CN103400230A - Wind power forecast system and method - Google Patents
Wind power forecast system and method Download PDFInfo
- Publication number
- CN103400230A CN103400230A CN2013103453545A CN201310345354A CN103400230A CN 103400230 A CN103400230 A CN 103400230A CN 2013103453545 A CN2013103453545 A CN 2013103453545A CN 201310345354 A CN201310345354 A CN 201310345354A CN 103400230 A CN103400230 A CN 103400230A
- Authority
- CN
- China
- Prior art keywords
- sequence
- layer
- wind
- data
- module
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B10/00—Integration of renewable energy sources in buildings
- Y02B10/30—Wind power
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a wind power forecast system and method. The method comprises the following steps: obtaining historical data of the wind turbines within an appointed time period; processing the historical data through clustering analysis, selecting the historical wind speed data of which the wind speed character parameter is similar to that of the forecast day, and taking the selected historical wind speed data as a sample in modeling; conducting wavelet decomposition to the selected wind speed sequence, projecting each sequence component onto different scales through the wavelet decomposition, and decomposing the sequence components onto different channels level-wise; reconstituting the decomposed sequence layer to the original scale, so as to increase signal point number; building forecasting model to each sequence; conducting forecasting to each layer data according to the built forecast model; overlaying the forecasting value of each layer data, so as to obtain original wind speed time sequence forecasting value. According to the system and method provided by the invention, multi-scale wavelet decomposition is added to the time sequence forecast method, so that forecast precision is improved.
Description
Technical field
The present invention, about a kind of wind power forecasting system and method, particularly relates to a kind of short-term wind-electricity power prognoses system and method based on Statistical Clustering Analysis analysis, multi-scale wavelet decomposition and time series method.
Background technology
Because China's wind power forecasting research work is started late, at present, it is mainly theory study, prognoses system is in mostly to be explored and conceptual phase, but the wind energy turbine set situation of China is more complicated, need to carry out the wind power prediction work with suiting measures to local conditions, also need advanced Forecasting Methodology is studied simultaneously, progressively to improve precision of prediction.The uncontrollability of natural cause, the randomness of wind power output power, intermittence and undulatory property bring stern challenge all will for the safe and stable operation of wind-electricity integration.The raising of short-term wind-electricity power precision of prediction, will help electric power system dispatching department reasonable arrangement operation plan, effectively alleviate the impact of wind-powered electricity generation on whole electrical network.
At present, the method that is used for the wind power prediction can be divided into two large classes: a kind of method that is based on physical model, and the method has been considered the information such as environment landform, roughness, according to related datas such as numerical weather predictions, obtains to predict the outcome; Another is based on the historical datas such as existing wind speed, wind power, sets up the forecast model of wind speed or wind power, wherein, what have need to predict single wind-powered electricity generation unit, then stack obtains whole power, although precision of prediction is high, but operand is large, and predetermined speed is slow; Some needs directly predict whole power, and its operand is less, and predetermined speed is fast, and shortcoming is that precision of prediction is low.Therefore, be necessary to find in fact a kind of wind power forecasting techniques that can take into account predetermined speed and precision of prediction.
Summary of the invention
The deficiency that exists for overcoming above-mentioned prior art, the present invention's purpose is to provide a kind of wind power forecasting system and method, it has taken into full account weather conditions, added the multi-scale wavelet decomposition on the basis of Time Series Forecasting Methods, improved precision of prediction taking into account on the basis of predetermined speed, especially to not steadily the prediction of wind series have higher precision of prediction and stronger adaptability.
For reaching above-mentioned and other purpose, the present invention proposes a kind of wind power forecasting method, comprises the steps:
Step 1, obtain the historical data of the wind-powered electricity generation unit in the fixed time scope;
Step 2, use cluster analysis to process historical data, selects the air speed data of historical day that has similarity with the wind speed characteristic parameter of predicting day, with them as the sample in modeling;
Step 3, carry out wavelet decomposition to the wind series of selecting, and utilizes wavelet decomposition that each sequence component is projected to respectively on different scale, successively decomposes on different channel;
Step 4, with each sequence of layer after decomposing respectively reconstruct return archeus and count to increase signal;
Step 5, set up respectively forecast model to each sequence of layer;
Step 6, predict each layer data with the above-mentioned forecast model of setting up;
Step 7,, with each layer data predicted value stack of gained, obtain original wind speed time series forecasting value.
Further, step 5 also comprises the steps:
Step 5.1, calculate the auto-correlation function value of each sequence of layer
, the partial correlation functional value
Step 5.2, by
,
Figure judge respectively whether each sequence of layer steady,, if turn to step 5.3, directly turn to if not step 5.1;
Step 5.3, utilize AIC to determine the rank criterion and determine each layer model exponent number;
Step 5.4, utilize each layer air speed data to try to achieve the parameters estimated value of each layer after model order is determined;
Step 5.5, judge whether the residual sequence of model of fit is a white noise sequence,, if institute's testing model changes step 6 over to, changes if not step 5.3 over to.
Further, this historical data comprises output power, wind speed, wind direction, temperature, atmospheric pressure and the relative humidity of wind-powered electricity generation unit.
Further, in step 2, use clustering method, take into full account weather conditions, formation reason based on wind speed, consider temperature, atmospheric pressure and three major influence factors of relative humidity, and the intrinsic dimensionality of wind speed sample be decided to be 8 dimensions, characterization factor be respectively " maximum temperature, temperature on average; Maximum atmospheric pressure, Zenith Distance pressure; Maximal humidity, medial humidity; Maximum wind power grade, average wind scale "; calculated each historical day and the wind speed property value of prediction day between Euclidean distance; the data of each corresponding prediction in historical day day have 8; then these 8 data are pressed Weight average, select several groups of the shortest data of Euclidean distance as sample data.
Further, in step 3, by different bandpass filter, one group of original series that will contain integrated information resolves into the time series of many group different characteristics, one group of inherent variation tendency of the former seasonal effect in time series of signal reaction; The impact that the sequence reflection random perturbation of all the other groups is brought, select different parameter models to predict for different characteristic signals.
For reaching above-mentioned purpose, the present invention also provides a kind of wind power forecasting system, comprises at least:
Historical data is obtained module, is used for obtaining the historical data of the wind-powered electricity generation unit in the fixed time scope;
The cluster analysis module, use cluster analysis to process historical data, selects the air speed data of historical day that has similarity with the wind speed characteristic parameter of predicting day, with them as the sample in modeling;
The wavelet decomposition module, carry out wavelet decomposition to the wind series of selecting, and utilizes wavelet decomposition that each sequence component is projected to respectively on different scale, successively decomposes on different channel;
The reconstruct module, with each sequence of layer after decomposing respectively reconstruct return archeus and count to increase signal;
Forecast model is set up module, is used for each sequence of layer is set up respectively forecast model;
The prediction module, predict each layer data with the above-mentioned forecast model of setting up;
The stack module,, with each layer data predicted value stack of gained, obtain original wind speed time series forecasting value.
Further, this forecast model is set up module and is further comprised:
Correlation function value calculates module, is used for calculating the auto-correlation function value of each sequence of layer
, the partial correlation functional value
The judgement module, according to
,
Figure judge respectively whether each sequence of layer steady;
Model is determined the rank module, in this judgement module judgment result is that each sequence of layer is steady the time, utilize AIC to determine the rank criterion and determine each layer model exponent number;
The model parameter estimation module, utilize each layer air speed data to try to achieve the parameters estimated value of each layer after model order is determined;
The check module, judge whether the residual sequence of model of fit is a white noise sequence, if suitable this prediction module that utilizes of institute's testing model is predicted, returns to if not model and determines rank.
Further, this historical data comprises output power, wind speed, wind direction, temperature, atmospheric pressure and the relative humidity of wind-powered electricity generation unit.
Further, this cluster analysis module uses clustering method, take into full account weather conditions, formation reason based on wind speed, consider temperature, atmospheric pressure and three major influence factors of relative humidity, and with the intrinsic dimensionality of wind speed sample be decided to be 8 the dimension, characterization factor be respectively " maximum temperature, temperature on average; Maximum atmospheric pressure, Zenith Distance pressure; Maximal humidity, medial humidity; Maximum wind power grade, average wind scale "; calculated each historical day and the wind speed property value of prediction day between Euclidean distance; the data of each corresponding prediction in historical day day have 8; then these 8 data are pressed Weight average, select several groups of the shortest data of Euclidean distance as sample data.
Further, this wavelet decomposition module is by different bandpass filter, and one group of original series that will contain integrated information resolves into the time series of many group different characteristics, one group of inherent variation tendency of the former seasonal effect in time series of signal reaction; The impact that the sequence reflection random perturbation of all the other groups is brought, select different parameter models to predict for different characteristic signals.
compared with prior art, a kind of wind power forecasting system of the present invention and method are by using clustering method, historical data is carried out automatic classification, and by means of prediction day existing relevant meteorologic factor data, principle according to the similarity maximum, select with prediction day similarity maximum that several groups data history day the wind speed data, as the training sample of predicting that modeling is used, then by wavelet decomposition, the wind speed nonstationary time series is decomposed into stationary time series on the different scale coordinate, and archeus is returned in each sequence of layer reconstruct after decomposing, applying autoregressive moving-average model predicts stationary time series again, finally by the synthetic predicted value that draws original wind series that superposes, divide and considered weather conditions, added the multi-scale wavelet decomposition on the basis of Time Series Forecasting Methods, improved precision of prediction, especially to not steadily the prediction of wind series have higher precision of prediction and stronger adaptability.
Description of drawings
Fig. 1 is the flow chart of steps of a kind of wind power forecasting method of the present invention;
Fig. 2 is the system architecture diagram of a kind of wind power forecasting system of the present invention.
Embodiment
Below by specific instantiation and accompanying drawings embodiments of the present invention, those skilled in the art can understand other advantage of the present invention and effect easily by content disclosed in the present specification.The present invention also can be implemented or be applied by other different instantiation, and the every details in this instructions also can be based on different viewpoints and application, carries out various modifications and change not deviating under spirit of the present invention.
Fig. 1 is the flow chart of steps of a kind of wind power forecasting method of the present invention.The present invention's wind power forecasting method is based on the Statistical Clustering Analysis analysis, multi-scale wavelet decomposes and the short-term wind-electricity power Forecasting Methodology of time series method, and as shown in Figure 1, a kind of wind-powered electricity generation Forecasting Methodology of the present invention, comprise the steps:
Better, in step 105, each sequence of layer is set up respectively forecast model comprise the steps:
Step 5.1, calculate the auto-correlation function value of each sequence of layer
, the partial correlation functional value
Step 5.2, by
,
Figure judge respectively whether each sequence of layer steady,, if turn to step 5.3, directly turn to if not step 5.1;
Step 5.3, model is determined rank: utilize AIC(Akaike information criterion, akaike information criterion) determine the rank criterion and determine each layer model exponent number;
Step 5.4, model parameter estimation: model order can utilize each layer air speed data to try to achieve the parameters estimated value of each layer after determining;
Step 5.5, the χ of model
2Check: whether the residual sequence that judges model of fit is a white noise sequence, if the suitable step 106 that changes over to of institute's testing model, change step 5.3 if not over to.
Fig. 2 is the system architecture diagram of a kind of wind power forecasting system of the present invention.The present invention's wind power forecasting system is based on the Statistical Clustering Analysis analysis, multi-scale wavelet decomposes and the short-term wind-electricity power prognoses system of time series method, as shown in Figure 2, a kind of wind-powered electricity generation prognoses system of the present invention comprises at least: historical data is obtained module 201, cluster analysis module 202, wavelet decomposition module 203, reconstruct module 204, forecast model and is set up module 205, prediction module 206 and stack module 207.
Wherein, historical data is obtained module 201 and is used for obtaining historical data,, obtains the historical datas such as wind-powered electricity generation unit output power, wind speed, wind direction, temperature, atmospheric pressure and relative humidity in the fixed time scope from data processing module that is; Cluster analysis module 202, use cluster analysis to process the historical data that obtains, and selects the air speed data of historical day that has similarity with the wind speed characteristic parameter of predicting day, with them as the sample in modeling.That is, cluster analysis module 202 is by screening former data, selects the air speed data of historical day that has similarity with the wind speed characteristic parameter of predicting day, with them as the sample in modeling.Specifically, cluster analysis module 202 uses clustering method, weather conditions have been taken into full account, formation reason based on wind speed, here considered temperature, atmospheric pressure, these three major influence factors of relative humidity, and with fixed 8 dimensions of the intrinsic dimensionality of wind speed sample, characterization factor be respectively " maximum temperature, temperature on average; Maximum atmospheric pressure, Zenith Distance pressure; Maximal humidity, medial humidity; Maximum wind power grade, average wind scale ".Calculated each historical day and the wind speed property value of prediction day between Euclidean distance, the data of each corresponding prediction in historical day day have 8, then these 8 data are pressed Weight average, select several groups of the shortest data of Euclidean distance as sample data.
203 pairs of wind series of selecting of wavelet decomposition module are carried out wavelet decomposition, that is, utilize wavelet decomposition that each sequence component is projected to respectively on different scale, successively decompose on different channel.In preferred embodiment of the present invention, wavelet decomposition is actually by different bandpass filter, one group of original series that will contain integrated information resolves into the time series of many group different characteristics, one group of former seasonal effect in time series of signal reaction inherent variation tendency, i.e. approximation signal; The impact that the sequence reflection random perturbation of all the other groups is brought, namely detail signal, select different parameter models to predict for different characteristic signals.
Each sequence of layer after reconstruct module 204 will decompose reconstruct respectively returns archeus and counts to increase signal.Than the corresponding minimizing of counting of the sequence before decomposing, the minimizing of counting can affect last predicting the outcome due to the Approximate Sequence that obtains after wavelet decomposition and details sequence, thus also need with each group sequence respectively reconstruct return archeus, count thereby increase signal.
Forecast model is set up 205 pairs of each sequence of layer of module and is set up respectively forecast model,, for different bursts, sets up respectively different time series models that is, namely sets up the model of suitable its sequence, makes later prediction more accurate.
The above-mentioned forecast model of setting up of prediction module 206 use is predicted each layer data; Stack module 207 is original wind speed time series forecasting value with each layer data predicted value stack of gained, each layer data predicted value stack is referred to the stack of the value of each layer synchronization is obtained the forecasting wind speed value in this moment here.
In preferred embodiment of the present invention, forecast model is set up module 205 and further comprised: correlation function value calculating module 251, judgement module 252, model are determined rank module 253, model parameter estimation module 254 and check module 255.
Wherein correlation function value calculates module 251 for the auto-correlation function value that calculates each sequence of layer
, the partial correlation functional value
Judgement module 252 bases
,
Figure judge respectively whether each sequence of layer steady; Model determine rank module 253 in judgement module 252 judgment result is that each sequence of layer is steady the time, utilize AIC(Akaike information criterion, akaike information criterion) determine the rank criterion and determine each layer model exponent number; Model parameter estimation module 254, utilize each layer air speed data to try to achieve the parameters estimated value of each layer after model order is determined; Check module 255 judges whether the residual sequence of model of fit is a white noise sequence, if the suitable utilization prediction of institute's testing model module 206 is predicted, returns to if not model and determines rank.
in sum, a kind of wind power forecasting system of the present invention and method are by using clustering method, historical data is carried out automatic classification, and by means of prediction day existing relevant meteorologic factor data, principle according to the similarity maximum, select with prediction day similarity maximum that several groups data history day the wind speed data, as the training sample of predicting that modeling is used, then by wavelet decomposition, the wind speed nonstationary time series is decomposed into stationary time series on the different scale coordinate, and archeus is returned in each sequence of layer reconstruct after decomposing, applying autoregressive moving-average model predicts stationary time series again, finally by the synthetic predicted value that draws original wind series that superposes, weather conditions have been taken into full account, added the multi-scale wavelet decomposition on the basis of Time Series Forecasting Methods, improved precision of prediction, especially to not steadily the prediction of wind series have higher precision of prediction and stronger adaptability.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not is used for restriction the present invention.Any those skilled in the art all can, under spirit of the present invention and category, modify and change above-described embodiment.Therefore, the scope of the present invention, should be as listed in claims.
Claims (10)
1. a wind power forecasting method, comprise the steps:
Step 1, obtain the historical data of the wind-powered electricity generation unit in the fixed time scope;
Step 2, use cluster analysis to process historical data, selects the air speed data of historical day that has similarity with the wind speed characteristic parameter of predicting day, with them as the sample in modeling;
Step 3, carry out wavelet decomposition to the wind series of selecting, and utilizes wavelet decomposition that each sequence component is projected to respectively on different scale, successively decomposes on different channel;
Step 4, with each sequence of layer after decomposing respectively reconstruct return archeus and count to increase signal;
Step 5, set up respectively forecast model to each sequence of layer;
Step 6, predict each layer data with the above-mentioned forecast model of setting up;
Step 7,, with each layer data predicted value stack of gained, obtain original wind speed time series forecasting value.
2. a kind of wind power forecasting method as claimed in claim 1, is characterized in that, step 5 also comprises the steps:
Step 5.1, calculate the auto-correlation function value of each sequence of layer
, the partial correlation functional value
Step 5.2, by
,
Figure judge respectively whether each sequence of layer steady,, if turn to step 5.3, directly turn to if not step 5.1;
Step 5.3, determine each layer model exponent number;
Step 5.4, utilize each layer air speed data to try to achieve the parameters estimated value of each layer after model order is determined;
Step 5.5, judge whether the residual sequence of model of fit is a white noise sequence,, if institute's testing model changes step 6 over to, changes if not step 5.3 over to.
3. a kind of wind power forecasting method as claimed in claim 2, it is characterized in that: this historical data comprises output power, wind speed, wind direction, temperature, atmospheric pressure and the relative humidity of wind-powered electricity generation unit.
4. a kind of wind power forecasting method as claimed in claim 2, it is characterized in that: in step 2, use clustering method, take into full account weather conditions, based on the formation reason of wind speed, consider temperature, atmospheric pressure and three major influence factors of relative humidity, calculated each historical day and the wind speed property value of prediction day between Euclidean distance, then to press Weight average for each data, selects several groups of the shortest data of Euclidean distance as sample data.
5. a kind of wind power forecasting method as claimed in claim 2, it is characterized in that: in step 3, by different bandpass filter, one group of original series that will contain integrated information resolves into the time series of many group different characteristics, one group of inherent variation tendency of the former seasonal effect in time series of signal reaction; The impact that the sequence reflection random perturbation of all the other groups is brought, select different parameter models to predict for different characteristic signals.
6. wind power forecasting system comprises at least:
Historical data is obtained module, is used for obtaining the historical data of the wind-powered electricity generation unit in the fixed time scope;
The cluster analysis module, use cluster analysis to process historical data, selects the air speed data of historical day that has similarity with the wind speed characteristic parameter of predicting day, with them as the sample in modeling;
The wavelet decomposition module, carry out wavelet decomposition to the wind series of selecting, and utilizes wavelet decomposition that each sequence component is projected to respectively on different scale, successively decomposes on different channel;
The reconstruct module, with each sequence of layer after decomposing respectively reconstruct return archeus and count to increase signal;
Forecast model is set up module, is used for each sequence of layer is set up respectively forecast model;
The prediction module, predict each layer data with the above-mentioned forecast model of setting up;
The stack module,, with each layer data predicted value stack of gained, obtain original wind speed time series forecasting value.
7. a kind of wind power forecasting system as claimed in claim 6, is characterized in that, this forecast model is set up module and further comprised:
Correlation function value calculates module, is used for calculating the auto-correlation function value of each sequence of layer
, the partial correlation functional value
The judgement module, according to
,
Figure judge respectively whether each sequence of layer steady;
Model is determined the rank module, in this judgement module judgment result is that each sequence of layer is steady the time, determine each layer model exponent number;
The model parameter estimation module, utilize each layer air speed data to try to achieve the parameters estimated value of each layer after model order is determined;
The check module, judge whether the residual sequence of model of fit is a white noise sequence, if suitable this prediction module that utilizes of institute's testing model is predicted, returns to if not model and determines rank.
8. a kind of wind power forecasting system as claimed in claim 7, it is characterized in that: this historical data comprises output power, wind speed, wind direction, temperature, atmospheric pressure and the relative humidity of wind-powered electricity generation unit.
9. a kind of wind power forecasting system as claimed in claim 7, it is characterized in that: this cluster analysis module uses clustering method, take into full account weather conditions, formation reason based on wind speed, consider temperature, atmospheric pressure and three major influence factors of relative humidity, calculated each historical day and the wind speed property value of prediction day between Euclidean distance, then each data are pressed Weight average, select several groups of the shortest data of Euclidean distance as sample data.
10. a kind of wind power forecasting system as claimed in claim 7, it is characterized in that: this wavelet decomposition module is by different bandpass filter, one group of original series that will contain integrated information resolves into the time series of many group different characteristics, one group of inherent variation tendency of the former seasonal effect in time series of signal reaction; The impact that the sequence reflection random perturbation of all the other groups is brought, select different parameter models to predict for different characteristic signals.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103453545A CN103400230A (en) | 2013-08-08 | 2013-08-08 | Wind power forecast system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103453545A CN103400230A (en) | 2013-08-08 | 2013-08-08 | Wind power forecast system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103400230A true CN103400230A (en) | 2013-11-20 |
Family
ID=49563847
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013103453545A Pending CN103400230A (en) | 2013-08-08 | 2013-08-08 | Wind power forecast system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103400230A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504466A (en) * | 2014-12-17 | 2015-04-08 | 华北电力大学(保定) | Wind power plant power prediction method considering atmospheric disturbance effect |
CN105932669A (en) * | 2016-05-19 | 2016-09-07 | 国家电网公司 | Wind power fluctuation component decomposer and wind power output fluctuation characteristic assessment method |
CN106203693A (en) * | 2016-07-05 | 2016-12-07 | 华北电力大学 | A kind of system and method for Power Output for Wind Power Field climbing event prediction |
CN106295908A (en) * | 2016-08-24 | 2017-01-04 | 上海电机学院 | A kind of SVM wind power forecasting method |
CN106886564A (en) * | 2017-01-03 | 2017-06-23 | 北京国能日新系统控制技术有限公司 | A kind of method and device that NWP wind energy collection of illustrative plates is corrected based on space clustering |
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 |
CN108154263A (en) * | 2017-12-21 | 2018-06-12 | 上海网波软件股份有限公司 | The monitoring and controlling forecast method of natural water resource |
CN109344875A (en) * | 2018-08-31 | 2019-02-15 | 中国南方电网有限责任公司电网技术研究中心 | Method, device and medium for generating solar wind power output time sequence based on cluster analysis |
CN109697527A (en) * | 2018-12-19 | 2019-04-30 | 浙江大学 | A kind of power predicating method of the various dimensions based on time series decomposition for trend |
CN112200376A (en) * | 2020-10-16 | 2021-01-08 | 国能日新科技股份有限公司 | System and method for predicting medium-term and long-term generated energy of new energy wind power plant |
CN113094997A (en) * | 2021-04-19 | 2021-07-09 | 华北电力大学 | Wind turbine generator operation simulation method, device, equipment and storage medium |
CN113487068A (en) * | 2021-06-21 | 2021-10-08 | 湖北工业大学 | Short-term wind power prediction method based on long-term and short-term memory module |
CN115357065A (en) * | 2022-08-27 | 2022-11-18 | 华能新能源股份有限公司 | Remote intelligent dehumidification control system and method for offshore wind turbine |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101414751A (en) * | 2008-11-20 | 2009-04-22 | 北京方鸿溪科技有限公司 | Wind power forecasting system and method thereof, network system |
CN101414317A (en) * | 2008-11-27 | 2009-04-22 | 东北电力大学 | Equivalent wind speed method for processing wind electric field static power equivalence dispersion problem |
CN101498926A (en) * | 2008-02-02 | 2009-08-05 | 北京能高自动化技术有限公司 | Large wind turbines optimization control system with layered hierarchical structure |
CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
-
2013
- 2013-08-08 CN CN2013103453545A patent/CN103400230A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101498926A (en) * | 2008-02-02 | 2009-08-05 | 北京能高自动化技术有限公司 | Large wind turbines optimization control system with layered hierarchical structure |
CN101414751A (en) * | 2008-11-20 | 2009-04-22 | 北京方鸿溪科技有限公司 | Wind power forecasting system and method thereof, network system |
CN101414317A (en) * | 2008-11-27 | 2009-04-22 | 东北电力大学 | Equivalent wind speed method for processing wind electric field static power equivalence dispersion problem |
CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
Non-Patent Citations (1)
Title |
---|
黄帅: "风电场超短期功率预测方法的研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, 15 June 2013 (2013-06-15) * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504466A (en) * | 2014-12-17 | 2015-04-08 | 华北电力大学(保定) | Wind power plant power prediction method considering atmospheric disturbance effect |
CN104504466B (en) * | 2014-12-17 | 2018-03-16 | 华北电力大学(保定) | Consider the wind electric field power prediction method of atmospheric perturbation effect |
CN105932669B (en) * | 2016-05-19 | 2018-06-22 | 国家电网公司 | Wind power swing component decomposer and wind power output wave characteristic appraisal procedure |
CN105932669A (en) * | 2016-05-19 | 2016-09-07 | 国家电网公司 | Wind power fluctuation component decomposer and wind power output fluctuation characteristic assessment method |
CN106203693A (en) * | 2016-07-05 | 2016-12-07 | 华北电力大学 | A kind of system and method for Power Output for Wind Power Field climbing event prediction |
CN106295908A (en) * | 2016-08-24 | 2017-01-04 | 上海电机学院 | A kind of SVM wind power forecasting method |
CN106886564A (en) * | 2017-01-03 | 2017-06-23 | 北京国能日新系统控制技术有限公司 | A kind of method and device that NWP wind energy collection of illustrative plates is corrected based on space clustering |
CN106886564B (en) * | 2017-01-03 | 2020-02-14 | 国能日新科技股份有限公司 | Method and device for correcting NWP (non-Newtonian Web Page) wind energy spectrum based on spatial clustering |
CN108154263A (en) * | 2017-12-21 | 2018-06-12 | 上海网波软件股份有限公司 | The monitoring and controlling forecast method of natural water resource |
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 |
CN109344875A (en) * | 2018-08-31 | 2019-02-15 | 中国南方电网有限责任公司电网技术研究中心 | Method, device and medium for generating solar wind power output time sequence based on cluster analysis |
CN109697527A (en) * | 2018-12-19 | 2019-04-30 | 浙江大学 | A kind of power predicating method of the various dimensions based on time series decomposition for trend |
CN112200376A (en) * | 2020-10-16 | 2021-01-08 | 国能日新科技股份有限公司 | System and method for predicting medium-term and long-term generated energy of new energy wind power plant |
CN113094997A (en) * | 2021-04-19 | 2021-07-09 | 华北电力大学 | Wind turbine generator operation simulation method, device, equipment and storage medium |
CN113487068A (en) * | 2021-06-21 | 2021-10-08 | 湖北工业大学 | Short-term wind power prediction method based on long-term and short-term memory module |
CN115357065A (en) * | 2022-08-27 | 2022-11-18 | 华能新能源股份有限公司 | Remote intelligent dehumidification control system and method for offshore wind turbine |
CN115357065B (en) * | 2022-08-27 | 2024-04-12 | 华能新能源股份有限公司 | Remote intelligent dehumidification control system and method for offshore wind turbine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103400230A (en) | Wind power forecast system and method | |
CN109492667A (en) | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring | |
CN109145949A (en) | Non-intrusive electrical load monitoring and decomposition method and system based on integrated study | |
CN103077402A (en) | Transformer partial-discharging mode recognition method based on singular value decomposition algorithm | |
CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
CN102609766B (en) | Method for intelligently forecasting wind speed in wind power station | |
CN113659565B (en) | Online prediction method for frequency situation of new energy power system | |
CN102682207A (en) | Ultrashort combined predicting method for wind speed of wind power plant | |
CN110991263B (en) | Non-invasive load identification method and system for resisting background load interference | |
CN111628494B (en) | Low-voltage distribution network topology identification method and system based on logistic regression method | |
CN108717579B (en) | Short-term wind power interval prediction method | |
CN106875033A (en) | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting | |
CN103746370A (en) | Wind-power-plant reliability modeling method | |
CN102270302A (en) | Grey support vector machine-based multi-stress accelerated life testing forecasting method | |
CN102738792B (en) | Wind power predicting method | |
CN102184335B (en) | Fire disaster time sequence prediction method based on ensemble empirical mode decomposition and phase space reconstruction | |
CN103903071A (en) | Wind power forecast combination method and system | |
CN109658006A (en) | A kind of large-scale wind power field group auxiliary dispatching method and device | |
CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
CN110197298A (en) | The method and device of multi-model sun normal direction radiation prediction based on clustering algorithm | |
CN104933471A (en) | Phase space reconstruction method for use in short-term wind speed prediction method | |
Xiaolan et al. | One-month ahead prediction of wind speed and output power based on EMD and LSSVM | |
Tang et al. | Semi-intrusive load monitoring for large-scale appliances | |
CN104504465A (en) | Power generation fuel supply prediction method | |
CN104834816A (en) | Short-term wind speed prediction 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 | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131120 |