CN105930900A - Method and system for predicting hybrid wind power generation - Google Patents
Method and system for predicting hybrid wind power generation Download PDFInfo
- Publication number
- CN105930900A CN105930900A CN201610300971.7A CN201610300971A CN105930900A CN 105930900 A CN105930900 A CN 105930900A CN 201610300971 A CN201610300971 A CN 201610300971A CN 105930900 A CN105930900 A CN 105930900A
- Authority
- CN
- China
- Prior art keywords
- wind
- wind power
- forecast model
- power generation
- hybrid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims abstract 2
- 230000005611 electricity Effects 0.000 claims description 57
- 238000012360 testing method Methods 0.000 claims description 43
- 238000004519 manufacturing process Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 239000012141 concentrate Substances 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 24
- 238000010586 diagram Methods 0.000 description 11
- 241001269238 Data Species 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000007935 neutral effect Effects 0.000 description 3
- 238000013179 statistical model Methods 0.000 description 3
- 241000628997 Flos Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004138 cluster model Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000013517 stratification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (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)
- Wind Motors (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a method and system for predicting hybrid wind power generation. The method comprises the following steps: acquiring wind directions, wind speeds and historical data of corresponding wind power output power of a wind farm, sampling from the historical data to obtain sample data; conducting judgment and analysis on statistical features of the sample data, acquiring wind directions that are featured by an integrated wind frequency and have a wind power output power difference which reaches a difference threshold value, and based on the acquired wind directions and corresponding relations between the wind directions, and the wind speeds and the wind power output power, adopting the fuzzy hierarchy clustering method in dividing the sample data into three types; adopting the neural network algorithm in training each type of samples, correspondingly forming three types of specific wind generation prediction models, then conducting combination and processing, establishing a hybrid wind generation prediction model which is intended for predicting wind power generation capacity. Therefore, the method, through the implementation, can conduct model prediction on different wind directions and wind speeds in a specific manner and can increase precision of prediction the wind power generation power.
Description
Technical field
The present invention relates to the technical field of wind power prediction, particularly to the prediction of a kind of hybrid wind power generation
Method and system.
Background technology
Wind park is when carrying out wind-power electricity generation, and wind power output power is not only affected by wind speed, and wind direction is also
Very important factor, but due to the effect of atmospheric pressure, wind speed and direction all can change at any time, because of
And the output of wind-driven generator also has the feature such as undulatory property and randomness, the fluctuation of this power output
Property is unfavorable for stationarity and the safety of regional power grid overall operation.Accordingly, it would be desirable to wind power output power is done
Go out reasonably prediction, to facilitate power operation department to carry out efficient scheduling.
At present, in terms of short-term wind-power electricity generation prediction, main employing physical model prediction and statistical model are predicted
Two ways.Wherein:
1) physical model prediction, mainly obtains wind speed, wind according to predicting the outcome of numerical weather forecast system
To, the weather data such as air pressure, temperature, then according to equal pitch contour around wind energy turbine set, roughness, barrier,
The information such as thermal stratification are calculated the information such as the wind speed of wind-powered machine unit hub height, wind direction, finally according to wind
The power curve of electric field is calculated the output of wind energy turbine set.Here, thing to be carried out to wind energy turbine set location
Reason modeling, including landform, surface vegetation and roughness, the peripheral obstacle etc. of wind field, the most also will be to blower fan
The firm height of wheel, power curve, machine driving and the control strategies etc. of itself are modeled.Additionally the method is defeated
The parameter entered is that digital meteorology forecasts (NWP) model.
But, due to physical model prediction physical model equation lack elasticity constraint and weather forecast more
The reasons such as new frequency is low so that it is do not adapt to the wind-force prediction of short-term.Though it addition, physical model Forecasting Methodology
So need not historical data, wind energy turbine set is gone into operation and be can be carried out, but needs NWP data and wind-powered electricity generation accurately
The on-site details in field, input parameter is more, and the collection of NWP data and process are the most numerous
Trivial.
2) statistical model prediction, this method does not consider the physical process that wind speed changes, according to historical statistics number
According to finding out the relation of weather conditions and output of wind electric field, then according to measured data and numerical value data of weather forecast
Power Output for Wind Power Field is predicted.The essence of this method is input (the NWP historical statistics in system
Data, measured data) and wind power between build one vertical mapping relations, usually linear relationship.This
Relation can show by the form of function, such as regression analysis, exponential smoothing, time series method,
Kalman filtering method, grey method etc., be all based on linear model.These models are by catching data
In be predicted with the information of time and space correlation.
But statistical model is predicted, data used are single, to short-term or the wind power prediction of ultra-short term
Result can meet required precision.But the prediction for the longer time, it was predicted that result precision is often inadequate,
And need long measurement data and substantial amounts of data processing work and extra training.It addition, it is right
Process bad in abrupt information, in the training stage, rare weather conditions seldom occur, and also be difficult to the most pre-
Survey.
Summary of the invention
In view of this, the purpose of the embodiment of the present invention be to propose the Forecasting Methodology of a kind of hybrid wind power generation and
System, it is possible to realize different wind directions, wind speed are carried out targetedly model prediction, and can improve
The precision of prediction of wind-power electricity generation power.
