CN106650784A - Feature clustering comparison-based power prediction method and device for photovoltaic power station - Google Patents
Feature clustering comparison-based power prediction method and device for photovoltaic power station Download PDFInfo
- Publication number
- CN106650784A CN106650784A CN201610966221.3A CN201610966221A CN106650784A CN 106650784 A CN106650784 A CN 106650784A CN 201610966221 A CN201610966221 A CN 201610966221A CN 106650784 A CN106650784 A CN 106650784A
- Authority
- CN
- China
- Prior art keywords
- prediction
- cluster
- power
- photovoltaic plant
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000005855 radiation Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000010248 power generation Methods 0.000 abstract description 3
- 210000002569 neuron Anatomy 0.000 description 8
- 239000013598 vector Substances 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 241000894007 species Species 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a feature clustering comparison-based power prediction method and a device for a photovoltaic power station and belongs to the technical field of photovoltaic power generation. According to the technical scheme of the method, firstly, three most significant feature amounts that influence the prediction precision of the photovoltaic power are acquired and accumulated as historical meteorological data. Secondly, the obtained historical meteorological data are adopted as data samples to be clustered, so that the samples are divided into k types of high similarity. Meanwhile, the cluster center of each type of samples is obtained. Thirdly, a prediction model of a corresponding type is established based on the historical data of each type. Fourthly, a corresponding prediction model nearest to the cluster center of a current object is selected for prediction. In this way, different meteorological data are divided into different types of samples. Meanwhile, photovoltaic output prediction models in different meteorological conditions are established, so that the prediction models are trained in the more targeted manner. Moreover, the power prediction is conducted based on the power prediction models established in different meteorological conditions. Therefore, the prediction accuracy of the photovoltaic power is improved.
Description
Technical field
The present invention relates to the predicting power of photovoltaic plant method and device that a kind of feature based cluster compares, belongs to photovoltaic and sends out
Electro-technical field.
Background technology
Photovoltaic generation worldwide all receives extensive attention, Chinese large-sized ground as one kind of clean energy resource
Face photovoltaic plant, distributed roof photovoltaic power station is more and more, but because photovoltaic generation has fluctuation and intermittence,
Very big difficulty is brought to dispatching of power netwoks, the development of photovoltaic power prediction effectively alleviates this problem, but at present on the market
Photovoltaic power predicated error it is larger, it is difficult to dispatching of power netwoks effectively referring to.
At present, China has carried out portion of techniques research, existing forecast model for the power prediction of photovoltaic plant
Including neural network model, RBF model and Multilayer Perception model etc..Wherein neural network model is most widely used,
The effect of neural network model various neurons in input layer, hidden layer and output layer generates output quantity, then is with error
Object function is constantly corrected to network weight until error reaches requirement, it is trained after network can be carried out prediction
Photovoltaic module is power output.But, current neural network model can only control predicated error 20% or so, if running into
Thunderstorm gale weather, precision of prediction can be worse, wants further to improve precision of prediction, and rational pre- place need to be done to input data
Reason, ensures in addition the accuracy of the historical data of training sample.
It is entitled《Based on weather pattern cluster and the photovoltaic power generation output forecasting of LS-SVM》Paper in provide a kind of prediction side
Method, the method is clustered history meteorological data by season type, obtains four kinds of different types cluster sample in each season, is formed
Corresponding forecast model;During actual prediction, first the season according to belonging to the date to be predicted determines, found by day Meteorological Characteristics to be predicted
Corresponding prediction submodel, is predicted, although a kind of sample range that reduces is given in article seeks optimum prediction submodel
The Forecasting Methodology being predicted, but because the date to be predicted is to divide season according to the time, seek to predict submodel, it is such
Division methods have certain subjectivity and mandatory, and then also limit the process for seeking optimum prediction model, part sample
Data sample data especially within the season alternation time period occurs unavoidably because seeking to cause less than optimum prediction model in advance
Survey the situation that precision is reduced.
