CN106849066A - A kind of regional wind power prediction method - Google Patents
A kind of regional wind power prediction method Download PDFInfo
- Publication number
- CN106849066A CN106849066A CN201710130285.4A CN201710130285A CN106849066A CN 106849066 A CN106849066 A CN 106849066A CN 201710130285 A CN201710130285 A CN 201710130285A CN 106849066 A CN106849066 A CN 106849066A
- Authority
- CN
- China
- Prior art keywords
- wind power
- power plant
- wind
- data
- region
- 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
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution 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
- 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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/16—Energy services, e.g. dispersed generation or demand or load or energy savings aggregation
Abstract
The application is related to a kind of regional wind power prediction method, belongs to technical field of wind power generation.The method includes：The wind-powered electricity generation data of each wind power plant in the region of the same line topological of collection access；Association between power data and air speed data and polymerization property in described each wind power plant wind-powered electricity generation data, are grouped to each wind power plant in the region；According to the wind-powered electricity generation data of wind power plant in described each wind power plant group, forecast model is set up；According to the forecast model, the power of prediction each wind power plant group；The wind power superposition of each wind power plant group that will be predicted, obtains region wind power prediction value.The method considers associating between the air speed data of each wind power plant in region and power data and polymerization property, the polymerization of wind-powered electricity generation data is realized using clustering algorithm, and by setting up prediction of the deep neural network model realization to region wind power, improve the accuracy of region wind power prediction.
Description
Technical field
The application is related to a kind of regional wind power prediction method, belongs to technical field of wind power generation.
Background technology
Wind-power electricity generation belongs to fluctuation and intermittent power supply, wind power output have randomness it is relatively strong, it is intermittent substantially, power
The features such as not possessing regulating power.Wind-powered electricity generation direct grid-connected can bring very big shadow to the stability of power system and the quality of power supply
Ring, some areas even wind farm grid-connected power of selectional restriction ensures the normal operation of power network.Thus wind power is carried out
Accurate ultra-short term prediction can provide data support for dispatching of power netwoks personnel, help to reduce the spinning reserve capacity of power network,
Improve the economy and stability of network system.
At present, the construction of wind power plant generally has sociability, and multiple wind power plants are connected to the grid system by same circuit,
Meteorological and the electric data of collection contain much information and with internal association and polymerization property.Opened up with specific circuit in power prediction
It is object to flutter, and output of wind electric field in regional power grid is predicted more quick, effective.However, directly predicting wind power output
Method does not consider association and the polymerization property of wind-powered electricity generation data, causes its precision of prediction relatively low.Accordingly, it would be desirable to a kind of new wind-powered electricity generation
Go out force prediction method, to improve the accuracy predicted region ultrashort-term wind power.
The content of the invention
This application provides a kind of regional wind power prediction method, to improve what region ultrashort-term wind power was predicted
Accuracy.
A kind of regional wind power prediction method, including：
The wind-powered electricity generation data of each wind power plant in step one, the region of the same line topological of collection access；
Step 2, the power data in described each wind power plant wind-powered electricity generation data and the association between air speed data with it is poly-
Characteristic is closed, each wind power plant in the region is grouped；
Step 3, the wind-powered electricity generation data according to wind power plant in described each wind power plant group, set up forecast model；
Step 4, according to the forecast model, the power of prediction each wind power plant group；
The wind power superposition of step 5, each wind power plant group that will be predicted, obtains region wind power prediction value.
Alternatively, the line topological is the single electrical grid transmission circuit for only accessing multiple wind power plants.
Alternatively, the association between the power data and air speed data in the wind-powered electricity generation data according to each wind power plant with
Polymerization property, is grouped to the wind power plant in the region, including：
Association and polymerization property between the power data and air speed data of the wind-powered electricity generation data according to each wind power plant,
Using k means clustering algorithms, the wind power plant in the region is grouped.
Alternatively, the step of k means clustering algorithms include：Determine that the cluster of each wind power plant is defeated according to historical data
Enter characteristic vector；Determine initial cluster center；It is determined that new cluster centre；Determine the packet knot of each wind power plant in the region
Really.
Alternatively, the historical data includes：The history of the power of each wind power plant and the region wind power
Coefficient correlation between value, the average value of the power data of each wind power plant, maximum and variance, described each wind power plant
The average value of air speed data, maximum and variance.
