CN110489719A - Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data - Google Patents
Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data Download PDFInfo
- Publication number
- CN110489719A CN110489719A CN201910703238.3A CN201910703238A CN110489719A CN 110489719 A CN110489719 A CN 110489719A CN 201910703238 A CN201910703238 A CN 201910703238A CN 110489719 A CN110489719 A CN 110489719A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction system
- data processing
- ensemble prediction
- wind speed
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 66
- 238000013277 forecasting method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000013138 pruning Methods 0.000 claims abstract description 12
- 230000001550 time effect Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 15
- 238000003066 decision tree Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 239000013589 supplement Substances 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 239000000047 product Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 4
- 238000007418 data mining Methods 0.000 abstract description 3
- 230000007812 deficiency Effects 0.000 description 3
- 230000001373 regressive effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to meteorological research and forecast field, to propose a kind of wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, can preferably using data mining means and DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM member's as a result, improve forecasting wind speed accuracy rate.Thus, the technical solution adopted by the present invention is that, wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, according to European Center for Medium Weather Forecasting's ensemble prediction product, 51 forecast members that each Time effect forecast generates, optimal member is selected using the method for CART (Classification And Regression Tree) beta pruning, GBDT (Gradient Boosting Descision Tree) model is constructed using optimal member, it is final to realize the forecasting wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data.Present invention is mainly applied to meteorological research and forecast occasions.
Description
Technical field
The present invention relates to meteorological research and forecast field, and it is pre- to be specifically related to a kind of wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
Survey method.
Background technique
Forecasting wind speed is one of the object more paid close attention to by people in weather prognosis, the prediction result of wind speed accurately with
The no group for affecting coastal life, operation.
The method that forecasting wind speed generally uses DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM, DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM are a kind of means of weather forecast, from number
Value forecast carries out mathematical modeling by the physics law to inner-atmopshere, and air heat power, the ability for simulating Real Atmosphere are kept
Perseverance, steam changing rule etc..The math equation of usually simulation Real Atmosphere state is more huge, by high-performance computer to this
A little models are calculated, and some weather conditions of our concerns are therefrom obtained, to realize weather conditions or weather conditions variation
Prediction.The Atmosphere System of nonlinearity is a chaos system, the chaotic property of initial value error, the error of mode and atmosphere
It is that there is a variety of uncertainties for numerical forecast.
The data that DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM provides can provide reference to the forecast work of meteorological research personnel, but its result exists not
Evitable mode error and systematic error, DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM result are corrected when in use or are returned based on forecast result
Return.Therefore the forecasting wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data can relatively accurately be realized by being badly in need of finding a kind of method.
Summary of the invention
In order to overcome the deficiencies of the prior art, the present invention is directed to propose in order to overcome the deficiencies of the prior art, the present invention is directed to mention
A kind of wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data out, can preferably using data mining means and DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM at
Member's as a result, improve the accuracy rate of forecasting wind speed.For this reason, the technical scheme adopted by the present invention is that based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
Wind speed forecasting method, according to European Center for Medium Weather Forecasting (European center for medium-range
Weather forecasts, ECMWF) ensemble prediction product, 51 forecast members that each Time effect forecast generates use CART
The method of (Classification And Regression Tree) beta pruning selects optimal member, is constructed using optimal member
GBDT (Gradient Boosting Descision Tree) model, it is final to realize that the wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data is pre-
It surveys.