From the point of view of further, the Forecasting Methodology of this hybrid wind power generation includes: obtain the wind direction of wind energy turbine set, wind speed
And the historical data of the wind power output power of correspondence, and it is sampled obtaining sample data to described historical data；
The statistical property of described sample data is carried out discriminatory analysis, obtains wind frequency and concentrate and wind power output power difference
Reach the wind direction of discrepancy threshold, and according to acquired wind direction and with wind speed, wind power output power corresponding
Relation uses fuzzy hierarchy clustering procedure, and described sample data is divided into three classes；Use neural network algorithm pair
Every class sample is trained, and is correspondingly formed three classes specific wind-power electricity generation forecast model, by specific for this three class
Wind-power electricity generation forecast model merges process, sets up the mixing wind for being predicted wind-power electricity generation production capacity
Power generating forecast model.
Alternatively, in certain embodiments, the Forecasting Methodology of above-mentioned hybrid wind power generation also includes: obtain
The sample data of test, debugs the hybrid wind power generation forecast model set up；According to mixing wind
The test result of power generating forecast model output, is modified described hybrid wind power generation forecast model；Its
In, the sample data of described test is from the wind power output power of wind direction, wind speed and the correspondence of described wind energy turbine set
Historical data in sample and obtain.
Alternatively, in certain embodiments, the Forecasting Methodology of above-mentioned hybrid wind power generation also includes: utilize institute
State hybrid wind power generation forecast model, the output production capacity of wind power plant is tested；When being predicted,
Judge input data wind direction, according to determined by wind direction, call correspondence wind-power electricity generation forecast model calculate
The predictive value of the wind power output power of described wind energy turbine set, the test result that output is corresponding.
Alternatively, in certain embodiments, the generation type of described hybrid wind power generation forecast model also includes:
It is respectively the sample weights parameter that the configuration of described three class specific wind-power electricity generation forecast model is corresponding；According to each
The sample weights parameter of forecast model, merges the forecast model set up according to wind direction, sets up mixing wind
Power generating forecast model.
Alternatively, in certain embodiments, the Forecasting Methodology of above-mentioned hybrid wind power generation also includes: to institute
State hybrid wind power generation forecast model to iterate, make described hybrid wind power generation forecast model gradually receive
Hold back, until output result tends towards stability.
For realizing said method, the embodiment of the present invention also proposes the prognoses system of a kind of hybrid wind power generation, should
System includes:
Decimation blocks, is used for the wind power output power of wind direction, wind speed and correspondence to acquired wind energy turbine set
Historical data is sampled obtaining sample data；
Analyze module, for the statistical property of described sample data is carried out discriminatory analysis, obtain wind frequency and concentrate
And wind power output power difference reaches the wind direction of discrepancy threshold；
Processing module, for according to acquired wind direction and with wind speed, the corresponding relation of wind power output power
Use fuzzy hierarchy clustering procedure, described sample data is divided into three classes；
Model block at the beginning of model, be used for using neural network algorithm that every class sample is trained, be correspondingly formed three
Class specific wind-power electricity generation forecast model；
Mixed processing module, for merging process, shape by this three class specific wind-power electricity generation forecast model
Become the hybrid wind power generation forecast model for wind-power electricity generation production capacity is predicted.
Alternatively, in certain embodiments, the prognoses system of above-mentioned hybrid wind power generation also includes: test is repaiied
Positive module, for obtaining the sample data of test, is carried out the hybrid wind power generation forecast model set up
Debug, revise and optimize.
Alternatively, in certain embodiments, the prognoses system of above-mentioned hybrid wind power generation also includes: data are defeated
Enter device, be used for obtaining test data；Test device, is configured with described hybrid wind power generation forecast model,
For according to acquired test data, it is judged that input data wind direction, according to determined by wind direction, call
Wind-power electricity generation forecast model corresponding in described hybrid wind power generation forecast model, the output to wind power plant
Production capacity is tested；Output device, the institute obtained for obtaining described hybrid wind power generation forecast model to test
State the predictive value of the wind power output power of wind energy turbine set, and export the test result of correspondence.
Alternatively, in certain embodiments, described mixed processing module also includes: parameter configuration unit, uses
In the sample weights parameter that the configuration of the most described three class specific wind-power electricity generation forecast model is corresponding；At merging
Reason unit, for the sample weights parameter according to each forecast model, the forecast model will set up according to wind direction
Merge, set up hybrid wind power generation forecast model；Iterative optimization unit, for described mixing wind-force
Generating forecast model iterates, and makes described hybrid wind power generation forecast model gradually restrain, until becoming
In stable.
Alternatively, in certain embodiments, described hybrid wind power generation forecast model farther includes wind direction knowledge
Other unit, for judging to input the wind direction of data；Model call unit, for wind direction determined by basis,
Call wind-power electricity generation forecast model corresponding in described hybrid wind power generation forecast model, to wind power plant
Output production capacity is tested.
