CN103473438A - Method for optimizing and correcting wind power prediction models - Google Patents

Method for optimizing and correcting wind power prediction models Download PDF

Info

Publication number
CN103473438A
CN103473438A CN2013103544313A CN201310354431A CN103473438A CN 103473438 A CN103473438 A CN 103473438A CN 2013103544313 A CN2013103544313 A CN 2013103544313A CN 201310354431 A CN201310354431 A CN 201310354431A CN 103473438 A CN103473438 A CN 103473438A
Authority
CN
China
Prior art keywords
wind power
numbers
ordered series
power prediction
prediction models
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
Application number
CN2013103544313A
Other languages
Chinese (zh)
Other versions
CN103473438B (en
Inventor
王玮
金国刚
屈富敏
付嘉渝
傅铮
张柏林
李晓晶
王福军
崔刚
陈新
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
State Grid Gansu Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
State Grid Gansu Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI, State Grid Gansu Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201310354431.3A priority Critical patent/CN103473438B/en
Publication of CN103473438A publication Critical patent/CN103473438A/en
Application granted granted Critical
Publication of CN103473438B publication Critical patent/CN103473438B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation

Abstract

The invention discloses a method for optimizing and correcting wind power prediction models, comprising the steps of selecting actual wind power values and prediction models, analyzing the association between the wind powers and the predicted wind powers and correcting the selected models. According to the method for optimizing and correcting the wind power prediction models, the fitting degree of the prediction models to actual wind power curves is evaluated according to the association degree, so that the advantages and disadvantages of the prediction models are evaluated; therefore, wind power plants in various regions are provided with an inspection basis for the selection of the prediction models according to the change characteristic of wind electricity output power of this region; moreover, error statistic analysis is implemented on the optimized prediction models and linear regression fitting is implemented on optimized original power prediction models, so that the corrected prediction models are obtained; therefore, the purpose of decreasing the prediction errors of the wind power prediction models is realized.

Description

Wind power prediction model preferably and modification method
Technical field
The present invention relates to wind power generation field, in particular it relates to which a kind of wind power prediction model is preferably and modification method.
Background technology
At present, as global energy situation is increasingly serious, traditional fossil energy faces exhausted crisis, and the regenerative resource especially wind energy of cleaning is increasingly paid attention to by people, as replacement fossil energy main energy sources.Wind speed and this basic research problem of wind power prediction have great significance for the safety and economic operation of power network after wind power plant planning, the control of wind power, wind-electricity integration.Prediction theory method and rational forecast model of the Accurate Prediction of wind speed and wind power dependent on science.Therefore, experts and scholars have carried out extensive theory study and proposed various Forecasting Methodologies both at home and abroad, by different modeling mechanism, wind speed and wind power prediction model can be divided mainly into physical model, statistical model, spatial coherence model, artificial intelligence model etc..
Wind power prediction is a kind of estimation to following wind power output size, and it still has a certain distance with objective reality, that is, there is predicated error.Produce source of error a lot：First, the Mathematical Modeling being predicted only includes some principal elements of studied phenomenon mostly, the factor wanted many times is all ignored, for complicated wind changed power, model is a kind of reflection by simplified wind power output situation, there is gap between actual wind power output value, be predicted with it and just inevitably there is error between actual wind performance number；Secondly as the mistake on calculating or judging, the selection of such as smoothing constant is improper, different degrees of error can be also produced.Error caused by various different reasons, which is often mixed, to be showed.Therefore, when predicated error is very big, predicting the outcome will be serious unfounded.
Because wind power fluctuation is influenceed by topography and geomorphology weather and wind power plant running status, forecast model, algorithm are difficult to the output-power fluctuation characteristic for accurately reflecting wind power plant, are inevitably present predicated error.
The content of the invention
It is an object of the invention to regarding to the issue above, a kind of wind power prediction model is proposed preferably and modification method, to reduce the advantage of wind power prediction model predictive error.
To achieve the above object, the technical solution adopted by the present invention is：
A kind of wind power prediction model preferably and modification method, comprise the following steps：
Step 1：Actual wind power ordered series of numbers of a certain specific period is chosen in the history wind power ordered series of numbers of wind power plant
Figure 2013103544313100002DEST_PATH_IMAGE002
, and show that predicted value ordered series of numbers is according to wind power prediction model
Figure 2013103544313100002DEST_PATH_IMAGE004
, the wind power prediction model is the different wind power prediction models of m, and draws according to each wind power prediction model different predicted value ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE004A
；Wherein
Figure 2013103544313100002DEST_PATH_IMAGE006
, then actual wind power ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE002A
It is with predicted value ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE004AA
It is expressed as：
Figure 2013103544313100002DEST_PATH_IMAGE009
 