Specific steps refinement is as follows:
(1) pretreatment of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
1) Bohai Sea Gulf A platform wind speed measured data is used, determines wind speed label data；
2) DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM DAT formatted data is read in the form of lattice point, constructs sample data；
3) DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM shortage of data value is handled；
4) data of same Time effect forecast are ranked up；
(2) optimal member is selected
1) generation of decision tree: by the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data after sequence, CART regression tree is generated；
2) beta pruning is carried out to decision tree, obtains dividing node；
3) it determines and divides attribute: calculating percentile shared in each data for dividing node after sequence, obtain most
Excellent percentile member；
4) optimal subtree is generated, according to the partitioning site collection of reservation, obtains optimal member's collection；
(3) gradient is constructed based on optimal member and promotes tree-model
1) training set and test set are constructed；
2) GBDT model is initialized；
3) setting terminates the number of iterations M, constructs CART regression tree by training sample；
4) leaf node region Rmj and corresponding output cm is obtained；
5) strong regression model is updated, the number of iterations m adds 1；
6) judge whether the number of iterations m is greater than and terminate the number of iterations M, if so, carrying out step 7)；Otherwise, return step
2)。
Final prediction model is obtained, training set is tested, obtains test result.
Processing DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM shortage of data value comprises the concrete steps that, missing values are supplemented in the way of linear interpolation；For whole
The case where row missing, by Delete Entire Row.Supplement the linear interpolation method of missing values:
Wherein, x is the missing value estimation value of supplement, x1For the previous data for lacking Value Data, x2For missing Value Data
The latter data.
The features of the present invention and beneficial effect are:
The present invention picks out optimal percentile according to the input as prediction model using beta pruning CART regression tree, passes through structure
It builds the strong regression model of GBDT integrated study and further improves forecasting wind speed performance.It is proposed by the present invention to be based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
Wind speed forecasting method can be efficiently modified the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM shadow of error bring to precision of prediction as caused by uncertainty
It rings；The present invention uses the prediction model based on decision tree, breaches the small problem of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM sample size, available more high-precision
The prediction result of degree.
Detailed description of the invention:
Data construct beta pruning regression tree after the sequence of Fig. 1 DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM.
Fig. 2 model prediction result.
Specific embodiment
In order to overcome the deficiencies of the prior art, the present invention is directed to propose a kind of forecasting wind speed side based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
Method, can preferably using data mining means and DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM member's as a result, improve forecasting wind speed accuracy rate.According to
51 forecast members that each Time effect forecast of ensemble prediction product ECWMF generates, using the method for CART beta pruning select it is optimal at
Member constructs GBDT model using optimal member, final to realize the forecasting wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data.For this purpose, the present invention adopts
Technical solution is that a kind of wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, steps are as follows:
(1) pretreatment of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
1) Bohai Sea Gulf A platform wind speed measured data is used, determines wind speed label data；
2) DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM DAT formatted data is read in the form of lattice point, constructs sample data；
3) DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM shortage of data value is handled；
4) data of same Time effect forecast are ranked up.
(2) optimal member is selected
1) generation of decision tree.By the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data after sequence, CART regression tree is generated；
2) beta pruning is carried out to decision tree, obtains dividing node；
3) it determines and divides attribute.Each division node percentile shared in the data after sequence is calculated, is obtained most
Excellent percentile member；
4) optimal subtree is generated, according to the partitioning site collection of reservation, obtains optimal member's collection.
(3) gradient is constructed based on optimal member and promotes tree-model
1) training set and test set are constructed；
2) GBDT model is initialized；
3) setting terminates the number of iterations M, constructs CART regression tree by training sample；
4) leaf node region Rmj and corresponding output cm is obtained；
5) strong regression model is updated, the number of iterations m adds 1；
6) judge whether the number of iterations m is greater than and terminate the number of iterations M, if so, carrying out step 7)；Otherwise, return step
2)。
Final prediction model is obtained, training set is tested, obtains test result.
Set specific embodiment is further elaborated the present invention below.
To solve the problems, such as the forecasting wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, the present invention proposes a kind of based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
Wind speed forecasting method, according to 51 forecast members that each Time effect forecast of ensemble prediction product ECMWF generates, algorithm uses CART
The method of beta pruning decision tree selects the optimal member of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM, according to optimal member, constructs GBDT regressive prediction model, most
The forecasting wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data is realized eventually.
Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data mainly includes the next steps.
