CN108985520A - A kind of wind speed forecasting method, device and equipment - Google Patents
A kind of wind speed forecasting method, device and equipment Download PDFInfo
- Publication number
- CN108985520A CN108985520A CN201810870558.3A CN201810870558A CN108985520A CN 108985520 A CN108985520 A CN 108985520A CN 201810870558 A CN201810870558 A CN 201810870558A CN 108985520 A CN108985520 A CN 108985520A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- bird
- data sequence
- nest
- prediction result
- 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
- 238000013277 forecasting method Methods 0.000 title claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 37
- 241000544061 Cuculus canorus Species 0.000 claims abstract description 28
- 238000005457 optimization Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 19
- 235000005770 birds nest Nutrition 0.000 claims description 29
- 235000005765 wild carrot Nutrition 0.000 claims description 29
- 244000000626 Daucus carota Species 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 9
- 230000005611 electricity Effects 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 210000004218 nerve net Anatomy 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002123 temporal effect Effects 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
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of wind speed forecasting methods, it can determine the air speed data sequence for prediction, air speed data sequence is decomposed and reconstructed using wavelet algorithm, and the neural network of the cuckoo algorithm optimization obtained using preparatory training respectively predicts each subsequence, multiple sub- prediction results are obtained, final prediction result is finally determined according to each sub- prediction result.It can be seen that, the characteristics of this method can reduce data fluctuations according to wavelet algorithm, the nonlinearity of air speed data sequence is reduced using wavelet algorithm,, to effectively prevent the problem of neural network falls into local optimum, precision of prediction is finally improved using by cuckoo algorithm optimization neural network simultaneously.The present invention also provides a kind of forecasting wind speed device, equipment and computer readable storage medium, effect is corresponded to the above method.
Description
Technical field
The present invention relates to computer field, in particular to a kind of wind speed forecasting method, device, equipment and computer-readable deposit
Storage media.
Background technique
In recent years, as the fast development of wind energy and utilization, installed capacity of wind-driven power steeply rise, global wind-powered electricity generation industry is flourishing
Development.However, due to the intermittence and randomness of wind-power electricity generation, wind-power electricity generation is combined with traditional power grid system face it is many
Challenge, including energy power generation planning and turbine service scheduling, the variation etc. of network system safe operation and interconnection standards.In order to
Mitigate the above problem caused by wind energy access electric system, carrying out accurate Dynamic Wind Speed prediction by reliable method is just becoming
It is more and more important.Forecasting wind speed is the important channel for obtaining accurate information, facilitates economic load dispatching planning and wind-power electricity generation
Measure the decision of increase and decrease amount.
Currently, most models all concentrate on a forecasting wind speed in document, these methods include Method of Physical Modeling NWP
(numerical weather forecast), time series models, artificial intelligence model and mixed model.But these models all have some lack
The problem of point, on the one hand the single neural network prediction model of tradition easily falls into local optimum, the prediction effect that cannot be optimal
On the other hand fruit is that single prediction technique is difficult to handle influence of the nonlinearity of air speed data to prediction result.
As it can be seen that traditional prediction model is easily trapped into local optimum, and the air speed data for handling nonlinearity is relatively more tired
It is difficult.
Summary of the invention
The object of the present invention is to provide a kind of wind speed forecasting method, device, equipment and computer readable storage medium, to
It solves traditional prediction model and is easily trapped into local optimum, and the problem that the air speed data for handling nonlinearity is relatively difficult.
In order to solve the above technical problems, the present invention provides a kind of wind speed forecasting methods, comprising:
Determine the historical wind speed data sequence for prediction；
The historical wind speed data sequence is decomposed into multiple subsequences using wavelet algorithm, and to each subsequence
It is reconstructed；
The neural network of the cuckoo algorithm optimization obtained using preparatory training respectively carries out each subsequence pre-
It surveys, obtains sub- prediction result；
According to each sub- prediction result, final prediction result is determined.
