CN109902743A - A kind of Wind turbines output power predicting method - Google Patents
A kind of Wind turbines output power predicting method Download PDFInfo
- Publication number
- CN109902743A CN109902743A CN201910153382.4A CN201910153382A CN109902743A CN 109902743 A CN109902743 A CN 109902743A CN 201910153382 A CN201910153382 A CN 201910153382A CN 109902743 A CN109902743 A CN 109902743A
- Authority
- CN
- China
- Prior art keywords
- matrix
- meteorological
- attribute
- sample
- wind turbines
- 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 36
- 239000011159 matrix material Substances 0.000 claims abstract description 64
- 230000009467 reduction Effects 0.000 claims abstract description 19
- 230000005611 electricity Effects 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 238000006116 polymerization reaction Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000001556 precipitation Methods 0.000 claims description 7
- 230000005855 radiation Effects 0.000 claims description 6
- 230000000704 physical effect Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 3
- 210000005036 nerve Anatomy 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 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
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Wind Motors (AREA)
Abstract
The present invention relates to a kind of Wind turbines output power predicting methods, comprising the following steps: S1: obtaining meteorological data and blower history goes out force data, construct meteorological matrix and blower power output matrix；S2: the fuzzy membership of each attribute is calculated with fuzzy C-means clustering；S3: attribute reduction is carried out to meteorological matrix using Fuzzy and Rough set method；S4: extra sample is rejected to the meteorological matrix after reduction using neighbour's polymerization；S5: the BP neural network of one three layers of creation, the data of the meteorological matrix after rejecting extra sample with S4 obtain the prediction model of blower power output to neural metwork training；S6: it is verified using validity of the test data to the wind-powered electricity generation prediction model；The present invention eliminates the number of samples of meteorological physical quantity, improve the precision of Wind turbines output power prediction, Wind turbines output power prediction model calculating speed is also improved simultaneously, necessary theoretical basis can be provided for the power supply management and economic load dispatching of electric system.
Description
Technical field
It is pre- more particularly, to a kind of Wind turbines output power the present invention relates to renewable energy power output prediction field
Survey method.
Background technique
With the fast development of world economy, corresponding energy demand also increases substantially therewith, traditional fossil energy face
Face exhausted threat；Simultaneously as the extensive consumption of traditional fossil energy, problem of environmental pollution is also got worse, to life
State system, social economy and human health constitute serious threat；As green regenerative energy sources, wind-power electricity generation exists
Countries in the world are widely applied and develop；But wind energy is also faced with outstanding problem during fast development, due to wind
The unstability of power itself, wind-power electricity generation have fluctuation and intermittence, will cause huge difficulty to the scheduling of power grid；Mesh
The preceding important directions for solving the problems, such as this are exactly to predict the output of the wind-powered electricity generation of following a period of time, mainly include short-term forecast,
Medium-term forecast and long-term forecast；Wherein, the result of short-term forecast can help power grid to carry out reasonable economic load dispatching, unit group
Close and select suitable opportunity to safeguard etc. to blower；The prediction of mid-term can help wind power plant do season scheduling power generation,
Arrange large-scale maintenance activity etc.；Long-term wind-powered electricity generation prediction can assess the possible average annual energy output in somewhere, main to apply
In the addressing of wind power plant.
Currently, wind-powered electricity generation prediction technique is broadly divided into statistical method and physics side according to using the source of data different
Method；Wherein, statistical method is that the measurement data of the wind power plant according to wind power plant historical measurement data and periphery establishes statistics
Model is practised, most common Statistical learning model includes time series analysis model, artificial nerve network model, support vector machines
The machine learning algorithms such as model；In addition, many data mining algorithms quickly grown in recent years are also more and more widely used
Come in the prediction of Wind turbines output power；For many years studies have shown that be used only power generating value historical data statistics
The precision of prediction of method can decrease with the increase of prediction duration, it would therefore be desirable to be effectively combined physical quantity
Wind-powered electricity generation is predicted；Physical quantity used is usually the prediction data of weather forecast, and type includes temperature, humidity, wind
Speed, air pressure and wind direction etc.；The physical quantity data complexity with higher of these types, the data volume pole that data set includes
Greatly, result in the calculation amount of forecasting wind speed model excessive in this way, thus make wind-powered electricity generation predicted time and accuracy rate it is impossible to meet
The requirement of electric power system dispatching；In conclusion the accuracy predicted of the huge and wind-powered electricity generation of statistical data is serious to restrict wind
The exploitation and effective use of electricity.
In existing method, often directly use all physical quantity meteorological datas considered as the input of model,
The not influence in view of " the more attributes " and " multisample " characteristic of wind-powered electricity generation prediction input data set to model, in simple terms
It is to predict that the data set of blower power output is complex, the power generating value of blower directly cannot be directly predicted by the data.Its reason
Have two, prediction interferes first is that the redundant attributes in multiattribute data may contribute to blower, leads to the result of prediction not
Accurately；Second is that various notebook data can make the calculating time of blower prediction power output method longer；Eventually lead to blower power output prediction side
Method is not able to satisfy requirement of the electric power system dispatching to " accuracy " and " rapidity " of prediction.
Summary of the invention
The present invention is that wind power output power described in the above-mentioned prior art is overcome to predict not accurate enough defect, provides one
Kind Wind turbines output power predicting method.
It the described method comprises the following steps:
S1: obtaining meteorological data and blower history goes out force data, constructs meteorological matrix and blower power output matrix；
S2: the fuzzy membership of each attribute is calculated with fuzzy C-means clustering；
S3: attribute reduction is carried out to meteorological matrix using Fuzzy and Rough set method；
S4: extra sample is rejected to the meteorological matrix after reduction using neighbour's polymerization；
S5: the BP neural network of one three layers of creation, the data of the meteorological matrix after rejecting extra sample with S4 are to nerve
Network training obtains the prediction model of blower power output；
S6: it is verified using validity of the test data to the wind-powered electricity generation prediction model.
The present invention passes through reduction number by the processing of " multisample " feature to data set to reduce the calculation amount of model
According to the redundant attributes in " the more attributes " of collection, the precision of prediction of blower power output model is improved；The basic principle is that considering mould simultaneously
The double characteristic of type input data " multisample ", " more attributes ", from the Energy Management System of meteorological administrative department and wind power plant point
Not Huo Qu blower history power generating value and physical quantity, calculate fuzzy coarse central using fuzzy C-means clustering first and being subordinate to
Degree secondly using " more attributes " feature of Fuzzy and Rough set method processing input data, while being cut down using neighbour's polymerization
" multisample " feature of input data establishes blower power output prediction model neural network based, realizes fast and accurately wind-powered electricity generation
The prediction of unit output power；Necessary theoretical basis is provided for the power supply management and economic load dispatching of electric system.
Preferably, in the meteorological matrix constructed in step S1 matrix element include temperature, humidity, wind speed, wind direction, precipitation,
Eight class of air pressure, radiation intensity and sunshine, respectively label 1,2 ..., 8；Meteorological matrix are as follows:
In formula, i indicates attribute, i≤8；J indicates number of samples, and j≤N, N take 365；xWj1、xWj2、…、 xWji、…、xWj8
Respectively indicate the numerical value of temperature in j sample, humidity, wind speed, wind direction, precipitation, air pressure, radiation intensity and sunshine, the number of data set
Amount is greater than 2.
Preferably, blower power output matrix in step S1 are as follows:
P=[p1 p2 p3 L pj L pN]T
In formula, p1(j)、p2(j)、…、pi(j)、…、p7(j) Wind turbines when being predicted using j sample are respectively indicated
The numerical value of output power, the transposition of T representing matrix.
Preferably, step S2 the following steps are included:
S2.1: the cluster centre initialization value of each environment attribute fuzzy C-means clustering is determined；
S2.2: the attribute value of o-th of sample corresponding to the formula calculated result according to S2.1 is as in first cluster
The initialization value C of the heart, then removes this attribute value, jumps back to S2.1 until the initialization value for finding c cluster centre；
S2.3: cluster centre Matrix C=[C is constructed according to the resulting results set of S2.21 C2 C3 C4], wherein Ci=
[Ci1 Ci2 K Cic], i indicates the i-th class meteorology physical attribute；
S2.4: the objective function of fuzzy C-means clustering is continued to optimize with the mode of iterative calculation, each ring is acquired with this
The optimal degree of membership of border attribute value；
S2.5: each physical property values in each meteorological matrix are carried out with the iterative calculation of S2.4, obtains fuzzy membership
Degree.
Preferably, the calculating of the cluster centre initialization value of each environment attribute fuzzy C-means clustering is public in step S2.1
Formula are as follows:
In formula,For the radius of neighbourhood, c is class number；N is in radius of neighbourhood range
Interior sample number, j ∈ N, o ∈ N, λ are the random number of (0,1), and M is the sample number in the radius of field, aiIt (x) is the i-th generic attribute
X-th of sample values of value.
Preferably, step S2.4 the following steps are included:
S2.4.1: initialization the number of iterations t, subordinated-degree matrix U, cluster centre value C, class number c and weight ω；
S2.4.2: subordinated-degree matrix μ is updated in the t times iterative calculationij, cluster centre value matrix vij；
S2.4.3: ifOr reach the number of iterations, then iteration terminates, output environment attribute value it is optimal
Degree of membership；Otherwise it returns to S2.4.2 and carries out next iteration, whereinFor the degree of membership of the t times iteration.
Preferably, subordinated-degree matrix μ in step S2.4.2ij, cluster centre value matrix vijCalculation formula be respectively as follows:
Wherein, CljFor the cluster centre of the jth generic attribute of l class meteorologic factor, l is the classification of meteorologic factor.
Preferably, the reduction form X ' of the meteorological matrix in step S3 after reductionWAre as follows:
In formula, c indicates the number of attributes after attribute reduction, c < 8, N=365.
Preferably, in step S4 extra sample rejecting process are as follows: choose X 'WFirst sample is core, to 365
Sample presses Euclidean distanceM sample is filtered out from small to large；Wherein x 'W1iIt is i-th in the 1st sample
The value of meteorologic factor；To rearranging in reverse order at the time of respectively record is corresponding in neighbour's set, still the expression before use is accorded with
Number, obtain corresponding matrix form X "W。
Compared with prior art, the beneficial effect of technical solution of the present invention is: Wind turbines output proposed by the invention
Power forecasting method is reduced wind-powered electricity generation and is predicted input data set using the BP neural network based on fuzzy coarse central and neighbour's set
Influence of " the more attributes " and " multisample " feature having to model；The present invention eliminates the number of samples of meteorological physical quantity,
The precision of Wind turbines output power prediction is improved, while also improving Wind turbines output power prediction model and calculating speed
Degree, can provide necessary theoretical basis for the power supply management and economic load dispatching of electric system.
Detailed description of the invention
Fig. 1 is a kind of flow chart of Wind turbines output power predicting method of the present invention.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
In order to better illustrate this embodiment, the certain components of attached drawing have omission, zoom in or out, and do not represent practical production
The size of product；
To those skilled in the art, it is to be understood that certain known features and its explanation, which may be omitted, in attached drawing
's.
The following further describes the technical solution of the present invention with reference to the accompanying drawings and examples.
The present embodiment provides a kind of Wind turbines output power predicting methods, as shown in Figure 1, the method includes following
Step:
S1: obtaining meteorological data and blower history goes out force data, constructs meteorological matrix and blower power output matrix；
S2: the fuzzy membership of each attribute is calculated with fuzzy C-means clustering；
S3: attribute reduction is carried out to meteorological matrix using Fuzzy and Rough set method；
S4: extra sample is rejected to the meteorological matrix after reduction using neighbour's polymerization；
S5: the BP neural network of one three layers of creation, the data of the meteorological matrix after rejecting extra sample with S4 are to nerve
Network training obtains the prediction model of blower power output；
S6: it is verified using validity of the test data to the wind-powered electricity generation prediction model.
S1 describes the building of data matrix in Fig. 1.
From meteorological department obtain meteorological data, including this area influence blower power output temperature, humidity, wind speed, air pressure,
The meteorology historical data such as wind direction, precipitation and sunshine；Blower history, which is obtained, from wind power plant control centre goes out force data；And will more than
Two kinds of historical datas are rewritten as corresponding matrix form.
Meteorological matrix element includes temperature, humidity, wind speed, wind direction, precipitation, eight class of air pressure, radiation intensity and sunshine, is divided
Not label 1,2 ..., 8.
Meteorological matrix are as follows:
In formula, i indicates attribute, i≤8；J indicates number of samples, and j≤N, N take 365；xWj1、xWj2、…、 xWji、…、xWj8
Respectively indicate the numerical value of temperature in j sample, humidity, wind speed, wind direction, precipitation, air pressure, radiation intensity and sunshine, the number of data set
Amount is 5.
Blower power output matrix includes preceding N days blowers history power generating value.
P=[p1 p2 p3 L pj L pN]T
In formula, p1(j)、p2(j)、…、pi(j)、…、p7(j) Wind turbines when being predicted using j sample are respectively indicated
The numerical value of output power, the transposition of T representing matrix.
S2 describes the fuzzy membership that each attribute is calculated with fuzzy C-means clustering in Fig. 1.
It is worth science in view of the feature of meteorological data and raising calculate degree of membership, using fuzzy C-means clustering meter
Calculate the fuzzy membership of each attribute.
Step S2 the following steps are included:
S2.1: the cluster centre initialization value of each environment attribute fuzzy C-means clustering is determined with following equation:
In formula,For the radius of neighbourhood, c is class number；N is in radius of neighbourhood range
Interior sample number, λ are the random number of (0,1), and M is the sample number in the radius of field, aiIt (x) is x-th of the i-th generic attribute value
Sample values.
S2.2: the formula according to S2.1, the attribute value of o-th of sample corresponding to formula calculated result is as first
The initialization value C of cluster centre, then removes this attribute value, jumps back to S2.1 until finding the initialization value of c cluster centre
Until.
S2.3 constructs cluster centre Matrix C=[C according to the resulting results set of S2.21 C2 C3 C4], wherein Ci=
[Ci1 Ci2 K Cic], i indicates the i-th class meteorology physical attribute.
S2.4: the objective function of fuzzy C-means clustering is continued to optimize with the mode of iterative calculation, each ring is acquired with this
The optimal degree of membership of border attribute value, the specific steps are as follows:
S2.4.1: initialization the number of iterations t, subordinated-degree matrix U, cluster centre value C, class number c and weight ω；
S2.4.2: subordinated-degree matrix, cluster centre value matrix, calculation formula difference are updated in the t times iterative calculation
Are as follows:
IfOr reaching the number of iterations, then iteration terminates, the optimal degree of membership of output environment attribute value；
Otherwise return step S2.4.2 carries out next iteration, whereinFor the degree of membership of the t times iteration.
S2.5: each physical property values in each meteorological matrix are carried out with the iterative calculation of S2.4, obtains fuzzy membership
Degree.
S3 describes to carry out attribute reduction to meteorological matrix using Fuzzy and Rough set method in Fig. 1.
Include more attribute classification in the data set of research, longitudinal letter is carried out to data set using attribute reduction
Change, unnecessary attribute is removed, that is, removing those will not influence the attribute of this model prediction accuracy, utilize Fuzzy and Rough
Set method carries out attribute reduction to meteorological matrix, obtains the reduction form X ' of meteorological matrixW。
In formula, c indicates the number of attributes after attribute reduction, c < 8, N=365.
S4 describes to reject extra sample using neighbour's polymerization in Fig. 1.
Data are concentrated with 5 × c × 365 sample, and number of samples is more, increase the calculation amount of model, are guaranteeing to predict
Under the premise of model accuracy, number of samples is cut down to increase calculating speed.
Choose X 'WFirst sample is core, presses Euclidean distance to 365 samplesFrom small to large
M sample is filtered out, the present embodiment m takes 100, wherein x 'W1iFor the value of i-th of meteorologic factor in the 1st sample；Neighbour is collected
It is rearranged in reverse order at the time of respectively record is corresponding in conjunction, still the expression symbol before use, obtains corresponding matrix form
X″W。
In Fig. 1 S5 describe in aforementioned manners resulting data to neural metwork training.
The BP neural network for creating one three layers first, uses matrix X "WThe neural network is trained, wind is obtained
The prediction model of machine power output.
S6 describes to examine the science of the wind-powered electricity generation prediction technique in Fig. 1.
It is verified using validity of the test data to above-mentioned wind-powered electricity generation prediction model.
The terms describing the positional relationship in the drawings are only for illustration, should not be understood as the limitation to this patent；
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (9)
1. a kind of Wind turbines output power predicting method, which is characterized in that the described method comprises the following steps:
S1: obtaining meteorological data and blower history goes out force data, constructs meteorological matrix and blower power output matrix；
S2: the fuzzy membership of each attribute is calculated with fuzzy C-means clustering；
S3: attribute reduction is carried out to meteorological matrix using Fuzzy and Rough set method；
S4: extra sample is rejected to the meteorological matrix after reduction using neighbour's polymerization；
S5: the BP neural network of one three layers of creation, the data of the meteorological matrix after rejecting extra sample with S4 are to neural network
Training obtains the prediction model of blower power output；
S6: it is verified using validity of the test data to the wind-powered electricity generation prediction model.
2. Wind turbines output power predicting method according to claim 1, which is characterized in that the gas constructed in step S1
As in matrix matrix element include temperature, humidity, wind speed, wind direction, precipitation, eight class of air pressure, radiation intensity and sunshine, mark respectively
1,2 ..., 8；Meteorological matrix are as follows:
In formula, i indicates attribute, i≤8；J indicates number of samples, and j≤N, N take 365；xWj1、xWj2、…、xWji、…、xWj8Table respectively
Show the numerical value of temperature in j sample, humidity, wind speed, wind direction, precipitation, air pressure, radiation intensity and sunshine, the quantity of data set is greater than
2。
3. Wind turbines output power predicting method according to claim 1, which is characterized in that blower is contributed in step S1
Matrix are as follows:
P=[p1 p2 p3 L pj L pN]T
In formula, p1(j)、p2(j)、…、pi(j)、…、p7(j) Wind turbines output work when being predicted using j sample is respectively indicated
The numerical value of rate, the transposition of T representing matrix.
4. Wind turbines output power predicting method according to claim 1, which is characterized in that step S2 includes following step
It is rapid:
S2.1: the cluster centre initialization value of each environment attribute fuzzy C-means clustering is determined；
S2.2: the attribute value of o-th of sample corresponding to the formula calculated result according to S2.1 is as first cluster centre
Then initialization value C removes this attribute value, jump back to S2.1 until the initialization value for finding c cluster centre；
S2.3: cluster centre Matrix C=[C is constructed according to the resulting results set of S2.21 C2 C3 C4], wherein Ci=[Ci1 Ci2
K Cic], i indicates the i-th class meteorology physical attribute；
S2.4: the objective function of fuzzy C-means clustering is continued to optimize with the mode of iterative calculation, each environment attribute is acquired with this
The optimal degree of membership of value；
S2.5: each physical property values in each meteorological matrix are carried out with the iterative calculation of S2.4, obtains fuzzy membership.
5. Wind turbines output power predicting method according to claim 4, which is characterized in that each ring in step S2.1
The calculation formula of the cluster centre initialization value of border attribute fuzzy C-means clustering are as follows:
In formula,For the radius of neighbourhood, c is class number；N is sample number, and j ∈ N, o ∈ N, λ are
The random number of (0,1), M are the sample number in the radius of field, aiIt (x) is x-th of sample values of the i-th generic attribute value.
6. Wind turbines output power predicting method according to claim 4, which is characterized in that step S2.4 includes following
Step:
S2.4.1: initialization the number of iterations t, subordinated-degree matrix U, cluster centre value C, class number c and weight ω；
S2.4.2: subordinated-degree matrix μ is updated in the t times iterative calculationij, cluster centre value matrix vij；
S2.4.3: ifOr reaching the number of iterations, then iteration terminates, and the optimal of output environment attribute value is subordinate to
Degree；Otherwise it returns to S2.4.2 and carries out next iteration, whereinFor the degree of membership of the t times iteration.
7. Wind turbines output power predicting method according to claim 6, which is characterized in that be subordinate in step S2.4.2
Spend matrix μij, cluster centre value matrix vijCalculation formula be respectively as follows:
Wherein, CljFor the cluster centre of the jth generic attribute of l class meteorologic factor, l is the classification of meteorologic factor.
8. Wind turbines output power predicting method according to claim 1, which is characterized in that in step S3 after reduction
The reduction form X ' of meteorological matrixWAre as follows:
In formula, c indicates the number of attributes after attribute reduction, c < 8, N=365.
9. Wind turbines output power predicting method according to claim 1, which is characterized in that extra sample in step S4
Rejecting process are as follows: choose X 'WFirst sample is core, presses Euclidean distance to 365 samplesFrom small
To m sample is filtered out greatly, wherein x 'W1iFor the value of i-th of meteorologic factor in the 1st sample；To neighbour set in respectively record pair
It is rearranged in reverse order at the time of answering, still the expression symbol before use, obtains corresponding matrix form X "W。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910153382.4A CN109902743A (en) | 2019-02-28 | 2019-02-28 | A kind of Wind turbines output power predicting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910153382.4A CN109902743A (en) | 2019-02-28 | 2019-02-28 | A kind of Wind turbines output power predicting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109902743A true CN109902743A (en) | 2019-06-18 |
Family
ID=66945902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910153382.4A Pending CN109902743A (en) | 2019-02-28 | 2019-02-28 | A kind of Wind turbines output power predicting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109902743A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705760A (en) * | 2019-09-19 | 2020-01-17 | 广东工业大学 | Photovoltaic power generation power prediction method based on deep belief network |
| CN112257953A (en) * | 2020-11-03 | 2021-01-22 | 上海电力大学 | Data processing method based on polar region new energy power generation power prediction |
| CN117111585A (en) * | 2023-09-08 | 2023-11-24 | 广东工业大学 | Numerical control machine tool health state prediction method based on tolerance sub-relation rough set |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916998A (en) * | 2010-07-12 | 2010-12-15 | 东北电力科学研究院有限公司 | Support vector machine-based wind electric powder prediction device and method |
| US20140172329A1 (en) * | 2012-12-17 | 2014-06-19 | Junshan Zhang | System and method for wind generation forecasting |
| CN104933483A (en) * | 2015-06-17 | 2015-09-23 | 中国电力科学研究院 | Wind power forecasting method dividing based on weather process |
| CN108846527A (en) * | 2018-08-27 | 2018-11-20 | 云南电网有限责任公司电力科学研究院 | A kind of photovoltaic power generation power prediction method |
| CN109325607A (en) * | 2017-08-01 | 2019-02-12 | 中国电力科学研究院 | A kind of short-term wind power forecast method and system |
-
2019
- 2019-02-28 CN CN201910153382.4A patent/CN109902743A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916998A (en) * | 2010-07-12 | 2010-12-15 | 东北电力科学研究院有限公司 | Support vector machine-based wind electric powder prediction device and method |
| US20140172329A1 (en) * | 2012-12-17 | 2014-06-19 | Junshan Zhang | System and method for wind generation forecasting |
| CN104933483A (en) * | 2015-06-17 | 2015-09-23 | 中国电力科学研究院 | Wind power forecasting method dividing based on weather process |
| CN109325607A (en) * | 2017-08-01 | 2019-02-12 | 中国电力科学研究院 | A kind of short-term wind power forecast method and system |
| CN108846527A (en) * | 2018-08-27 | 2018-11-20 | 云南电网有限责任公司电力科学研究院 | A kind of photovoltaic power generation power prediction method |
Non-Patent Citations (8)
| Title |
|---|
| 廖倩: "基于粗糙集和模糊粗糙集的属性约简研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 8, pages 140 - 22 * |
| 徐晓蕊: "基于一致性的不完备数据模糊聚类方法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
| 徐晓蕊: "基于一致性的不完备数据模糊聚类方法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 4, 15 April 2018 (2018-04-15), pages 031 - 399 * |
| 王东: "无人机协同组网感知融合技术研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》 * |
| 王东: "无人机协同组网感知融合技术研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》, no. 3, 15 March 2016 (2016-03-15), pages 138 - 1927 * |
| 赵天娜: "多伴随模糊粗糙集的属性约简与三支决策", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 7, pages 002 - 125 * |
| 齐亚丽: "基于模糊粗糙集属性约简方法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 8, pages 140 - 120 * |
| 齐媛媛: "基于邻域和模糊粗糙集的属性约简研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 8, pages 140 - 119 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705760A (en) * | 2019-09-19 | 2020-01-17 | 广东工业大学 | Photovoltaic power generation power prediction method based on deep belief network |
| CN112257953A (en) * | 2020-11-03 | 2021-01-22 | 上海电力大学 | Data processing method based on polar region new energy power generation power prediction |
| CN117111585A (en) * | 2023-09-08 | 2023-11-24 | 广东工业大学 | Numerical control machine tool health state prediction method based on tolerance sub-relation rough set |
| CN117111585B (en) * | 2023-09-08 | 2024-02-09 | 广东工业大学 | Numerical control machine tool health state prediction method based on tolerance sub-relation rough set |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Random forest solar power forecast based on classification optimization | |
| Han et al. | A PV power interval forecasting based on seasonal model and nonparametric estimation algorithm | |
| CN103390202B (en) | A kind of photovoltaic plant output power predicting method chosen based on set of metadata of similar data | |
| CN104573879A (en) | Photovoltaic power station output predicting method based on optimal similar day set | |
| CN105069521A (en) | Photovoltaic power plant output power prediction method based on weighted FCM clustering algorithm | |
| CN107944622A (en) | Wind power forecasting method based on continuous time cluster | |
| CN106022528A (en) | Short-term power prediction method of photovoltaic power plant based on density peak hierarchical clustering | |
| CN106447098A (en) | Photovoltaic ultra-short period power predicting method and device | |
| CN109902743A (en) | A kind of Wind turbines output power predicting method | |
| CN106485093B (en) | Based on the solar irradiance time series synthetic method for improving Markov chain | |
| CN103489046A (en) | Method for predicting wind power plant short-term power | |
| CN103942736B (en) | A kind of wind power plant multimachine equivalent modeling method | |
| CN107679687A (en) | A kind of photovoltaic output modeling method and Generation System Reliability appraisal procedure | |
| CN102938562B (en) | Prediction method of total wind electricity power in area | |
| CN104809658A (en) | Method for rapidly analyzing low-voltage distributing network area line loss | |
| CN102147839A (en) | Method for forecasting photovoltaic power generation quantity | |
| CN111401603A (en) | Multi-type energy demand prediction method | |
| CN106022538A (en) | Photovoltaic power generating predicting method based on K-mean clustering improved generalized weather | |
| CN105868887A (en) | Building comprehensive energy efficiency analysis method based on subentry measure | |
| CN107748940A (en) | A kind of energy conservation potential Quantitative prediction methods | |
| CN115829126A (en) | Photovoltaic power generation power prediction method based on multi-view self-adaptive feature fusion | |
| CN110458722A (en) | Flood interval prediction method based on multiple target random vector function connection network | |
| CN104915727B (en) | Various dimensions allomer BP neural network optical power ultra-short term prediction method | |
| CN108960522A (en) | A kind of photovoltaic power generation quantity prediction analysis method | |
| CN116611702A (en) | Integrated learning photovoltaic power generation prediction method for building integrated energy management |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190618 |