Pretreatment operation of the step 1 to DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
The European Center for Medium Weather Forecasting ECMWF set that collective data in the present invention is introduced using China Meteorological Administration is pre-
Report mode.The mode initial disturbance uses pooling information assimilation and singular value vector method to generate, and uncertain use of mode is repaired
The random parameter disturbance scheme and random back-off scheme ordered.Numerical model uses high-resolution T319 mode, carries out two daily
Secondary report, the Time effect forecast forecast every time are 15 days.The DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM model results are gathered for 51 totally including control forecast
Member.When forecasting or correct using DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, need to use measured data as label, and DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM number
According to there are excalation values.Specific step is as follows:
(1) wind speed label data is determined
Bohai Sea Gulf A platform wind speed measured data sample size is more, and missing values are few, therefore chooses Bohai Sea Gulf A platform and survey wind speed number
According to for label.
(2) sample data is constructed；
DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data storage format is DAT format, and each data file has the description file of corresponding CTL format,
File can be described according to CTL to read DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM DAT formatted data in the form of lattice point.The range for reading data is 2016 3
To in October, 2017, there are two groups of data in the moon daily.DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data are read by Bohai Sea Gulf A platform lattice site coordinate: Bohai Sea
The bay position of platform A latitude and longitude coordinates are (118.416,38.449), and being converted to lattice point coordinate is x=98, y=78；According to when
Between DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data are compareed with Bohai Sea Gulf A platform data, obtain with 51 members of synchronization DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM and Bohai Sea Gulf A
The sample data that platform fact is one group.The construction of complete paired-sample.
(3) processing of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM shortage of data value
For the case where there are excalation values in data, missing values are supplemented in the way of linear interpolation；For full line
The case where missing, by Delete Entire Row.Supplement the linear interpolation method of missing values:
Wherein, x is the missing value estimation value of supplement, x1For the previous data for lacking Value Data, x2For missing Value Data
The latter data.
(4) data of same Time effect forecast are ranked up, the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data after obtaining one group of sequence, for optimal
Member's analysis.
Step 2 selects optimal member
(1) CART decision tree is generated.51 members of the same Time effect forecast of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM are sorted from small to large, are constructed
CART regression tree.
(2) beta pruning is carried out to decision tree, obtains partitioning site, divided after beta pruning node be the 13rd, the 31st, the 35th, the
42, the 43rd member.
(3) it determines and divides attribute.Each division node percentile shared in the data after sequence is calculated, is obtained most
Excellent percentile member, the 25th percentile in the data after corresponding sequence, the 61st percentile, the 69th percentile, the 82nd percentile, the
84 percentiles.
(4) optimal subtree is generated, optimal subtree is as shown in Figure 1.According to the partitioning site collection of reservation, optimal member is obtained
Collection.
Step 3 is based on optimal member and constructs gradient promotion tree-model
(1) training set and test set are constructed.Training set chooses 24 days 00 March in 2015 when 14 days 12 April in 2017
Totally 1480, test set chooses 15 days 00 April in 2017 totally 375 when 22 days 12 October in 2017.
(2) GBDT model is initialized.Input attribute be 84 percentile of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM chosen by optimal percentile method,
82 percentiles, 69 percentiles, 61 percentiles, 25 percentiles, predicted value are wind speed.Choose the set that Time effect forecast is 6 hours
Forecast data is predicted.
(3) setting terminates the number of iterations M, constructs CART regression tree by training sample；
(4) leaf node region Rmj and corresponding output cm is obtained；
(5) strong regression model is updated, the number of iterations m adds 1；
(6) judge whether the number of iterations m is greater than and terminate the number of iterations M, if so, carrying out step 7)；Otherwise, return step
2)。
(7) final prediction model is obtained, training set is tested, carries out the regression forecasting of 300 continuous times, at that time
Effect is 6 hours, obtains test result, the prediction curve of model is as shown in Figure 2.
The present invention uses DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, carries out selecting for optimal member using CART decision tree, optimal member is pressed
It is ranked up according to optimal Percentiles, constructs GBDT regressive prediction model, it is final to realize based on set by the training of training set
The forecasting wind speed of forecast data, it can be seen that the method based on optimal percentile GBDT prediction has preferably capability of fitting.Make
With DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, available more Grid datas compensate for the effectively meteorological survey station platform lazy weight in Bohai Sea Gulf
Disadvantage is conducive to promote to Adjacent Sea Area；Forecasting model based on decision tree does not need great amount of samples, in DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM sample size
It is more applicable in lesser situation.
Claims (3)
1. a kind of wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, characterized in that according to European Center for Medium Weather Forecasting
ECMWF (European center for medium-range weather forecasts) ensemble prediction product, it is each pre-
51 forecast members that effect of giving the correct time generates, use the side of CART (Classification And Regression Tree) beta pruning
Method selects optimal member, constructs GBDT (Gradient Boosting Descision Tree) model using optimal member, most
The forecasting wind speed based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data is realized eventually.
2. the wind speed forecasting method as described in claim 1 based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, characterized in that specific steps refine such as
Under:
(1) pretreatment of DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data
1) Bohai Sea Gulf A platform wind speed measured data is used, determines wind speed label data；
2) DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM DAT formatted data is read in the form of lattice point, constructs sample data；
3) DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM shortage of data value is handled；
4) data of same Time effect forecast are ranked up；
(2) optimal member is selected
1) generation of decision tree: by the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data after sequence, CART regression tree is generated；
2) beta pruning is carried out to decision tree, obtains dividing node；
3) it determines and divides attribute: calculating percentile shared in each data for dividing node after sequence, obtain optimal hundred
Quartile member；
4) optimal subtree is generated, according to the partitioning site collection of reservation, obtains optimal member's collection；
(3) gradient is constructed based on optimal member and promotes tree-model
1) training set and test set are constructed；
2) GBDT model is initialized；
3) setting terminates the number of iterations M, constructs CART regression tree by training sample；
4) leaf node region Rmj and corresponding output cm is obtained；
5) strong regression model is updated, the number of iterations m adds 1；
6) judge whether the number of iterations m is greater than and terminate the number of iterations M, if so, carrying out step 7)；Otherwise, return step 2)；
Final prediction model is obtained, training set is tested, obtains test result.
3. the wind speed forecasting method as claimed in claim 2 based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data, characterized in that processing DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM number
It is comprised the concrete steps that according to missing values, missing values is supplemented in the way of linear interpolation；The case where for full line missing, full line is deleted
It removes.Supplement the linear interpolation method of missing values:
Wherein, x is the missing value estimation value of supplement, x1For the previous data for lacking Value Data, x2For the latter of missing Value Data
A data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910703238.3A CN110489719A (en) | 2019-07-31 | 2019-07-31 | Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910703238.3A CN110489719A (en) | 2019-07-31 | 2019-07-31 | Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110489719A true CN110489719A (en) | 2019-11-22 |
Family
ID=68548860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910703238.3A Pending CN110489719A (en) | 2019-07-31 | 2019-07-31 | Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110489719A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888186A (en) * | 2019-11-29 | 2020-03-17 | 天津大学 | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model |
| CN111582551A (en) * | 2020-04-15 | 2020-08-25 | 中南大学 | Method and system for predicting short-term wind speed of wind power plant and electronic equipment |
| CN113537648A (en) * | 2021-09-16 | 2021-10-22 | 国能日新科技股份有限公司 | Wind speed prediction method and device based on set data |
| CN114330478A (en) * | 2021-11-09 | 2022-04-12 | 国网山东省电力公司应急管理中心 | Wind speed classification correction method for power grid wind speed forecast |
| WO2022197239A1 (en) * | 2021-03-16 | 2022-09-22 | Envision Digital International Pte. Ltd. | System and method for generating a series of short period local wind speed forecasts employing k-means clustering and stacked machine learning analysis |
| WO2022197238A1 (en) * | 2021-03-16 | 2022-09-22 | Envision Digital International Pte. Ltd. | System and method for optimizing composition of ensemble member outputs to generate a series of short period local wind speed forecasts |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933483A (en) * | 2015-06-17 | 2015-09-23 | 中国电力科学研究院 | Wind power forecasting method dividing based on weather process |
| CN106156880A (en) * | 2015-04-22 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of predict the method for inventory allocation ratio, device and electronic equipment |
| CN108540320A (en) * | 2018-04-03 | 2018-09-14 | 南京华苏科技有限公司 | The appraisal procedure of user satisfaction is excavated based on signaling |
| CN108539738A (en) * | 2018-05-10 | 2018-09-14 | 国网山东省电力公司电力科学研究院 | A kind of short-term load forecasting method promoting decision tree based on gradient |
| CN108733631A (en) * | 2018-04-09 | 2018-11-02 | 中国平安人寿保险股份有限公司 | A kind of data assessment method, apparatus, terminal device and storage medium |
| CN108830423A (en) * | 2018-06-21 | 2018-11-16 | 中国水利水电科学研究院 | A kind of Annual Runoff Prediction method based on forecast domain |
| CN108876019A (en) * | 2018-05-31 | 2018-11-23 | 中国电力科学研究院有限公司 | A kind of electro-load forecast method and system based on big data |
| CN109617715A (en) * | 2018-11-27 | 2019-04-12 | 中盈优创资讯科技有限公司 | Network fault diagnosis method, system |
| CN109711913A (en) * | 2017-10-25 | 2019-05-03 | 中国电力科学研究院有限公司 | A kind of electric car supply and demand difference prediction technique and charging pile method of allocation plan |
-
2019
- 2019-07-31 CN CN201910703238.3A patent/CN110489719A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156880A (en) * | 2015-04-22 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of predict the method for inventory allocation ratio, device and electronic equipment |
| CN104933483A (en) * | 2015-06-17 | 2015-09-23 | 中国电力科学研究院 | Wind power forecasting method dividing based on weather process |
| CN109711913A (en) * | 2017-10-25 | 2019-05-03 | 中国电力科学研究院有限公司 | A kind of electric car supply and demand difference prediction technique and charging pile method of allocation plan |
| CN108540320A (en) * | 2018-04-03 | 2018-09-14 | 南京华苏科技有限公司 | The appraisal procedure of user satisfaction is excavated based on signaling |
| CN108733631A (en) * | 2018-04-09 | 2018-11-02 | 中国平安人寿保险股份有限公司 | A kind of data assessment method, apparatus, terminal device and storage medium |
| CN108539738A (en) * | 2018-05-10 | 2018-09-14 | 国网山东省电力公司电力科学研究院 | A kind of short-term load forecasting method promoting decision tree based on gradient |
| CN108876019A (en) * | 2018-05-31 | 2018-11-23 | 中国电力科学研究院有限公司 | A kind of electro-load forecast method and system based on big data |
| CN108830423A (en) * | 2018-06-21 | 2018-11-16 | 中国水利水电科学研究院 | A kind of Annual Runoff Prediction method based on forecast domain |
| CN109617715A (en) * | 2018-11-27 | 2019-04-12 | 中盈优创资讯科技有限公司 | Network fault diagnosis method, system |
Non-Patent Citations (3)
| Title |
|---|
| 代刊 等: "集合模式定量降水预报的统计后处理技术研究综述", 《气象学报》 * |
| 毕云帆 等: "基于梯度提升决策树的电力短期负荷预测模型", 《青岛大学学报(工程技术版)》 * |
| 麻巨慧 等: "NCEP 、 ECMWF 及 CMC 全球集合预报业务***发展综述", 《大气科学学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888186A (en) * | 2019-11-29 | 2020-03-17 | 天津大学 | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model |
| CN111582551A (en) * | 2020-04-15 | 2020-08-25 | 中南大学 | Method and system for predicting short-term wind speed of wind power plant and electronic equipment |
| CN111582551B (en) * | 2020-04-15 | 2023-12-08 | 中南大学 | Wind power plant short-term wind speed prediction method and system and electronic equipment |
| WO2022197239A1 (en) * | 2021-03-16 | 2022-09-22 | Envision Digital International Pte. Ltd. | System and method for generating a series of short period local wind speed forecasts employing k-means clustering and stacked machine learning analysis |
| WO2022197238A1 (en) * | 2021-03-16 | 2022-09-22 | Envision Digital International Pte. Ltd. | System and method for optimizing composition of ensemble member outputs to generate a series of short period local wind speed forecasts |
| CN113537648A (en) * | 2021-09-16 | 2021-10-22 | 国能日新科技股份有限公司 | Wind speed prediction method and device based on set data |
| CN114330478A (en) * | 2021-11-09 | 2022-04-12 | 国网山东省电力公司应急管理中心 | Wind speed classification correction method for power grid wind speed forecast |
| CN114330478B (en) * | 2021-11-09 | 2023-10-20 | 国网山东省电力公司应急管理中心 | Wind speed classification correction method for wind speed forecast of power grid |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489719A (en) | Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data | |
| CN103425772B (en) | A kind of mass data inquiry method with multidimensional information | |
| CN104036121B (en) | Wind measurement data wind speed correction method based on probability distribution transfer | |
| CN108763713B (en) | Mathematical model calculation method and system | |
| CN105760970A (en) | Method for predicting AQI | |
| CN107016095A (en) | Climate change comprehensive estimation method based on multi-source carbon number evidence | |
| CN112949178A (en) | Sea surface wind field wind speed intelligent prediction forecasting system based on deep learning, computer equipment and storage medium | |
| Mengoli et al. | Ecosystem photosynthesis in land‐surface models: a first‐principles approach incorporating acclimation | |
| CN110347671A (en) | The method for constructing wind energy on the sea data bank and offshore wind power generation amount database | |
| Ma et al. | PyLUR: Efficient software for land use regression modeling the spatial distribution of air pollutants using GDAL/OGR library in Python | |
| CN111291520B (en) | Ocean anchoring buoy station intelligent site selection method for optimizing space efficiency | |
| CN116467933A (en) | Storm surge water increasing prediction method and system based on deep learning | |
| Steinkruger et al. | An artificially intelligent system for the automated issuance of tornado warnings in simulated convective storms | |
| CN116822185A (en) | Daily precipitation data space simulation method and system based on HASM | |
| Majumdar et al. | Advanced tropical cyclone prediction using the experimental global ECMWF and operational regional COAMPS-TC systems | |
| Kargashin et al. | Data processing as a critical part of GIS based mapping of renewable energy perspectives | |
| CN116542385A (en) | Integrated learning method and system for wind and light power prediction | |
| CN116760006A (en) | Wind power prediction method, device, equipment and storage medium | |
| CN105184072B (en) | The method and apparatus of data interpolation | |
| Ludwig et al. | Evaluating an objective wind analysis technique with a long record of routinely collected data | |
| Azad et al. | Study on wind energy potential by eight numerical methods of Weibull distribution | |
| Ji et al. | The research on the compression algorithms for vector data | |
| Rahimian et al. | The analysis on distribution of NOX pollutant concentration from exhaust flues in Shahid Montazeri Power Plant at Isfahan using combined WRF-CALPUFF model | |
| CN117668765B (en) | Intelligent fusion processing method based on survey big data | |
| Cotton et al. | Weather modification and three-dimensional mesoscale models |
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 |
Application publication date: 20191122 |
|
| RJ01 | Rejection of invention patent application after publication |