CN104112166A - Short-term wind speed prediction method and system of wind power felid - Google Patents
Short-term wind speed prediction method and system of wind power felid Download PDFInfo
- Publication number
- CN104112166A CN104112166A CN201410217851.1A CN201410217851A CN104112166A CN 104112166 A CN104112166 A CN 104112166A CN 201410217851 A CN201410217851 A CN 201410217851A CN 104112166 A CN104112166 A CN 104112166A
- Authority
- CN
- China
- Prior art keywords
- neural network
- wind speed
- short
- wind
- term
- 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 abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims description 63
- 238000012549 training Methods 0.000 claims description 31
- 238000013277 forecasting method Methods 0.000 claims description 15
- 238000006467 substitution reaction Methods 0.000 claims description 7
- 230000001537 neural effect Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 abstract 1
- 238000011161 development Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000005611 electricity Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 101100269885 Arabidopsis thaliana ANN1 gene Proteins 0.000 description 1
- 206010003694 Atrophy Diseases 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000037444 atrophy Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000010348 incorporation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- 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
Abstract
The invention discloses a short-term wind speed prediction method and system of a wind power felid. The method and system involve, first of all, obtaining a wind speed of the wind power field and then substituting the wind speed to a nerve network which is constructed in advance so as to calculate wind speed data in a future period. The prediction method can be used for predicting the wind speed data of the wind power field in the future period and accordingly predicting output power according to the wind speed data and a power curve of a blower fan, such that an electric power scheduling department can adjust a scheduling plan timely.
Description
Technical field
The application relates to wind power technology field, more particularly, relates to a kind of short-term wind speed forecasting method and system of wind energy turbine set.
Background technology
Wind energy is a kind of regenerative resource of cleaning, and its advantage is not need fuel, does not occupy cultivated land, pollutes less, reserves are large.Along with the energy and environmental issue become increasingly conspicuous, countries in the world are all at the Renewable Energy Development generation technology of sparing no effort.Wind-power electricity generation is with fastest developing speed and maturation the most a kind of in renewable energy power generation technology, has possessed technology and the economic condition of large-scale commercial applications exploitation.
In recent years, the new forms of energy such as China investment wind energy, sun power as warm as before, since from 2009, wind-powered electricity generation mark post rate for incorporation into the power network was implemented on the bank, Development of Wind Power In China has experienced high speed development, atrophy suddenly and of short duration adjustment period.2014, Wind Power In China will be in stable and positive policy environment, sane development.It is predicted, within 2014, the newly-increased wind-powered electricity generation installation scale in the whole nation is 1,400 ten thousand kilowatts.
But due to the height random of wind and the feature such as intermittent, a large amount of wind-powered electricity generations access electrical networks bring severe challenge to power supply and demand balance, power system security and the quality of power supply, thereby have limited the scale of Wind Power Development.An effective way of head it off is carries out short-term forecasting to the wind speed of wind energy turbine set, and then predicts its output power according to the powertrace of blower fan; By predicting the outcome, power scheduling department can shift to an earlier date and adjust in time operation plan, reduces margin capacity, the reduction Operation of Electric Systems cost of electric system simultaneously.Therefore need a kind of short-term wind speed forecasting method and system that minute field gas velocity is carried out to short-term forecasting badly.
Summary of the invention
In view of this, the application provides a kind of short-term wind speed forecasting method and system of wind energy turbine set, for the air speed data of wind energy turbine set period in future is predicted, for providing power scheduling foundation to power scheduling department.
To achieve these goals, the existing scheme proposing is as follows:
A short-term wind speed forecasting method for wind energy turbine set, comprises the steps:
Obtain the wind velocity signal of wind energy turbine set;
Described wind velocity signal is updated to the neural network building in advance, calculates the air speed data of period in the future.
Preferably, described neural network builds as follows:
Build initial neural network;
Choose training sample;
Utilize described training sample to train described initial neural network;
Utilize training result to described initial neural network initialize, obtain described neural network.