Alternatively, the forecast model is deep neural network forecast model, wherein, the deep neural network predicts mould
The input of type includes：The wind series of main wind power plant and wind power sequence in wind power plant group, from the air speed data of wind power plant
Average value, maximum and variance, average value, maximum and variance from the power data of wind power plant；The depth nerve
Network Prediction Model is output as the predicted value of wind power plant group power；
The main wind power plant is wind power plant nearest away from cluster centre during wind power plant group cluster, described to be from wind power plant
Main wind-powered electricity generation wind power plant outside the venue is removed in the wind power plant group.
The technical scheme that the application is provided includes following Advantageous Effects：
The application with specific circuit topology under region in each wind power plant as object, according to the power number of the wind power plant
Wind power plant is grouped according to the association with air speed data and polymerization property, and it is pre- to set up depth nerve based on deep learning theory
Model is surveyed, according to input data autonomous learning optimal characteristics, association and polymerization property fully to excavate, between learning data are real
Now to the ultra-short term prediction of region wind power, the accuracy of region wind power prediction is improved.
Brief description of the drawings
In order to illustrate more clearly of the technical scheme of the application, letter will be made to the accompanying drawing to be used needed for embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without having to pay creative labor,
Other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of flow chart of regional wind power prediction method.
Specific embodiment
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the implementation for meeting the application
Example, and it is used to explain the principle of the application together with specification.
In order to illustrate more clearly of the application or technical scheme of the prior art, below will be to embodiment or prior art
The accompanying drawing to be used needed for description is briefly described, it should be apparent that, for those of ordinary skills, not
On the premise of paying creative labor, other accompanying drawings can also be obtained according to these accompanying drawings.
A kind of regional wind power prediction method, comprises the following steps：
The wind-powered electricity generation data of each wind power plant in step one, the region of the same line topological of collection access.
Alternatively, the line topological is the single electrical grid transmission circuit for only accessing multiple wind power plants.The wind power plant
Wind-powered electricity generation data include the history value of the air speed data, power data and the region wind power of the wind power plant.
Step 2, the power data in described each wind power plant wind-powered electricity generation data and the association between air speed data with it is poly-
Characteristic is closed, each wind power plant in the region is grouped.
Associate feature refers in a wind power plant cluster, due to each wind power plant be closer on locus and
Interconnected on topological structure of electric, each survey wind data of sub- wind power plant and power monitoring data are each other in wind power plant cluster
Influence, the incidence relation that there is inherence；Polymerization property then refers to when multiple wind power plants are distributed Relatively centralized and company on locus
When being connected to same electrical communication line, the wind speed of each wind power plant, power data can have a certain degree of uniformity, can use
The means of data aggregate merge the data of each wind power plant to carry out unified analyzing and processing.
Alternatively, the association between the power data and air speed data of the wind-powered electricity generation data of each wind power plant described in the basis
With polymerization property, the wind power plant in the region is grouped, including：The work(of the wind-powered electricity generation data according to each wind power plant
Association and polymerization property between rate data and air speed data, using k means clustering algorithms, enter to the wind power plant in the region
Row packet；Wherein, the cluster input feature value of the k means clustering algorithms is calculated according to historical data, the historical data
Including：Coefficient correlation between the history value of the power of each wind power plant and the region wind power, described each wind
The average value of the power data of electric field, maximum and variance, the average value of the air speed data of each wind power plant, maximum and
Variance.
The k means clustering algorithms are comprised the following steps that：
(1) cluster input feature value is determined.The cluster input feature value is that each wind power plant is used for k mean clusters
The data of algorithm.The cluster input feature value is calculated according to historical data, and the historical data includes：Described each wind power plant
Power and the history value of the region wind power between coefficient correlation, the power data of each wind power plant it is average
Value, maximum and variance, the average value of the air speed data of each wind power plant, maximum and variance.
(2) initial cluster center is determined.Select k cluster defeated from the cluster input feature value of each wind power plant
Enter characteristic vector as initial cluster center.
(3) new cluster centre is determined.The cluster input feature value and current each for calculating each wind power plant gather
Euclidean distance between class center, described each wind power plant being divided in cluster the closest cluster of input feature value with it
In classification representated by the heart, after all wind power plants are divided in a certain class, each apoplectic stroke electric field cluster feature vector is calculated
Average value as new cluster centre.
(4) group result of wind power plant is determined.Repeat step (3) is until cluster centre no longer changes or reach maximum repetition
Calculation times, and using the result of now wind power plant category division as final cluster result, i.e. wind power plant group result.
In conjunction with five wind power plants on the circuit of somewhere, to the consideration association and the region wind-powered electricity generation work(of polymerization property
The wind power plant group technology of the Forecasting Methodology of rate is illustrative.Data shown in table 1 include accessing same line topological
Region in each wind power plant power and region wind power history value coefficient correlation, the power data of each wind power plant
Average value, maximum and variance, the average value of each wind farm wind velocity data, maximum and variance.
The historical data of table 1 each wind power plant
In table 1, shown in the computing formula such as formula (1) of coefficient correlation：
Wherein, rxyIt is the power and region wind power history value of each wind power plant in the region for accessing same line topological
Coefficient correlation；xiIt is the power of each wind power plant；It is the average value of each wind power；yiFor region wind power is gone through
History value；It is the average value of region wind power history value, i=1,2 ... n (n is wind power plant number).
Shown in the computing formula of variance such as formula (2)：
Wherein, D is the variance of each wind power/wind speed；xiIt is the power/wind speed of each wind power plant；It is each wind
The average value of electric field power/wind speed, i=1,2 ... ..., n (n is wind power plant number).
Association and polymerization property in view of wind farm data, it is equal that 5 data of wind power plant according to table 1 carry out k
Value cluster calculation is grouped to each wind power plant in region, wherein, k=2 is taken, wind farm group is divided into two wind as follows
Electric field group：
Wind power plant group 1：Wind power plant 1, wind power plant 2, wind power plant 3, wind power plant 4；
Wind power plant group 2：Wind power plant 5.
Step 3, the wind-powered electricity generation data according to wind power plant in described each wind power plant group, set up forecast model
Alternatively, the forecast model is deep neural network forecast model, the deep neural network forecast model
Input includes：The wind series of main wind power plant and wind power sequence in wind power plant group, from the average of the air speed data of wind power plant
Value, maximum and variance, average value, maximum and variance from the power data of wind power plant；The deep neural network
Forecast model is output as the predicted value of wind power plant group power；
The wind series refer to the air speed data of anemometer tower collection in wind power plant, and the air speed data is at regular intervals
It is spaced average value of the T records air speed data once in T time.
The wind power sequence refers to the Power Output for Wind Power Field data of wind power's supervision equipment record, the power data
To be spaced average value of the T records wind power output power once in T time at regular intervals.
The main wind power plant is wind power plant nearest away from cluster centre during the cluster calculation of wind power plant group, described from wind
Electric field is except main wind-powered electricity generation other wind power plants outside the venue in the wind power plant group.
During the cluster centre refers to wind power plant group, the average value of the cluster input feature value of each wind power plant.
The deep neural network forecast model is more conventional depth artificial neural network mould in deep learning theory
Type, the model includes input layer, hidden layer (multilayer), output layer, and only has connection between the node of adjacent layer, same layer with
And it is mutually connectionless between cross-layer node.The neural network prediction model carries out wind power prediction by object of wind power plant group,
Take full advantage of the associate feature of each wind power plant in region；Neural network prediction model input not only includes the wind power plant group
Middle main wind farm data, further comprises group in other from wind-powered electricity generation data, take full advantage of the association of each wind power plant wind-powered electricity generation data
Characteristic.
Easily there is over-fitting and not convergent phenomenon when the mapping of such input and output is fitted in traditional neural network model,
Cause model prediction accuracy relatively low, so that setting up increasingly complex depth artificial nerve network model to process this mapping
Relation.Alternatively, in the present embodiment, the deep neural network forecast model is by the programming realization on MATLAB platforms,
Mode input layer includes 40 nodes, and output layer includes 16 nodes, i.e., 40 dimensions are input into, 16 dimension outputs, and hidden layer is 7 layers, often
Layer includes 90 nodes.
Step 4, according to the deep neural network forecast model, the power of prediction each wind power plant group.
The deep neural network forecast model can according to input feature value autonomous learning optimal characteristics, fully to excavate,
Association and polymerization property between learning data, realize to the complicated function relation fitting between input data and output data, to carry
Accuracy to region wind power prediction high, and realize the ultra-short term prediction to wind power plant wind power in region.
From time scale angle divide, typically can by wind power prediction be divided into medium- and long-term forecasting, short-term forecast and
Ultra-short term is predicted.Wherein, ultra-short term prediction is general can predict the wind-powered electricity generation of following 0-4h with " hour ", " minute " for unit
Power output.
Specifically, in this step, each wind power plant group can be predicted using the deep neural network model carries out following 4
The ultra-short term performance number of hours yardstick.
The wind power superposition of step 5, each wind power plant group that will be predicted, obtains region wind power prediction value.
To verify the validity of the Forecasting Methodology, area power is directly predicted and is associated and polymerization property with the consideration
Two methods of region wind power prediction are contrasted, as a result as shown in table 2.
The Forecasting Methodology results contrast of table 2
| Forecasting Methodology | MAE | MSE | R |
| Directly predict | 0.9743 | 2.3254 | 0.9953 |
| Consider association with polymerization property prediction | 0.8764 | 1.8078 | 0.9963 |
In table 2, the computing formula of MAE (mean absolute error) is formula (3), and the computing formula of MSE (mean square error) is
Formula (4), R is the cross-correlation coefficient for predicting power sequence and actual power sequence.
Wherein, Pt,iIt is the i-th time period actual power；Pp,iIt is the i-th time period pre- power scale.
From table 2 it can be seen that compared with DIRECT FORECASTING METHOD, it is considered to the region wind power prediction of association and polymerization property
MAE the and MSE values of method have dropped 10.05% and 22.26% respectively, and precision of prediction is obviously improved, the R values of two methods result
Change is little, but the R values obtained by deep learning methods and resultses have still obtained certain raising.
The application with specific circuit topology under region in each wind power plant as object, according to each wind power plant in region
The association of power data and air speed data wind power plant is grouped with polymerization property, and set up deep based on deep learning is theoretical
Degree neural prediction model, according to input data autonomous learning optimal characteristics, association fully to excavate, between learning data be polymerized
Characteristic, realizes the ultra-short term prediction to region wind power, improves the accuracy of wind power prediction.
It should be noted that term " including ", "comprising" or its any other variant be intended to the bag of nonexcludability
Contain, so that article or equipment including a series of key elements not only include those key elements, but also including not arranging clearly
Other key elements for going out, or it is this process, method, article or the intrinsic key element of equipment also to include.Not more
In the case of limitation, the key element limited by sentence "including a ...", it is not excluded that in the process including the key element, side
Also there is other identical element in method, article or equipment.
The above is only the specific embodiment of the application, is made skilled artisans appreciate that or realizing this Shen
Please.Various modifications to these embodiments will be apparent to one skilled in the art, as defined herein
General Principle can in other embodiments be realized in the case where spirit herein or scope is not departed from.Therefore, the application
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The scope most wide for causing.
It should be appreciated that the application is not limited to the content being described above, and its model can not departed from
Enclosing carries out various modifications and changes.Scope of the present application is only limited by appended claim.
Claims (6)
1. a kind of regional wind power prediction method, it is characterised in that methods described includes：
The wind-powered electricity generation data of each wind power plant in the region of the same line topological of collection access；
Association between power data and air speed data and polymerization property in described each wind power plant wind-powered electricity generation data, to institute
Each wind power plant is grouped in stating region；
According to the wind-powered electricity generation data of wind power plant in described each wind power plant group, forecast model is set up；
According to the forecast model, the power of prediction each wind power plant group；
The wind power superposition of each wind power plant group that will be predicted, obtains region wind power prediction value.
2. method according to claim 1, it is characterised in that the line topological is only access multiple wind power plants single
Electrical grid transmission circuit.
3. the method according to claim any one of 1-2, it is characterised in that according in described each wind power plant wind-powered electricity generation data
Power data and air speed data between association and polymerization property, each wind power plant in the region is grouped, including：
Association and polymerization property between the power data and air speed data of the wind-powered electricity generation data according to each wind power plant, use
K means clustering algorithms, are grouped to the wind power plant in the region.
4. method according to claim 3, it is characterised in that include the step of the k means clustering algorithms：
The cluster input feature value of each wind power plant is determined according to historical data；
Determine initial cluster center；
It is determined that new cluster centre；
Determine the group result of each wind power plant in the region.
5. method according to claim 4, it is characterised in that the historical data includes：The work(of each wind power plant
Coefficient correlation between the history value of rate and the region wind power, the average value of the power data of each wind power plant,
Maximum and variance, the average value of the air speed data of each wind power plant, maximum and variance.
6. method according to claim 1, it is characterised in that the forecast model is deep neural network forecast model,
Wherein,
The input of the deep neural network forecast model includes：The wind series and wind power of main wind power plant in wind power plant group
Sequence, average value, maximum and variance from the air speed data of wind power plant, average value from the power data of wind power plant, most
Big value and variance；The deep neural network forecast model is output as the predicted value of wind power plant group power；
The main wind power plant is wind power plant nearest away from cluster centre during wind power plant group cluster, and described is described from wind power plant
Main wind-powered electricity generation wind power plant outside the venue is removed in wind power plant group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710130285.4A CN106849066A (en) | 2017-03-07 | 2017-03-07 | A kind of regional wind power prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710130285.4A CN106849066A (en) | 2017-03-07 | 2017-03-07 | A kind of regional wind power prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106849066A true CN106849066A (en) | 2017-06-13 |
Family
ID=59137449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710130285.4A Pending CN106849066A (en) | 2017-03-07 | 2017-03-07 | A kind of regional wind power prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106849066A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909219A (en) * | 2017-12-06 | 2018-04-13 | 广东工业大学 | A kind of day electricity sales amount Forecasting Methodology and system based on dual cluster |
| CN108074015A (en) * | 2017-12-25 | 2018-05-25 | 中国电力科学研究院有限公司 | A kind of ultrashort-term wind power prediction method and system |
| CN108448610A (en) * | 2018-03-12 | 2018-08-24 | 华南理工大学 | A kind of short-term wind power prediction method based on deep learning |
| CN108985515A (en) * | 2018-07-24 | 2018-12-11 | 国网河南省电力公司电力科学研究院 | A kind of new energy based on independent loops neural network goes out force prediction method and system |
| CN109658006A (en) * | 2018-12-30 | 2019-04-19 | 广东电网有限责任公司 | A kind of large-scale wind power field group auxiliary dispatching method and device |
| CN110991122A (en) * | 2019-11-19 | 2020-04-10 | 浙江大学 | Wind power system reliability estimation method using neural network and cross entropy sampling |
| CN112231976A (en) * | 2020-10-15 | 2021-01-15 | 华北电力大学（保定） | Method for establishing equivalent model of wind power plant |
| CN113570132A (en) * | 2021-07-23 | 2021-10-29 | 华中科技大学 | Wind power prediction method for space-time meteorological feature extraction and deep learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204287917U (en) * | 2014-10-24 | 2015-04-22 | 云南电网公司电力科学研究院 | A kind of wind energy turbine set field level AVC system hardware framework based on Clustering |
| CN105654207A (en) * | 2016-01-07 | 2016-06-08 | 国网辽宁省电力有限公司锦州供电公司 | Wind power prediction method based on wind speed information and wind direction information |
-
2017
- 2017-03-07 CN CN201710130285.4A patent/CN106849066A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204287917U (en) * | 2014-10-24 | 2015-04-22 | 云南电网公司电力科学研究院 | A kind of wind energy turbine set field level AVC system hardware framework based on Clustering |
| CN105654207A (en) * | 2016-01-07 | 2016-06-08 | 国网辽宁省电力有限公司锦州供电公司 | Wind power prediction method based on wind speed information and wind direction information |
Non-Patent Citations (2)
| Title |
|---|
| 别朝红等: "一种考虑时空分布特性的区域风电功率预测方法", 《西安交通大学学报》 * |
| 高小力: "大型风电场分组建模方法及其在功率预测中的应用", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909219A (en) * | 2017-12-06 | 2018-04-13 | 广东工业大学 | A kind of day electricity sales amount Forecasting Methodology and system based on dual cluster |
| CN108074015A (en) * | 2017-12-25 | 2018-05-25 | 中国电力科学研究院有限公司 | A kind of ultrashort-term wind power prediction method and system |
| CN108074015B (en) * | 2017-12-25 | 2023-10-27 | 中国电力科学研究院有限公司 | Ultra-short-term prediction method and system for wind power |
| CN108448610A (en) * | 2018-03-12 | 2018-08-24 | 华南理工大学 | A kind of short-term wind power prediction method based on deep learning |
| CN108985515A (en) * | 2018-07-24 | 2018-12-11 | 国网河南省电力公司电力科学研究院 | A kind of new energy based on independent loops neural network goes out force prediction method and system |
| CN108985515B (en) * | 2018-07-24 | 2021-11-26 | 国网河南省电力公司电力科学研究院 | New energy output prediction method and system based on independent cyclic neural network |
| CN109658006A (en) * | 2018-12-30 | 2019-04-19 | 广东电网有限责任公司 | A kind of large-scale wind power field group auxiliary dispatching method and device |
| CN110991122A (en) * | 2019-11-19 | 2020-04-10 | 浙江大学 | Wind power system reliability estimation method using neural network and cross entropy sampling |
| CN110991122B (en) * | 2019-11-19 | 2021-08-10 | 浙江大学 | Wind power system reliability estimation method using neural network and cross entropy sampling |
| CN112231976A (en) * | 2020-10-15 | 2021-01-15 | 华北电力大学（保定） | Method for establishing equivalent model of wind power plant |
| CN112231976B (en) * | 2020-10-15 | 2023-06-13 | 华北电力大学（保定） | Method for establishing wind farm equivalent model |
| CN113570132A (en) * | 2021-07-23 | 2021-10-29 | 华中科技大学 | Wind power prediction method for space-time meteorological feature extraction and deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106849066A (en) | A kind of regional wind power prediction method | |
| CN103268366A (en) | Combined wind power prediction method suitable for distributed wind power plant | |
| CN105069236B (en) | Consider the broad sense load joint probability modeling method of wind power plant node space correlation | |
| Asghar et al. | Estimation of wind speed probability distribution and wind energy potential using adaptive neuro-fuzzy methodology | |
| CN103942736B (en) | A kind of wind power plant multimachine equivalent modeling method | |
| CN105868853B (en) | Method for predicting short-term wind power combination probability | |
| CN108414848B (en) | A kind of multi-period comprehensive pre-warning method of power quality containing distributed power distribution network | |
| Hayes et al. | Equivalent power curve model of a wind farm based on field measurement data | |
| CN102012956A (en) | Wind farm equivalent method based on wind farm input wind speed and wind direction chance fluctuation | |
| CN106684905B (en) | A kind of wind power plant Dynamic Equivalence considering wind-powered electricity generation uncertainty in traffic | |
| CN106548418A (en) | Power system small interference stability appraisal procedure | |
| CN103489046A (en) | Method for predicting wind power plant short-term power | |
| Singh et al. | Wind power estimation using artificial neural network | |
| CN103440405A (en) | Method and system for steady-state modeling of wind power plant based on measured data | |
| CN103996071A (en) | Wind power plant wind speed prediction method based on Markov theory | |
| Chen et al. | Research on wind power prediction method based on convolutional neural network and genetic algorithm | |
| CN110070223A (en) | A kind of short term power prediction technique applied to newly-built wind power plant | |
| Munir et al. | Solar pv generation forecast model based on the most effective weather parameters | |
| CN112287531A (en) | Offshore wind farm multi-state reliability obtaining method considering typhoon influence | |
| CN104021315A (en) | Method for calculating station service power consumption rate of power station on basis of BP neutral network | |
| Liu et al. | A weight-varying ensemble method for short-term forecasting PV power output | |
| CN109586279B (en) | Interconnected power grid planning method | |
| WO2021128223A1 (en) | Wind farm layout optimization method and optimization system, and computer readable storage medium | |
| CN110909994A (en) | Small hydropower station power generation amount prediction method based on big data drive | |
| Ni et al. | A review of line loss analysis of the low-voltage distribution system |
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: 20170613 |