Relative to prior art, various embodiments of the present invention have the advantage that
After using the technical scheme of the embodiment of the present invention, by wind direction, wind speed and the wind-powered electricity generation of wind park are exported
The statistical analysis of the historical datas such as power, the history number to wind direction, wind speed and the wind power output power of wind energy turbine set
According to being sampled, obtain sample data, by fuzzy hierarchy clustering procedure, according to wind direction, sample data is divided into
Three classes, then use Hopfield neural network algorithm to be trained every class sample data, set up spy respectively
Levy the wind-power electricity generation forecast model of wind direction, three class forecast models are merged process, build one based on not
Hybrid wind power generation forecast model with wind direction.Then, utilize the hybrid wind power generation forecast model set up,
By analyzing the wind direction feature of wind park different times, the production capacity of wind park is predicted.Wind-powered electricity generation is exported
During power is predicted, consider wind direction and the impact of two aspects of wind-force simultaneously, and according to wind direction,
Wind-force and the corresponding relation of wind power output power, carried out fuzzy hierarchy cluster.As such, it is possible to by one group
The sampled data having noise redundancy is divided into the corresponding several parts of sample datas that there is internal association, then to these
Sample data models respectively, and the internal characteristics of different classes of data just can be fully demonstrated by different models,
Thus different wind directions, wind speed are carried out targetedly model prediction.
It addition, when being predicted, first judge the wind direction of input data, substitute in corresponding forecast model and obtain
To the predictive value of wind power output power, it is thus possible to accurately carry out short-term wind-electricity prediction, improve wind power pre-
The precision surveyed.
Detailed description of the invention later is explained by more features and the advantage of the embodiment of the present invention.
Accompanying drawing explanation
The accompanying drawing constituting an embodiment of the present invention part is used for providing being further appreciated by the embodiment of the present invention,
The schematic description and description of the present invention is used for explaining the present invention, is not intended that the improper limit to the present invention
Fixed.In the accompanying drawings:
The Forecasting Methodology schematic flow sheet of a kind of hybrid wind power generation that Fig. 1 provides for the embodiment of the present invention；
Fig. 2 is the operation principle schematic diagram of Hopfield neural network algorithm in the embodiment of the present invention；
Fig. 3 is dynamic wind rose and the contrast schematic diagram of electric power Flos Rosae Rugosae figure in the embodiment of the present invention；
Fig. 4 is the level incidence relation schematic diagram between the other class that in the embodiment of the present invention, sample data is different；
Fig. 5 is the classification schematic diagram of sample data in the embodiment of the present invention；
Fig. 6 is the contrast schematic diagram that predicts the outcome of different models in the embodiment of the present invention；
The composition schematic diagram of the prognoses system of a kind of hybrid wind power generation that Fig. 7 provides for the embodiment of the present invention；
Fig. 8 is the composition schematic diagram of data modeling and correcting device in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, be fully described by, it is clear that described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
The every other embodiment obtained under property work premise, broadly falls into the scope of protection of the invention.
It should be noted that in the case of not conflicting, the feature in the embodiment of the present invention and embodiment is permissible
It is mutually combined.
Owing to being affected by wind speed and direction while wind power output power, particularly under identical wind speed,
Wind power output power under different wind directions has a long way to go, and therefore, does not consider traditional Individual forecast mould of wind direction
Type error is very big, and in view of this, the present invention provides a kind of comprehensive wind direction and the mixing wind of wind speed the two factor
Electric output power forecast model, thus improve the precision of prediction of wind-power electricity generation power.
Below in conjunction with the accompanying drawings, various embodiments of the present invention are described further:
Embodiment of the method
With reference to shown in Fig. 1, it is the Forecasting Methodology stream of a kind of hybrid wind power generation of embodiment of the present invention proposition
Journey schematic diagram, the Forecasting Methodology of this hybrid wind power generation comprises the following steps:
S100: obtain the historical data of the wind power output power of the wind direction of wind energy turbine set, wind speed and correspondence, and right
Described historical data is sampled obtaining sample data；
S102: the statistical property of described sample data is carried out discriminatory analysis, obtains wind frequency concentration and wind-powered electricity generation is defeated
Go out power difference and reach the wind direction of discrepancy threshold, and according to acquired wind direction and with wind speed, wind-powered electricity generation output
The corresponding relation of power uses fuzzy hierarchy clustering procedure, and described sample data is divided into three classes；
S104: use neural network algorithm that every class sample is trained, be correspondingly formed the three specific wind-force of class
Generating forecast model, merges process by this three class specific wind-power electricity generation forecast model, sets up for right
The hybrid wind power generation forecast model that wind-power electricity generation production capacity is predicted.
In the present embodiment, pre-build hybrid wind power generation forecast model, by the wind direction of wind park, wind
Find after the statistical analysis of the historical datas such as speed and wind power output power, high frequency wind direction correspond to high output
Frequency, based on this, the present embodiment first historical data to wind direction, wind speed and the wind power output power of wind energy turbine set
It is sampled, obtains sample data, by fuzzy hierarchy clustering procedure, according to wind direction, sample data is divided into three
Class, then uses Hopfield neural network algorithm to be trained every class sample data, sets up feature respectively
Three class forecast models are merged process by the wind-power electricity generation forecast model of wind direction, build one based on difference
The hybrid wind power generation forecast model of wind direction.Then, utilize the hybrid wind power generation forecast model set up,
By analyzing the wind direction feature of wind park different times, the production capacity of wind park is predicted.The present embodiment root
Classifying input data according to wind direction, when being predicted, first judge the wind direction of input data, it is right to substitute into
The forecast model answered obtains the predictive value of wind power output power, it is thus possible to accurately carry out short-term wind-electricity prediction,
Improve the precision of wind power prediction.
It is pointed out that above-mentioned discrepancy threshold can be configured according to the practical situation of wind power plant, use
Wind direction in screening sample data.
As the optional embodiment of one, the Forecasting Methodology of above-mentioned hybrid wind power generation may also include following step
Rapid:
S106: obtain the sample data of test, the hybrid wind power generation forecast model set up is adjusted
Examination；
S108: according to the test result of hybrid wind power generation forecast model output, to described hybrid wind power generation
Forecast model is modified.
It should be noted that the sample data of described test is from wind direction, wind speed and the correspondence of described wind energy turbine set
Wind power output power historical data in sample and obtain.
Optionally, based on one embodiment of any of the above, the Forecasting Methodology of above-mentioned hybrid wind power generation is implemented
Example can also include below step:
S110: utilize described hybrid wind power generation forecast model, surveys the output production capacity of wind power plant
Examination；
S112: when being predicted, it is judged that input data wind direction, according to determined by wind direction, it is right to call
The wind-power electricity generation forecast model answered calculates the predictive value of the wind power output power of described wind energy turbine set, output correspondence
Test result.
In the present embodiment, difference and feature according to wind direction carry out classification model construction to input data, it was predicted that time,
The wind direction of discriminatory analysis input data, according to determined by wind direction, corresponding data are substituted into corresponding prediction
In model, obtain the predictive value of wind power output power, thus realize accurately short-term wind-electricity prediction.
In the various embodiments described above, by first setting up hybrid wind power generation forecast model, then utilize mixing wind-force
Wind-power electricity generation is predicted by generating forecast model according to short-term wind speed, wind direction data.Here, for further
Explain hybrid wind power generation forecast model, below its forming process is once illustrated, above-mentioned steps S104
Including following processing procedure:
S1041: be respectively the sample weights ginseng that the configuration of described three class specific wind-power electricity generation forecast model is corresponding
Number；
S1042: according to the sample weights parameter of each forecast model, the forecast model set up according to wind direction is entered
Row merges, and sets up hybrid wind power generation forecast model；
Alternatively, the process of the forecast model setting up hybrid wind power generation in above-mentioned steps S104 may also include that
S1043: described hybrid wind power generation forecast model is iterated, makes described hybrid wind power generation
Forecast model is gradually restrained, until output result tends towards stability.
Such as: with reference to Fig. 2, it is the operation principle schematic diagram of Hopfield neural network algorithm, as logical
With a kind of derivation of nerve network system, outside algorithm itself is independent of data, different data pass through algorithm
Process form different models, by screen three different classes of training set data being put into
Hopfield neutral net is trained, the forecast model that three classes are different can be drawn.These models only with its
Corresponding data set is correlated with, and then can pass through the test set number that Fuzzy Cluster Model before is by other 30%
It is divided three classes according to by same principle, each class testing collection data is put in the model of correspondence and be predicted,
Just can draw and predict output accordingly.
If needing to judge the prediction precision of overall mixed model, then need the prediction of three class difference models
Value is made comparisons with the actual value of corresponding sample, obtains its mean square error, and is pressed certain Weight just
Obtain the prediction precision of entirety.Wherein, the weight of each model predication value mean square error is by all kinds of test sets
Data account for the proportion of integrated testability collection data and determine, thus strengthen fault-tolerant ability and the generalization ability of model, make
Obtain hybrid wind power generation forecast model and can more adapt to the outer data of sample.In addition, it is necessary to important to note
It is, during actual prediction, if a new sample point is transfused to model, then to be judged by fuzzy clustering
It is A class, is the most directly predicted by A class model, and obtains a result, and the present embodiment is by weight
Integrate the whole structure weighing whole model cluster.
Compared with existing wind-power electricity generation forecast model, the hybrid wind power generation prediction that the various embodiments described above use
Model is obtained in that higher precision of prediction.Below to the Forecasting Methodology embodiment of above-mentioned hybrid wind power generation
Advantage is further analyzed and described, and generally, above-described embodiment mainly uses following handling process:
1) modeling sample data are collected
The historical data obtaining wind park wind direction, wind speed and wind-powered electricity generation output is sampled, and obtains sample data.
The statistical property of whole sample is judged, utilizes polar coordinate system to draw the wind frequency on different directions, find out
Classification generating forecast model is set up in several directions of wind frequency concentration and wind power output power significant difference.
Here, owing to wind-power electricity generation output is not only related to angle, also it is related to wind direction, therefore, passes through
Particular prediction model on different wind directions is merged, it is possible to obtain more accurate wind-force and find forecast model,
I.e. hybrid wind power generation forecast model, this hybrid wind power generation forecast model can divide by distinguishing different wind direction
Do not set up the relation between wind speed and output generated output.
2) sample data classification model construction
The model corresponding with output in order to set up wind direction, wind speed, needs to divide sample, no
Then overlapping sample point will affect independence and the accuracy of each model.Therefore, ask in order to avoid this
Sample, before carrying out model foundation, is first carried out by topic hybrid wind power generation forecast model by fuzzy hierarchy clustering procedure
Classification processes, and lays foundation for setting up model accurately.
In above-described embodiment, fuzzy hierarchy clustering procedure is used to carry out data mining, according to wind direction by sample data
Being divided three classes, the height of each of which layer represents the distance between two types data space, and distance is the biggest
Represent that the border between two kinds of data spaces is the most obvious, border can be selected from result the most obvious, have minimum
Conforming a few class sample group.Such as, sample can be divided into two parts, the sample of 70% is used for training mould
Type, the sample of 30% is used for test model；The sample group that several classes selected have obvious border imports
In Hopfield algorithm, it is respectively trained out the model on corresponding different wind direction, then the sample with remaining 30%
The model set up is tested.
Above-described embodiment sets up different forecast models for different classes of sample data, for example with
Hopfield neural network algorithm sets up specific wind-power electricity generation forecast model, by Hopfield neutral net
The forecast model that the study of sample characteristics is set up by algorithm, can not only reflect what wind-power electricity generation exported
Shortage term fluctuation, additionally it is possible to overcome the weakness of other Short-term Forecasting Model anti-noise ability differences.
3) hybrid wind power generation forecast model is set up
According to the sample weights of each model, on each wind direction will set up in back, forecast model closes
And, set up a new hybrid prediction model.The sample not carrying out fuzzy classification polymerization process is imported to
In Hopfield model, become original predictive model.Iterate hybrid prediction model and original predictive model,
Make model gradually restrain, finally tend towards stability, carry out contrasting by both results it appeared that mixed model
Precision is higher.
4) it is predicted
Use hybrid wind power generation forecast model when being predicted, it is judged that the wind direction of input data, according to really
Fixed wind direction, the wind-power electricity generation forecast model calling correspondence calculates wind power output power pre-of described wind energy turbine set
Measured value, the test result that output is corresponding.
Herein, in conjunction with an example, the Forecasting Methodology embodiment of above-mentioned hybrid wind power generation is once lifted
Example illustrates:
With reference to Fig. 3, it is dynamic wind rose and the contrast schematic diagram of electric power Flos Rosae Rugosae figure, passes through dynamic wind rose
Can tentatively judge that northeast, the southeast and northwest wind frequency upwards is maximum.Defeated for wind-force and electric power with regard to wind direction
For going out power, relatively big and wind-powered electricity generation the output of the wind-force in direction is the highest northeast；Next to that come
From northwest and the wind of southeast both direction, although the wind-force in the two direction is the biggest, but its correspondence
Output is the least.Therefore, it is necessary to be separated consideration when modeling.So, present problem is just come
, in training sample, some data is between the classification that this three class is different, it is impossible to the most effective
It is made a distinction.In order to reach to quantify and objective effect, this example uses the method for fuzzy clustering to instruct
Practice sample according to it: the corresponding relation of wind direction, wind-force and output is divided into three classes, the most why selects
Fuzzy hierarchy cluster is because we have found that not only some sample point it being different between two kinds using in data
It is difficult to differentiate between classification, and there is also level association between different other classes, as shown in Figure 4.Logical
Cross fuzzy hierarchy cluster, it can be determined which kind of each sample point belongs to actually, and the pass between class and class
Connection degree how, and the most original training sample just effectively be divide into different classifications.As it is shown in figure 5,
The difference of these sample point categories is put forward, just obtains three groups of new samples, and each class sample number
According to all correspond to a kind of wind-powered electricity generation input/output relation specific, rational, and then can be by these three groups of data
Set up regression model, obtain wind-powered electricity generation forecast model based on different wind speed and directions.
With reference to Fig. 6, it is the prediction of the archetype before hybrid wind power generation forecast model and mixed processing
Comparative result schematic diagram.In this example, Hopfield model is used to set up the model on different wind direction respectively,
Wind-force forecast error in result display northeastward is minimum, and the error that northwest is upwards is maximum, finally will
Three model combinations are hybrid prediction model.Carry out with archetype contrasting (result is as shown in Figure 6): mix
The mean square deviation of wind-power electricity generation forecast model is less than the mean square deviation of archetype, and the former is 18.32, and the latter is 35.1；
The R side of hybrid wind power generation forecast model is 0.73, compared to archetype 0.7 closer to 1, also
That is, in hybrid wind power generation forecast model, independent variable can preferably explain dependent variable.Though additionally,
So the operation time of hybrid prediction model is slightly longer, but its difference is only 0.38 second, has no effect on reality
Operation.Therefore, from predicting the outcome, hybrid wind power generation forecast model can obtain higher precision, and
And practical operation can be applied to.
To sum up, clustering and the mixing of Hopfield neutral net based on fuzzy hierarchy described in the various embodiments described above
The advantage of wind-powered electricity generation forecast model is: during being predicted wind power output power, considers wind direction simultaneously
With the impact of two aspects of wind-force, and according to wind direction, the corresponding relation of wind-force and wind power output power, by it
Carry out fuzzy hierarchy cluster.As such, it is possible to the sampled data that a group has noise redundancy to be divided into corresponding several parts
There is the sample data of internal association, then these sample datas are modeled respectively, different classes of data
Internal characteristics just can be fully demonstrated by different models, thus carry out model prediction targetedly, it was predicted that
Precision also thus increase.
It should be noted that for aforesaid embodiment of the method, in order to be briefly described, therefore it is all expressed as
A series of combination of actions, but those skilled in the art should know, and the present invention is not moved by described
The restriction of work order, because according to the present invention, some step can use other orders or carry out simultaneously.
Secondly, those skilled in the art also should know, embodiment described in this description belongs to be preferable to carry out
Example, involved action is the most essential to the invention.
System embodiment
For realizing said method, the present embodiment proposes the prognoses system of a kind of hybrid wind power generation, such as Fig. 7 and
Shown in Fig. 8, the prognoses system embodiment of this hybrid wind power generation includes: data input device 101, configuration
There are test device 102 and the output device 103 of hybrid wind power generation forecast model.
In the prognoses system of this hybrid wind power generation, data input device 101 is used for obtaining test data；
Test device 102 is for the test data according to data input device 101 input, it is judged that the wind of input data
To, according to determined by wind direction, call in described hybrid wind power generation forecast model 1021 corresponding with wind direction
Wind-power electricity generation forecast model, tests the output production capacity of wind power plant；Output device 103 is used for obtaining
Take the prediction of the wind power output power of the described wind energy turbine set that the test of described hybrid wind power generation forecast model obtains
Value, and export the test result of correspondence.
In above-described embodiment, the prognoses system of this hybrid wind power generation may also include that data modeling and revises dress
Put 104, be used for setting up hybrid wind power generation forecast model 1021 and revising or optimize hybrid wind power generation
Forecast model 1021, therefore, data modeling and correcting device 104 farther include consisting of:
1) decimation blocks 201, for the wind-powered electricity generation output of wind direction, wind speed and correspondence to acquired wind energy turbine set
The historical data of power is sampled obtaining sample data；
2) analyze module 202, for the statistical property of described sample data is carried out discriminatory analysis, obtain wind
Frequency concentration and wind power output power difference reach the wind direction of discrepancy threshold；
3) processing module 203, for according to acquired wind direction and with wind speed, wind power output power right
Employing fuzzy hierarchy clustering procedure should be related to, described sample data is divided into three classes；
4) model block 204 at the beginning of model, be used for using neural network algorithm that every class sample is trained, corresponding
Form three classes specific wind-power electricity generation forecast model；
5) mixed processing module 205, for merging place by this three class specific wind-power electricity generation forecast model
Reason, forms the hybrid wind power generation forecast model for being predicted wind-power electricity generation production capacity.
As the optional embodiment of one, in above-described embodiment, the prognoses system of hybrid wind power generation also may be used
Including:
6) test correcting module 206, for obtaining the sample data of test, to the mixing wind-force set up
Generating forecast model carries out debugging, revising.
From the point of view of further, in an alternative embodiment, above-mentioned mixed processing module 205 may also include following group
Become:
Parameter configuration unit 51, for the most described three class specific wind-power electricity generation forecast model configuration correspondence
Sample weights parameter；
Merging treatment unit 52, for the sample weights parameter according to each forecast model, will build according to wind direction
Vertical forecast model merges, and sets up hybrid wind power generation forecast model；
Iterative optimization unit 53, for iterating described hybrid wind power generation forecast model, makes institute
State hybrid wind power generation forecast model gradually to restrain, until output result tends towards stability.
As the optional embodiment of one, above-mentioned hybrid wind power generation forecast model 1021 farther include with
Lower comprising modules:
Wind direction recognition unit, for judging to input the wind direction of data；
Model call unit, for wind direction determined by basis, calls described hybrid wind power generation forecast model
The wind-power electricity generation forecast model of middle correspondence, tests the output production capacity of wind power plant.
Obviously, those skilled in the art should be understood that the hybrid wind power generation of the above-mentioned embodiment of the present invention
The each module of prognoses system or each step of Forecasting Methodology of hybrid wind power generation can be with general calculating device
Realizing, they can concentrate on single calculating device, or be distributed in what multiple calculating device was formed
On network, alternatively, they can realize with calculating the executable program code of device, it is thus possible to
It is stored in storing in device and is performed by calculating device, or it is integrated that they are fabricated to respectively
Circuit module, or the multiple modules in them or step are fabricated to single integrated circuit module realize.
So, the present invention is not restricted to the combination of any specific hardware and software.Described storage device is non-volatile
Memorizer, such as: ROM/RAM, flash memory, magnetic disc, CD etc..
The foregoing is only embodiments of the invention, not in order to limit the present invention, all the present invention's
Within spirit and principle, any modification, equivalent substitution and improvement etc. made, should be included in the present invention's
Within protection domain.
Claims (10)
1. the Forecasting Methodology of a hybrid wind power generation, it is characterised in that including:
Obtain the historical data of the wind power output power of the wind direction of wind energy turbine set, wind speed and correspondence, and go through described
History data are sampled obtaining sample data；
The statistical property of described sample data is carried out discriminatory analysis, obtains wind frequency and concentrate and wind power output power
Difference reaches the wind direction of discrepancy threshold, and according to acquired wind direction and with wind speed, wind power output power
Corresponding relation uses fuzzy hierarchy clustering procedure, and described sample data is divided into three classes；
Use neural network algorithm that every class sample is trained, be correspondingly formed the three specific wind-power electricity generations of class pre-
Survey model, this three class specific wind-power electricity generation forecast model is merged process, set up for wind-force is sent out
The hybrid wind power generation forecast model that electricity production capacity is predicted.
The Forecasting Methodology of hybrid wind power generation the most according to claim 1, it is characterised in that also include:
Obtain the sample data of test, the hybrid wind power generation forecast model set up is debugged；
According to the test result of hybrid wind power generation forecast model output, described hybrid wind power generation is predicted mould
Type is modified；
Wherein, the sample data of described test is defeated from the wind-powered electricity generation of wind direction, wind speed and the correspondence of described wind energy turbine set
Go out sampling in the historical data of power to obtain.