Preferably, described neural network comprises 3 layers of BP subnet.
Preferably, the concealed nodes number of described neural network is 6～10.
Preferably, described concealed nodes number is 9.
A short-term wind speed forecasting system for wind energy turbine set, comprises the steps:
Acquisition module, is disposed at wind energy turbine set, for obtaining described wind speed;
Calculate output module, for described wind velocity signal being updated to the neural network building in advance, calculate and export the air speed data of period in the future.
Preferably, described calculating output module comprises:
Construction unit, for building initial neural network;
Input block, for receiving training sample;
Training unit, for utilizing described training sample to train described initial neural network;
Assignment unit, for utilizing training result to described initial neural network initialize, obtains neural network;
Computing unit, for obtaining and export described air speed data by neural computing described in described wind speed substitution.
Preferably, described neural network comprises 3 layers of BP subnet.
Preferably, the concealed nodes number of described neural network is 6～10.
Preferably, described concealed nodes number is 9.
From technique scheme, can find out, the application provides a kind of short-term wind speed forecasting method and system of wind energy turbine set, first this method and system obtain the wind speed of wind energy turbine set, the neural network then wind speed substitution being built in advance, thus calculate the air speed data of period in the future.Be that this Forecasting Methodology can be predicted the air speed data of wind energy turbine set period in future, and then can predict output power according to the powertrace of this air speed data and blower fan, thereby power scheduling department can adjust operation plan in time.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present application or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiment of the application, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
The process flow diagram of the short-term wind speed forecasting method of a kind of wind energy turbine set that Fig. 1 provides for the embodiment of the present application;
Fig. 2 is the structural drawing of the initial neural network of the embodiment of the present application;
Fig. 3 is the structural drawing of three layers of BP network of standard of the embodiment of the present application;
Fig. 4 is the short-term wind speed forecasting result figure of the embodiment of the present application;
The structural drawing of the short-term wind speed forecasting system of a kind of wind energy turbine set that Fig. 5 provides for another embodiment of the application.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present application, the technical scheme in the embodiment of the present application is clearly and completely described, obviously, described embodiment is only the application's part embodiment, rather than whole embodiment.Embodiment based in the application, those of ordinary skills are not making the every other embodiment obtaining under creative work prerequisite, all belong to the scope of the application's protection.
Embodiment mono-
The process flow diagram of the short-term wind speed forecasting method of a kind of wind energy turbine set that Fig. 1 provides for the embodiment of the present application.
The short-term wind speed forecasting method of the wind energy turbine set that as shown in Figure 1, the present embodiment provides comprises the steps:
S100: obtain wind energy turbine set wind speed.
S200: calculate the air speed data of period in the future.
The neural network that the wind speed substitution of the wind energy turbine set of obtaining is built in advance, calculates the air speed data of period in the future.
From technique scheme, can find out, the present embodiment provides a kind of short-term wind speed forecasting method of wind energy turbine set, first obtains the wind speed of wind energy turbine set, the neural network then wind speed substitution being built in advance, thus calculate the air speed data of period in the future.Be that this Forecasting Methodology can be predicted the air speed data of wind energy turbine set period in future, and then can predict output power according to the powertrace of this air speed data and blower fan, thereby power scheduling department can adjust operation plan in time.
Neural network in the present embodiment builds as follows:
S201: build initial neural network.
The structure of initial neural network as shown in Figure 2, ANN, ANN ..., ANN formed BP network group, wherein ANN ..., the ANN BP subnet that is network group.Be i BP subnet input (wherein, i=1,2 ..., n; J=1,2 ..., m), for network output.Network group has reduced the input quantity of each network, thereby has accelerated the speed of convergence of network.
For neural network group's BP subnet, its input is actual measurement air speed value, is output as and the prediction of wind speed of surveying wind speed time corresponding point.The BP subnet of choosing in the present invention is three layers of BP network of standard, as shown in Figure 3.
The wind speed time needs coupling mutually.As shown in table 1, when τ and m get 8, the error of prediction is minimum, be 6.68%, and the predicated error of other combination is also smaller, approaches 6.68%.
The optimum matching of table 1 wind speed time series m and τ
S202: choose training sample.
BP network obtains knowledge by the study to sample, and for a neural network, obtaining of sample is particularly important.In neural network group structure, sample is also divided into the sample of BP subnet ANN1～ANNn and sample two parts of general comment network A NN0.The sample of BP subnet be actual wind speed value on the basis of phase space reconfiguration, extract phase space reference point.The output that the sample of total matching network A NN0 is each subnet, i.e. the prediction output to same time point.
The data of obtaining by assessment, do not have unified dimension, therefore will quantize and normalized processing primary data.For different BP subnets, processing mode is similar, the hidden layer of BP neural network generally adopts Sigmoid transfer function, for the saturation region that improves training speed and sensitivity and effectively avoid Sigmoid function, therefore, to quantize and normalized input data, make import-restriction between 0～1.This method can reduce the randomness of sample greatly, the speed of accelerating network convergence.
Subnet model is the neural network prediction model based on chaos phase space reconstruction,, on the basis of phase space reconfiguration, extracts phase space reference point and trains as BP neural network sample.By BP neural network, carrying out fitting reconfiguration function, wherein, be used as the input layer sample of neural network, is exactly the Output rusults of neural network.Subnet selects 3,, three groups of average error minimum in match condition, and in Table 2.The subnet of each neural network group structure is selected 3 layers, and the input layer dimension of network is got respectively the more excellent embedding dimension of chaos phase space reconstruction, and output dimension is 1, is exactly the output of prediction.Hidden layer dimension is 10.The model of total matching network is conventional 3 layers of BP pessimistic concurrency control.Input layer dimension is 3 herein, and the number of hidden nodes is 10, and output dimension is 1.
Table 2 subnet Choice
S203: utilize described training sample to train described initial neural network.
Facts have proved: three layers of BP neural network can be simulated the Nonlinear Mapping relation between any input and output.Therefore the application also adopts this topology network architecture that only has a hidden layer.Being chosen in BP network of the number of hidden nodes plays conclusive effect, and nodes very little learning outcome may not restrained, and increases the number of hidden nodes, the mapping ability of network is stronger, but easily cause overtraining, can reduce the fault-tolerance of network, when easily making to train, occur " over-fitting ".Through a large amount of emulation, find, for input less (<4), the number of hidden nodes selects 6～10 to be best.When input is more, generally choose 9 the number of hidden nodes, when rolling up the number of hidden nodes, can reduce the training speed of network.
For the BP network group structure proposing in the application, the coordination between neural subnet is particularly important.In training, be mutually independently between BP subnet, each neural subnet output sample is given and preservation, all BP subnet results are as the input of total matching network A NN0.
Owing to will note rationality and the popularity of sample when choosing training sample, the present invention chooses air speed data in front 30 days 10 minutes January, i.e. 4320 points, as the input sample of subnet.Because subnet is in conjunction with the more excellent embedding dimension of chaos phase space reconstruction, by program optimization means, make subnet accomplish limit training limit prediction of output sample herein, can shorten program runtime like this, be also that data processing is more convenient.Therefore next introduce the formation of test sample book of the training sample of total net.
By subnet, input above-mentioned 4320 air speed data points, utilize subnet to dope the wind speed of whole day on the 31st in January, subnet is predicted 144 points continuously.Wherein front 132 points are as the training sample of total net, and rear 12 points are as the test sample book of total net.Owing to having chosen 3 subnets, therefore training sample and test sample book are 3 groups of data, in Table 3.
The total net training sample of table 3
S204: utilize training result to initial neural network initialize, obtain neural network.
The application is with first 30 days of January of Fujin, Heilungkiang wind energy turbine set, and 4320 10 minutes air speed datas are data inputs, and according to above-mentioned sample, by total net ANN0 matching, neural network group structure is made a prediction to the air speed data on January 31, predicts the outcome as table 4 and Fig. 4.
By table 4, can find out, it is 9.97%, 7.21%, 7.36% that the average error that each BP subnet is predicted is separately respectively, and that is to say, least error is still 7.21%.And the average error of neural network group structure prediction is 5.98%, 6.68% also more excellent before.In addition, by precision of prediction 10% with interior statistics, each subnet all only has 58.33% 10% with interior, and the precision of prediction of neural network group structure has 83.33% 10% with interior, has improved nearly 50%.These all show to adopt neural network group structure to predict example of calculation shows, and precision is higher, and tool has great advantage.As seen in Figure 4, neural network group structure prediction of wind speed is more consistent with actual measurement wind speed trend, fluctuates less, can play the resultant effect that each neural network subnet is had complementary advantages, and has practical feasibility.
Table 4 neural network group structure forecasting wind speed result
Embodiment bis-
The structural drawing of the short-term wind speed forecasting system of a kind of wind energy turbine set that Fig. 5 provides for another embodiment of the application.
The short-term wind speed forecasting system of the wind energy turbine set that as shown in Figure 5, the present embodiment provides comprises acquisition module 100 and coupled calculating output module 200.
Acquisition module 100 is for obtaining the wind speed in a multiple spot place of wind energy turbine set.
Calculate the neural network of output module 200 for the wind speed substitution of obtaining from wind energy turbine set is built in advance, calculate the air speed data of period in the future.
From technique scheme, can find out, the present embodiment provides a kind of short-term wind speed forecasting system of wind energy turbine set, comprise acquisition module and calculate output module, first computing module obtains the wind speed of wind energy turbine set, calculates output module for calculate the air speed data of period in the future according to the wind gage of input.Be that this Forecasting Methodology can be predicted the air speed data of wind energy turbine set period in future, and then can predict output power according to the powertrace of this air speed data and blower fan, thereby power scheduling department can adjust operation plan in time.
Calculating output module 200 in the present embodiment comprises construction unit 201, input block 202, training unit 203, assignment unit 204 and computing unit 205.
Construction unit 201 is for building initial neural network.
Input block 202 is for receiving training sample;
Training unit 203 is for utilizing training sample to train initial neural network;
Assignment unit 204, for utilizing training result to initial neural network initialize, obtains neural network;
Computing unit 205 is for obtaining and export air speed data by wind velocity signal substitution neural computing.
Finally, also it should be noted that, in this article, relational terms such as the first and second grades is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply and between these entities or operation, have the relation of any this reality or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thereby the process, method, article or the equipment that make to comprise a series of key elements not only comprise those key elements, but also comprise other key elements of clearly not listing, or be also included as the intrinsic key element of this process, method, article or equipment.The in the situation that of more restrictions not, the key element being limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment that comprises described key element and also have other identical element.
In this instructions, each embodiment adopts the mode of going forward one by one to describe, and each embodiment stresses is the difference with other embodiment, between each embodiment identical similar part mutually referring to.
Above-mentioned explanation to the disclosed embodiments, makes professional and technical personnel in the field can realize or use the application.To the multiple modification of these embodiment, will be apparent for those skilled in the art, General Principle as defined herein can be in the situation that do not depart from the application's spirit or scope, realization in other embodiments.Therefore, the application will can not be restricted to these embodiment shown in this article, but will meet the widest scope consistent with principle disclosed herein and features of novelty.
Claims (10)
1. a short-term wind speed forecasting method for wind energy turbine set, is characterized in that, comprises the steps:
Obtain the wind speed of wind energy turbine set;
Described wind velocity signal is updated to the neural network building in advance, calculates the air speed data of period in the future.
2. short-term wind speed forecasting method as claimed in claim 1, is characterized in that, described neural network builds as follows:
Build initial neural network;
Choose training sample;
Utilize described training sample to train described initial neural network;
Utilize training result to described initial neural network initialize, obtain described neural network.
3. short-term wind speed forecasting method as claimed in claim 2, is characterized in that, described neural network comprises 3 layers of BP subnet.
4. short-term wind speed forecasting method as claimed in claim 2, is characterized in that, the concealed nodes number of described neural network is 6～10.
5. short-term wind speed forecasting method as claimed in claim 4, is characterized in that, described concealed nodes number is 9.
6. a short-term wind speed forecasting system for wind energy turbine set, is characterized in that, comprises the steps:
Acquisition module, is disposed at wind energy turbine set, for obtaining described wind speed;
Calculate output module, for described wind speed being updated to the neural network building in advance, calculate and export the air speed data of period in the future.
7. short-term wind speed forecasting system as claimed in claim 6, is characterized in that, described calculating output module comprises:
Construction unit, for building initial neural network;
Input block, for receiving training sample;
Training unit, for utilizing described training sample to train described initial neural network;
Assignment unit, for utilizing training result to described initial neural network initialize, obtains neural network;
Computing unit, for obtaining and export described air speed data by neural computing described in described wind velocity signal substitution.
8. short-term wind speed forecasting system as claimed in claim 7, is characterized in that, described neural network comprises 3 layers of BP subnet.
9. short-term wind speed forecasting system as claimed in claim 7, is characterized in that, the concealed nodes number of described neural network is 6～10.
10. short-term wind speed forecasting system as claimed in claim 9, is characterized in that, described concealed nodes number is 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410217851.1A CN104112166A (en) | 2014-05-22 | 2014-05-22 | Short-term wind speed prediction method and system of wind power felid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410217851.1A CN104112166A (en) | 2014-05-22 | 2014-05-22 | Short-term wind speed prediction method and system of wind power felid |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104112166A true CN104112166A (en) | 2014-10-22 |
Family
ID=51708950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410217851.1A Pending CN104112166A (en) | 2014-05-22 | 2014-05-22 | Short-term wind speed prediction method and system of wind power felid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104112166A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376386A (en) * | 2014-11-28 | 2015-02-25 | 新疆中科捷高光电科技有限公司 | Method for predicating power of wind turbine in wind farm |
| CN106874557A (en) * | 2017-01-12 | 2017-06-20 | 西安电子科技大学 | A kind of forecasting wind speed bearing calibration based on ratio distribution |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030160457A1 (en) * | 2000-07-07 | 2003-08-28 | Mario Ragwitz | Method and device for processing and predicting the flow parameters of turbulent media |
| CN101793907A (en) * | 2010-02-05 | 2010-08-04 | 浙江大学 | Short-term wind speed forecasting method of wind farm |
| US20120046917A1 (en) * | 2010-08-23 | 2012-02-23 | Hsin-Fa Fang | Wind energy forecasting method with extreme wind speed prediction function |
| CN102479339A (en) * | 2010-11-24 | 2012-05-30 | 香港理工大学 | Method and system for forecasting short-term wind speed of wind farm based on hybrid neural network |
| CN102479347A (en) * | 2010-11-24 | 2012-05-30 | 香港理工大学 | Method and system for forecasting short-term wind speed of wind farm based on data driving |
| CN103020743A (en) * | 2012-12-27 | 2013-04-03 | 中国科学院电工研究所 | Ultra-short-term wind speed forecasting method for wind power plant |
-
2014
- 2014-05-22 CN CN201410217851.1A patent/CN104112166A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030160457A1 (en) * | 2000-07-07 | 2003-08-28 | Mario Ragwitz | Method and device for processing and predicting the flow parameters of turbulent media |
| CN101793907A (en) * | 2010-02-05 | 2010-08-04 | 浙江大学 | Short-term wind speed forecasting method of wind farm |
| US20120046917A1 (en) * | 2010-08-23 | 2012-02-23 | Hsin-Fa Fang | Wind energy forecasting method with extreme wind speed prediction function |
| CN102479339A (en) * | 2010-11-24 | 2012-05-30 | 香港理工大学 | Method and system for forecasting short-term wind speed of wind farm based on hybrid neural network |
| CN102479347A (en) * | 2010-11-24 | 2012-05-30 | 香港理工大学 | Method and system for forecasting short-term wind speed of wind farm based on data driving |
| CN103020743A (en) * | 2012-12-27 | 2013-04-03 | 中国科学院电工研究所 | Ultra-short-term wind speed forecasting method for wind power plant |
Non-Patent Citations (1)
| Title |
|---|
| 谷悦 等: "基于BP神经网络群结构的风电场短期风速预测", 《农村电气化》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376386A (en) * | 2014-11-28 | 2015-02-25 | 新疆中科捷高光电科技有限公司 | Method for predicating power of wind turbine in wind farm |
| CN106874557A (en) * | 2017-01-12 | 2017-06-20 | 西安电子科技大学 | A kind of forecasting wind speed bearing calibration based on ratio distribution |
| CN106874557B (en) * | 2017-01-12 | 2019-07-02 | 西安电子科技大学 | A kind of forecasting wind speed bearing calibration based on ratio distribution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | A novel competitive swarm optimized RBF neural network model for short-term solar power generation forecasting | |
| Ren et al. | A fully data-driven method based on generative adversarial networks for power system dynamic security assessment with missing data | |
| CN105426956B (en) | A kind of ultra-short term photovoltaic prediction technique | |
| CN103049798B (en) | A kind of short-term power generation power Forecasting Methodology being applied to photovoltaic generating system | |
| CN103683326B (en) | A kind of regional power grid wind-powered electricity generation multiple spot accesses the computational methods of best receiving ability | |
| CN103559561B (en) | A kind of ultra-short term prediction method of photovoltaic plant irradiance | |
| CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
| CN109117951A (en) | Probabilistic Load Flow on-line calculation method based on BP neural network | |
| Gómez et al. | Optimal placement and sizing from standpoint of the investor of photovoltaics grid-connected systems using binary particle swarm optimization | |
| CN104636801A (en) | Transmission line audible noise prediction method based on BP neural network optimization | |
| CN105279615A (en) | Active power distribution network frame planning method on the basis of bi-level planning | |
| CN104392394B (en) | A kind of detection method of micro-capacitance sensor energy storage nargin | |
| CN104636985A (en) | Method for predicting radio disturbance of electric transmission line by using improved BP (back propagation) neural network | |
| CN103106544A (en) | Photovoltaic power generation prediction system based on T-S-type fuzzy neural network | |
| CN106126863A (en) | Based on artificial fish-swarm and the photovoltaic cell parameter identification method of the algorithm that leapfrogs | |
| CN103927460A (en) | Wind power plant short-term wind speed prediction method based on RBF | |
| CN104734175A (en) | Method for intelligently modifying wind speed and power curve of wind turbine generator | |
| CN107681655A (en) | A kind of tidal current energy generating field coordinated planning method | |
| CN105634018A (en) | Random response surface method and interior point method based wind-power-plant-contained random optimal power flow solving method | |
| CN107239856A (en) | A kind of wind direction data interpolating method | |
| CN105160597B (en) | A kind of reduction of greenhouse gas discharge control method based on electric system | |
| Gómez et al. | Evaluation of a particle swarm optimization based method for optimal location of photovoltaic grid-connected systems | |
| CN110084430A (en) | A method of considering space-time characterisation design distributed photovoltaic power output prediction model | |
| Chen et al. | An improved brain storm optimization for a hybrid renewable energy system | |
| CN104112166A (en) | Short-term wind speed prediction method and system of wind power felid |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141022 |