The content of the invention
It is an object of the invention to provide a kind of predicting power of photovoltaic plant method that feature based cluster compares, and it is huge
Current predicting power of photovoltaic plant precision is low, the problem that accuracy is not high.Additionally provide a kind of feature based cluster simultaneously to compare
Predicting power of photovoltaic plant device.
The present invention provides the predicting power of photovoltaic plant that a kind of feature based cluster compares to solve above-mentioned technical problem
The step of method, Forecasting Methodology, is as follows:
1) collection affects the characteristic quantity of photovoltaic power precision of prediction, global radiation, wind speed and temperature, and going through using characteristic quantity
History data constitute sample set;
2) sample set for obtaining is carried out into feature clustering, sample set is divided into into the higher k classes of similitude, and obtain all kinds of
The cluster centre C of sample datai, i=1,2 ... ..., k;
3) Different categories of samples data correspondence establishment k class forecast models are respectively adopted;
4) the distance between cluster centre of current predictive object and Different categories of samples data is calculated, is chosen and current predictive pair
As the closest corresponding forecast model of cluster centre place class is predicted.
Further, the step 2) feature clustering is carried out using K-means algorithms, all kinds of initial cluster centers are adopted
The thought of Huffman construction trees is obtained.
Further, the step 3) forecast model adopt BP neural network forecast model, the forecast model is using bag
The three-decker of input layer, hidden layer and output layer is included, input layer adopts global radiation, temperature, three characteristic quantities of wind speed, output layer
For photovoltaic plant power output.
Further, the step 4) in the distance between current predictive object and all kinds of cluster centres adopt weighting method
Euclidean distance be calculated.
Further, the step 2) sample set is divided into into three classes, overcast and rainy, cloudy and fine day is represented respectively.
Present invention also offers the predicting power of photovoltaic plant device that a kind of feature based cluster compares, the prediction meanss bag
Include acquisition module, feature clustering module, forecast model and set up module and prediction module,
Described acquisition module be used for collection affect photovoltaic power precision of prediction characteristic quantity, global radiation, wind speed and temperature,
And the historical data using characteristic quantity constitutes sample set;
Described feature clustering module is used to for the sample set for obtaining to carry out feature clustering, and sample set is divided into into similitude
Higher k classes, and obtain the cluster centre C of Different categories of samples datai, i=1,2 ... ..., k;
Described prediction module sets up module and is utilized respectively Different categories of samples data foundation correspondence k class forecast models;
Described prediction module is used to calculate the distance between cluster centre of current predictive object and Different categories of samples data,
Choose the corresponding forecast model of nearest with current predictive object distance cluster centre place class to be predicted.
Further, described feature clustering module carries out feature clustering, all kinds of initial clusterings using K-means algorithms
Center is obtained using the thought that Huffman constructs tree.
Further, described prediction module sets up module using BP neural network forecast model, and the forecast model is adopted
Including the three-decker of input layer, hidden layer and output layer, input layer adopts global radiation, temperature, three characteristic quantities of wind speed, output
Layer is photovoltaic plant power output.
Further, distance of the described prediction module between calculating current predictive object and all kinds of cluster centres is adopted
It is calculated with the Euclidean distance of weighting method.
Further, sample set is divided into three classes by described feature clustering module, is represented respectively overcast and rainy, cloudy and fine
My god.
The invention has the beneficial effects as follows:The present invention obtains first three main features for affecting photovoltaic power precision of prediction
Amount, and it is history meteorological data to accumulate;Then the history meteorological data for obtaining is clustered as data sample, by sample point
Into the higher k classes of similitude, and obtain all kinds of cluster centers;Set up the prediction mould of respective class using all kinds of historical datas respectively
Type;Selection is predicted with the forecast model corresponding to the closest cluster center of existing object.The present invention is by different meteorological numbers
According to different sample types, and the photovoltaic power generation output forecasting model set up under DIFFERENT METEOROLOGICAL CONDITIONS is divided into, the training of forecast model is made
More targetedly, the power prediction model set up using DIFFERENT METEOROLOGICAL CONDITIONS is predicted, and improves luminous power precision of prediction.
Description of the drawings
Fig. 1 is the flow chart of the predicting power of photovoltaic plant method that feature based cluster of the present invention compares;
Fig. 2 is the construction process schematic diagram of Huffman trees;
Fig. 3 is that the initial cluster center based on Huffman trees chooses flow chart;
Fig. 4 is based on the forecast model figure of BP neural network.
Specific embodiment
The specific embodiment of the present invention is described further below in conjunction with the accompanying drawings.
The embodiment of the predicting power of photovoltaic plant method that feature based cluster of the present invention compares
The predicting power of photovoltaic plant method of the present invention obtains first impact photovoltaic power precision of prediction characteristic quantity, using spy
The historical data of the amount of levying constitutes sample set;Then sample is gathered for k classes by feature clustering algorithm, using all kinds of historical datas
Set up the forecast model of respective class;The distance between existing object and all kinds of cluster centers are finally calculated, and is chosen and existing object
The closest corresponding forecast model of cluster center place class is predicted existing object, so as to realize the pre- of photovoltaic plant power
Survey.The implementing procedure of the method is as shown in figure 1, comprise the following steps that.
1. three main characteristic quantities for affecting photovoltaic power precision of prediction are obtained, and using the historical data structure of characteristic quantity
Into sample set.
Three main characteristic quantities of the impact photovoltaic power precision of prediction selected by the present invention are respectively global radiation, wind speed
And temperature, these three characteristic quantities can obtain from NWP numerical weather forecasts.
2. the sample set for obtaining is carried out into feature clustering, sample is divided into into the higher k classes of similitude, and obtain all kinds of gathering
Class center Ci, i=1,2 ... ..., k.
Realizing the algorithm of sample clustering has various, based on the clustering algorithm for dividing, based on the clustering algorithm of level, based on net
Clustering algorithm, density-based algorithms of lattice etc., the cluster process being capable of achieving in the present invention, below with poly- based on dividing
In class algorithm as a example by most typical K-means algorithms, the cluster process of the present invention is described in detail, is embodied as follows:
(1) eigenmatrix is set up.
Using photovoltaic plant history meteorological data as sample, characteristic quantity is respectively global radiation, temperature, wind speed, then sample structure
Into as follows:
Each sample data covers each characteristic quantity
Wherein, ui1, ui2, ui3Global radiation, wind speed, 3 characteristic quantities of temperature are represented respectively.
(2) initial cluster center is chosen.
The present embodiment is adopted and chooses initial cluster center based on Huffman trees tectonic ideology.Vectorial number be n, sample
Collection dimension is 3, and it is 3 classes to intend cluster species, and cluster species can be adjusted according to actual conditions, and 3 classes are only given in the present embodiment
Situation, initial center point choose comprise the following steps that.
The first step:Calculate the Euclidean distance two-by-two between vector.
Wherein i=1,2 ... n;J=1,2 ... n;And i ≠ j.
Obtain dissimilarity matrix, matrix such as following formula:
Second step:Find minimum of a value d in matrixij, calculate ui,ujTwo vectorial mean values, obtain vectorial V1。
3rd step:U is deleted from former eigenmatrixi,ujTwo vectors, and add incoming vector V1, obtain new eigenmatrix.
4th step:Repeat step one, step 2, step 3, only remain next vector, iterative process in eigenmatrix
The process of middle construction tree is as shown in Figure 2.
5th step:Data are gathered for 5 classes, from summit JmRise and successively cut node from tree, it is 4 to cut number, structure
Set into 5, as shown in Figure 3.
6th step, asks for respectively the mean value of the knot vector of 3 tree bottoms, obtains vectorAs just
Beginning cluster centre.
(3) mean error criterion function under initial cluster center is calculated.
Wherein k=3, represents the number of institute's cluster dividing;ui (0)Represent the center of 3 clusters.
(4) new cluster centre is calculated.
N1Expression belongs toElement number
N2Expression belongs toElement number
N3Expression belongs toElement number
Wherein N1+N2+N3=n n represent sample data total amount
(5) repeat the above steps (2), (3), (4), until meeting following relation.
And there is E(s+1)≤E(s), illustrate after s time clusters iteration, to put down
Error rule function is presented convergence state, and cluster center no longer changes, and stops iteration, and so far cluster result is completed.
3. photovoltaic power forecast model is set up.
Used respectively after cluster as the forecast model of luminous power using BP neural network forecast model in the present embodiment
All kinds of historical datas are trained to BP neural network model, to obtain and all kinds of corresponding forecast models.As shown in figure 4, BP
Neural network prediction model adopts three-decker, input layer, hidden layer, output layer, input layer to adopt global radiation, temperature, wind speed
Three characteristic quantities, output layer is photovoltaic plant power output, hidden layer neuron number is obtained by engineering actual verification.According to
Cluster result is obtained in step 2, the sample data of three classes is brought into respectively in BP neural network forecast model and is trained, i.e.,
The different forecast model of available three classes.Implement process as follows:
The first step, netinit:The random number in an interval (- 1,1) is assigned respectively to each connection weight, sets error
Function e, gives computational accuracy value Δ and maximum study number of times.
Second step, choose k input sample (historical datas of nearest 30 days) and correspondingly desired output (desired output is
Corresponding 30 days actual generation powers).
3rd step, calculates the input and output of each neuron of hidden layer.
4th step, using output result after network desired output (actual generation power) and hands-on, calculation error letter
Several partial derivatives to exporting each neuron.
5th step, using the error partial derivative of each neuron of output layer and the output of each neuron of hidden layer connection is corrected
Weights.
6th step, using the error partial derivative and the output amendment connection weight of each neuron of input layer of each neuron of hidden layer
Value.
7th step, calculates global error.
8th step, judges whether network error meets requirement, when error reaches default precision or study number of times more than setting
Maximum times, then terminate algorithm, otherwise, choose next learning sample and corresponding desired output, return to the 3rd step, enter
Enter next round study.
4. the distance between current predictive object and all kinds of cluster centres are calculated, is chosen with current predictive object distance most
The near corresponding forecast model of cluster centre place class is predicted.
The first step, obtains the meteorological data of current predictive object, according to clustering algorithm output result, selectes forecast model.
Calculate existing object meteorological data and all kinds of cluster centres between weighted euclidean distance, if with the i-th class cluster in
Heart CiDistance is minimum, then be predicted using the i-th class forecast model.
Second step, meteorological data normalized.
3rd step, using current weather data as input, loads corresponding forecast model, and output predicts the outcome.
The power prediction model that can be set up according to different meteorological conditions by the said process present invention, can be effectively improved
The low problem of photovoltaic power output precision of prediction under the conditions of rainy weather.
The embodiment of the predicting power of photovoltaic plant device that feature based cluster of the present invention compares
Prediction meanss in the present embodiment include that acquisition module, feature clustering module, forecast model set up module and prediction
Module;Acquisition module is used for collection affects the characteristic quantity of photovoltaic power precision of prediction, global radiation, wind speed and temperature, and utilizes special
The historical data of the amount of levying constitutes sample set;Feature clustering module is used to for the sample set for obtaining to carry out feature clustering, by sample set
Change is divided into the higher k classes of similitude, and obtains the cluster centre C of Different categories of samples datai, i=1,2 ... ..., k;Prediction module is built
Formwork erection block is utilized respectively Different categories of samples data and sets up correspondence k class forecast models;Prediction module be used for calculate current predictive object with
The distance between cluster centre of Different categories of samples data, chooses and the nearest cluster centre place class pair of current predictive object distance
The forecast model answered is predicted.The means that implement of each module are illustrated in the example of method, are no longer gone to live in the household of one's in-laws on getting married here
State.
Claims (10)
1. the predicting power of photovoltaic plant method that a kind of feature based cluster compares, it is characterised in that the step of the Forecasting Methodology
It is as follows:
1) characteristic quantity of collection impact photovoltaic power precision of prediction, global radiation, wind speed and temperature, and using the history number of characteristic quantity
According to composition sample set;
2) sample set for obtaining is carried out into feature clustering, sample set is divided into into the higher k classes of similitude, and obtain Different categories of samples
The cluster centre C of datai, i=1,2 ... ..., k;
3) Different categories of samples data correspondence establishment k class forecast models are respectively adopted;
4) the distance between cluster centre of current predictive object and Different categories of samples data is calculated, is chosen with current predictive to image distance
It is predicted from the nearest corresponding forecast model of cluster centre place class.
2. the predicting power of photovoltaic plant method that feature based cluster according to claim 1 compares, it is characterised in that institute
State step 2) feature clustering is carried out using K-means algorithms, all kinds of initial cluster centers constructs the thought of tree using Huffman
Obtain.
3. the predicting power of photovoltaic plant method that feature based cluster according to claim 1 and 2 compares, its feature exists
In the step 3) forecast model adopt BP neural network forecast model, the forecast model is using including input layer, hidden layer
With the three-decker of output layer, using global radiation, temperature, three characteristic quantities of wind speed, output layer is photovoltaic plant output to input layer
Power.
4. the predicting power of photovoltaic plant method that feature based cluster according to claim 1 compares, it is characterised in that institute
State step 4) in the distance between current predictive object and all kinds of cluster centres be calculated using the Euclidean distance of weighting method.
5. the predicting power of photovoltaic plant method that feature based cluster according to claim 2 compares, it is characterised in that institute
State step 2) sample set is divided into into three classes, overcast and rainy, cloudy and fine day is represented respectively.
6. the predicting power of photovoltaic plant device that a kind of feature based cluster compares, it is characterised in that the prediction meanss include adopting
Collection module, feature clustering module, forecast model set up module and prediction module,
Described acquisition module is used for collection affects the characteristic quantity of photovoltaic power precision of prediction, global radiation, wind speed and temperature, and profit
Sample set is constituted with the historical data of characteristic quantity;
Described feature clustering module is used to for the sample set for obtaining to carry out feature clustering, sample set is divided into into similitude higher
K classes, and obtain the cluster centre C of Different categories of samples datai, i=1,2 ... ..., k;
Described prediction module sets up module and is utilized respectively Different categories of samples data foundation correspondence k class forecast models;
Described prediction module is used to calculate the distance between cluster centre of current predictive object and Different categories of samples data, chooses
The corresponding forecast model of the cluster centre place class nearest with current predictive object distance is predicted.
7. the predicting power of photovoltaic plant device that feature based cluster according to claim 6 compares, it is characterised in that institute
The feature clustering module stated carries out feature clustering using K-means algorithms, and all kinds of initial cluster centers are constructed using Huffman
The thought of tree is obtained.
8. the predicting power of photovoltaic plant device that the feature based cluster according to claim 6 or 7 compares, its feature exists
In described prediction module sets up module using BP neural network forecast model, and the forecast model is adopted to be included input layer, imply
The three-decker of layer and output layer, input layer adopts global radiation, temperature, three characteristic quantities of wind speed, and output layer is that photovoltaic plant is defeated
Go out power.
9. the predicting power of photovoltaic plant device that feature based cluster according to claim 6 compares, it is characterised in that institute
The prediction module stated is calculating Euclidean distance of the distance between current predictive object and all kinds of cluster centres using weighting method
It is calculated.
10. the predicting power of photovoltaic plant device that feature based cluster according to claim 7 compares, it is characterised in that
Sample set is divided into three classes by described feature clustering module, and overcast and rainy, cloudy and fine day is represented respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610966221.3A CN106650784A (en) | 2016-11-04 | 2016-11-04 | Feature clustering comparison-based power prediction method and device for photovoltaic power station |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610966221.3A CN106650784A (en) | 2016-11-04 | 2016-11-04 | Feature clustering comparison-based power prediction method and device for photovoltaic power station |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106650784A true CN106650784A (en) | 2017-05-10 |
Family
ID=58820784
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610966221.3A Pending CN106650784A (en) | 2016-11-04 | 2016-11-04 | Feature clustering comparison-based power prediction method and device for photovoltaic power station |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106650784A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107331068A (en) * | 2017-07-17 | 2017-11-07 | 重庆壹元电科技有限公司 | A kind of portable power source lease management system and method towards the ultimate attainment Consumer's Experience of amnesia |
CN107784165A (en) * | 2017-09-29 | 2018-03-09 | 国网青海省电力公司 | Surface temperature field multi-scale data assimilation method based on photovoltaic plant |
CN108197664A (en) * | 2018-01-24 | 2018-06-22 | 北京墨丘科技有限公司 | Model acquisition methods, device, electronic equipment and computer readable storage medium |
CN108320050A (en) * | 2018-01-11 | 2018-07-24 | 国家电网公司 | A method of photovoltaic short term power precision of prediction is improved based on wind speed forecasting |
CN109242209A (en) * | 2018-10-12 | 2019-01-18 | 北京交通大学 | Railway emergency event grading forewarning system method based on K-means cluster |
CN109543911A (en) * | 2018-11-29 | 2019-03-29 | 中国农业科学院农业信息研究所 | A kind of solar radiation prediction technique and system |
CN109670644A (en) * | 2018-12-20 | 2019-04-23 | 华北水利水电大学 | Forecasting system and method neural network based |
CN110197298A (en) * | 2019-05-10 | 2019-09-03 | 中国电建集团西北勘测设计研究院有限公司 | The method and device of multi-model sun normal direction radiation prediction based on clustering algorithm |
CN110348175A (en) * | 2019-08-12 | 2019-10-18 | 阳光电源股份有限公司 | A kind of photovoltaic plant effective irradiation calculation method and device |
CN110472770A (en) * | 2019-07-05 | 2019-11-19 | 广东工业大学 | A kind of photovoltaic power generation power prediction method |
CN110598956A (en) * | 2019-09-29 | 2019-12-20 | 国核电力规划设计研究院有限公司 | Method and device for predicting power generation power of photovoltaic power station |
CN111210071A (en) * | 2020-01-03 | 2020-05-29 | 深圳前海微众银行股份有限公司 | Business object prediction method, device, equipment and readable storage medium |
CN112365081A (en) * | 2020-11-24 | 2021-02-12 | 国家电网有限公司 | Photovoltaic power station power generation capacity prediction method and device |
CN113177360A (en) * | 2021-05-06 | 2021-07-27 | 中国人民解放军国防科技大学 | Rain intensity self-adaptive estimation system and method based on clustering rain attenuation relation |
CN113827233A (en) * | 2020-06-24 | 2021-12-24 | 京东方科技集团股份有限公司 | User characteristic value detection method and device, storage medium and electronic equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930358A (en) * | 2012-11-28 | 2013-02-13 | 江西九江供电公司 | Neural network prediction method for generated output of photovoltaic power station |
CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
CN103904682A (en) * | 2014-03-18 | 2014-07-02 | 许继电气股份有限公司 | Power prediction method based on wind-solar hybrid model |
CN104573879A (en) * | 2015-01-30 | 2015-04-29 | 河海大学 | Photovoltaic power station output predicting method based on optimal similar day set |
CN104915899A (en) * | 2015-06-30 | 2015-09-16 | 许继集团有限公司 | Photovoltaic power station operation state classifying method based on characteristic cluster analysis |
CN105184678A (en) * | 2015-09-18 | 2015-12-23 | 齐齐哈尔大学 | Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms |
CN105373857A (en) * | 2015-11-27 | 2016-03-02 | 许昌许继软件技术有限公司 | Photovoltaic power station irradiance prediction method |
CN106022528A (en) * | 2016-05-26 | 2016-10-12 | 上海电力学院 | Short-term power prediction method of photovoltaic power plant based on density peak hierarchical clustering |
-
2016
- 2016-11-04 CN CN201610966221.3A patent/CN106650784A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930358A (en) * | 2012-11-28 | 2013-02-13 | 江西九江供电公司 | Neural network prediction method for generated output of photovoltaic power station |
CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
CN103904682A (en) * | 2014-03-18 | 2014-07-02 | 许继电气股份有限公司 | Power prediction method based on wind-solar hybrid model |
CN104573879A (en) * | 2015-01-30 | 2015-04-29 | 河海大学 | Photovoltaic power station output predicting method based on optimal similar day set |
CN104915899A (en) * | 2015-06-30 | 2015-09-16 | 许继集团有限公司 | Photovoltaic power station operation state classifying method based on characteristic cluster analysis |
CN105184678A (en) * | 2015-09-18 | 2015-12-23 | 齐齐哈尔大学 | Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms |
CN105373857A (en) * | 2015-11-27 | 2016-03-02 | 许昌许继软件技术有限公司 | Photovoltaic power station irradiance prediction method |
CN106022528A (en) * | 2016-05-26 | 2016-10-12 | 上海电力学院 | Short-term power prediction method of photovoltaic power plant based on density peak hierarchical clustering |
Non-Patent Citations (3)
Title |
---|
嵇灵等: "《基于相似日聚类和贝叶斯神经网络的光伏发电功率预测研究》", 《中国管理科学》 * |
胡斌等: "《考虑大规模光伏电站接入的电力系统旋转备用需求评估》", 《电力系统自动化》 * |
金鑫等: "《天气类型聚类的支持向量机在光伏系统输出功率预测中的应用》", 《现代电力》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107331068A (en) * | 2017-07-17 | 2017-11-07 | 重庆壹元电科技有限公司 | A kind of portable power source lease management system and method towards the ultimate attainment Consumer's Experience of amnesia |
CN107784165A (en) * | 2017-09-29 | 2018-03-09 | 国网青海省电力公司 | Surface temperature field multi-scale data assimilation method based on photovoltaic plant |
CN107784165B (en) * | 2017-09-29 | 2021-07-09 | 国网青海省电力公司 | Surface temperature field multi-scale data assimilation method based on photovoltaic power station |
CN108320050A (en) * | 2018-01-11 | 2018-07-24 | 国家电网公司 | A method of photovoltaic short term power precision of prediction is improved based on wind speed forecasting |
CN108197664A (en) * | 2018-01-24 | 2018-06-22 | 北京墨丘科技有限公司 | Model acquisition methods, device, electronic equipment and computer readable storage medium |
CN109242209A (en) * | 2018-10-12 | 2019-01-18 | 北京交通大学 | Railway emergency event grading forewarning system method based on K-means cluster |
CN109543911A (en) * | 2018-11-29 | 2019-03-29 | 中国农业科学院农业信息研究所 | A kind of solar radiation prediction technique and system |
CN109543911B (en) * | 2018-11-29 | 2020-09-18 | 中国农业科学院农业信息研究所 | Sunlight radiation prediction method and system |
CN109670644A (en) * | 2018-12-20 | 2019-04-23 | 华北水利水电大学 | Forecasting system and method neural network based |
CN109670644B (en) * | 2018-12-20 | 2023-04-25 | 华北水利水电大学 | Prediction system and method based on neural network |
CN110197298A (en) * | 2019-05-10 | 2019-09-03 | 中国电建集团西北勘测设计研究院有限公司 | The method and device of multi-model sun normal direction radiation prediction based on clustering algorithm |
CN110472770A (en) * | 2019-07-05 | 2019-11-19 | 广东工业大学 | A kind of photovoltaic power generation power prediction method |
CN110348175A (en) * | 2019-08-12 | 2019-10-18 | 阳光电源股份有限公司 | A kind of photovoltaic plant effective irradiation calculation method and device |
CN110348175B (en) * | 2019-08-12 | 2023-01-06 | 阳光电源股份有限公司 | Effective irradiation calculation method and device for photovoltaic power station |
CN110598956A (en) * | 2019-09-29 | 2019-12-20 | 国核电力规划设计研究院有限公司 | Method and device for predicting power generation power of photovoltaic power station |
CN110598956B (en) * | 2019-09-29 | 2022-02-18 | 国核电力规划设计研究院有限公司 | Method and device for predicting power generation power of photovoltaic power station |
CN111210071A (en) * | 2020-01-03 | 2020-05-29 | 深圳前海微众银行股份有限公司 | Business object prediction method, device, equipment and readable storage medium |
CN113827233A (en) * | 2020-06-24 | 2021-12-24 | 京东方科技集团股份有限公司 | User characteristic value detection method and device, storage medium and electronic equipment |
CN112365081A (en) * | 2020-11-24 | 2021-02-12 | 国家电网有限公司 | Photovoltaic power station power generation capacity prediction method and device |
CN113177360A (en) * | 2021-05-06 | 2021-07-27 | 中国人民解放军国防科技大学 | Rain intensity self-adaptive estimation system and method based on clustering rain attenuation relation |
CN113177360B (en) * | 2021-05-06 | 2022-04-29 | 中国人民解放军国防科技大学 | Rain intensity self-adaptive estimation system and method based on clustering rain attenuation relation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106650784A (en) | Feature clustering comparison-based power prediction method and device for photovoltaic power station | |
CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
CN112288164B (en) | Wind power combined prediction method considering spatial correlation and correcting numerical weather forecast | |
CN109086928A (en) | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model | |
CN105139264A (en) | Photovoltaic generation capacity prediction method based on particle swarm algorithm wavelet neural network | |
CN110334870B (en) | Photovoltaic power station short-term power prediction method based on gated cyclic unit network | |
CN105389634A (en) | Combined short-term wind power prediction system and method | |
CN105701572B (en) | Photovoltaic short-term output prediction method based on improved Gaussian process regression | |
CN113468817B (en) | Ultra-short-term wind power prediction method based on IGOA (insulated gate bipolar transistor) optimized ELM (ELM) | |
CN108074004A (en) | A kind of GIS-Geographic Information System short-term load forecasting method based on gridding method | |
CN109376950A (en) | A kind of polynary Load Forecasting based on BP neural network | |
CN112330487B (en) | Photovoltaic power generation short-term power prediction method | |
CN112488208B (en) | Method for acquiring remaining life of island pillar insulator | |
CN107466816A (en) | A kind of irrigation method based on dynamic multilayer extreme learning machine | |
CN108204944A (en) | The Buried Pipeline rate prediction method of LSSVM based on APSO optimizations | |
CN108062720A (en) | A kind of load forecasting method based on similar day selection and random forests algorithm | |
CN110070228A (en) | BP neural network wind speed prediction method for neuron branch evolution | |
CN111292124A (en) | Water demand prediction method based on optimized combined neural network | |
Shang et al. | Research on intelligent pest prediction of based on improved artificial neural network | |
CN114298377A (en) | Photovoltaic power generation prediction method based on improved extreme learning machine | |
CN115186857A (en) | Neural network reservoir water level prediction method based on ensemble learning | |
CN106296434A (en) | A kind of Grain Crop Yield Prediction method based on PSO LSSVM algorithm | |
CN116702937A (en) | Photovoltaic output day-ahead prediction method based on K-means mean value clustering and BP neural network optimization | |
CN106786499A (en) | Based on the short-term wind power forecast method for improving AFSA optimizations ELM | |
CN109426901A (en) | Long-term power consumption prediction method and device in one kind |
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: 20170510 |