Wherein, the formula that the historical wind speed data sequence is decomposed into multiple subsequences using wavelet algorithm are as follows:
Decomposed signalWherein, f (u) is the historical wind speed data sequence pair
The continuous function answered, a=2-j, g=k2-j, k is Decomposition order, and ψ () is mother wavelet function；
The formula that each subsequence is reconstructed are as follows:
Wherein CψFor parameter of consistency, and Cψ< ∞.
Wherein, the Decomposition order k is 3, and the quantity of the subsequence is 4.
Wherein, the training process of the neural network of the cuckoo algorithm optimization includes:
It is random to generate initial populationThe initial population includes M Bird's Nest,It is described
I-th of Bird's Nest in initial population, the Bird's Nest indicate the weight and threshold value for the neural network that one group of needs is trained；
When each iteration starts, according to Lay dimension flight theory to t-1 for populationIn
Each Bird's Nest is updated, and is obtainedWherein 1≤t≤T；
It calculatesIn each Bird's Nest fitness, and compareWithFitness size, ifFitness be less thanFitness, then willIt updatesThe position at place, whereinIt is t-1 for population
In i-th of Bird's Nest；
It generates random number r ∈ (0,1), and compares the size of r and Pa, wherein Pa is preset probability of detection；
If r > Pa, an arbitrary width is generated, and with arbitrary width updateIt obtains
T is for population
If r < Pa, according toIt is rightIn it is each
A Bird's Nest is updated, and obtains t for populationWherein, random dimension d1∈ (1, D), random dimension
d2∈ (1, D), D are the dimension of Bird's Nest；
It calculatesIn each Bird's Nest fitness, and compareWithFitness size, ifFitness be greater thanFitness, then willIt updatesThe position at place；
Judge whether t is equal to T；If being not equal to, t=t+1 simultaneously continues iteration；If being equal to, it is determined that the t generation
PopulationThe middle maximum Bird's Nest of fitnessBy Bird's NestAs the neural network weight and
Threshold value, to complete the training of the neural network of the cuckoo algorithm optimization.
Wherein, described with arbitrary width updateFormula specifically:
Wherein, α is step size controlling amount, and L (λ) is random search path,Multiply to be point-to-point
Method.
Wherein, historical wind speed data sequence of the determination for predicting includes:
It determines the historical wind speed data sequence for prediction, and the historical wind speed data sequence is pre-processed.
Wherein, described according to each sub- prediction result, determine that final prediction result includes:
To each sub- prediction result summation, final prediction result is obtained.
Corresponding, the present invention also provides a kind of forecasting wind speed devices, comprising:
Determining module: for determining the historical wind speed data sequence for prediction；
Decomposed and reconstituted module: for the historical wind speed data sequence to be decomposed into multiple subsequences using wavelet algorithm,
And each subsequence is reconstructed；
Sub- prediction result determining module: for being distinguished using the neural network for the cuckoo algorithm optimization that training obtains in advance
Each subsequence is predicted, sub- prediction result is obtained；
Final prediction result determining module: for determining final prediction result according to each sub- prediction result.
In addition, the present invention also provides a kind of forecasting wind speed equipment, comprising:
Memory: for storing computer program；
Processor: the step of for executing the computer program to realize a kind of wind speed forecasting method as described above.
Finally, being deposited on the computer readable storage medium the present invention also provides a kind of computer readable storage medium
Computer program is contained, a kind of step of wind speed forecasting method as described above is realized when the computer program is executed by processor
Suddenly.
A kind of wind speed forecasting method provided by the present invention, can determine the air speed data sequence for prediction, and utilization is small
Wave algorithm is decomposed and is reconstructed to air speed data sequence, and utilizes the nerve net for the cuckoo algorithm optimization that training obtains in advance
Network respectively predicts each subsequence, obtains multiple sub- prediction results, is finally determined according to each sub- prediction result final
Prediction result.As it can be seen that the characteristics of this method can reduce data fluctuations according to wavelet algorithm, reduces wind using wavelet algorithm
The nonlinearity of fast data sequence, while using process cuckoo algorithm optimization neural network to effectively prevent nerve net
Network falls into the problem of local optimum, finally improves precision of prediction.
The present invention also provides a kind of forecasting wind speed device, equipment and computer readable storage medium, effect with it is above-mentioned
Method is corresponding, and which is not described herein again.
Detailed description of the invention
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present invention or the prior art
Attached drawing needed in technical description is briefly described, it should be apparent that, the accompanying drawings in the following description is only this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of implementation flow chart of wind speed forecasting method embodiment provided by the invention；
Fig. 2 is a kind of training process schematic diagram of the neural network of cuckoo optimization provided in this embodiment；
Fig. 3 is a kind of structural block diagram of forecasting wind speed Installation practice provided by the invention.
Specific embodiment
Core of the invention is to provide a kind of wind speed forecasting method, device, equipment and computer readable storage medium, reduces
Air speed data sequence for prediction it is non-linear, it is thus also avoided that neural network falls into the problem of local optimum, improve pre-
Survey precision.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiments are only a part of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
A kind of wind speed forecasting method embodiment provided by the invention is introduced below, referring to Fig. 1, the embodiment packet
It includes:
Step S101: the historical wind speed data sequence for prediction is determined.
Specifically, available continuous 4 weeks air speed datas, temporal resolution can be 1h, i.e., one day includes 24 numbers
Strong point.Data are divided into two subsets, trained and neural network and prediction of wind speed are respectively used to, specifically, can be by first three
The air speed data in week is used as training sample, the neural network optimized namely for the cuckoo mentioned in training step S103
Sample, using the air speed data in last week as the historical wind speed data sequence being previously mentioned in forecast sample, that is, step S101
Column.
After determining historical wind speed data sequence, it can be pre-processed, in order to carry out subsequent step.
Step S102: the historical wind speed data sequence is decomposed into multiple subsequences using wavelet algorithm, and to each
The subsequence is reconstructed.
Existing certain decomposition techniques are a kind of adaptive to the not apparent effect of forecasting wind speed precision, wavelet algorithm is improved
Induction signal processing technique, it can obtain the appropriate component and details of original series, reduce the instability of data sequence.
Specifically, the historical wind speed data sequence is decomposed into multiple subsequences and can be divided into following decomposition by above-mentioned utilization wavelet algorithm
Two parts of a reconstruct:
Decomposed signalWherein, f (u) is the historical wind speed data sequence pair
The continuous function answered, a=2-j, g=k2-j, k is Decomposition order, and ψ () is mother wavelet function.
The formula that each subsequence is reconstructed are as follows:
Wherein CψFor parameter of consistency, and Cψ< ∞.
Decomposition order described in the present embodiment can be 3, correspondingly, the quantity of the subsequence can be 4.
Step S103: the neural network of the cuckoo algorithm optimization obtained using preparatory training is respectively to each sub- sequence
Column are predicted, sub- prediction result is obtained.
Specifically, carrying out the forecasting wind speed of 1h in advance to each subsequence using the neural network that cuckoo optimizes, obtain
Sub- prediction result.
For the specific implementation process of step S103, does not do expansion first here and introduce, it can hereafter be retouched in detail
It states.
Step S104: according to each sub- prediction result, final prediction result is determined.
It specifically can be by summing to each sub- prediction result, obtain final prediction result.
Each subsequence is predicted respectively using the neural network of cuckoo algorithm optimization in the present embodiment, with
Conventional neural network model is compared, and the neural network model after being optimized using optimization algorithm compensates for many deficiencies, it is avoided
The parameter of neural network falls into the defect of local optimum, improves the generalization ability of neural network.Some scholars have used greatly
The function of amount, which carries out test, proves cuckoo algorithm (cuckoo search, CS) in some aspects better than particle swarm algorithm and something lost
Propagation algorithm, advantage are embodied in: ability of searching optimum is strong, fast convergence rate, institute's containing parameter are few, versatility and robustness, the advantages that,
Therefore CS algorithm is widely used in solving many practical problems.CS Optimized model is used for share price by such as some documents, wind speed is predicted
In field, so that precision of prediction increases.
Referring to fig. 2, below will be to step S103, that is, the training process of neural network of cuckoo algorithm optimization carries out
Description in detail, mainly comprises the steps that
Step S1031: initial population is generated at randomThe initial population includes M Bird's Nest,For i-th of Bird's Nest in the initial population, the Bird's Nest indicate the neural network that one group of needs is trained weight and
Threshold value.
Step S1032: when each iteration starts, according to Lay dimension flight theory to t-1 for populationIn each Bird's Nest be updated, obtainWherein 1≤t≤T.
Step S1033: it calculatesIn each Bird's Nest fitness, and compareWithIt is suitable
Response size, ifFitness be less thanFitness, then willIt updatesThe position at place, whereinFor
T-1 is for i-th of Bird's Nest in population.
Step S1034: generating random number r ∈ (0,1), and compare the size of r and Pa, and wherein Pa is that preset discovery is general
Rate.
Step S1035: if r > Pa, an arbitrary width is generated, and with arbitrary width updateT is obtained for population
Specifically, described with arbitrary width updateFormula specifically:
Wherein, α is step size controlling amount, and L (λ) is random search path,Multiply to be point-to-point
Method.
Step S1036: if r < Pa, according toIt is right
In each Bird's Nest be updated, obtain t for populationWherein, random dimension d1∈ (1, D), with
Machine dimension d2∈ (1, D), D are the dimension of Bird's Nest.
Step S1037: it calculatesIn each Bird's Nest fitness, and compareWithIt is suitable
Response size, ifFitness be greater thanFitness, then willIt updatesThe position at place.
Step S1038: judge whether t is equal to T；If being not equal to, t=t+1 simultaneously continues iteration.
Step S1039: if being equal to, it is determined that the t is for populationThe middle maximum bird of fitness
NestBy Bird's NestAs the weight and threshold value of the neural network, to complete the nerve net of the cuckoo algorithm optimization
The training of network.
To prove that the present embodiment effectively increases precision of prediction, the present invention also provides the forecasting wind speed precision of different models
Comparative test, specific as follows:
Include following three schemes for what is compared with the present embodiment: individual neural network (BP), cuckoo are calculated
Method optimization neural network (CS-BP) and improvement cuckoo algorithm optimization neural network model (ICS-BP) model.
This embodiment scheme is specific as follows: carrying out wavelet decomposition (WD) to air speed data sequence, each son obtained to decomposition
Sequence establishes the prediction model progress model training for improving cuckoo algorithm (ICS) optimization neural network (BP) and prediction, will be each
The prediction result of subsequence is superimposed to obtain wind speed actual prediction value.Fig. 3 is the prediction effect figure of WD-ICS-BP.
The prediction model (WD-ICS-BP) of BP, CS-BP, ICS-BP and this embodiment scheme is done into error comparative analysis, accidentally
Difference comparison is as shown in table 1.As it can be seen from table 1 being predicted from traditional BP, predicted to CS-BP and ICS-BP, then arrives WD-ICS-
BP prediction, precision of prediction are improving step by step.
Table 1
In summary, nonlinearity data can not be handled for existing forecasting wind speed model, and is easily trapped into office
The optimal problem in portion.Wavelet algorithm is utilized as a kind of Adaptive Signal Processing technology in the present embodiment, can obtain data sequence
Appropriate component and details, the characteristics of reducing the instability of data sequence, also use improved cuckoo algorithm
The neural network model convergence rate of optimization faster, improves the generalization ability of neural network, solves the later period and easily falls into part
Optimal feature ultimately provides a kind of wind speed forecasting method, is decomposed using wavelet algorithm to air speed data sequence and again
Structure, and the neural network of the cuckoo algorithm optimization obtained using preparatory training respectively predicts each subsequence, obtains
Multiple sub- prediction results finally determine final prediction result according to each sub- prediction result.Effectively reduce air speed data sequence
Nonlinearity, while falling into part using by cuckoo algorithm optimization neural network to effectively preventing neural network
Optimal problem, finally improves precision of prediction.This method can be applied to the section of electric system and generation of electricity by new energy related fields
Research and engineer application are learned, the generalization ability and precision of prediction of prediction model can be improved.
A kind of forecasting wind speed Installation practice provided in an embodiment of the present invention is introduced below, one kind described below
Forecasting wind speed device can correspond to each other reference with a kind of above-described wind speed forecasting method.
Referring to Fig. 3, which includes:
Determining module 301: for determining the historical wind speed data sequence for prediction.
Decomposed and reconstituted module 302: for the historical wind speed data sequence to be decomposed into multiple sub- sequences using wavelet algorithm
Column, and each subsequence is reconstructed.
Sub- prediction result determining module 303: for the neural network using the cuckoo algorithm optimization that training obtains in advance
Each subsequence is predicted respectively, obtains sub- prediction result.
Final prediction result determining module 304: for determining final prediction result according to each sub- prediction result.
A kind of forecasting wind speed device provided in this embodiment is for realizing a kind of wind speed forecasting method above-mentioned, therefore the dress
The embodiment part of the visible wind speed forecasting method one of above of specific embodiment in setting, for example, determining module 301,
Decomposed and reconstituted module 302, sub- prediction result determining module 303, final prediction result determining module 304, are respectively used in realization
State step S101, S102, S103, S104 in a kind of forecasting wind speed device.So specific embodiment is referred to accordingly
The description of various pieces embodiment, herein not reinflated introduction.
In addition, since a kind of forecasting wind speed device provided in this embodiment is for realizing a kind of forecasting wind speed side above-mentioned
Method, therefore its effect is corresponding with the effect of the above method, which is not described herein again.
In addition, the present invention also provides a kind of forecasting wind speed equipment, comprising:
Memory: for storing computer program；
Processor: the step of for executing the computer program to realize a kind of wind speed forecasting method as described above.
Finally, being deposited on the computer readable storage medium the present invention also provides a kind of computer readable storage medium
Computer program is contained, a kind of step of wind speed forecasting method as described above is realized when the computer program is executed by processor
Suddenly.
A kind of forecasting wind speed equipment provided by the invention and computer readable storage medium are for realizing one kind above-mentioned
Wind speed forecasting method, therefore its specific embodiment is referred to the description of corresponding various pieces embodiment, no longer opens up herein
Open introduction.Furthermore, it is to be understood that its effect is also corresponding with the effect of the above method, also repeat no more here.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part
Explanation.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above to a kind of wind speed forecasting method provided by the present invention, device, equipment and computer readable storage medium
It is described in detail.Used herein a specific example illustrates the principle and implementation of the invention, the above reality
The explanation for applying example is merely used to help understand method and its core concept of the invention.It should be pointed out that for the art
For those of ordinary skill, without departing from the principle of the present invention, can with several improvements and modifications are made to the present invention,
These improvements and modifications also fall within the scope of protection of the claims of the present invention.
Claims (10)
1. a kind of wind speed forecasting method characterized by comprising
Determine the historical wind speed data sequence for prediction；
The historical wind speed data sequence is decomposed into multiple subsequences using wavelet algorithm, and each subsequence is carried out
Reconstruct；
The neural network of the cuckoo algorithm optimization obtained using preparatory training respectively predicts each subsequence, obtains
To sub- prediction result；
According to each sub- prediction result, final prediction result is determined.
2. the method as described in claim 1, which is characterized in that described to utilize wavelet algorithm by the historical wind speed data sequence
It is decomposed into the formula of multiple subsequences are as follows:
Decomposed signalWherein, f (u) is that the historical wind speed data sequence is corresponding
Continuous function, a=2-j, g=k2-j, k is Decomposition order, and ψ () is mother wavelet function；
The formula that each subsequence is reconstructed are as follows:
Wherein CψFor parameter of consistency, and Cψ< ∞.
3. method according to claim 2, which is characterized in that the Decomposition order k is 3, and the quantity of the subsequence is 4.
4. the method as described in claim 1, which is characterized in that the training process of the neural network of the cuckoo algorithm optimization
Include:
It is random to generate initial populationThe initial population includes M Bird's Nest,It is described initial
I-th of Bird's Nest in population, the Bird's Nest indicate the weight and threshold value for the neural network that one group of needs is trained；
When each iteration starts, according to Lay dimension flight theory to t-1 for populationIn it is each
Bird's Nest is updated, and is obtainedWherein 1≤t≤T；
It calculatesIn each Bird's Nest fitness, and compareWithFitness size, if
Fitness be less thanFitness, then willIt updatesThe position at place, whereinIt is t-1 in population
I-th of Bird's Nest；
It generates random number r ∈ (0,1), and compares the size of r and Pa, wherein Pa is preset probability of detection；
If r > Pa, an arbitrary width is generated, and with arbitrary width updateObtain t
For population
If r < Pa, according toIt is rightIn each bird
Nest is updated, and obtains t for populationWherein, random dimension d1∈ (1, D), random dimension d2∈
(1, D), D are the dimension of Bird's Nest；
It calculatesIn each Bird's Nest fitness, and compareWithFitness size, if's
Fitness is greater thanFitness, then willIt updatesThe position at place；
Judge whether t is equal to T；If being not equal to, t=t+1 simultaneously continues iteration；If being equal to, it is determined that the t is for populationThe middle maximum Bird's Nest of fitnessBy Bird's NestWeight and threshold as the neural network
Value, to complete the training of the neural network of the cuckoo algorithm optimization.
5. method as claimed in claim 4, which is characterized in that described with arbitrary width update
Formula specifically:
Wherein, α is step size controlling amount, and L (λ) is random search path,For point-to-point multiplication.
6. the method as described in claim 1, which is characterized in that historical wind speed data sequence packet of the determination for prediction
It includes:
It determines the historical wind speed data sequence for prediction, and the historical wind speed data sequence is pre-processed.
7. the method as described in claim 1, which is characterized in that it is described according to each sub- prediction result, it determines final pre-
Surveying result includes:
To each sub- prediction result summation, final prediction result is obtained.
8. a kind of forecasting wind speed device characterized by comprising
Determining module: for determining the historical wind speed data sequence for prediction；
Decomposed and reconstituted module: for the historical wind speed data sequence to be decomposed into multiple subsequences using wavelet algorithm, and it is right
Each subsequence is reconstructed；
Sub- prediction result determining module: for the neural network using the cuckoo algorithm optimization that training obtains in advance respectively to each
A subsequence is predicted, sub- prediction result is obtained；
Final prediction result determining module: for determining final prediction result according to each sub- prediction result.
9. a kind of forecasting wind speed equipment characterized by comprising
Memory: for storing computer program；
Processor: for executing the computer program to realize that a kind of wind speed as described in claim 1-7 any one is pre-
The step of survey method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes a kind of forecasting wind speed as described in claim 1-7 any one when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810870558.3A CN108985520A (en) | 2018-08-02 | 2018-08-02 | A kind of wind speed forecasting method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810870558.3A CN108985520A (en) | 2018-08-02 | 2018-08-02 | A kind of wind speed forecasting method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108985520A true CN108985520A (en) | 2018-12-11 |
Family
ID=64554589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810870558.3A Pending CN108985520A (en) | 2018-08-02 | 2018-08-02 | A kind of wind speed forecasting method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985520A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458364A (en) * | 2019-08-16 | 2019-11-15 | 东莞理工学院 | A kind of smoothed data preprocess method of short-term load forecasting |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408529A (en) * | 2014-11-21 | 2015-03-11 | 广东工业大学 | Short-term load predicting method of power grid |
| CN106503793A (en) * | 2016-10-25 | 2017-03-15 | 广东工业大学 | A kind of neural network short-term wind speed forecasting method based on improvement difference algorithm |
| CN106557840A (en) * | 2016-11-14 | 2017-04-05 | 中南大学 | A kind of high wind line of high-speed railway wind speed adaptive decomposition Forecasting Methodology |
| CN106779151A (en) * | 2016-11-14 | 2017-05-31 | 中南大学 | A kind of line of high-speed railway wind speed multi-point multi-layer coupling prediction method |
| CN107506861A (en) * | 2017-08-25 | 2017-12-22 | 广东工业大学 | A kind of short-term wind speed forecasting method, apparatus and system |
-
2018
- 2018-08-02 CN CN201810870558.3A patent/CN108985520A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408529A (en) * | 2014-11-21 | 2015-03-11 | 广东工业大学 | Short-term load predicting method of power grid |
| CN106503793A (en) * | 2016-10-25 | 2017-03-15 | 广东工业大学 | A kind of neural network short-term wind speed forecasting method based on improvement difference algorithm |
| CN106557840A (en) * | 2016-11-14 | 2017-04-05 | 中南大学 | A kind of high wind line of high-speed railway wind speed adaptive decomposition Forecasting Methodology |
| CN106779151A (en) * | 2016-11-14 | 2017-05-31 | 中南大学 | A kind of line of high-speed railway wind speed multi-point multi-layer coupling prediction method |
| CN107506861A (en) * | 2017-08-25 | 2017-12-22 | 广东工业大学 | A kind of short-term wind speed forecasting method, apparatus and system |
Non-Patent Citations (1)
| Title |
|---|
| 殷豪，曾云等: "基于奇异谱分析-模糊信息粒化和极限学习机的风速多步区间预测", 《电网技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458364A (en) * | 2019-08-16 | 2019-11-15 | 东莞理工学院 | A kind of smoothed data preprocess method of short-term load forecasting |
| CN110458364B (en) * | 2019-08-16 | 2021-10-15 | 东莞理工学院 | Smooth data preprocessing method for short-term load prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108985521A (en) | Output power predicting method, device, equipment and the medium of photovoltaic generating system | |
| CN107124394A (en) | A kind of powerline network security postures Forecasting Methodology and system | |
| Liu et al. | Short-term photovoltaic power prediction on modal reconstruction: A novel hybrid model approach | |
| CN109034484A (en) | A kind of wind speed forecasting method, device and equipment | |
| CN107947164A (en) | It is a kind of to consider multiple uncertain and correlation electric system Robust Scheduling method a few days ago | |
| CN110309603A (en) | A kind of short-term wind speed forecasting method and system based on wind speed characteristics | |
| CN107977744A (en) | A kind of electric system based on traditional Benders decomposition methods Robust Scheduling method a few days ago | |
| CN110751318A (en) | IPSO-LSTM-based ultra-short-term power load prediction method | |
| CN112785027B (en) | Wind-solar-storage combined power generation system confidence capacity evaluation method and system | |
| CN107204615A (en) | A kind of method and system for realizing power prediction | |
| CN109063902A (en) | A kind of short-term load forecasting method, device, equipment and storage medium | |
| CN110264012A (en) | Renewable energy power combination prediction technique and system based on empirical mode decomposition | |
| CN109242169A (en) | A kind of short-term load forecasting method towards large power customers | |
| CN113285490A (en) | Power system scheduling method and device, computer equipment and storage medium | |
| Liu et al. | Wind power short-term forecasting based on LSTM neural network with dragonfly algorithm | |
| CN109214546A (en) | A kind of Power Short-Term Load Forecasting method based on improved HS-NARX neural network | |
| Sun et al. | Forecasting Carbon Dioxide Emissions in China Using Optimization Grey Model. | |
| CN107358059A (en) | Short-term photovoltaic energy Forecasting Methodology and device | |
| CN108985520A (en) | A kind of wind speed forecasting method, device and equipment | |
| CN112613650B (en) | Novel three-stage short-term power load prediction method | |
| CN115528750B (en) | Power grid safety and stability oriented data model hybrid drive unit combination method | |
| CN110059840B (en) | Method and system for selecting address of battery energy storage system in receiving-end power grid | |
| CN113779861B (en) | Photovoltaic Power Prediction Method and Terminal Equipment | |
| CN115965124A (en) | Dynamic optimization control method and system for orderly charging of electric automobile in transformer area | |
| CN106682760A (en) | Wind power climbing prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181211 |
|
| RJ01 | Rejection of invention patent application after publication |