Wherein, n counts for period interior prediction, actual wind power ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE002AA
Smoothly corrected according to the date of prediction day, remove the step of data, make data smooth variation；
Step 2：To above-mentioned actual wind power ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE002AAA
It is with predicted value ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE004AAA
Incidence coefficient of each curve in kth point is calculated respectively：Specific formula is as follows：
Figure 2013103544313100002DEST_PATH_IMAGE011
In above formula：
Referred to as
Figure 2013103544313100002DEST_PATH_IMAGE017
Point
Figure 2013103544313100002DEST_PATH_IMAGE019
With
Figure 2013103544313100002DEST_PATH_IMAGE021
Absolute error,
Figure 2013103544313100002DEST_PATH_IMAGE023
Referred to as two-stage lowest difference, whereinIt is first order lowest difference, this is represented
Figure 2013103544313100002DEST_PATH_IMAGE021A
On curve, look for each point with
Figure 2013103544313100002DEST_PATH_IMAGE019A
Lowest difference,
Figure 2013103544313100002DEST_PATH_IMAGE027
It is second level lowest difference, on the basis of the lowest difference that expression is found out in each bar curve, then presses
Figure 2013103544313100002DEST_PATH_IMAGE029
Figure 2013103544313100002DEST_PATH_IMAGE031
Figure 2013103544313100002DEST_PATH_IMAGE033
Figure 2013103544313100002DEST_PATH_IMAGE035
Look for all curves
Figure 2013103544313100002DEST_PATH_IMAGE004AAAA
In lowest difference；
Figure 2013103544313100002DEST_PATH_IMAGE037
It is two-stage maximum difference,Referred to as resolution ratio, is the number between 0 and 1, and the incidence coefficient for each point that summary is calculated can draw whole wind power prediction value curve
Figure 2013103544313100002DEST_PATH_IMAGE021AA
With actual wind performance number curve
Figure 2013103544313100002DEST_PATH_IMAGE019AA
Correlation degree be
Figure 2013103544313100002DEST_PATH_IMAGE042
：
Figure 2013103544313100002DEST_PATH_IMAGE044
；
Step 3：According to the degree of association of above-mentioned actual wind power and predicted value ordered series of numbers
Figure 2013103544313100002DEST_PATH_IMAGE042A
, the maximum wind power prediction model of the degree of association is chosen, and wind power prediction model is modified using following equation：
Figure 2013103544313100002DEST_PATH_IMAGE046
In formula：A and b is coefficient, can be determined by least square method,For pre- power scale,For actual power.
According to a preferred embodiment of the invention, it is described
Figure 2013103544313100002DEST_PATH_IMAGE052
。
According to a preferred embodiment of the invention, in step 2 above, nondimensionalization, normalized are done to the numerical value in each ordered series of numbers first.
Technical scheme has the advantages that：
Technical scheme is with fitting degree of the degree of association size valuation prediction models to actual wind power curve, and then the quality of valuation prediction models, be different regions wind power plant according to this area's wind power output power Variation Features, selection forecast model provides test basis；And error statistics analysis is carried out to the forecast model preferably gone out, and to carrying out linear regression fit to the original power forecast model preferably gone out, obtain revised forecast model.The purpose for reducing wind power prediction model predictive error is reached.
Below by drawings and Examples, technical scheme is described in further detail.
Brief description of the drawings
Fig. 1 be the embodiment of the present invention described in wind power prediction model preferably and modification method flow chart；
Fig. 2 is the schematic diagram of the existence form of the wind power prediction error described in the embodiment of the present invention；
Fig. 3 is that the forecast model described in the embodiment of the present invention predicts the outcome and measured result comparison diagram.
In wherein Fig. 3, * represents the numerical point of actual power；.Represent the numerical point of pre- power scale.
Embodiment
The preferred embodiments of the present invention are illustrated below in conjunction with accompanying drawing, it will be appreciated that preferred embodiment described herein is merely to illustrate and explain the present invention, and is not intended to limit the present invention.
As shown in figure 1, a kind of wind power prediction model preferably and modification method, comprise the following steps：
Step 101：Actual wind power ordered series of numbers of a certain specific period is chosen in the history wind power ordered series of numbers of wind power plant, and show that predicted value ordered series of numbers is according to wind power prediction model
Figure DEST_PATH_IMAGE004AAAAA
, the wind power prediction model is the different wind power prediction models of m, and draws according to each wind power prediction model different predicted value ordered series of numbers；Wherein
Figure DEST_PATH_IMAGE006A
, then actual wind power ordered series of numbersIt is with predicted value ordered series of numbersIt is expressed as：
Figure DEST_PATH_IMAGE009A
 
Wherein, n counts for period interior prediction, actual wind power ordered series of numbers
Figure DEST_PATH_IMAGE002AAAAAA
Smoothly corrected according to the date of prediction day, remove the step of data, make data smooth variation；
Step 102：To above-mentioned actual wind power ordered series of numbersIt is with predicted value ordered series of numbers
Figure DEST_PATH_IMAGE004AAAAAAAA
Incidence coefficient of each curve in kth point is calculated respectively：Specific formula is as follows：
In above formula：
Figure DEST_PATH_IMAGE015A
Referred to as
Figure DEST_PATH_IMAGE017A
Point
Figure DEST_PATH_IMAGE019AAA
With
Figure DEST_PATH_IMAGE021AAA
Absolute error,
Figure DEST_PATH_IMAGE023A
Referred to as two-stage lowest difference, whereinIt is first order lowest difference, this is represented
Figure DEST_PATH_IMAGE021AAAA
On curve, look for each point with
Figure DEST_PATH_IMAGE019AAAA
Lowest difference,
Figure DEST_PATH_IMAGE027A
It is second level lowest difference, on the basis of the lowest difference that expression is found out in each bar curve, then presses
Figure DEST_PATH_IMAGE029A
Figure DEST_PATH_IMAGE031A
Figure DEST_PATH_IMAGE033A
Figure DEST_PATH_IMAGE035A
Look for all curves
Figure DEST_PATH_IMAGE004AAAAAAAAA
In lowest difference；
Figure DEST_PATH_IMAGE037A
It is two-stage maximum difference,
Figure DEST_PATH_IMAGE039A
Referred to as resolution ratio, is the number between 0 and 1,
Figure DEST_PATH_IMAGE052A
For preferred parameter.
The incidence coefficient for each point that summary is calculated, can draw whole wind power prediction value curve
Figure DEST_PATH_IMAGE021AAAAA
With actual wind performance number curve
Figure DEST_PATH_IMAGE019AAAAA
Correlation degree be
Figure DEST_PATH_IMAGE042AA
：
Figure DEST_PATH_IMAGE044A
；
Step 103：According to the degree of association of above-mentioned actual wind power and predicted value ordered series of numbers
Figure DEST_PATH_IMAGE042AAA
, the maximum wind power prediction model of the degree of association is chosen, and wind power prediction model is modified using following equation：
Figure DEST_PATH_IMAGE054
In formula：A and b is coefficient, can be determined by least square method,
Figure DEST_PATH_IMAGE048A
For pre- power scale,
Figure DEST_PATH_IMAGE050A
For actual power.
The degree of association：It is that correlation degree is judged according to similarity degree between curve, the com-parison and analysis of geometry between substantially several curves thinks geometry closer to then development and change situation is closer to correlation degree is bigger.The fitting degree of the corresponding several prediction curves of several forecast models of comparison and an actual curve can be carried out with the method, the degree of association is bigger, then illustrates that corresponding forecast model is more excellent, error of fitting is also just smaller.
In above-mentioned steps 101, the order of accuarcy predicted the outcome depends on the correct degree of selected Forecasting Methodology and the Mathematical Modeling set up, it is more dependent upon the order of accuarcy for the information and data selected, therefore when choosing history wind power data, history wind power data should smoothly be corrected according to the date of prediction day, remove the step of data, make data smooth variation, so as to improve precision of prediction.
In a step 102,：In order that the numerical value between each ordered series of numbers has comparativity, it is different for unit, or initial value different predicted value ordered series of numbers is when making correlation analysis, first have to do nondimensionalization, normalization pretreatment, and it is required that all ordered series of numbers have common intersection, other numbers are removed with the first number of each ordered series of numbers so that there is comparativity between each ordered series of numbers.
Compare the correlation degree of each forecast model
Figure DEST_PATH_IMAGE055
It is more suitable from which kind of wind power prediction model to determine：The degree of association is bigger, then the wind power prediction fitting degree of corresponding model is better, precision is higher, and error is also smaller.
In above-mentioned steps 103, correlation degree is bigger, development and change situation closer to, original wind power prediction model can predict the variation tendency of Power Output for Wind Power Field well, but can only ensure that wind power lateral prediction error is smaller, wind power longitudinal direction predicated error may be still very big as shown in Fig. 2 predicting the outcome for original wind power prediction model may integrally be less than or greater than wind power measured result.In order to contrast predicting the outcome and measured result for original predictive model, the coordinate that can be set up as shown in Figure 3 carries out error analysis.
After degree of association predicated error is analyzed and be preferred, the model preferably gone out can track the change of actual power very well in variation tendency, it can thus be assumed that meeting following linear relationship between the predicted value and actual value of forecast model：
Figure DEST_PATH_IMAGE056
In formula：A and b is coefficient, can be determined by least square method,
Figure DEST_PATH_IMAGE057
For pre- power scale,For actual power.
Above formula accuracy by with historical data and experience accumulation and update, the systematic error of model can be eliminated with above formula.
Linear regression fit is carried out to the original power forecast model preferably gone out using least square method, revised forecast model is obtained.
Wherein, wind power prediction model is existing, mainly there is time series models（Persistence forecasting method, kalman filter method etc.）With the forecast model based on numerical weather forecast（Physical model, statistical model）.
Finally it should be noted that：It the foregoing is only the preferred embodiments of the present invention, it is not intended to limit the invention, although the present invention is described in detail with reference to the foregoing embodiments, for a person skilled in the art, it can still modify to the technical scheme described in foregoing embodiments, or carry out equivalent to which part technical characteristic.Within the spirit and principles of the invention, any modifications, equivalent substitutions and improvements made etc., should be included within the scope of the present invention.

Claims (3)

1. a kind of wind power prediction model preferably and modification method, it is characterised in that comprise the following steps：
Step 1：Actual wind power ordered series of numbers of a certain specific period is chosen in the history wind power ordered series of numbers of wind power plant, and show that predicted value ordered series of numbers is according to wind power prediction model
Figure DEST_PATH_IMAGE004
, the wind power prediction model is the different wind power prediction models of m, and draws according to each wind power prediction model different predicted value ordered series of numbers
Figure DEST_PATH_IMAGE004A
；Wherein
Figure DEST_PATH_IMAGE006
, then actual wind power ordered series of numbers
Figure DEST_PATH_IMAGE002A
It is with predicted value ordered series of numbers
Figure DEST_PATH_IMAGE004AA
It is expressed as：
Figure DEST_PATH_IMAGE009
 
Wherein, n counts for period interior prediction, actual wind power ordered series of numbers
Figure DEST_PATH_IMAGE002AA
Smoothly corrected according to the date of prediction day, remove the step of data, make data smooth variation；
Step 2：To above-mentioned actual wind power ordered series of numbers
Figure DEST_PATH_IMAGE002AAA
It is with predicted value ordered series of numbers
Figure DEST_PATH_IMAGE004AAA
Incidence coefficient of each curve in kth point is calculated respectively：Specific formula is as follows：
Figure DEST_PATH_IMAGE011
In above formula：
Figure DEST_PATH_IMAGE015
Referred to as
Figure DEST_PATH_IMAGE017
Point
Figure DEST_PATH_IMAGE019
With
Figure DEST_PATH_IMAGE021
Absolute error,
Figure DEST_PATH_IMAGE023
Referred to as two-stage lowest difference, whereinIt is first order lowest difference, this is represented
Figure DEST_PATH_IMAGE021A
On curve, look for each point with
Figure DEST_PATH_IMAGE019A
Lowest difference,
Figure DEST_PATH_IMAGE027
It is second level lowest difference, on the basis of the lowest difference that expression is found out in each bar curve, then presses
Figure DEST_PATH_IMAGE029
Figure DEST_PATH_IMAGE031
Figure DEST_PATH_IMAGE033
Figure DEST_PATH_IMAGE035
Look for all curves
Figure DEST_PATH_IMAGE004AAAA
In lowest difference；
Figure DEST_PATH_IMAGE037
It is two-stage maximum difference,Referred to as resolution ratio, is the number between 0 and 1, and the incidence coefficient for each point that summary is calculated can draw whole wind power prediction value curve
Figure DEST_PATH_IMAGE021AA
With actual wind performance number curve
Figure DEST_PATH_IMAGE019AA
Correlation degree be：
；
Step 3：According to the degree of association of above-mentioned actual wind power and predicted value ordered series of numbers
Figure DEST_PATH_IMAGE042A
, the maximum wind power prediction model of the degree of association is chosen, and wind power prediction model is modified using following equation：
Figure DEST_PATH_IMAGE046
In formula：A and b is coefficient, can be determined by least square method,
Figure DEST_PATH_IMAGE048
For pre- power scale,For actual power.
2. wind power prediction model according to claim 1 preferably and modification method, it is characterised in that it is described。
3. wind power prediction model according to claim 1 or 2 preferably and modification method, it is characterised in that in step 2 above, nondimensionalization, normalized are done to the numerical value in each ordered series of numbers first.
CN201310354431.3A 2013-08-15 2013-08-15 Wind power prediction model preferably and modification method Expired - Fee Related CN103473438B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310354431.3A CN103473438B (en) 2013-08-15 2013-08-15 Wind power prediction model preferably and modification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310354431.3A CN103473438B (en) 2013-08-15 2013-08-15 Wind power prediction model preferably and modification method

Publications (2)

Publication Number Publication Date
CN103473438A true CN103473438A (en) 2013-12-25
CN103473438B CN103473438B (en) 2018-07-31

Family

ID=49798285

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310354431.3A Expired - Fee Related CN103473438B (en) 2013-08-15 2013-08-15 Wind power prediction model preferably and modification method

Country Status (1)

Country Link
CN (1) CN103473438B (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104361398A (en) * 2014-08-04 2015-02-18 浙江工业大学 Method for predicting natural demands on public bicycle rental spots
CN104850914A (en) * 2015-05-29 2015-08-19 东南大学 Feature modeling based new energy power generation capacity forecasting method
CN105512766A (en) * 2015-12-11 2016-04-20 中能电力科技开发有限公司 Wind power plant power predication method
CN105591380A (en) * 2014-11-18 2016-05-18 国家电网公司 Photo-thermal power station smooth output method
CN105680486A (en) * 2014-11-18 2016-06-15 国家电网公司 Smooth output method of wind-power combined power generation system
CN105680459A (en) * 2014-11-18 2016-06-15 国家电网公司 Combined power generation smooth output method of wind power system and energy storage system
CN108022179A (en) * 2017-11-20 2018-05-11 国网福建省电力有限公司 A kind of doubtful stealing Subject elements based on Chi-square Test determine method
CN108646688A (en) * 2018-05-31 2018-10-12 成都天衡智造科技有限公司 A kind of process parameter optimizing analysis method based on recurrence learning
CN109193791A (en) * 2018-11-10 2019-01-11 东北电力大学 It is a kind of that tendency isloation state quantization method is converged based on the wind-powered electricity generation for improving shapley value
CN109816165A (en) * 2019-01-16 2019-05-28 国能日新科技股份有限公司 Wind-powered electricity generation ultra-short term power forecasting method and system
CN110457821A (en) * 2019-08-12 2019-11-15 华北电力大学 Wind power curve Objective Comprehensive Evaluation Method method, apparatus and server
CN112021626A (en) * 2020-07-10 2020-12-04 张家口卷烟厂有限责任公司 Intelligent control system and method for tobacco shred making link

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1744058A1 (en) * 2004-05-07 2007-01-17 Mitsubishi Denki Kabushiki Kaisha Wind power generation evaluation system and prediction control service system for wind power generator
WO2011130297A2 (en) * 2010-04-13 2011-10-20 The Regents Of The University Of California Methods of using generalized order differentiation and integration of input variables to forecast trends
CN102545211A (en) * 2011-12-21 2012-07-04 西安交通大学 Universal data preprocessing device and method for wind power prediction
CN102570449A (en) * 2011-12-21 2012-07-11 西安交通大学 Regional wind power prediction method based on spatial and temporal distribution characteristics
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
CN102738792A (en) * 2012-06-13 2012-10-17 华北电力大学（保定） Wind power predicting method
JP2013108462A (en) * 2011-11-22 2013-06-06 Fuji Electric Co Ltd System and program for predicting wind power generated electricity

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1744058A1 (en) * 2004-05-07 2007-01-17 Mitsubishi Denki Kabushiki Kaisha Wind power generation evaluation system and prediction control service system for wind power generator
WO2011130297A2 (en) * 2010-04-13 2011-10-20 The Regents Of The University Of California Methods of using generalized order differentiation and integration of input variables to forecast trends
JP2013108462A (en) * 2011-11-22 2013-06-06 Fuji Electric Co Ltd System and program for predicting wind power generated electricity
CN102545211A (en) * 2011-12-21 2012-07-04 西安交通大学 Universal data preprocessing device and method for wind power prediction
CN102570449A (en) * 2011-12-21 2012-07-11 西安交通大学 Regional wind power prediction method based on spatial and temporal distribution characteristics
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
CN102738792A (en) * 2012-06-13 2012-10-17 华北电力大学（保定） Wind power predicting method

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
刘永前 等: "风电场输出功率预测中两种神经网络算法的研究", 《现代电力》 *
周礼刚 等: "基于对数灰关联度的IOWGA算子最优组合预测模型", 《运筹与管理》 *
良艳: "电力系统负荷特性分析与负荷预测研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *
陈倩: "区域风电功率一体化预测方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104361398A (en) * 2014-08-04 2015-02-18 浙江工业大学 Method for predicting natural demands on public bicycle rental spots
CN105680486B (en) * 2014-11-18 2018-09-18 国家电网公司 A kind of smooth output method of wind-solar-storage joint electricity generation system
CN105680459A (en) * 2014-11-18 2016-06-15 国家电网公司 Combined power generation smooth output method of wind power system and energy storage system
CN105680486A (en) * 2014-11-18 2016-06-15 国家电网公司 Smooth output method of wind-power combined power generation system
CN105591380A (en) * 2014-11-18 2016-05-18 国家电网公司 Photo-thermal power station smooth output method
CN105680459B (en) * 2014-11-18 2018-03-23 国家电网公司 A kind of wind power system and energy-storage system cogeneration are smoothly contributed method
CN105591380B (en) * 2014-11-18 2017-12-12 国家电网公司 A kind of photo-thermal power station is smoothly contributed method
CN104850914B (en) * 2015-05-29 2018-07-17 东南大学 A kind of generation of electricity by new energy amount prediction technique of feature based modeling
CN104850914A (en) * 2015-05-29 2015-08-19 东南大学 Feature modeling based new energy power generation capacity forecasting method
CN105512766A (en) * 2015-12-11 2016-04-20 中能电力科技开发有限公司 Wind power plant power predication method
CN108022179A (en) * 2017-11-20 2018-05-11 国网福建省电力有限公司 A kind of doubtful stealing Subject elements based on Chi-square Test determine method
CN108022179B (en) * 2017-11-20 2024-03-26 国网福建省电力有限公司 Suspected electricity larceny subject factor determination method based on chi-square test
CN108646688A (en) * 2018-05-31 2018-10-12 成都天衡智造科技有限公司 A kind of process parameter optimizing analysis method based on recurrence learning
CN108646688B (en) * 2018-05-31 2019-05-07 成都天衡智造科技有限公司 A kind of process parameter optimizing analysis method based on recurrence learning
CN109193791B (en) * 2018-11-10 2021-05-25 东北电力大学 Wind power convergence tendency state-based quantification method based on improved shape value
CN109193791A (en) * 2018-11-10 2019-01-11 东北电力大学 It is a kind of that tendency isloation state quantization method is converged based on the wind-powered electricity generation for improving shapley value
CN109816165A (en) * 2019-01-16 2019-05-28 国能日新科技股份有限公司 Wind-powered electricity generation ultra-short term power forecasting method and system
CN109816165B (en) * 2019-01-16 2020-09-25 国能日新科技股份有限公司 Wind power ultra-short term power prediction method and system
CN110457821B (en) * 2019-08-12 2021-07-02 华北电力大学 Wind power curve multi-target comprehensive evaluation method and device and server
CN110457821A (en) * 2019-08-12 2019-11-15 华北电力大学 Wind power curve Objective Comprehensive Evaluation Method method, apparatus and server
CN112021626A (en) * 2020-07-10 2020-12-04 张家口卷烟厂有限责任公司 Intelligent control system and method for tobacco shred making link
CN112021626B (en) * 2020-07-10 2021-08-17 张家口卷烟厂有限责任公司 Intelligent control system and method for tobacco shred making link

Also Published As

Publication number Publication date
CN103473438B (en) 2018-07-31

Similar Documents

Publication Publication Date Title
CN103473438A (en) Method for optimizing and correcting wind power prediction models
CN103218675B (en) A kind of based on the short-term load forecasting method of cluster and moving window
CN101551884B (en) A fast CVR electric load forecast method for large samples
CN102763048B (en) Using adaptability prediction algorithm and when determine the method and apparatus of using adaptability prediction algorithm in virtual measurement
CN105243502B (en) A kind of power station schedule risk appraisal procedure based on runoff interval prediction and system
CN103023065B (en) Wind power short-term power prediction method based on relative error entropy evaluation method
CN109800898A (en) A kind of intelligence short-term load forecasting method and system
CN106651089A (en) Modeling and optimization method for production scheduling problem distribution set robust model
Zhang et al. Development and evaluation of cooling load prediction models for a factory workshop
CN108664682A (en) A kind of prediction technique and its system of transformer top-oil temperature
CN105205326B (en) A kind of power plant's Real-time Load on-line prediction method
CN102509173A (en) Markov chain based method for accurately forecasting power system loads
CN110428084B (en) Wind power nonparametric interval prediction method based on self-adaptive double-layer optimization
CN101149822A (en) Reservoir forecast dispatch grey dynamic programming method
CN104699890A (en) Modeling method of short-term forewarning model for heavy overload of distribution transformer of urban power network
CN105488592A (en) Method for predicting generated energy of photovoltaic power station
CN105631550A (en) Short-term wind power combined prediction method
CN103996071A (en) Wind power plant wind speed prediction method based on Markov theory
CN105184398A (en) Power maximum load small-sample prediction method
CN111832839B (en) Energy consumption prediction method based on sufficient incremental learning
Ho Forecasting of CO2 emissions, renewable energy consumption and economic growth in vietnam using grey models
CN104036356A (en) Method for predicting future operating state of power grid by using fractal algorithm
CN116757057A (en) Air quality prediction method based on PSO-GA-LSTM model
CN103996087A (en) Method and system for forecasting new energy power generation power
CN114219185A (en) Urban scale industrial carbon emission prediction method based on uncertain set

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20180731

Termination date: 20200815

CF01 Termination of patent right due to non-payment of annual fee