The Forecasting Methodology of hybrid wind power generation the most according to claim 1 and 2, it is characterised in that also
Including:
Utilize described hybrid wind power generation forecast model, the output production capacity of wind power plant is tested；
When being predicted, it is judged that input data wind direction, according to determined by wind direction, call correspondence wind
Power generating forecast model calculates the predictive value of the wind power output power of described wind energy turbine set, the test knot that output is corresponding
Really.
The Forecasting Methodology of hybrid wind power generation the most according to claim 1, it is characterised in that described mixed
The generation type closing wind-power electricity generation forecast model also includes:
It is respectively the sample weights parameter that the configuration of described three class specific wind-power electricity generation forecast model is corresponding；
Sample weights parameter according to each forecast model, merges the forecast model set up according to wind direction,
Set up hybrid wind power generation forecast model.
5., according to the Forecasting Methodology of the hybrid wind power generation described in any one of Claims 1-4, its feature exists
In, the method also includes:
Described hybrid wind power generation forecast model is iterated, makes described hybrid wind power generation predict mould
Type gradually restrains, until output result tends towards stability.
6. the prognoses system of a hybrid wind power generation, it is characterised in that including:
Decimation blocks, is used for the wind power output power of wind direction, wind speed and correspondence to acquired wind energy turbine set
Historical data is sampled obtaining sample data；
Analyze module, for the statistical property of described sample data is carried out discriminatory analysis, obtain wind frequency and concentrate
And wind power output power difference reaches the wind direction of discrepancy threshold；
Processing module, for according to acquired wind direction and with wind speed, the corresponding relation of wind power output power
Use fuzzy hierarchy clustering procedure, described sample data is divided into three classes；
Model block at the beginning of model, be used for using neural network algorithm that every class sample is trained, be correspondingly formed three
Class specific wind-power electricity generation forecast model；
Mixed processing module, for merging process, shape by this three class specific wind-power electricity generation forecast model
Become the hybrid wind power generation forecast model for wind-power electricity generation production capacity is predicted.
The prognoses system of hybrid wind power generation the most according to claim 6, it is characterised in that this system
Also include:
Test correcting module, for obtaining the sample data of test, pre-to the hybrid wind power generation set up
Survey model to carry out debugging, revise and optimizing.
8. according to the prognoses system of the hybrid wind power generation described in claim 6 or 7, it is characterised in that should
System also includes:
Data input device, is used for obtaining test data；
Test device, is configured with described hybrid wind power generation forecast model, for according to acquired test number
According to, it is judged that input data wind direction, according to determined by wind direction, call described hybrid wind power generation prediction mould
Wind-power electricity generation forecast model corresponding in type, tests the output production capacity of wind power plant；
Output device, for obtaining the described wind energy turbine set that the test of described hybrid wind power generation forecast model obtains
The predictive value of wind power output power, and export the test result of correspondence.
9., according to the prognoses system of the hybrid wind power generation described in any one of claim 6 to 8, its feature exists
In, described mixed processing module also includes:
Parameter configuration unit, for the most described three class specific wind-power electricity generation forecast model configuration correspondence
Sample weights parameter；
Merging treatment unit, for the sample weights parameter according to each forecast model, will set up according to wind direction
Forecast model merge, set up hybrid wind power generation forecast model；
Iterative optimization unit, for iterating described hybrid wind power generation forecast model, makes described
Hybrid wind power generation forecast model is gradually restrained, until tending towards stability.
10. according to the prognoses system of the hybrid wind power generation described in any one of claim 6 to 9, its feature
Being, described hybrid wind power generation forecast model farther includes:
Wind direction recognition unit, for judging to input the wind direction of data；
Model call unit, for wind direction determined by basis, calls described hybrid wind power generation forecast model
The wind-power electricity generation forecast model of middle correspondence, tests the output production capacity of wind power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610300971.7A CN105930900B (en) | 2016-05-09 | 2016-05-09 | The Forecasting Methodology and system of a kind of hybrid wind power generation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610300971.7A CN105930900B (en) | 2016-05-09 | 2016-05-09 | The Forecasting Methodology and system of a kind of hybrid wind power generation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105930900A true CN105930900A (en) | 2016-09-07 |
| CN105930900B CN105930900B (en) | 2018-02-27 |
Family
ID=56835381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610300971.7A Active CN105930900B (en) | 2016-05-09 | 2016-05-09 | The Forecasting Methodology and system of a kind of hybrid wind power generation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105930900B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529741A (en) * | 2016-12-12 | 2017-03-22 | 国网电力科学研究院 | Space relevant characteristic-based ultra-short-period wind power prediction method |
| CN108596415A (en) * | 2017-12-15 | 2018-09-28 | 阿里巴巴集团控股有限公司 | A kind of model integration method and device |
| CN108898251A (en) * | 2018-06-29 | 2018-11-27 | 上海电力学院 | Consider the marine wind electric field power forecasting method of meteorological similitude and power swing |
| CN109597901A (en) * | 2018-11-15 | 2019-04-09 | 韶关学院 | A kind of data analysing method based on biological data |
| CN110276468A (en) * | 2018-03-14 | 2019-09-24 | 北京金风科创风电设备有限公司 | Method and device for predicting generated power of wind generating set |
| CN111353629A (en) * | 2018-12-24 | 2020-06-30 | 顺丰科技有限公司 | Frequency updating method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184453A (en) * | 2011-05-16 | 2011-09-14 | 上海电气集团股份有限公司 | Wind power combination predicting method based on fuzzy neural network and support vector machine |
| KR20150082804A (en) * | 2014-01-08 | 2015-07-16 | 김상훈 | Vertical wind turbines |
| JP2015203387A (en) * | 2014-04-16 | 2015-11-16 | 株式会社日立製作所 | Wind turbine generator system |
| CN105389634A (en) * | 2015-12-01 | 2016-03-09 | 广东智造能源科技研究有限公司 | Combined short-term wind power prediction system and method |
-
2016
- 2016-05-09 CN CN201610300971.7A patent/CN105930900B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184453A (en) * | 2011-05-16 | 2011-09-14 | 上海电气集团股份有限公司 | Wind power combination predicting method based on fuzzy neural network and support vector machine |
| KR20150082804A (en) * | 2014-01-08 | 2015-07-16 | 김상훈 | Vertical wind turbines |
| JP2015203387A (en) * | 2014-04-16 | 2015-11-16 | 株式会社日立製作所 | Wind turbine generator system |
| CN105389634A (en) * | 2015-12-01 | 2016-03-09 | 广东智造能源科技研究有限公司 | Combined short-term wind power prediction system and method |
Non-Patent Citations (2)
| Title |
|---|
| 吴丹丹: ""风电场输出功率组合算法的研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 方江晓: ""短期风速和风电功率预测模型的研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529741A (en) * | 2016-12-12 | 2017-03-22 | 国网电力科学研究院 | Space relevant characteristic-based ultra-short-period wind power prediction method |
| CN106529741B (en) * | 2016-12-12 | 2019-12-06 | 国网电力科学研究院 | Ultra-short-term wind power prediction method based on spatial correlation characteristics |
| CN108596415A (en) * | 2017-12-15 | 2018-09-28 | 阿里巴巴集团控股有限公司 | A kind of model integration method and device |
| US11132624B2 (en) | 2017-12-15 | 2021-09-28 | Advanced New Technologies Co., Ltd. | Model integration method and device |
| CN108596415B (en) * | 2017-12-15 | 2023-11-24 | 创新先进技术有限公司 | Model integration method and device |
| CN110276468A (en) * | 2018-03-14 | 2019-09-24 | 北京金风科创风电设备有限公司 | Method and device for predicting generated power of wind generating set |
| CN108898251A (en) * | 2018-06-29 | 2018-11-27 | 上海电力学院 | Consider the marine wind electric field power forecasting method of meteorological similitude and power swing |
| CN109597901A (en) * | 2018-11-15 | 2019-04-09 | 韶关学院 | A kind of data analysing method based on biological data |
| CN111353629A (en) * | 2018-12-24 | 2020-06-30 | 顺丰科技有限公司 | Frequency updating method and device |
| CN111353629B (en) * | 2018-12-24 | 2023-09-29 | 顺丰科技有限公司 | Frequency updating method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105930900B (en) | 2018-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930900A (en) | Method and system for predicting hybrid wind power generation | |
| CN109614997A (en) | A kind of stealing Risk Forecast Method and device based on deep learning | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN108375808A (en) | Dense fog forecasting procedures of the NRIET based on machine learning | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN108664010A (en) | Generating set fault data prediction technique, device and computer equipment | |
| CN106777984A (en) | A kind of method that photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm | |
| CN110442833A (en) | One kind assessing Wind turbines health state evaluation method based on various dimensions SCADA data | |
| CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
| CN113298297B (en) | Wind power output power prediction method based on isolated forest and WGAN network | |
| CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
| CN105846780A (en) | Decision tree model-based photovoltaic assembly fault diagnosis method | |
| CN105975797B (en) | A kind of product initial failure root primordium recognition methods based on Fuzzy data processing | |
| CN110703057A (en) | Power equipment partial discharge diagnosis method based on data enhancement and neural network | |
| CN104408562A (en) | Photovoltaic system generating efficiency comprehensive evaluation method based on BP (back propagation) neural network | |
| CN108053128A (en) | A kind of Power Network Transient Stability fast evaluation method based on ELM and TF | |
| CN108876163A (en) | The transient rotor angle stability fast evaluation method of comprehensive causality analysis and machine learning | |
| CN104112062B (en) | The acquisition methods of wind-resources distribution based on interpolation method | |
| CN114358427B (en) | Method for predicting final recoverable reserves of shale gas well | |
| CN104239712A (en) | Real-time evaluation method for anti-interference performance of radar | |
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| CN102147839A (en) | Method for forecasting photovoltaic power generation quantity | |
| CN116432123A (en) | Electric energy meter fault early warning method based on CART decision tree algorithm | |
| CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
| CN108734359A (en) | A kind of wind power prediction data preprocessing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Song Xiaohua Inventor after: Zhang Yulin Inventor after: Long Yun Inventor after: Zhang Xubei Inventor after: Li Leming Inventor before: Song Xiaohua Inventor before: Zhang Yulin Inventor before: Li Leming |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |