CN112668807A - Wind speed prediction method for wind power plant power prediction - Google Patents
Wind speed prediction method for wind power plant power prediction Download PDFInfo
- Publication number
- CN112668807A CN112668807A CN202110058962.2A CN202110058962A CN112668807A CN 112668807 A CN112668807 A CN 112668807A CN 202110058962 A CN202110058962 A CN 202110058962A CN 112668807 A CN112668807 A CN 112668807A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- deviation
- prediction
- speed prediction
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a wind speed prediction method for wind power plant power prediction, which comprises the following steps of firstly, randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods; calculating wind speed prediction deviation data in each time period, and cleaning the data; thirdly, normalization processing; fourthly, detecting outliers; fifthly, fitting a wind speed prediction deviation curve to obtain a basic model of the wind speed prediction deviation value; sixthly, obtaining a prediction deviation data set; constructing a training set of the extreme learning machine; constructing two extreme learning machine models, and training to obtain a deviation correction model of the wind speed prediction deviation value; and ninthly, obtaining a final predicted value of the wind speed through a basic model of the wind speed prediction deviation value and a deviation correction model of the wind speed prediction deviation value. The wind speed prediction method based on the deviation correction technology can be used for predicting the wind speed by combining the existing wind speed prediction method, further improves the wind speed prediction precision, has obvious effect and is convenient to popularize.
Description
Technical Field
The invention belongs to the technical field of new energy power generation, and particularly relates to a wind speed prediction method for wind power plant power prediction.
Background
Renewable energy power generation has been rapidly developed worldwide to cope with energy crisis and environmental issues. Wind power generation, a typical renewable energy power generation mode, has an increasing penetration rate in modern power grids. However, because wind energy has strong uncertainty, high wind permeability brings great challenges to the stable operation of a power grid, and is an important problem which needs to be solved urgently by a power dispatching department, and realizing accurate prediction of wind power plant power is a key way for solving the problem.
The accurate prediction of the power of the wind power plant is realized mainly by accurately predicting the wind speed, the prediction is an estimation of the future, a certain difference exists between the prediction and the objective reality, and the difference is prediction deviation. In the prior art, a plurality of effective methods for predicting the wind speed are available, the prediction accuracy is higher and higher, but an effective reasonable method for predicting the wind speed by adopting a deviation correction technology from the perspective of prediction deviation is lacked.
Disclosure of Invention
The invention aims to solve the technical problem of providing a wind speed prediction method for wind power plant power prediction, aiming at the defects in the prior art, the method has simple steps, reasonable design and convenient realization, carries out wind speed prediction based on a deviation correction technology, can combine the existing wind speed prediction method to carry out wind speed prediction, further improves the precision of wind speed prediction, further obtains better wind power plant power prediction effect, has obvious effect and is convenient for popularization.
In order to solve the technical problems, the invention adopts the technical scheme that: a wind speed prediction method for wind farm power prediction comprises the following steps:
step one, in the normal operation process of a wind power plant, randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods;
step two, calculating wind speed prediction deviation data in each time period, and cleaning the data;
step three, carrying out normalization processing on the wind speed prediction deviation data;
fourthly, performing outlier detection on the normalized data by adopting a K-NN algorithm;
step five, fitting a wind speed prediction deviation curve by adopting a logistic function to obtain a basic model of the wind speed prediction deviation value;
predicting the wind speed by adopting a basic model of the wind speed prediction deviation value to obtain a prediction deviation data set;
constructing a training set of the extreme learning machine by adopting a low-pass filter to predict a deviation data set;
step eight, constructing two extreme learning machine models, and training by adopting the training set in the step seven to obtain a deviation correction model of the wind speed prediction deviation value;
step nine, obtaining a final predicted value of the wind speed through a basic model of the wind speed prediction deviation value and a deviation correction model of the wind speed prediction deviation value;
step 901, predicting value V of wind speed at t moment of wind power plantCALInputting the wind speed prediction deviation value into a basic model of the wind speed prediction deviation value in the fifth step to obtain a wind speed prediction deviation basic value VBASE；
Step 902, inputting the wind speed prediction deviation at the t-20, t-19, and t-1 moments into the low-pass filter in the step seven as input characteristics to obtain a high-frequency part and a low-frequency part of the input characteristics;
step 903, inputting the high frequency part and the low frequency part of the input characteristics into a deviation correction model of the wind speed prediction deviation value respectively to obtain a high frequency deviation correction value fELMHAnd a low frequency deviation correction amount fELML；
Step 904, obtaining the final predicted value of the wind speed as VCAL+VBASE+fELMH+fELML。
In the above wind speed prediction method for wind farm power prediction, in the first step, the specific process of randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods includes: wind speed measurement data and wind speed prediction data in 50-100 time periods are randomly extracted, and the duration of each time period is 1 hour.
In the wind speed prediction method for wind power plant power prediction, in the second step, the specific process of calculating the wind speed prediction deviation data in each time period and performing data cleaning includes: according to the formula Δ vi＝|vc-vmCalculating wind speed prediction deviation data in each time period, wherein Δ viPredicting a deviation value, v, for the wind speedcAs a predicted value of wind speed, vmIs a wind speed measurement; then, data elimination is carried out by adopting a triple standard deviation method.
The wind speed prediction method for wind power plant power prediction comprises the third stepThe specific process of normalizing the wind speed prediction deviation data comprises the following steps: according to the formula
Normalizing the wind speed prediction deviation data to obtain a normalized wind speed prediction deviation value delta v'iWherein, Δ viPrediction of deviation value, mean (Δ v) for wind speedi) Is Δ viMean value of (a), std (Δ v)i) Is Δ viStandard deviation of (2).
In the wind speed prediction method for wind power plant power prediction, the specific process of predicting the wind speed by using the basic model of the wind speed prediction deviation value to obtain the prediction deviation data set in the sixth step includes: predicting the wind speed in a plurality of time intervals in the future, substituting the predicted wind speed value into the basic model of the predicted wind speed deviation value to obtain the predicted wind speed deviation value in the future time intervals, and obtaining the predicted wind speed deviation value according to a formula delta vfi＝|(vfc+Δvfmi)-vfmCalculating the wind speed prediction deviation value of a future time period, and setting the wind speed prediction deviation value of a plurality of future time periods to form a prediction deviation data set, wherein deltavfiPredicting deviation values, v, for wind speed over a future period of timefcFor wind speed prediction for future time periods, Δ vfmiFor the predicted deviation value of wind speed, v, over the future time period calculated from the base model of the predicted deviation value of wind speedfmIs a measure of the wind speed at the time of arrival of the period.
In the wind speed prediction method for wind power plant power prediction, in the seventh step, the specific process of constructing the training set of the extreme learning machine by using the prediction deviation data set includes: adopting a time sequence sliding window method, taking 20 as an input feature number, taking 1 as an interval to perform sliding window, taking the prediction deviation of 15 minutes in the future as a training target, and obtaining a training feature set and a training target set; then, a low-pass filter is used
Filtering the training feature set and the training target set to obtain a low-frequency part and a high-frequency part of the training feature set, and trainingThe low-frequency part and the high-frequency part of the training target set, and the low-frequency part of the training feature set correspond to the low-frequency part of the training target set to form a low-frequency part training set; and the high-frequency part of the training feature set corresponds to the high-frequency part of the training target set to form a high-frequency part training set, wherein 1/tau is the bandwidth of the low-pass filter.
Compared with the prior art, the invention has the following advantages:
1. the method has simple steps, reasonable design and convenient realization.
2. According to the method, the wind speed measurement data and the wind speed prediction data in a plurality of time periods in the normal operation process of the wind power plant are randomly extracted to serve as the data basis of the basic model of the wind speed prediction deviation value, the wind speed prediction deviation basic value can be objectively obtained in a probability mode, and the reliability is high.
3. The method fully utilizes the existing wind speed prediction data in the wind power plant, obtains the basic model of the wind speed prediction deviation value by using the wind speed prediction deviation curve under the condition of not solving the atmospheric motion equation, and can obtain the wind speed prediction deviation basic value with lower calculation cost in practical use.
4. According to the wind speed prediction deviation correction method, the wind speed prediction deviation correction model based on the double-pole limit learning machine is established according to the high-frequency and low-frequency decomposition results, and the wind speed prediction precision can be improved by a simple structure.
5. The wind speed prediction method based on the deviation correction technology can be used for predicting the wind speed by combining all existing wind speed prediction methods, so that the wind speed prediction precision is further improved, a better wind power plant power prediction effect is obtained, the effect is obvious, and the popularization is convenient.
In conclusion, the method provided by the invention has the advantages of simple steps, reasonable design and convenience in implementation, can be used for predicting the wind speed based on the deviation correction technology, can be combined with the existing wind speed prediction method to predict the wind speed, further improves the wind speed prediction precision, further obtains a better wind power plant power prediction effect, has an obvious effect and is convenient to popularize.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a flow chart of a prediction method of the present invention;
FIG. 2 is a diagram illustrating the effect of the prediction method of the present invention.
Detailed Description
As shown in FIG. 1, the wind speed prediction method for wind power plant power prediction of the invention comprises the following steps:
step one, in the normal operation process of a wind power plant, randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods;
step two, calculating wind speed prediction deviation data in each time period, and cleaning the data;
step three, carrying out normalization processing on the wind speed prediction deviation data;
fourthly, performing outlier detection on the normalized data by adopting a K-NN algorithm;
step five, fitting a wind speed prediction deviation curve by adopting a logistic function to obtain a basic model of the wind speed prediction deviation value;
predicting the wind speed by adopting a basic model of the wind speed prediction deviation value to obtain a prediction deviation data set;
constructing a training set of the extreme learning machine by adopting a low-pass filter to predict a deviation data set;
step eight, constructing two extreme learning machine models, and training by adopting the training set in the step seven to obtain a deviation correction model of the wind speed prediction deviation value;
step nine, obtaining a final predicted value of the wind speed through a basic model of the wind speed prediction deviation value and a deviation correction model of the wind speed prediction deviation value;
step 901, predicting value V of wind speed at t moment of wind power plantCALInputting the wind speed prediction deviation value into a basic model of the wind speed prediction deviation value in the fifth step to obtain a wind speed prediction deviation basic value VBASE；
Step 902, inputting the wind speed prediction deviation at the t-20, t-19, and t-1 moments into the low-pass filter in the step seven as input characteristics to obtain a high-frequency part and a low-frequency part of the input characteristics;
step 903, inputting the high frequency part and the low frequency part of the input characteristics into a deviation correction model of the wind speed prediction deviation value respectively to obtain a high frequency deviation correction value fELMHAnd a low frequency deviation correction amount fELML；
Step 904, obtaining the final predicted value of the wind speed as VCAL+VBASE+fELMH+fELML。
In this embodiment, the specific process of randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods in the first step includes: wind speed measurement data and wind speed prediction data in 50-100 time periods are randomly extracted, and the duration of each time period is 1 hour.
In this embodiment, the specific process of calculating the wind speed prediction deviation data in each time period and performing data cleaning in step two includes: according to the formula Δ vi＝|vc-vmCalculating wind speed prediction deviation data in each time period, wherein Δ viPredicting a deviation value, v, for the wind speedcAs a predicted value of wind speed, vmIs a wind speed measurement; then, data elimination is carried out by adopting a triple standard deviation method.
In this embodiment, the specific process of normalizing the wind speed prediction deviation data in step three includes: according to the formula
Normalizing the wind speed prediction deviation data to obtain a normalized wind speed prediction deviation value delta v'iWherein, Δ viPrediction of deviation value, mean (Δ v) for wind speedi) Is Δ viMean value of (a), std (Δ v)i) Is Δ viStandard deviation of (2).
In specific implementation, normalization processing facilitates rejection of outliers within a set wind speed range.
In this embodiment, the specific process of predicting the wind speed by using the basic model of the wind speed prediction deviation value to obtain the prediction deviation data set in the sixth step includes: for wind in a plurality of time intervals in the futurePredicting the wind speed, substituting the predicted wind speed value into the basic model of the predicted wind speed deviation value to obtain the predicted wind speed deviation value in the future period, and calculating the predicted wind speed deviation value according to the formula delta vfi＝|(vfc+Δvfmi)-vfmCalculating the wind speed prediction deviation value of a future time period, and setting the wind speed prediction deviation value of a plurality of future time periods to form a prediction deviation data set, wherein deltavfiPredicting deviation values, v, for wind speed over a future period of timefcFor wind speed prediction for future time periods, Δ vfmiFor the predicted deviation value of wind speed, v, over the future time period calculated from the base model of the predicted deviation value of wind speedfmIs a measure of the wind speed at the time of arrival of the period.
In specific implementation, all the existing prediction methods can be adopted in the process of predicting the wind speeds in a plurality of time intervals in the future.
In this embodiment, the specific process of constructing the training set of the extreme learning machine by using the predicted deviation data set in the seventh step includes: adopting a time sequence sliding window method, taking 20 as an input feature number, taking 1 as an interval to perform sliding window, taking the prediction deviation of 15 minutes in the future as a training target, and obtaining a training feature set and a training target set; then, a low-pass filter is used
Filtering the training feature set and the training target set to obtain a low-frequency part and a high-frequency part of the training feature set and a low-frequency part and a high-frequency part of the training target set, wherein the low-frequency part of the training feature set corresponds to the low-frequency part of the training target set to form a low-frequency part training set; and the high-frequency part of the training feature set corresponds to the high-frequency part of the training target set to form a high-frequency part training set, wherein 1/tau is the bandwidth of the low-pass filter.
In specific implementation, τ is 2.
In order to verify the effect of the prediction method, the wind speed data of a certain wind power plant in China within one month is adopted for modeling, and the wind speed within two hours in the future is predicted.
Acquiring wind speed data of a wind turbine generator within one month, and randomly extracting wind speed measurement data and wind speed prediction data within 80 time periods; calculating wind speed prediction deviation data in each time period, and cleaning the data by adopting a '3 sigma' principle; carrying out normalization processing on the wind speed prediction deviation data; performing outlier detection on the normalized data by adopting a K-NN algorithm; fitting a wind speed prediction deviation curve by adopting a logistic function to obtain a basic model of the wind speed prediction deviation value; predicting the wind speed by using the basic model of the wind speed prediction deviation value to obtain a prediction deviation data set; constructing a training set of an extreme learning machine; constructing a limit learning machine system as a wind speed prediction deviation correction model, and training to obtain a deviation correction model of a wind speed prediction deviation value; and obtaining a final predicted value of the wind speed by using the basic model of the wind speed prediction deviation value and the deviation correction model of the wind speed prediction deviation value.
FIG. 2 is a comparison graph of the final predicted value and the actual value of the wind speed according to the present invention, and it can be seen from FIG. 2 that the wind speed prediction method according to the present invention has high prediction accuracy.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and all simple modifications, changes and equivalent structural changes made to the above embodiment according to the technical spirit of the present invention still fall within the protection scope of the technical solution of the present invention.
Claims (6)
1. A wind speed prediction method for wind power plant power prediction is characterized by comprising the following steps: the method comprises the following steps:
step one, in the normal operation process of a wind power plant, randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods;
step two, calculating wind speed prediction deviation data in each time period, and cleaning the data;
step three, carrying out normalization processing on the wind speed prediction deviation data;
fourthly, performing outlier detection on the normalized data by adopting a K-NN algorithm;
step five, fitting a wind speed prediction deviation curve by adopting a logistic function to obtain a basic model of the wind speed prediction deviation value;
predicting the wind speed by adopting a basic model of the wind speed prediction deviation value to obtain a prediction deviation data set;
constructing a training set of the extreme learning machine by adopting a low-pass filter to predict a deviation data set;
step eight, constructing two extreme learning machine models, and training by adopting the training set in the step seven to obtain a deviation correction model of the wind speed prediction deviation value;
step nine, obtaining a final predicted value of the wind speed through a basic model of the wind speed prediction deviation value and a deviation correction model of the wind speed prediction deviation value;
step 901, predicting value V of wind speed at t moment of wind power plantCALInputting the wind speed prediction deviation value into a basic model of the wind speed prediction deviation value in the fifth step to obtain a wind speed prediction deviation basic value VBASE；
Step 902, inputting the wind speed prediction deviation at the t-20, t-19, and t-1 moments into the low-pass filter in the step seven as input characteristics to obtain a high-frequency part and a low-frequency part of the input characteristics;
step 903, inputting the high frequency part and the low frequency part of the input characteristics into a deviation correction model of the wind speed prediction deviation value respectively to obtain a high frequency deviation correction value fELMHAnd a low frequency deviation correction amount fELML；
Step 904, obtaining the final predicted value of the wind speed as VCAL+VBASE+fELMH+fELML。
2. The wind speed prediction method for wind farm power prediction according to claim 1, wherein the specific process of randomly extracting wind speed measurement data and wind speed prediction data in a plurality of time periods in the step one comprises: wind speed measurement data and wind speed prediction data in 50-100 time periods are randomly extracted, and the duration of each time period is 1 hour.
3. A wind speed prediction method for wind farm power prediction according to claim 1, characterized in that in step two said calculation is performed every timeForecasting deviation data of the wind speed in the section, and performing a specific process of data cleaning, wherein the specific process comprises the following steps: according to the formula Δ vi＝|vc-vmCalculating wind speed prediction deviation data in each time period, wherein Δ viPredicting a deviation value, v, for the wind speedcAs a predicted value of wind speed, vmIs a wind speed measurement; then, data elimination is carried out by adopting a triple standard deviation method.
4. The wind speed prediction method for wind power plant power prediction according to claim 1, wherein the concrete process of normalizing the wind speed prediction deviation data in the third step comprises: according to the formula
Normalizing the wind speed prediction deviation data to obtain a normalized wind speed prediction deviation value delta v'iWherein, Δ viPrediction of deviation value, mean (Δ v) for wind speedi) Is Δ viMean value of (a), std (Δ v)i) Is Δ viStandard deviation of (2).
5. The wind speed prediction method for wind power plant power prediction according to claim 1, wherein the step six of predicting the wind speed by using the basic model of the wind speed prediction deviation value comprises the following specific steps of: predicting the wind speed in a plurality of time intervals in the future, substituting the predicted wind speed value into the basic model of the predicted wind speed deviation value to obtain the predicted wind speed deviation value in the future time intervals, and obtaining the predicted wind speed deviation value according to a formula delta vfi＝|(vfc+Δvfmi)-vfmCalculating the wind speed prediction deviation value of a future time period, and setting the wind speed prediction deviation value of a plurality of future time periods to form a prediction deviation data set, wherein deltavfiPredicting deviation values, v, for wind speed over a future period of timefcFor wind speed prediction for future time periods, Δ vfmiFor the predicted deviation value of wind speed, v, over the future time period calculated from the base model of the predicted deviation value of wind speedfmAs a measure of wind speed at that time。
6. The wind speed prediction method for wind farm power prediction according to claim 1, wherein the concrete process of constructing the training set of the extreme learning machine by the prediction deviation data set in the seventh step comprises the following steps: adopting a time sequence sliding window method, taking 20 as an input feature number, taking 1 as an interval to perform sliding window, taking the prediction deviation of 15 minutes in the future as a training target, and obtaining a training feature set and a training target set; then, a low-pass filter is used
Filtering the training feature set and the training target set to obtain a low-frequency part and a high-frequency part of the training feature set and a low-frequency part and a high-frequency part of the training target set, wherein the low-frequency part of the training feature set corresponds to the low-frequency part of the training target set to form a low-frequency part training set; and the high-frequency part of the training feature set corresponds to the high-frequency part of the training target set to form a high-frequency part training set, wherein 1/tau is the bandwidth of the low-pass filter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110058962.2A CN112668807B (en) | 2021-01-17 | 2021-01-17 | Wind speed prediction method for wind power plant power prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110058962.2A CN112668807B (en) | 2021-01-17 | 2021-01-17 | Wind speed prediction method for wind power plant power prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112668807A true CN112668807A (en) | 2021-04-16 |
| CN112668807B CN112668807B (en) | 2023-07-11 |
Family
ID=75415389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110058962.2A Active CN112668807B (en) | 2021-01-17 | 2021-01-17 | Wind speed prediction method for wind power plant power prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112668807B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435653A (en) * | 2021-07-02 | 2021-09-24 | 国网新疆电力有限公司经济技术研究院 | Saturated power consumption prediction method and system based on logistic model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496927A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Wind power station power projection method based on error statistics modification |
| CN102663513A (en) * | 2012-03-13 | 2012-09-12 | 华北电力大学 | Combination forecast modeling method of wind farm power by using gray correlation analysis |
| CN108229732A (en) * | 2017-12-20 | 2018-06-29 | 上海电机学院 | ExtremeLearningMachine wind speed ultra-short term prediction method based on error correction |
-
2021
- 2021-01-17 CN CN202110058962.2A patent/CN112668807B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496927A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Wind power station power projection method based on error statistics modification |
| CN102663513A (en) * | 2012-03-13 | 2012-09-12 | 华北电力大学 | Combination forecast modeling method of wind farm power by using gray correlation analysis |
| CN108229732A (en) * | 2017-12-20 | 2018-06-29 | 上海电机学院 | ExtremeLearningMachine wind speed ultra-short term prediction method based on error correction |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435653A (en) * | 2021-07-02 | 2021-09-24 | 国网新疆电力有限公司经济技术研究院 | Saturated power consumption prediction method and system based on logistic model |
| CN113435653B (en) * | 2021-07-02 | 2022-11-04 | 国网新疆电力有限公司经济技术研究院 | Method and system for predicting saturated power consumption based on logistic model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112668807B (en) | 2023-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109308522B (en) | GIS fault prediction method based on recurrent neural network | |
| CN110807554B (en) | Generation method and system based on wind power/photovoltaic classical scene set | |
| CN111582551B (en) | Wind power plant short-term wind speed prediction method and system and electronic equipment | |
| CN112712215A (en) | Wind power plant power prediction method | |
| CN110658462B (en) | Lithium battery online service life prediction method based on data fusion and ARIMA model | |
| CN109145516B (en) | Analog circuit fault identification method based on improved extreme learning machine | |
| CN104573876A (en) | Wind power plant short-period wind speed prediction method based on time sequence long memory model | |
| CN105719023A (en) | Real-time wind power prediction and error analysis method based on mixture Gaussian distribution | |
| CN111415010B (en) | Bayesian neural network-based wind turbine generator parameter identification method | |
| CN111426957B (en) | SOC estimation optimization method for power battery under simulated vehicle working condition | |
| CN107885968B (en) | Method and system for predicting annual average wind speed of wind power plant based on period superposition extrapolation | |
| CN103631681A (en) | Method for online restoring abnormal data of wind power plant | |
| CN110378504B (en) | Photovoltaic power generation climbing event probability prediction method based on high-dimensional Copula technology | |
| CN108717579B (en) | Short-term wind power interval prediction method | |
| CN104237853B (en) | A kind of for the particle filter method of trace point mark sequence before multi frame detection | |
| CN106203693A (en) | A kind of system and method for Power Output for Wind Power Field climbing event prediction | |
| CN109655751A (en) | A kind of method and system using Gaussian process regression estimates battery charging state | |
| CN108960329A (en) | A kind of chemical process fault detection method comprising missing data | |
| CN109583075A (en) | Permanent magnet direct-drive wind-force machine military service quality evaluating method based on temperature parameter prediction | |
| CN112668807A (en) | Wind speed prediction method for wind power plant power prediction | |
| CN114819374A (en) | Regional new energy ultra-short term power prediction method and system | |
| CN111709454A (en) | Multi-wind-field output clustering evaluation method based on optimal copula model | |
| CN105956708A (en) | Grey correlation time sequence based short-term wind speed forecasting method | |
| CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
| CN116485049B (en) | Electric energy metering error prediction and optimization system based on artificial intelligence |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |