponding weights are given to different characteristics in a self-adaptive mode. And further excavating implicit correlations of different areas according to different degrees of influence of geographical positions on offshore wind turbine output of offshore, shallow and deep sea three feature matrixes, endowing different weights with self-adaption by using the graph annotation force, finally obtaining a new feature matrix, transmitting the new feature matrix to a bidirectional gating circulation unit network, predicting from a plurality of time scales by using a trained prediction model, and obtaining power time sequences of corresponding offshore wind power fields under different time scales to realize offshore wind power prediction under multiple time-space scales. The method can effectively improve the precision of offshore wind power prediction.
Example 2
In this embodiment, the specific procedure of performing the preliminary processing on the data in step S1 is as follows: and correcting background field systems such as a global forecast system (Global Forecasting System, GFS), a weather forecast mode system (WEATHER RESEARCH Forecast, WRF) and the like according to actual measurement meteorological data near the offshore wind farm area to obtain the grid NWP data with the horizontal resolution of 3km multiplied by 3 km. Filling up the missing data in the historical meteorological record data of the offshore wind farm to obtain complete historical meteorological record data of the wind farm; and carrying out min-max normalization processing on the power sequence, the wind speed sequence, the temperature sequence, the air pressure sequence, the cloud amount sequence and the ocean current sequence to obtain a processed power sequence P, a processed wind speed sequence WS, a processed temperature sequence T, a processed humidity sequence H, a processed precipitation amount sequence PRECIP, a processed air pressure sequence PA, a processed cloud amount sequence CU and a processed ocean current sequence OC, wherein the wind direction sequence adopts sine and cosine processing to obtain a wind direction sine WDS and a wind direction cosine WDC.
Further, in step S2, the preprocessed historical meteorological record data of the offshore wind farm is divided according to 8:2 and obtaining training samples and test samples.
In this embodiment, motif spectrum clustering is used for the processed sample features, and the best sensitivity factor screening is deployed by using laplace feature mapping, so that the data is subjected to dimension reduction, and the specific steps are as follows:
S31, constructing a similarity matrix , and calculating the similarity between samples according to the distance between the data samples;
s32, constructing an adjacent matrix , and constructing by using a Gaussian distance method:
Wherein 、/> is the i-th and j-th points (i, j=1,., n) in the n samples, s is the standard deviation, and e is an exponential function;
S33, calculating an order moment D and a Laplacian matrix L:
wherein is an order moment matrix of i rows and j columns, and/() is a Laplacian matrix of i rows and j columns;
S34, carrying out feature decomposition on the Laplace matrix to obtain feature vectors and feature values; selecting the first k eigenvectors as new data representations according to the magnitude of the eigenvalues; generating a feature matrix under a low dimension;
s35, carrying out K-Means clustering in the new feature space after dimension reduction, and dividing the new feature space into offshore, shallow and deep sea types to obtain a feature matrix ,/>,/>;
＝［M1,M2,...,Mn］,/> Wherein M n represents a matrix of features at times t-1 to t-M of the nth wind farm.
In this embodiment, the specific steps for constructing the multidimensional attention fusion mechanism are as follows:
The time attention module and the feature attention module are connected in series, input into a matrix of H multiplied by W multiplied by C, the feature diagram obtained after the processing of the two attention sub-modules is subjected to element addition operation, so that the two features are fused together, and output results are processed through a ReLU activation function and used as the input of the channel attention module and the space attention module, and the two modules are connected together by adopting a serial structure; in both attention modules, different feature information is acquired from different perspectives using both the average pooling and the maximum pooling operations.
The time attention module comprises a convolution layer, an FC layer, a softmax layer, a sigmoid activation function and a global average pooling layer; in the time attention module, global spatial average pooling GAP is applied to the feature matrix to ensure that the time attention module has low computational cost; then generating a position-sensitive importance map using a plurality of 1D convolutions with non-linearities over the entire time domain to enhance the frame-by-frame feature; generating a channel self-adaptive kernel based on global time information in each channel through the FC layer, and obtaining a time attention module weight coefficient Mt through the softmax layer; finally, multiplying the characteristic matrix by a weight coefficient to obtain a new zoomed characteristic matrix;
In the formula, GAP is global space average pooling, conv1D is one-dimensional convolution, X is an input sample, is a sigmoid activation function, FC is a full-connection layer, mt is a time attention module weight coefficient, and/() is a new feature matrix; delta represents the attention weight,/> is the vector product.
The feature attention module comprises a convolution layer, relu activation functions, sigmoid activation functions and a pooling layer; in the feature attention module, features are input first, pass through a pooling layer, then pass through two convolution layers, an activation function is Relu, and then the obtained features are fed back to self-adaptive weight coefficients of the features in different environments through a Sigmoid activation function to obtain weight coefficients ; finally, multiplying the original characteristic matrix/> by a weight coefficient to obtain a new zoomed characteristic matrix;
where Conv is convolution, is Relu activation function, and/> is the new feature matrix.
The spatial attention module comprises a convolution layer, a maximum pooling layer, an average pooling layer and a sigmoid activation function; in the space attention module, firstly, carrying out average pooling and maximum pooling of one channel dimension respectively to obtain two H multiplied by W multiplied by 1 channels, and splicing the channels together; then, through a C×C convolution layer, the activation function is Sigmoid, and the weight coefficient Ms is obtained; finally, multiplying the characteristic matrix by a weight coefficient to obtain a new zoomed characteristic matrix;
Where is mean pooling,/> is maximum pooling and/> is the new feature matrix.
The channel attention module comprises a convolution layer, a maximum pooling layer, an average pooling layer and a sigmoid activation function; in the channel attention module, firstly, carrying out global average pooling and maximum pooling on space to obtain two channels of 1 multiplied by C, respectively sending the channels into a two-layer shared neural network, wherein the number of neurons in the first layer is C/r, the activation function is Relu, and the number of neurons in the second layer is C; adding the obtained two features, and then obtaining a weight coefficient Mc through a Sigmoid activation function; finally, multiplying the original feature matrix by the weight coefficient to obtain a new zoomed feature matrix;
Wherein, MLP is a multi-layer perceptron and is a new feature matrix.
In the embodiment, a feature matrix ,/>,/> is input into a prediction model, the internal and external relations of the features are considered through a multidimensional attention mechanism in the prediction model, the offshore wind power feature enhancement of a multi-attention depth fusion mechanism is developed from different dimensions, deep coupling relations on time, space and features are mined, and corresponding weights are given to different features in a self-adaptive mode; based on time attention/> , feature attention/> , spatial attention/> , channel attention/> , deep-development feature enhancement;
Wherein is a weight matrix calculated by attention, wherein/() is a neural network corresponding to the attention, and/() is a characteristic value corresponding to the calculated dimension;
multiplying the obtained weights with the characteristics of the corresponding offshore wind farm respectively to obtain a weighted characteristic matrix ,/>,/>;
。
in the embodiment, the implicit relevance of different areas is further excavated according to different influence degrees of the offshore wind turbine output by the offshore, shallow and deep sea three feature matrixes according to geographic positions, different weights are self-adaptively given by using the schematic injection force, and finally a new feature matrix is obtained; the method comprises the following specific steps:
s61, defining a weight matrix W, and converting the feature matrix into adjacent nodes: ,/> For the j-th input sample (h=h1, … hn);
S62, splicing and mapping adjacent nodes i and j into scalar quantities, wherein is an attention calculating function: in the formula,/> , wherein/> is the original attention contribution degree obtained by calculating a certain node and is used for carrying out the normalization of the next step;
s63, passing the adjacent node matrix through leakyRelu layers and then through a softmax layer, calculating the contribution degree of each adjacent node j of the node i to the i and normalizing the contribution degree of each adjacent node j;
S64, after the contribution degree of each adjacent node of the i node is calculated, carrying out feature summation update on all the adjacent nodes of the i node according to the weight; as the final output of the i-node, is obtained;
The number of the output neurons is 3, the weights of the offshore, shallow and deep sea areas are respectively corresponding to the output neurons, and finally a new feature matrix is obtained;
Wherein ;
。
in this embodiment, the bidirectional gating cycle unit network is constructed as follows: taking a feature matrix as input, constructing a multi-layer cascade bidirectional gating circulation unit network, wherein the multi-layer cascade bidirectional gating circulation unit network consists of a forward GRU and a backward GRU, and the activation function is tanh;
Wherein 、/>、/>、/>、/>、/> is a weight parameter matrix,/> 、/>、/> is a bias parameter matrix,/> is a matrix multiplication,/> is a Sigmoid function,/> is a reset gate,/> is an update gate,/> is a candidate state of an hidden layer at the current moment,/> is a current hidden state,/> is a hidden state at the previous moment,/> is an input state at the current moment,/> is a reverse transfer calculation/> and/> are hidden states of a forward GRU and a backward GRU, and F is an output merging method of two directions.
In this embodiment, the time scale is n, where n is an integer and n is 2. And respectively adopting data of four time scales of 15 minutes, one hour, one day, three days and four time scales to predict four time scales in the future, thereby realizing ultra-short-term and short-term prediction.
Setting the time scale of the current prediction system as i, and inputting the running data of the previous moment with ,/> as the time scale i; the output of the prediction system is/> ,/> which is the prediction data of the current time scale; predicting power of a target offshore wind farm from a plurality of time scales by using a trained prediction model, obtaining power time sequences of the corresponding offshore wind farms under different time scales, respectively completing ultra-short-term prediction and short-term prediction of the offshore wind farm, and realizing offshore wind power prediction under the plurality of time scales;
Where is the predicted output load result on the i-th scale and/() is the input matrix for the i-n-1 to i-1 time scale.
In order to further verify the effectiveness of the offshore wind power interval prediction method in embodiment 1 of the present invention, in this embodiment:
in step S1, acquiring power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage and ocean current data of an offshore wind farm in a certain area;
in step S6, to ensure that the variance of the output is always positive, the number of neurons input is 64, and the number of neurons of the output layer is 3;
The above data were substituted into the offshore wind power section prediction method of example 1 to perform prediction, the training batch was 64, and the training number was 256.
Finally, the offshore wind power interval prediction effect shown in fig. 4 is obtained. From the prediction effect in fig. 4, it can be seen that the method for predicting the offshore wind power interval can effectively improve the accuracy of the offshore wind power interval prediction.
Example 3
The embodiment provides a multi-time-space-scale offshore wind power feature screening and enhanced power prediction system, as shown in fig. 5, including:
the data acquisition unit is used for acquiring multisource data sets of a target and an adjacent offshore wind farm, and comprises power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud accumulation and ocean current data of the target offshore wind farm;
The preprocessing unit is used for preprocessing the characteristic sequences obtained by the data acquisition unit to obtain characteristic vectors, taking the offshore wind power time sequences as prediction target samples, and dividing the characteristic vectors and the offshore wind power time sequences into training sets and verification sets respectively;
The multi-space scale feature screening unit is used for carrying out motif spectrum clustering according to the ocean current data acquired by the data acquisition unit, utilizing Laplace feature mapping to develop optimal sensitivity factor screening, carrying out dimension reduction on the data, and dividing the feature data into three areas of offshore, shallow and deep sea to respectively form three feature matrixes;
The feature enhancement unit is used for carrying out offshore wind power feature enhancement of a multi-attention depth fusion mechanism from different dimensions by taking the internal and external relations of the features into consideration through a multi-dimensional attention mechanism in the prediction model, excavating deep coupling relations on time, space and features, and self-adaptively giving corresponding weights to the different features; based on time attention, feature attention, space attention, channel attention and depth development feature enhancement, multiplying attention weight by input feature map to obtain weighted feature matrix, and sending the feature matrix to a multi-time scale prediction unit;
The multi-time scale prediction unit is used for inputting the feature matrix given with the weight into the bidirectional gating circulation unit network, predicting the power of the target offshore wind power plant from a plurality of time scales by using the trained prediction model, obtaining the power time sequences of the corresponding offshore wind power plant at different time scales, and completing the offshore wind power prediction at the multi-time-space scale.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
It is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (10)
1. The multi-time space-scale offshore wind power characteristic screening and enhanced power prediction method is characterized by comprising the following steps of:
S1, acquiring a multi-source data set of a target and an adjacent offshore wind farm, wherein the multi-source data set comprises power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage and ocean current data of the target offshore wind farm, and performing primary processing;
S2, dividing the preprocessed historical meteorological record data of the offshore wind farm to obtain a training sample and a testing sample;
S3, carrying out motif spectrum clustering according to the acquired ocean current data, utilizing Laplace feature mapping to develop optimal sensitivity factor screening, carrying out dimension reduction on the data, and dividing the feature data into three areas of offshore, shallow and deep sea; the processed power, wind speed, wind direction, temperature, precipitation, humidity, air pressure, cloud storage quantity and ocean current data of the offshore wind farm form a feature matrix ,/>,;
S4, constructing a multidimensional attention fusion mechanism and a prediction model of a bidirectional gating circulation unit network;
S5, inputting a feature matrix ,/>,/> into a prediction model, taking the internal and external relations of the features into consideration through a multidimensional attention mechanism in the prediction model, developing the offshore wind power feature enhancement of a multi-attention depth fusion mechanism from different dimensions, excavating deep coupling relations on time, space and features, and giving corresponding weights to different features in a self-adaptive manner;
s6, further excavating implicit correlations of different areas according to different degrees of influence of geographical positions on the offshore wind turbine output on three feature matrixes of offshore, shallow sea and deep sea, giving different weights by using self-adaption of the schematic injection force, and finally obtaining a new feature matrix ;
S7, transmitting the feature matrix with the given weight and the enhanced features to a bidirectional gating circulation unit network, and mining hidden relations in the feature matrix by the bidirectional gating circulation unit network;
And S8, predicting the power of the target offshore wind power plant from a plurality of time scales by using the trained prediction model, and obtaining a power time sequence of the corresponding offshore wind power plant under different time scales so as to realize offshore wind power prediction under a plurality of time scales.
2. The multi-time space-scale offshore wind power feature screening and enhanced power prediction method according to claim 1, wherein in step S1, the specific process of performing preliminary processing on data is as follows: correcting a global forecasting system and a weather forecasting mode system according to actual measurement meteorological data near an offshore wind farm area to obtain NWP data with the horizontal resolution of Nkm multiplied by Nkm gridding; filling up the missing data in the historical meteorological record data of the offshore wind farm to obtain complete historical meteorological record data of the wind farm; carrying out min-max normalization processing on the power sequence, the wind speed sequence, the temperature sequence, the air pressure sequence, the cloud amount sequence and the ocean current sequence to obtain a processed power sequence P, a processed wind speed sequence WS, a processed temperature sequence T, a processed humidity sequence H, a processed precipitation amount sequence PRECIP, a processed air pressure sequence PA, a processed cloud amount sequence CU and a processed ocean current sequence OC, wherein the wind direction sequence adopts sine and cosine processing to obtain a wind direction sine WDS and a wind direction cosine WDC; in step S2, the preprocessed historical meteorological record data of the offshore wind farm is divided according to 8:2 and obtaining training samples and test samples.
3. The multi-time-space scale offshore wind power feature screening and enhanced power prediction method according to claim 1, wherein in step S3, motif spectral clustering is used for the processed sample features, laplace feature mapping is utilized to develop optimal sensitivity factor screening, and the data is subjected to dimension reduction, which comprises the following specific steps:
S31, constructing a similarity matrix , and calculating the similarity between samples according to the distance between the data samples;
s32, constructing an adjacent matrix , and constructing by using a Gaussian distance method:
Wherein 、/> is the i-th and j-th points (i, j=1,., n) in the n samples, s is the standard deviation, and e is an exponential function;
S33, calculating an order moment D and a Laplacian matrix L:
wherein is an order moment matrix of i rows and j columns, and/() is a Laplacian matrix of i rows and j columns;
S34, carrying out feature decomposition on the Laplace matrix to obtain feature vectors and feature values; selecting the first k eigenvectors as new data representations according to the magnitude of the eigenvalues; generating a feature matrix under a low dimension;
S35, carrying out K-Means clustering in the new feature space after dimension reduction, and dividing the new feature space into offshore, shallow and deep sea types to obtain a feature matrix ,/>,/>;
＝［M1,M2,...,Mn］,/> Wherein M n represents a matrix of features at times t-1 to t-M of the nth wind farm.
4. The multi-time-space scale offshore wind power feature screening and enhanced power prediction method according to claim 3, wherein in step S4, the specific steps of constructing a multi-dimensional attention fusion mechanism are as follows:
The time attention module and the feature attention module are connected in series, input into a matrix of H multiplied by W multiplied by C, the feature diagram obtained after the processing of the two attention sub-modules is subjected to element addition operation, so that the two features are fused together, and output results are processed through a ReLU activation function and used as the input of the channel attention module and the space attention module, and the two modules are connected together by adopting a serial structure; in both attention modules, different feature information is acquired from different perspectives using both the average pooling and the maximum pooling operations.
5. The multi-time-space scale offshore wind feature screening and enhanced power prediction method of claim 4, wherein the time attention module comprises a convolution layer, an FC layer, a softmax layer, a sigmoid activation function and a global average pooling layer; in the time attention module, global spatial average pooling GAP is applied to the feature matrix to ensure that the time attention module has low computational cost; then generating a position-sensitive importance map using a plurality of 1D convolutions with non-linearities over the entire time domain to enhance the frame-by-frame feature; generating a channel self-adaptive kernel based on global time information in each channel through the FC layer, and obtaining a time attention module weight coefficient Mt through the softmax layer; finally, multiplying the characteristic matrix by a weight coefficient to obtain a new zoomed characteristic matrix;
In the formula, GAP is global space average pooling, conv1D is one-dimensional convolution, X is an input sample, is a sigmoid activation function, FC is a full-connection layer, mt is a time attention module weight coefficient, and/() is a new feature matrix; delta represents the attention weight, is the vector product;
The feature attention module comprises a convolution layer, relu activation functions, sigmoid activation functions and a pooling layer; in the feature attention module, features are input first, pass through a pooling layer, then pass through two convolution layers, an activation function is Relu, and then the obtained features are fed back to self-adaptive weight coefficients of the features in different environments through a Sigmoid activation function to obtain weight coefficients ; finally, multiplying the original characteristic matrix/> by a weight coefficient to obtain a new zoomed characteristic matrix;
wherein Conv is convolution, is Relu activation function, and/> is new feature matrix;
The spatial attention module comprises a convolution layer, a maximum pooling layer, an average pooling layer and a sigmoid activation function; in the space attention module, firstly, carrying out average pooling and maximum pooling of one channel dimension respectively to obtain two H multiplied by W multiplied by 1 channels, and splicing the channels together; then, through a C×C convolution layer, the activation function is Sigmoid, and a weight coefficient is obtained; finally, multiplying the characteristic matrix/> by a weight coefficient to obtain a new zoomed characteristic matrix;
wherein is average pooling,/> is maximum pooling, and/> is a new feature matrix;
The channel attention module comprises a convolution layer, a maximum pooling layer, an average pooling layer and a sigmoid activation function; in the channel attention module, firstly, carrying out global average pooling and maximum pooling on space to obtain two channels of 1 multiplied by C, respectively sending the channels into a two-layer shared neural network, wherein the number of neurons in the first layer is C/r, the activation function is Relu, and the number of neurons in the second layer is C; adding the obtained two features, and then obtaining a weight coefficient Mc through a Sigmoid activation function; finally, multiplying the original feature matrix by the weight coefficient to obtain a new zoomed feature matrix;
Wherein, MLP is a multi-layer perceptron and is a new feature matrix.
6. The multi-time space-scale offshore wind power feature screening and enhancing power prediction method according to claim 5, wherein in step S5, feature matrix ,/>,/> is input into a prediction model, the internal and external relationships of features are considered through a multi-dimensional attention mechanism in the prediction model, the offshore wind power feature enhancement of a multi-attention depth fusion mechanism is carried out from different dimensions, the deep coupling relationship in time, space and features is mined, and the corresponding weights are given to the different features in a self-adaptive manner; based on time attention/> , feature attention/> , spatial attention/> , channel attention/> , deep-development feature enhancement;
Wherein is a weight matrix calculated by attention, wherein/() is a neural network corresponding to the attention, and/() is a characteristic value corresponding to the calculated dimension;
Multiplying the obtained weights with the characteristics of the corresponding offshore wind farm respectively to obtain a weighted characteristic matrix ,/>,;
。
7. The multi-time-space scale offshore wind power feature screening and enhanced power prediction method according to claim 6, wherein step S6 specifically comprises:
S61, defining a weight matrix W, and converting the feature matrix into adjacent nodes: ,/> For the j-th input sample (h=h1, … hn);
S62, splicing and mapping adjacent nodes i and j into scalar quantities, wherein is an attention calculating function: in the formula,/> , wherein/> is the original attention contribution degree obtained by calculating a certain node and is used for carrying out the normalization of the next step;
s63, passing the adjacent node matrix through leakyRelu layers and then through a softmax layer, calculating the contribution degree of each adjacent node j of the node i to the i and normalizing the contribution degree of each adjacent node j;
s64, after the contribution degree of each adjacent node of the i node is calculated, carrying out feature summation update on all the adjacent nodes of the i node according to the weight; as the final output of the i-node, is obtained;
the number of the output neurons is 3, the weights of the offshore, shallow and deep sea areas are respectively corresponding to the output neurons, and finally a new feature matrix is obtained;
Wherein ;
。
8. The multi-time-space scale offshore wind power feature screening and enhanced power prediction method according to claim 7, wherein in step S7, the bidirectional gating cyclic unit network is constructed as follows: taking a feature matrix as input, constructing a multi-layer cascade bidirectional gating circulation unit network, wherein the multi-layer cascade bidirectional gating circulation unit network consists of a forward GRU and a backward GRU, and the activation function is tanh;
Wherein 、/>、/>、/>、/>、/> is a weight parameter matrix,/> 、/>、/> is a bias parameter matrix,/> is a matrix multiplication,/> is a Sigmoid function,/> is a reset gate,/> is an update gate,/> is a candidate state of an hidden layer at the current moment, is a current hidden state,/> is a hidden state at the previous moment,/> is an input state at the current moment,/> is a reverse transfer calculation/> and/> are hidden states of a forward GRU and a backward GRU, and F is an output merging method of two directions.
9. The multi-time-space scale offshore wind power feature screening and enhancement power prediction method of claim 8, wherein in step S8, the time scale is n, where n is an integer and n 2;
setting the time scale of the current prediction system as i, and inputting the running data of the previous moment with ,/> as the time scale i; the output of the prediction system is/> ,/> which is the prediction data of the current time scale; predicting power of a target offshore wind farm from a plurality of time scales by using a trained prediction model, obtaining power time sequences of the corresponding offshore wind farms under different time scales, respectively completing ultra-short-term prediction and short-term prediction of the offshore wind farm, and realizing offshore wind power prediction under the plurality of time scales;
Where is the predicted output load result on the i-th scale and/() is the input matrix for the i-n-1 to i-1 time scale.
10. The multi-time-space scale offshore wind power feature screening and enhancement power prediction method according to claim 9, wherein data of 15 minutes, one hour, one day, three days and four time scales are used for predicting four time scales in the future respectively to realize ultra-short-term and short-term prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410303869.7A CN117893362B (en) | 2024-03-18 | 2024-03-18 | Multi-time-space-scale offshore wind power characteristic screening and enhanced power prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410303869.7A CN117893362B (en) | 2024-03-18 | 2024-03-18 | Multi-time-space-scale offshore wind power characteristic screening and enhanced power prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117893362A true CN117893362A (en) | 2024-04-16 |
| CN117893362B CN117893362B (en) | 2024-07-26 |
Family
ID=90641602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410303869.7A Active CN117893362B (en) | 2024-03-18 | 2024-03-18 | Multi-time-space-scale offshore wind power characteristic screening and enhanced power prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893362B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118568673A (en) * | 2024-07-31 | 2024-08-30 | 阿里云飞天(杭州)云计算技术有限公司 | Timing prediction system, method, apparatus, storage medium, and program product |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990553A (en) * | 2021-02-23 | 2021-06-18 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method using self-attention mechanism and bilinear fusion |
| CN113689030A (en) * | 2021-08-03 | 2021-11-23 | 广东工业大学 | Short-term wind power prediction method based on bidirectional attention and secondary optimization |
| CN114429078A (en) * | 2021-12-22 | 2022-05-03 | 广东工业大学 | Short-term wind power prediction method and system |
| US20220197233A1 (en) * | 2020-12-18 | 2022-06-23 | Wuhan University | Wind power prediction method and system for optimizing deep transformer network |
| CN115293415A (en) * | 2022-07-28 | 2022-11-04 | 三峡大学 | Multi-wind-farm short-term power prediction method considering time evolution and space correlation |
| CN116128122A (en) * | 2023-01-03 | 2023-05-16 | 北京交通大学 | Urban rail transit short-time passenger flow prediction method considering burst factors |
| CN116316591A (en) * | 2023-03-17 | 2023-06-23 | 山东科技大学 | Short-term photovoltaic power prediction method and system based on hybrid bidirectional gating cycle |
| CN116702831A (en) * | 2023-06-05 | 2023-09-05 | 广西大学 | Hybrid short-term wind power prediction method considering massive loss of data |
| CN116826727A (en) * | 2023-06-28 | 2023-09-29 | 河海大学 | Ultra-short-term wind power prediction method and prediction system based on time sequence representation and multistage attention |
| CN116894504A (en) * | 2023-02-16 | 2023-10-17 | 国网河南省电力公司濮阳供电公司 | Wind power cluster power ultra-short-term prediction model establishment method |
| CN117114192A (en) * | 2023-08-29 | 2023-11-24 | 淮阴工学院 | Offshore wind power prediction method and device based on multi-scale space-time diagram transformation network |
-
2024
- 2024-03-18 CN CN202410303869.7A patent/CN117893362B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220197233A1 (en) * | 2020-12-18 | 2022-06-23 | Wuhan University | Wind power prediction method and system for optimizing deep transformer network |
| CN112990553A (en) * | 2021-02-23 | 2021-06-18 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method using self-attention mechanism and bilinear fusion |
| CN113689030A (en) * | 2021-08-03 | 2021-11-23 | 广东工业大学 | Short-term wind power prediction method based on bidirectional attention and secondary optimization |
| CN114429078A (en) * | 2021-12-22 | 2022-05-03 | 广东工业大学 | Short-term wind power prediction method and system |
| CN115293415A (en) * | 2022-07-28 | 2022-11-04 | 三峡大学 | Multi-wind-farm short-term power prediction method considering time evolution and space correlation |
| CN116128122A (en) * | 2023-01-03 | 2023-05-16 | 北京交通大学 | Urban rail transit short-time passenger flow prediction method considering burst factors |
