CN114897204A - Method and device for predicting short-term wind speed of offshore wind farm - Google Patents
Method and device for predicting short-term wind speed of offshore wind farm Download PDFInfo
- Publication number
- CN114897204A CN114897204A CN202210146830.XA CN202210146830A CN114897204A CN 114897204 A CN114897204 A CN 114897204A CN 202210146830 A CN202210146830 A CN 202210146830A CN 114897204 A CN114897204 A CN 114897204A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- prediction
- data
- factors
- short
- 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 34
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims abstract description 31
- 241000287127 Passeridae Species 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000013507 mapping Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000000739 chaotic effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 2
- 239000011541 reaction mixture Substances 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims 1
- 238000011161 development Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000053 physical method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical compound [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 244000062645 predators Species 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012795 verification Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/048—Activation functions
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (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 method for predicting the short-term wind speed of an offshore wind farm, which comprises the steps of inputting a plurality of wind speed influence meteorological factors into an offshore wind farm short-term wind speed prediction model based on a BP neural network to obtain the short-term wind speed prediction of the offshore wind farm. The method for establishing the prediction model comprises the following steps: acquiring historical wind speed data of the offshore wind farm, wherein the historical wind speed data comprises meteorological data corresponding to the historical wind speed data; extracting meteorological wind speed influence factors with high correlation degree for analysis by adopting a grey correlation degree theory, and removing secondary factors; and taking the meteorological influence factors with high relevance as input variables of the prediction model. And optimizing the initial weight and the threshold of the BP neural network of the prediction model by a sparrow algorithm.
Description
Technical Field
The invention belongs to the technical field of wind power generation, and particularly relates to a method and a device for predicting short-term wind speed of an offshore wind farm.
Background
With the accelerated development of energy internet construction, renewable energy has been valued by various countries. Wind energy has received significant attention as a clean, environmentally friendly renewable energy source. The inland area has uneven distribution of wind energy resources and larger difference of wind speed, so compared with the inland area, the coastal area has larger development scale. The wind power generation system has the advantages of rich wind energy resources and low noise pollution, and offshore wind power is expected to open up a new stage of wind power generation. However, the intermittency and volatility of wind speed present a significant challenge to offshore wind power development.
Disclosure of Invention
According to the method for predicting the short-term wind speed of the offshore wind farm, a plurality of wind speed influence meteorological factors are input into an offshore wind farm short-term wind speed prediction model based on a BP neural network, and the short-term wind speed prediction of the offshore wind farm is obtained. The method for establishing the prediction model comprises the following steps:
acquiring historical wind speed data of the offshore wind farm, wherein the historical wind speed data comprises meteorological data corresponding to the historical wind speed data;
extracting meteorological wind speed influence factors with high correlation degree for analysis by adopting a grey correlation degree theory, and removing secondary factors;
and taking the meteorological influence factors with high relevance as input variables of the prediction model.
And optimizing the initial weight and the threshold of the BP neural network of the prediction model by a sparrow algorithm.
The method has the advantages that due to the fact that the natural climate factors influencing the offshore wind speed are numerous, different input variables can generate huge changes on the prediction error, the influence factors are sorted by the grey correlation degree theory in the grey theory, the natural climate factors with small influence are removed, the input variables of the obtained prediction model are simpler, and the prediction error result is more reliable. Meanwhile, the prediction is optimized by adopting a sparrow algorithm, and the BP neural network is combined, so that the defects of the prediction of the traditional neural network model are overcome, and the prediction accuracy of the prediction model is obviously improved. The prediction model method can also be used for prediction research in other fields and provides important reference value.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
FIG. 1 is a flow chart of wind speed prediction for an offshore wind farm according to one embodiment of the present invention.
Fig. 2 is a schematic diagram of a predicted value and an actual value of the offshore wind speed under the improved algorithm according to one embodiment of the present invention.
FIG. 3 is a comparison of predicted values of offshore wind speed for two algorithms according to one embodiment of the invention.
FIG. 4 is a diagram of an analysis of the prediction error in the undersea and overseas for two algorithms according to one embodiment of the invention.
Detailed Description
The wind speed prediction can be divided into ultra-short term, medium term and long term prediction according to the time level, and the existing wind speed prediction method mainly comprises a physical method and an artificial intelligence statistical method. The physical method is mainly combined for prediction according to huge and complex environmental changes and climatic factors, and is generally used for long-term prediction and not suitable for short-term prediction. The artificial intelligence statistical method utilizes an intelligent algorithm to establish a mapping relation between past historical data and future data changes, and continuously trains and learns to obtain a prediction result, and mainly comprises a support vector machine, a neural network, a time series method and the like.
The physical method has complex modeling and high cost, is only suitable for prediction in a relatively stable state, and has unsatisfactory precision. The artificial intelligence statistical method has large prediction error due to long-time prediction, and the single algorithm prediction is easy to trap into the value, so that the result is not satisfactory. Due to the influence of many factors on the offshore wind speed, the prediction method needs to be combined with different algorithms for prediction.
According to one or more embodiments, a method for short-term wind speed prediction of an offshore wind farm comprises the steps of:
and collecting historical data within a specific time range, and preprocessing the data.
And (5) analyzing and removing redundant secondary factors by adopting a grey correlation degree theory. The extracted influencing factors comprise: temperature, humidity and air pressure.
And (3) optimizing the initial weight and the threshold of the BP neural network by adopting an improved algorithm, including adopting Logistic chaotic mapping and Levy flight strategy.
And dividing the preprocessed data set into a training set and a testing set, and performing precision evaluation on a prediction result by adopting mean square error (RMSE).
In the embodiment of the invention, because the wind speed data is interacted with various factors, model prediction is established on various influencing factors, a more accurate prediction model cannot be established, and the prediction error is larger. Various prediction methods are often only suitable for prediction within a certain time range, and a satisfactory prediction result cannot be obtained beyond a certain time. The data is preprocessed, the important degree of influence of various factors is determined by adopting a grey theory, the natural climate factor with high influence degree is used as an input variable of a prediction model, and the prediction speed is quicker.
The offshore wind speed has stronger volatility and randomness compared with the inland wind speed, so that the offshore wind speed can be accurately predicted by removing redundant influence factors, and the offshore wind power plant short-term wind speed prediction method for optimizing the BP neural network by improving the sparrow algorithm is provided by the embodiment of the invention aiming at the problem of network structure uncertainty in the BP neural network wind speed prediction. And improving the quality of the initial population by adopting Logistic chaotic mapping, and updating position information by adopting Levy flight. And optimizing by utilizing an improved sparrow algorithm to obtain an initial weight and a threshold of the BP neural network, taking temperature, humidity, air pressure and other influence factors as input variables, and obtaining a wind speed predicted value through a combined model. Compared with the traditional BP neural network, the algorithm has higher prediction precision and enlarges the measurement range. The prediction method is not only suitable for wind speed prediction, but also can improve important reference value in the fields of photovoltaic power generation power prediction, equipment fault diagnosis and the like.
According to one or more embodiments, a method for short-term wind speed prediction for an offshore wind farm includes the steps of,
step 1, collecting measured wind speed data of a marine wind field, preprocessing the data, and analyzing and optimizing the measured wind speed data to obtain more excellent historical data so as to ensure that
v(t)=f(v(t-1),v(t-2),...v(t-n)) (1)
V (t-n) represents historical data from v (t-n) to v (t-1), and v (t) is predicted wind speed data in formula (1). Wherein, each wind speed component of the wind speed is expressed as follows:
v=v b +v s +v a +v v (2)
in the formula (2), v represents the synthetic wind speed, v b 、v s 、v a 、v v Respectively representing the base wind speed, the gust variable wind speed, the gradual change wind speed and the noise wind speed. Experimentally derived from a large amount of wind speed data, it can be found that the wind speed probability density function obeys Weibull distribution, and is expressed as follows:
in the formula (3), v represents a wind speed, k represents a shape parameter, c represents a scale parameter, and the dimension is the same as the wind speed. Because the wind power data can be directly calculated according to the wind speed data, the prediction method is also suitable for wind power prediction. Here, further, the collected historical data is normalized by the following formula:
in the formula (4), the reaction mixture is,for the normalized data, v (t) is the wind speed value before processing, v max And v min Respectively, the maximum value and the minimum value of the normalized processing data.
And 2, removing redundant secondary factors by adopting a correlation degree analysis method in a grey theory, and screening three main influence factors influencing the offshore wind speed as the input of the BP neural network. Compared with inland wind speed, sea wind speed has a plurality of factors, such as waves, typhoons, lightning, humid air, floating ice, tides and the like, the influence degree of the above natural climate factors is analyzed based on a grey correlation degree theory, and the high correlation degree is selected as an input variable of a training set.
Specifically, the method comprises the following steps of,
s21, defining a plurality of natural climate factors as comparison arrays, defining a wind speed data set as a reference array, and calculating the correlation coefficient of each natural climate factor by adopting the following formula:
in formula (5), λ i Is the grey correlation coefficient of the ith natural climate factor, alpha is the correlation resolution coefficient, and deltav i (t) is the absolute value of the difference between the reference sequence and the comparison sequence, Δ v max Is Δ v i Maximum value of (t), Δ v min Is Δ v i Minimum value in (t).
S22, calculating the grey correlation degree:
in the formula (6), ρ i Is the grey correlation of the ith natural climate factor and n is the total number of data samples.
And S23, sorting the grey correlation coefficients of the natural climate factors, and defining that the grey correlation coefficients are ranked in the front and the grey correlation coefficients are ranked in the back. And finally, selecting the temperature, the humidity and the air pressure as main influence factors through calculation. And step 3, improving a newly-emerging sparrow search algorithm, and optimally solving the initial weight and the threshold of the BP neural network input layer. Firstly, adding Logistic chaotic mapping to improve initial population diversity, secondly introducing a sparrow updating mode of an algorithm, and finally updating a vigilant person in the algorithm by adopting a Levy flight strategy to jump out local optimality, wherein the method specifically comprises the following steps:
(31) selecting a newly-developed sparrow algorithm for preliminary optimization, and improving the quality of an initial population by adopting Logistic chaotic mapping, wherein the formula is as follows:
wherein α is a Logistic parameter, X t+1 And X t Real number sequences are mapped to the chaos.
(32) Sparrows can be classified into discoverers, enrollees and vigilators according to habits, the discoverer task is to find captured food and provide food information for other sparrows, and the formula is as follows:
where T is the number of iterations, ITER max Is the maximum number of iterations, which is a constant; x is the number of ij Representing the position information of the ith sparrow in the jth dimension; alpha is a random number between 0 and 1; q follows normal distribution and is also a random number; l is a one-dimensional matrix, each element being 1. R 2 Representing an early warning value and S a safety value.
(33) After the joining person obtains the predation information that predator sent, carry out position adjustment rapidly and get food, the position information formula is:
wherein A is a 1 × d matrix with elements of 1 or-1 at random, and A ° ═ A T (AA T ) -1 。i>n/2, the ith sparrow is in a hungry state and flies to other directions to search for food.
(34) The alerter generally accounts for only 10% -20% of the population quantity, and the mathematical expression is as follows:
in the formula, beta is a control step length, and follows normal distribution with the mean value of 0 and the variance of 1, and k is positioned between-1 and is also a random number; e is the smallest constant, f i >f g When the sparrows are located at the edge of the population, the sparrows are vulnerable. The adoption of the Levy flight strategy is beneficial to jumping out of local optimum, and the improvement formula is as follows:
wherein Levy (d) is 0.01 × a 1 ×δ/(a 2 ) 1/β And δ can be represented by the following formula:
And 4, step 4: the BP neural network comprises an input layer, a hidden layer and an output layer, an improved sparrow algorithm is adopted to optimize the initial weight and the threshold of the input layer, a Sigmod function is selected as an excitation function of the input layer, and the quantity relationship among the three layers is as follows:
wherein m and n are the numbers of neurons in the input layer and the output layer, respectively, and x is an arbitrary integer from 0 to 10.
Data is transmitted from an input layer to an output layer to obtain output data and errors, then the errors are continuously reduced by continuously adjusting weights and thresholds from the output layer to the input layer by adopting a gradient descent method, iteration is continuously carried out until the convergence of the algorithm is terminated, and the whole prediction process comprises the following steps:
(41) constructing a historical data set, and preprocessing data;
(42) eliminating redundant factors by adopting the grey correlation degree, and determining a main input variable;
(43) setting the population scale, the maximum iteration times and the quantity of each parameter, and initializing the population by adopting Logistic chaotic mapping;
(44) calculating the fitness value of sparrow individuals, and determining the current optimal individual and the worst individual;
(45) selecting a part from the current optimal individual as a finder, and updating according to a finder formula;
(46) the rest individuals update the position information of the entrant according to a Levy flight strategy, and a smaller part is randomly selected to be updated according to the position information of the scout;
(47) whether the end condition is met or not, if not, returning to the step (44);
(48) and if so, assigning the best sparrow individual to a BP neural network input layer, and repeatedly iteratively correcting the prediction error through three layers.
And 5, selecting 300 groups of offshore wind speed data as a training set and 15 groups of offshore wind speed data as a test set to predict by adopting the prediction model. To better evaluate the accuracy of the prediction model, the prediction result is quantitatively analyzed by mean square error (RMSE), and the formula is as follows:
in the formula, v MSE Predicting mean square error, V, for wind speed i Is the actual wind speed, v i To predict wind speed.
The embodiment of the invention adopts an intelligent algorithm sparrow algorithm and a BP neural network algorithm to predict the wind speed. The defects of the two algorithms are improved and optimized, the accuracy of the prediction result is greatly improved, and the mean square error is used as the evaluation standard verification of the SSA-BP neural network and the BP neural network.
As shown in FIG. 2, the ISSA-BPNN combined algorithm is adopted to predict that the offshore wind speed value is in good agreement with the actual value, and the deviation is small overall. This is because the better weight and threshold are obtained before the neural network training begins, and therefore a predicted value with higher accuracy can be obtained, which also proves the effectiveness of the present invention.
As shown in fig. 3, the predicted wind speed value of the BP neural network is consistent with the variation trend of the actual value, but the numerical difference is large, wherein the main reason is that the BP neural network is easy to fall into a local minimum value to cause insufficient training, so that the prediction accuracy is not high. Meanwhile, compared with a BP neural network single algorithm, the ISSA-BPNN combined algorithm is closer to a true value, and the importance of improving the sparrow algorithm is proved.
As shown in FIG. 4, the prediction accuracy of the two algorithms is evaluated, the mean square error of the ISSA-BP neural network is basically maintained within plus or minus 0.2, while the mean square error of the single BP neural network algorithm reaches minus 0.6 when being the highest, compared with the prediction of the single BP neural network, the prediction error of the improved method is reduced to a certain extent, and the prediction accuracy is improved. Meanwhile, the simulation running time of the improved algorithm is shorter than that of a BP neural network, and the feasibility of the method is verified again.
The embodiment of the invention adopts the sparrow algorithm for prediction research, combines the excellent performance characteristics with the BP neural network algorithm, makes up for the deficiencies, is applied to the field of offshore wind speed prediction, and can greatly improve the prediction precision. Because the wind speed is closely related to the wind power, the uncertainty of the output of the fan is determined by the random change of the wind speed. The wind speed is accurately predicted, the variation trend of the output of the fan can be remarkably predicted, and an important reference value is provided for the practical application development of engineering.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units involved in the invention, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for predicting the short-term wind speed of an offshore wind farm is characterized in that a plurality of wind speed influence meteorological factors are input into an offshore wind farm short-term wind speed prediction model based on a BP neural network, and the short-term wind speed prediction of the offshore wind farm is obtained.
2. The prediction method according to claim 1, wherein the method for establishing the prediction model comprises the steps of:
acquiring historical wind speed data of the offshore wind farm, wherein the historical wind speed data comprises meteorological data corresponding to the historical wind speed data;
extracting meteorological wind speed influence factors with high correlation degree for analysis by adopting a grey correlation degree theory, and removing secondary factors;
and taking the meteorological influence factors with high relevance as input variables of the prediction model.
3. The prediction method according to claim 1, wherein initial weights and thresholds of the BP neural network of the prediction model are optimized by a sparrow algorithm.
4. The prediction method according to claim 3, wherein the optimization of the sparrow algorithm comprises increasing population diversity through Logistic chaotic mapping and updating sparrow position information through a Levy flight strategy.
5. The prediction method according to claim 1, wherein the training data set of the prediction model is divided into a training set and a test set, and the prediction result is subjected to precision evaluation by mean square error.
6. The prediction method according to claim 2, wherein the extracted influencing factors include temperature, humidity and air pressure.
7. The prediction method according to claim 2, characterized in that the processing of historical wind speed data comprises the steps of,
let v (t) f (v (t-1), v (t-2),. v (t-n)) (1)
V (t-n) represents historical data from v (t-n) to v (t-1) time, and v (t) is predicted wind speed data, wherein,
each wind speed component of the wind speed is expressed as follows,
v=v b +v s +v a +v v (2)
in the formula (2), v represents the synthetic wind speed, v b 、v s 、v a 、v v Respectively representing the basic wind speed, the gust variable wind speed, the gradual change wind speed and the noise wind speed,
the wind speed probability density function is expressed as follows,
in the formula (3), v represents the wind speed, k represents the shape parameter, c represents the scale parameter, and the dimension is the same as the wind speed
The historical wind speed data is normalized by the formula,
8. An offshore wind farm short term wind speed prediction device, characterized in that the device comprises a memory; and
a processor coupled to the memory, the processor configured to execute instructions stored in the memory, the processor to:
inputting a plurality of wind speed influence meteorological factors into an offshore wind farm short-term wind speed prediction model which is based on a BP neural network and optimizes an initial weight and a threshold value of the BP neural network through a sparrow algorithm, and obtaining short-term wind speed prediction of the offshore wind farm.
9. The prediction apparatus of claim 8, wherein the wind speed affecting meteorological factors include temperature, humidity, and barometric pressure.
10. A storage medium on which a computer program is stored which, when executed by a processor, carries out the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210146830.XA CN114897204A (en) | 2022-02-17 | 2022-02-17 | Method and device for predicting short-term wind speed of offshore wind farm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210146830.XA CN114897204A (en) | 2022-02-17 | 2022-02-17 | Method and device for predicting short-term wind speed of offshore wind farm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114897204A true CN114897204A (en) | 2022-08-12 |
Family
ID=82714916
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210146830.XA Pending CN114897204A (en) | 2022-02-17 | 2022-02-17 | Method and device for predicting short-term wind speed of offshore wind farm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114897204A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116720627A (en) * | 2023-07-28 | 2023-09-08 | 北京工业大学 | Collaborative time sequence prediction method and system for wind speed and wind direction of monitoring station |
CN117875848A (en) * | 2024-03-13 | 2024-04-12 | 中铁四局集团有限公司 | Data warehouse management system based on Internet of things |
CN117875848B (en) * | 2024-03-13 | 2024-06-07 | 中铁四局集团有限公司 | Data warehouse management system based on Internet of things |
-
2022
- 2022-02-17 CN CN202210146830.XA patent/CN114897204A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116720627A (en) * | 2023-07-28 | 2023-09-08 | 北京工业大学 | Collaborative time sequence prediction method and system for wind speed and wind direction of monitoring station |
CN116720627B (en) * | 2023-07-28 | 2024-03-19 | 北京工业大学 | Collaborative time sequence prediction method and system for wind speed and wind direction of monitoring station |
CN117875848A (en) * | 2024-03-13 | 2024-04-12 | 中铁四局集团有限公司 | Data warehouse management system based on Internet of things |
CN117875848B (en) * | 2024-03-13 | 2024-06-07 | 中铁四局集团有限公司 | Data warehouse management system based on Internet of things |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108320016B (en) | Short-term prediction method for building energy consumption | |
CN113762603B (en) | Photovoltaic base station short-term photovoltaic power prediction method based on improved sparrow algorithm optimization | |
CN111144644B (en) | Short-term wind speed prediction method based on variation variance Gaussian process regression | |
JP2013074695A (en) | Device, method and program for predicting photovoltaic generation | |
CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
CN113326969A (en) | Short-term wind speed prediction method and system based on improved whale algorithm for optimizing ELM | |
CN114970952B (en) | Photovoltaic output short-term prediction method and system considering environmental factors | |
CN114462718A (en) | CNN-GRU wind power prediction method based on time sliding window | |
CN111931983A (en) | Precipitation prediction method and system | |
CN112149883A (en) | Photovoltaic power prediction method based on FWA-BP neural network | |
CN114676923A (en) | Method and device for predicting generated power, computer equipment and storage medium | |
CN115877483A (en) | Typhoon path forecasting method based on random forest and GRU | |
Sari et al. | Deep learning approach using the GRU-LSTM hybrid model for Air temperature prediction on daily basis | |
CN114897204A (en) | Method and device for predicting short-term wind speed of offshore wind farm | |
CN114154401A (en) | Soil erosion modulus calculation method and system based on machine learning and observation data | |
CN117458480A (en) | Photovoltaic power generation power short-term prediction method and system based on improved LOF | |
CN117370766A (en) | Satellite mission planning scheme evaluation method based on deep learning | |
CN113095547A (en) | Short-term wind power prediction method based on GRA-LSTM-ICE model | |
CN112307672A (en) | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization | |
CN116526478A (en) | Short-term wind power prediction method and system based on improved snake group optimization algorithm | |
CN116681154A (en) | Photovoltaic power calculation method based on EMD-AO-DELM | |
CN114578087B (en) | Wind speed uncertainty measurement method based on non-dominant sorting and stochastic simulation algorithm | |
CN115907131A (en) | Method and system for building electric heating load prediction model in northern area | |
CN114819382A (en) | Photovoltaic power prediction method based on LSTM | |
CN114139783A (en) | Wind power short-term power prediction method and device based on nonlinear weighted combination |
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 |