CN103473461A - Method for estimating wind power prediction error based on data feature extraction - Google Patents
Method for estimating wind power prediction error based on data feature extraction Download PDFInfo
- Publication number
- CN103473461A CN103473461A CN2013104225796A CN201310422579A CN103473461A CN 103473461 A CN103473461 A CN 103473461A CN 2013104225796 A CN2013104225796 A CN 2013104225796A CN 201310422579 A CN201310422579 A CN 201310422579A CN 103473461 A CN103473461 A CN 103473461A
- Authority
- CN
- China
- Prior art keywords
- wind
- fore
- wind power
- powered electricity
- mean
- 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
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
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
Abstract
The invention discloses a method for estimating a wind power prediction error based on data feature extraction. The method comprises the following steps: (1) summarizing and analyzing historical data about wind power running in the latest one year, and analyzing and calculating a wind power amplitude, the fluctuating degree of day-ahead predicted output, the fluctuating degree of wind power output in the latest three days and the influence weight coefficients of prediction accuracy on the wind power prediction error; (2) according to the weight coefficients obtained in step (1), utilizing the day-ahead predicted output and the wind power running data in the latest three days to calculate the day-ahead prediction amplitude and fluctuation degree of wind power, and the fluctuation degree and the prediction accuracy of the wind power output in the latest three days, and then estimating the wind power prediction error. The historical data features about wind power running are summarized, analyzed and extracted, and the wind power running data in the latest three days are utilized to estimate the wind power prediction error. The method has the characteristics of low online calculation intensity, reliable data resource and easiness in data acquisition and has a high engineering practical value.
Description
Technical field
The invention belongs to dispatching automation of electric power systems technical field in the generation of electricity by new energy technology, be specifically related to a kind of wind power prediction error estimation of based on data feature extraction.
Background technology
In recent years, the novel energy that the wind-powered electricity generation of take is representative is because of its pollution-free, reproducible inherent characteristic, and without greenhouse gas emission, the permeability in electrical network sharply raises, and becomes the important directions of energy development.One of utilization of new energy resources mode that wind-powered electricity generation is the most ripe as technology, realized under support energetically in a government office increasing fast.But grid-connected along with large-scale wind power, due to the intrinsic randomness of wind-powered electricity generation, intermittence and uncertain, make the uncertain factor in the Operation of Electric Systems process constantly increase, and this has just brought very large impact for the safety and stability economical operation of electric system.The wind power prediction error is made to more meticulous estimation, for wind power prediction, all be significant containing the dispatching of power netwoks of wind-powered electricity generation and control, the fields such as power grid security defence that contain wind-powered electricity generation.The wind power prediction error is determined in the comparison predicted the outcome that proposes to provide by several different wind-powered electricity generation forecasting tools with regard to wind power prediction estimation of error aspect both at home and abroad at present, the method in the specific implementation, need multiple forecasting tool and corresponding Data Source will be provided, and may bring larger calculated amount.Therefore, be based upon that line computation intensity is low, Data Source is reliable and wind power prediction model of error estimate that easily obtain, for the wind power prediction, containing the dispatching of power netwoks of wind-powered electricity generation, all there is important value with controlling.
The wind-powered electricity generation predicated error is not only relevant with Forecasting Methodology, and also relevant with wind speed size and the degree of fluctuation of predetermined period, future position, generally, predetermined period is longer, and prediction is exerted oneself larger, and the future position degree of fluctuation of exerting oneself is larger, and predicated error is just larger.It is considered herein that, the wind speed amplitude of wind-powered electricity generation predicated error and Forecasting Methodology, predetermined period, future position and the relation of degree of fluctuation, can and dope the force data seizure by statistical study wind-powered electricity generation operation history data a few days ago and obtain, then estimate the wind power prediction error.Acquired results is meticulousr, reliable and science, for improving large-scale wind power power system security economical operation off the net, has great importance.
Summary of the invention
The objective of the invention is the wind power prediction error is made to more meticulous estimation.The wind power prediction error estimation of based on data feature extraction provided by the invention, only need that the history of wind-powered electricity generation operation is actual exerts oneself and prediction is exerted oneself, and prediction is exerted oneself a few days ago, wind power prediction model of error estimate after foundation adaptation large-scale wind power is grid-connected is estimated the wind power prediction error, reduce or eliminated the grid-connected rear adverse effect to electric power netting safe running of large-scale wind power, having guaranteed the reliability service of electric system.
The wind power prediction error estimation of based on data feature extraction, it is characterized in that nearly 1 year wind-powered electricity generation operation history data of the method statistical study, analytical calculation wind power magnitude, prediction is exerted oneself a few days ago degree of fluctuation, nearly 3 days wind-powered electricity generations degree of fluctuation and the precision of prediction weighing factor coefficient to the wind power prediction error of exerting oneself, then utilize wind power prediction a few days ago to exert oneself and nearly 3 days wind-powered electricity generation service datas, calculate a few days ago wind power prediction amplitude and degree of fluctuation, nearly 3 days wind-powered electricity generations exert oneself degree of fluctuation and precision of prediction, finally estimate the wind power prediction error.Specific as follows:
(1) nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate wind power magnitude, prediction is exerted oneself a few days ago degree of fluctuation, nearly 3 days wind-powered electricity generations degree of fluctuation and the precision of prediction weighing factor coefficient to the wind power prediction error of exerting oneself;
Nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate the wind power magnitude to the formula of the weighing factor factor alpha of wind power prediction error as shown in (1),
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jmean actual the exerting oneself of j time point wind-powered electricity generation, P
fore, jthe prediction that means j time point wind-powered electricity generation is exerted oneself,
mean all K that meet constraint condition
1, jmean value,
mean that all correspondences meet the K of constraint condition
1, jthe prediction P that exerts oneself
fore, jmean value, α
minmean the lower limit of wind power magnitude to the weighing factor coefficient of wind power prediction error, α
maxmean the higher limit of wind power magnitude to the weighing factor coefficient of wind power prediction error.
Nearly 1 year wind-powered electricity generation operation history data of statistical study, carry out staging treating by the close principle of exerting oneself to dope force data a few days ago, calculate prediction is exerted oneself a few days ago degree of fluctuation to the formula of the weighing factor factor beta of wind power prediction error as shown in (2),
Wherein, i means the hop count divided dope force data a few days ago, P
act, i, maxmean the actual maximal value of exerting oneself of wind-powered electricity generation in i time period of being divided; P
act, i, minmean the actual minimum value of exerting oneself of wind-powered electricity generation in i time period of being divided; P
fore, i, maxmean that wind-powered electricity generation in time period that i divided dopes the maximal value of power, its corresponding time is t
fore, i, max; P
fore, i, minmean that wind-powered electricity generation in time period that i divided dopes the minimum value of power, its corresponding time is t
fore, i, min,
mean all K
2, imean value.
Nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate nearly 3 days wind-powered electricity generations degree of fluctuation and precision of prediction weighing factor COEFFICIENT K to the wind power prediction error of exerting oneself
3and K
4formula as shown in (3),
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jactual the exerting oneself of wind-powered electricity generation that means the j time point, P
fore, jthe wind-powered electricity generation prediction that is the j time point is exerted oneself,
mean
mean value,
mean P
act, jmean value.
(2) weight coefficient obtained according to (1), utilize wind power prediction a few days ago to exert oneself and nearly 3 days wind-powered electricity generation data, calculate a few days ago wind power prediction amplitude and degree of fluctuation, nearly 3 days wind-powered electricity generations exert oneself degree of fluctuation and nearly 3 days precision of predictions, then estimate the wind power prediction error;
Analyze wind-powered electricity generation and dope force data a few days ago, by the close principle of exerting oneself, to dope force data a few days ago, carry out staging treating, calculate the degree of fluctuation σ of i time period data of being divided
iformula as shown in (4):
Wherein, i means the hop count divided dope force data a few days ago, P
fore, i, maxmean that wind-powered electricity generation in time period that i divided dopes the maximal value of power, its corresponding time is t
fore, i, max; P
fore, i, minmean that wind-powered electricity generation in time period that i divided dopes the minimum value of power, its corresponding time is t
fore, i, min.
Analyze wind-powered electricity generation and move nearly 3 day data, calculate nearly 3 days wind-powered electricity generations and exert oneself the formula of degree of fluctuation S and nearly 3 days precision of prediction ε as shown in (5)
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jand P
fore, jbe that j time point wind-powered electricity generation actual exerted oneself and prediction is exerted oneself,
mean
mean value,
mean P
act, jmean value.
Estimate that the formula of wind power prediction error is as shown in (6):
Wherein, i means the hop count divided dope force data a few days ago,
mean to predict the wind power P in i time period of being divided a few days ago
fore, imean value, e
max, iand e
min, imean respectively higher limit and the lower limit of wind power prediction error in i time period of being divided, other parameters are same as above.
Compared with prior art, the present invention has following beneficial effect:
1) historical data of moving according to wind-powered electricity generation, electric system is the wind power prediction data a few days ago, extract data characteristics prediction wind power prediction error, there is online calculating strength low, reliable and the easy characteristics that obtain of Data Source, guaranteed the enforceability of this invention in electric system and the accuracy of income analysis result.
2) utilize the methods analyst wind power prediction error of extracting data characteristics, not only consider the historical variations rule of wind power prediction error, also analyzed the wind power current features such as the degree of fluctuation of prediction curve, the actual fluctuation of exerting oneself of wind-powered electricity generation in the recent period and precision of prediction a few days ago.This invention has been made and has both been continued its historical variations rule the estimation of wind power prediction error, meets again predicting the outcome reliably of its realistic performance.
The accompanying drawing explanation
Fig. 1 is the wind power prediction error estimation process flow diagram of based on data feature extraction of the present invention;
Fig. 2 is the process flow diagram to the statistical study of wind-powered electricity generation operation history data of the present invention;
Fig. 3 of the present inventionly moves recent characteristic according to historical data statistics gained in conjunction with wind-powered electricity generation, estimates the process flow diagram of wind power prediction error.
Embodiment
Below in conjunction with Figure of description, the present invention is further illustrated.
As shown in Figure 1, the wind power prediction error estimation of based on data feature extraction of the present invention, nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate the wind power magnitude, the degree of fluctuation that prediction is exerted oneself a few days ago, nearly 3 days wind-powered electricity generations degree of fluctuation and precision of prediction weighing factor coefficient to the wind power prediction error of exerting oneself, in conjunction with wind power prediction a few days ago, exert oneself again and wind-powered electricity generation moves nearly 3 day data and calculates wind power prediction amplitude and degree of fluctuation a few days ago, nearly 3 days wind-powered electricity generations exert oneself degree of fluctuation and precision of prediction, finally estimate the wind power prediction error, as shown in Figure 1, comprise several large steps
Step a, nearly 1 year wind-powered electricity generation operation history data of statistical study.Step 1, calculate wind power magnitude, prediction is exerted oneself a few days ago degree of fluctuation, nearly 3 days wind-powered electricity generations and exert oneself degree of fluctuation and precision of prediction to the weighing factor coefficient of wind power prediction error, as shown in Figure 2, specifically comprises the following steps;
Step 1.1, nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate the wind power magnitude to the formula of the weighing factor factor alpha of wind power prediction error as shown in (1),
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jmean actual the exerting oneself of j time point wind-powered electricity generation, P
fore, jthe prediction that means j time point wind-powered electricity generation is exerted oneself,
mean all K that meet constraint condition
1, jmean value,
mean that all correspondences meet the K of constraint condition
1, jthe prediction P that exerts oneself
fore, jmean value, α
minmean the lower limit of wind power magnitude to the weighing factor coefficient of wind power prediction error, α
maxmean the higher limit of wind power magnitude to the weighing factor coefficient of wind power prediction error.
Step 1.2, nearly 1 year wind-powered electricity generation operation history data of statistical study, carry out staging treating by the close principle of exerting oneself to dope force data a few days ago, calculate prediction is exerted oneself a few days ago degree of fluctuation to the formula of the weighing factor factor beta of wind power prediction error as shown in (2)
Wherein, i means the hop count divided dope force data a few days ago, P
act, i, maxmean the actual maximal value of exerting oneself of wind-powered electricity generation in i time period of being divided; P
act, i, minmean the actual minimum value of exerting oneself of wind-powered electricity generation in i time period of being divided; P
fore, i, maxmean that wind-powered electricity generation in time period that i divided dopes the maximal value of power, its corresponding time is t
fore, i, max; P
fore, i, minmean that wind-powered electricity generation in time period that i divided dopes the minimum value of power, its corresponding time is t
fore, i, min,
mean all K
2, imean value.
Step 1.3, nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate recent wind-powered electricity generation degree of fluctuation and the precision of prediction weighing factor COEFFICIENT K to the wind power prediction error of exerting oneself
3and K
4formula as shown in (3),
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jactual the exerting oneself of wind-powered electricity generation that means the j time point, P
fore, jthe wind-powered electricity generation prediction that is the j time point is exerted oneself,
mean
mean value,
mean P
act, jmean value.
The weight coefficient obtained according to step 1, as shown in Figure 1, step b, analyze wind power prediction a few days ago and exert oneself and nearly 3 days wind-powered electricity generation data.Step 2, calculate a few days ago wind power prediction amplitude and degree of fluctuation, nearly 3 days wind-powered electricity generations exert oneself degree of fluctuation and nearly 3 days precision of predictions, then estimates the wind power prediction error, as shown in Figure 3, specifically comprises the following steps;
Step 2.1, analyze wind-powered electricity generation and dope force data a few days ago, by the close principle of exerting oneself, to dope force data a few days ago, carries out staging treating, calculates the degree of fluctuation σ of i time period data of being divided
iformula as shown in (4):
Wherein, i means the hop count divided dope force data a few days ago, P
fore, i, maxmean that wind-powered electricity generation in time period that i divided dopes the maximal value of power, its corresponding time is t
fore, i, max; P
fore, i, minmean that wind-powered electricity generation in time period that i divided dopes the minimum value of power, its corresponding time is t
fore, i, min.
Step 2.2, analyze wind-powered electricity generation and move nearly 3 day data, calculates nearly 3 days wind-powered electricity generations and exert oneself the formula of degree of fluctuation S and nearly 3 days precision of prediction ε as shown in (5)
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jand P
fore, jbe that j time point wind-powered electricity generation actual exerted oneself and prediction is exerted oneself,
mean
mean value,
mean P
act, jmean value.
Step 2.3, estimate that the formula of wind power prediction error is as shown in (6):
Wherein, i means the hop count divided dope force data a few days ago,
mean to predict the wind power P in i time period of being divided a few days ago
fore, imean value, e
max, iand e
min, imean respectively higher limit and the lower limit of wind power prediction error in i time period of being divided, other parameters are same as above.
The present invention is according to the historical data of wind-powered electricity generation operation, electric system is the wind power prediction data a few days ago, extract data characteristics prediction wind power prediction error, have a Data Source reliable, and the characteristics that easily obtain, guaranteed the enforceability of this invention in electric system and the accuracy of income analysis result.The present invention utilizes the methods analyst wind power prediction error of extracting data characteristics, not only consider the historical variations rule of wind power prediction error, also analyzed the wind power current features such as the degree of fluctuation of prediction curve, the actual fluctuation of exerting oneself of wind-powered electricity generation in the recent period and precision of prediction a few days ago.This invention has been made and has both been continued its historical variations rule the estimation of wind power prediction error, meets again the reliable estimated result of its realistic performance.
According to the above, just can realize the present invention.Those skilled in the art can carry out various changes and modification and not break away from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention also is intended to comprise these changes and modification interior.
Claims (2)
1. the wind power prediction error estimation of a based on data feature extraction, it is characterized in that, said method comprising the steps of: nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate wind power magnitude, prediction is exerted oneself a few days ago degree of fluctuation, nearly 3 days wind-powered electricity generations degree of fluctuation and the precision of prediction weighing factor coefficient to the wind power prediction error of exerting oneself; Again prediction a few days ago exert oneself and the basis of nearly 3 days wind-powered electricity generation service datas on, calculate a few days ago wind power prediction amplitude and degree of fluctuation, nearly 3 days wind-powered electricity generations exert oneself degree of fluctuation and precision of prediction; Then estimate the wind power prediction error.
2. method according to claim 1, is characterized in that, specifically comprises the following steps:
(1) nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate wind power magnitude, prediction is exerted oneself a few days ago degree of fluctuation, nearly 3 days wind-powered electricity generations degree of fluctuation and the precision of prediction weighing factor coefficient to the wind power prediction error of exerting oneself;
Nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate the wind power magnitude to the formula of the weighing factor factor alpha of wind power prediction error as shown in (1),
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jmean actual the exerting oneself of j time point wind-powered electricity generation, P
fore, jthe prediction that means j time point wind-powered electricity generation is exerted oneself,
mean all K that meet constraint condition
1, jmean value,
mean all constraint condition K that meet
1, jthe corresponding prediction P that exerts oneself
fore, jmean value, α
minmean the lower limit of wind power magnitude to the weighing factor coefficient of wind power prediction error, α
maxmean the higher limit of wind power magnitude to the weighing factor coefficient of wind power prediction error;
Nearly 1 year wind-powered electricity generation operation history data of statistical study, carry out staging treating by the close principle of exerting oneself to dope force data a few days ago, calculate prediction is exerted oneself a few days ago degree of fluctuation to the formula of the weighing factor factor beta of wind power prediction error as shown in (2),
Wherein, i means the hop count divided dope force data a few days ago, P
act, i, maxmean the actual maximal value of exerting oneself of wind-powered electricity generation in i time period of being divided; P
act, i, minmean the actual minimum value of exerting oneself of wind-powered electricity generation in i time period of being divided; P
fore, i, maxmean that wind-powered electricity generation in time period that i divided dopes the maximal value of power, its corresponding time is t
fore, i, max; P
fore, i, minmean that wind-powered electricity generation in time period that i divided dopes the minimum value of power, its corresponding time is t
fore, i, min,
mean all K
2, imean value;
Nearly 1 year wind-powered electricity generation operation history data of statistical study, calculate nearly 3 days wind-powered electricity generations degree of fluctuation and precision of prediction weighing factor COEFFICIENT K to the wind power prediction error of exerting oneself
3and K
4formula as shown in (3),
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jactual the exerting oneself of wind-powered electricity generation that means the j time point, P
fore, jthe wind-powered electricity generation prediction that is the j time point is exerted oneself,
mean
mean value,
mean P
act, jmean value.
(2) weight coefficient obtained according to (1), utilize wind power prediction a few days ago to exert oneself and nearly 3 days wind-powered electricity generation data, calculate a few days ago wind power prediction amplitude and degree of fluctuation, nearly 3 days wind-powered electricity generations exert oneself degree of fluctuation and nearly 3 days precision of predictions, then estimate the wind power prediction error;
Analyze wind-powered electricity generation and dope force data a few days ago, by the close principle of exerting oneself, to dope force data a few days ago, carry out staging treating, calculate the degree of fluctuation σ of i time period data of being divided
iformula as shown in (4):
Wherein, i means the hop count divided dope force data a few days ago, P
fore, i, maxmean that wind-powered electricity generation in time period that i divided dopes the maximal value of power, its corresponding time is t
fore, i, max; P
fore, i, minmean that wind-powered electricity generation in time period that i divided dopes the minimum value of power, its corresponding time is t
fore, i, min.
Analyze wind-powered electricity generation and move nearly 3 day data, calculate nearly 3 days wind-powered electricity generations and exert oneself the formula of degree of fluctuation S and nearly 3 days precision of prediction ε as shown in (5)
Wherein, j means the granularity of historical data, within every 15 minutes, is a time point, P
act, jand P
fore, jbe that j time point wind-powered electricity generation actual exerted oneself and prediction is exerted oneself,
mean
mean value,
mean P
act, jmean value.
Estimate that the formula of wind power prediction error is as shown in (6):
Wherein, i means the hop count divided dope force data a few days ago,
mean to predict the wind power P in i time period of being divided a few days ago
fore, imean value, e
max, iand e
min, imean respectively higher limit and the lower limit of wind power prediction error in i time period of being divided, other parameters are same as above.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310422579.6A CN103473461B (en) | 2013-09-16 | 2013-09-16 | Based on the wind power prediction error estimation that data characteristics is extracted |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310422579.6A CN103473461B (en) | 2013-09-16 | 2013-09-16 | Based on the wind power prediction error estimation that data characteristics is extracted |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103473461A true CN103473461A (en) | 2013-12-25 |
CN103473461B CN103473461B (en) | 2016-06-15 |
Family
ID=49798308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310422579.6A Expired - Fee Related CN103473461B (en) | 2013-09-16 | 2013-09-16 | Based on the wind power prediction error estimation that data characteristics is extracted |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103473461B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106099932A (en) * | 2016-07-22 | 2016-11-09 | 中国电力科学研究院 | A kind of tidal current analysis method of plan a few days ago considering probabilistic temporal correlation |
CN107358060A (en) * | 2017-09-06 | 2017-11-17 | 大连理工大学 | A kind of method estimated wind power prediction error burst based on HMM |
US10742040B2 (en) | 2015-02-23 | 2020-08-11 | Okinawa Institute Of Science And Technology School Corporation | System and method of determining forecast error for renewable energy fluctuations |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110307109A1 (en) * | 2010-05-27 | 2011-12-15 | Sri-Jayantha Sri M | Smarter-Grid: Method to Forecast Electric Energy Production and Utilization Subject to Uncertain Environmental Variables |
CN102509027A (en) * | 2011-12-19 | 2012-06-20 | 国网电力科学研究院 | Wind powder combined predication method based on cross entropy theory |
US20120185414A1 (en) * | 2010-12-15 | 2012-07-19 | Vaisala, Inc. | Systems and methods for wind forecasting and grid management |
US20130024044A1 (en) * | 2011-07-18 | 2013-01-24 | Nec Laboratories America, Inc. | Optimal storage sizing for integrating wind and load forecast uncertainties |
CN103198235A (en) * | 2013-04-27 | 2013-07-10 | 国家电网公司 | Wind power predication value pre-evaluation method based on wind power longitudinal time probability distribution |
-
2013
- 2013-09-16 CN CN201310422579.6A patent/CN103473461B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110307109A1 (en) * | 2010-05-27 | 2011-12-15 | Sri-Jayantha Sri M | Smarter-Grid: Method to Forecast Electric Energy Production and Utilization Subject to Uncertain Environmental Variables |
US20120185414A1 (en) * | 2010-12-15 | 2012-07-19 | Vaisala, Inc. | Systems and methods for wind forecasting and grid management |
US20130024044A1 (en) * | 2011-07-18 | 2013-01-24 | Nec Laboratories America, Inc. | Optimal storage sizing for integrating wind and load forecast uncertainties |
CN102509027A (en) * | 2011-12-19 | 2012-06-20 | 国网电力科学研究院 | Wind powder combined predication method based on cross entropy theory |
CN103198235A (en) * | 2013-04-27 | 2013-07-10 | 国家电网公司 | Wind power predication value pre-evaluation method based on wind power longitudinal time probability distribution |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10742040B2 (en) | 2015-02-23 | 2020-08-11 | Okinawa Institute Of Science And Technology School Corporation | System and method of determining forecast error for renewable energy fluctuations |
CN106099932A (en) * | 2016-07-22 | 2016-11-09 | 中国电力科学研究院 | A kind of tidal current analysis method of plan a few days ago considering probabilistic temporal correlation |
CN106099932B (en) * | 2016-07-22 | 2021-11-19 | 中国电力科学研究院 | Day-ahead planning power flow analysis method considering uncertainty time-space correlation |
CN107358060A (en) * | 2017-09-06 | 2017-11-17 | 大连理工大学 | A kind of method estimated wind power prediction error burst based on HMM |
CN107358060B (en) * | 2017-09-06 | 2019-10-11 | 大连理工大学 | The method that a kind of pair of wind power prediction burst error is estimated |
Also Published As
Publication number | Publication date |
---|---|
CN103473461B (en) | 2016-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Shi et al. | Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features | |
CN103198235B (en) | Based on the wind power prediction value Pre-Evaluation method of the longitudinal moment probability distribution of wind power | |
CN102880989B (en) | A kind of wind power output time series modeling method | |
CN103927695A (en) | Ultra-short-term wind power prediction method based on self-learning composite data source | |
CN102832617B (en) | Large power grid transient state stabilization analyzing method based on precision pattern discrimination | |
CN105354636B (en) | A kind of wind power swing probability density modeling method based on nonparametric probability | |
CN106875033A (en) | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting | |
CN103020743B (en) | Wind energy turbine set ultra-short term wind speed forecasting method | |
CN104319807A (en) | Method for obtaining multiple-wind farm capacity credit based on Copula function | |
CN103065202A (en) | Wind power plant ultrashort term wind speed prediction method based on combination kernel function | |
CN105095668B (en) | Electrical network icing Long-range Forecasting Methods based on whirlpool, pole, the Asia factor | |
CN105488592A (en) | Method for predicting generated energy of photovoltaic power station | |
CN105406476A (en) | Historical data-based power system stability fast judging method | |
CN109255728A (en) | The photovoltaic generation power neural network prediction method of chaos phase space optimal reconfiguration | |
CN103996079A (en) | Wind power weighting predication method based on conditional probability | |
CN106611243A (en) | Residual correction method for wind speed prediction based on GARCH (Generalized ARCH) model | |
CN104933469B (en) | A kind of short-term wind speed forecasting method based on grey generation Disturbance Model | |
CN103473461B (en) | Based on the wind power prediction error estimation that data characteristics is extracted | |
CN103927597A (en) | Ultra-short-term wind power prediction method based on autoregression moving average model | |
CN104951654A (en) | Method for evaluating reliability of large-scale wind power plant based on control variable sampling | |
CN105140967A (en) | Estimation method with new energy power system peak regulation demands | |
CN105160434A (en) | Wind power ramp event prediction method by adopting SVM to select forecasting model | |
CN105654189B (en) | Icing short-term prediction method based on time series analysis and Kalman filtering algorithm | |
CN105046349A (en) | Wind power prediction method considering wake effect | |
KR20230076695A (en) | Solar power generation forcasting device and method reflecting solar periodic time variable |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160615 Termination date: 20190916 |
|
CF01 | Termination of patent right due to non-payment of annual fee |