| CN116894504A (en) * | 2023-02-16 | 2023-10-17 | 国网河南省电力公司濮阳供电公司 | Wind power cluster power ultra-short-term prediction model establishment method |
| CN116316591A (en) * | 2023-03-17 | 2023-06-23 | 山东科技大学 | Short-term photovoltaic power prediction method and system based on hybrid bidirectional gating cycle |
| CN116702831A (en) * | 2023-06-05 | 2023-09-05 | 广西大学 | Hybrid short-term wind power prediction method considering massive loss of data |
| CN116826727A (en) * | 2023-06-28 | 2023-09-29 | 河海大学 | Ultra-short-term wind power prediction method and prediction system based on time sequence representation and multistage attention |
| CN117114192A (en) * | 2023-08-29 | 2023-11-24 | 淮阴工学院 | Offshore wind power prediction method and device based on multi-scale space-time diagram transformation network |
Non-Patent Citations (2)
| Title |
|---|
| 李豪 等: "基于时空相关性的短期光伏出力预测混合模型", 《电力系统及其自动化学报》, 12 July 2023 (2023-07-12), pages 1 - 12 * |
| 胡健鹏 等: "面向多时间步风功率预测的深度时空网络模型", 《计算机应用》, 12 March 2024 (2024-03-12), pages 1 - 13 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118568673A (en) * | 2024-07-31 | 2024-08-30 | 阿里云飞天(杭州)云计算技术有限公司 | Timing prediction system, method, apparatus, storage medium, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117893362B (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Photovoltaic power forecasting with a hybrid deep learning approach | |
| US10302066B2 (en) | Reducing curtailment of wind power generation | |
| Ghaderi et al. | Deep forecast: Deep learning-based spatio-temporal forecasting | |
| US10598157B2 (en) | Reducing curtailment of wind power generation | |
| Bhardwaj et al. | Estimation of solar radiation using a combination of Hidden Markov Model and generalized Fuzzy model | |
| Chen et al. | Online 24-h solar power forecasting based on weather type classification using artificial neural network | |
| Mellit et al. | A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy | |
| Eom et al. | Feature-selective ensemble learning-based long-term regional PV generation forecasting | |
| CN117893362B (en) | Multi-time-space-scale offshore wind power characteristic screening and enhanced power prediction method | |
| CN115688579B (en) | Drainage basin multipoint water level prediction and early warning method based on generation countermeasure network | |
| Mei et al. | Day-ahead nonparametric probabilistic forecasting of photovoltaic power generation based on the LSTM-QRA ensemble model | |
| Yao et al. | Wave height forecast method with multi-step training set extension LSTM neural network | |
| CN116720156A (en) | Weather element forecasting method based on graph neural network multi-mode weather data fusion | |
| CN115204032A (en) | ENSO prediction method and device based on multi-channel intelligent model | |
| CN116451821A (en) | Deep learning-based large-area new energy generation power prediction method and system | |
| Wang et al. | CNN-BiLSTM-attention model in forecasting wave height over South-East China Seas | |
| CN117934208B (en) | Multi-channel depth network-based multi-source data offshore wind power prediction method | |
| CN116029419A (en) | Deep learning-based long-term new energy daily average generation power prediction method and system | |
| CN117556312A (en) | Power grid transmission line fault prediction method and system under extreme weather | |
| Kutucu et al. | An application of artificial neural networks to assessment of the wind energy potential in Libya | |
| Shahid et al. | Short term solar energy prediction by machine learning algorithms | |
| CN113962432A (en) | Wind power prediction method and system integrating three-dimensional convolution and light-weight convolution threshold unit | |
| Zameer et al. | Intelligent forecast models for daily solar energy prediction | |
| Obeidi et al. | Sunspot number-based neural network model for global solar radiation estimation in Ghardaïa | |
| Peng et al. | A hybrid model for solar radiation forecasting towards energy efficient buildings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |