CN104657787A - Wind power time series combined prediction method - Google Patents
Wind power time series combined prediction method Download PDFInfo
- Publication number
- CN104657787A CN104657787A CN201510056776.XA CN201510056776A CN104657787A CN 104657787 A CN104657787 A CN 104657787A CN 201510056776 A CN201510056776 A CN 201510056776A CN 104657787 A CN104657787 A CN 104657787A
- Authority
- CN
- China
- Prior art keywords
- wind power
- dms
- ims
- time series
- predicted
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a wind power time series combined prediction method. The method is based on a direct multi-step prediction method and a rolling multi-step prediction method for performing combined prediction on day-ahead wind power of a wind power plant. By adopting the wind power time series combined prediction method disclosed by the invention, day-ahead prediction precision of the wind power prediction method can be effectively improved, the problem of poor wind power prediction effect in an existing engineering wind power short-term prediction technology is solved, purchase cost for huge spare power generation capacity can be reduced for a power grid enterprise and the operation benefits of the power grid enterprise are upgraded; meanwhile, abandoned wind power can be effectively reduced, wind power effective grid-connected capacity can be upgraded, huge profits are brought to a power generation enterprise and energy conservation and emission reduction are promoted.
Description
Technical field
The present invention relates to wind power electric powder prediction in generation of electricity by new energy process, particularly relate to a kind of wind power time series combination forecasting method.
Background technology
Under the whole world is faced with energy crisis and environmental crisis background, wind-power electricity generation is one of the most competitive regenerative resource of following many decades, and wind energy content is huge; utilize wind energy to generate electricity; can not only environmental pollution be reduced, the fuel cost of electric system can also be reduced, bring considerable economic benefit.
Ended for the end of the year 2010, China's wind-powered electricity generation total installed capacity exceedes the U.S., leaps to the first in the world; End in Dec, 2014, the installed capacity of Jiangsu Power Grid grid connected wind power has reached 2,970,000 kilowatts, accounts for 3.7% of Jiangsu Power Grid total installation of generating capacity, becomes the second largest main force power supply being only second to thermoelectricity.Along with the swift and violent growth of wind-power electricity generation installation total amount, the intrinsic intermittence of wind-powered electricity generation self, undulatory property have become the principal element hindering wind power integration electrical network.The each main wind power base in the whole nation is abandoned wind phenomenon and is taken place frequently, and wind-powered electricity generation enterprise has wind not generate electricity, has electricity can not send; Power grid enterprises are wind-powered electricity generation of dissolving to greatest extent simultaneously, and when lacking high-precision wind power prediction technical support, can only improve constantly the margin capacity of genset in generation schedule, this must cause the continuous deterioration of unit generation economy.
Predict accurately wind-powered electricity generation, significantly can reduce the impact of wind-powered electricity generation on electrical network, experience shows, wind-powered electricity generation prognoses system is the key factor reducing generating margin capacity, promote the economic operation level of electric system, improve wind-powered electricity generation permeability accurately and reliably; Can be generation of electricity by new energy Real-Time Scheduling simultaneously, generation of electricity by new energy planned a few days ago, generation of electricity by new energy monthly plan, generation of electricity by new energy capability evaluation and abandon wind-powered electricity generation amount estimate key message is provided.
Nearly decades, in order to solve the accurately predicting problem of wind-powered electricity generation, scientific research personnel is mainly by Forecasting Methodology, statistical method (the persistence forecasting method based on numerical weather forecast, autoregressive moving average method, artificial neural network method), hybrid forecasting method, the method improving the accuracy of wind energy turbine set wind power prediction is explored, and achieves certain achievement.But the precision of prediction of existing wind power prediction method is still not high, international advanced wind power prediction systematic error, about 15%, can not meet requirement of engineering.
Summary of the invention
Goal of the invention: the object of this invention is to provide a kind of precision of prediction high, abandon the few wind power prediction method of wind-powered electricity generation amount.
Technical scheme: for reaching this object, the present invention by the following technical solutions:
Wind power time series combination forecasting method of the present invention, comprises the following steps:
S1: the wind power generation power data per diem gathering wind energy turbine set to be predicted, i.e. history wind power data, and the history wind power data collected is generated a corresponding time series amount X, as training sample set;
S2: utilize training sample set X is nuclear model with time series predicting model, adopts direct multi-step prediction method, calculates and generates wind power prediction sequence X
dMS;
S3: utilize training sample set X take time series predicting model as nuclear model, adopts rolling multi-step prediction method, calculates and generate wind power prediction sequence X
iMS;
S4: per diem to wind power prediction sequence X
dMS, X
iMScarry out statistical study with training sample set X, under degree of confidence factor alpha, calculate respective high precision predicted time scope T
dMSand T
iMS, wherein ∑ T
dMS+ ∑ T
iMS=24 hours;
S5: adopt time series predicting model as nuclear model, at time range T
dMSthe direct multistep forecasting method of interior employing to day to be predicted at time range T
dMSinterior wind power is predicted, obtains time range T
dMSinterior predicts the outcome; At time range T
iMSinterior employing rolling multistep forecasting method to day to be predicted at time range T
iMSinterior wind power is predicted, obtains time range T
iMSinterior predicts the outcome;
S6: by time range T
dMSinterior predicts the outcome and time range T
iMSin predict the outcome and combine, form complete day to be measured wind power prediction result;
" day " described in above step S1, S4, S5 and S6 is 24 hours.
Further, described step S4 comprises the following steps:
S4.1: per diem to wind power prediction sequence X
dMScarry out predicated error calculating with training sample set X, under degree of confidence factor alpha, calculate the average error curve E of direct multistep forecasting method predicated error band
dMS;
S4.2: per diem to wind power prediction sequence X
iMScarry out predicated error calculating with training sample set X, under degree of confidence factor alpha, calculate the average error curve E of rolling multistep forecasting method predicated error band
iMS;
S4.3: compare E
dMSwith E
iMSnumerical values recited in 24 hours, chooses E
dMS<E
iMScorresponding time interval is time range T
dMS, choose E
iMS<E
dMSthe time domain scale T that corresponding time interval is predicted as rolling multistep processes
iMS;
" day " described in above step S4.1 and S4.2 is 24 hours.
Further, described time series predicting model comprises any one in arma modeling, AR model, MA model and ANN model.
Beneficial effect: the present invention effectively can improve the precision of prediction a few days ago of wind power prediction method, solve the problem that current engineering wind power short-term forecasting technology exists wind power prediction weak effect, huge reserve generation capacity buying expenses can be saved for power grid enterprises, promote power grid enterprises' operation benefits, effectively can reduce simultaneously and abandon wind-powered electricity generation amount, promote the effective grid connection capacity of wind-powered electricity generation, for electricity power enterprise brings enormous profits, promote energy-saving and emission-reduction.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention;
Fig. 2 is multistep processes predicted time scope T of the present invention
dMSwith the time domain scale T of rolling multistep processes prediction
iMSchoosing method;
Fig. 3 is the contrast of the prediction effect of the present invention and traditional persistence model.
Embodiment
Below in conjunction with accompanying drawing, further illustrate technical scheme of the present invention by embodiment.
Fig. 1 is process flow diagram of the present invention.A kind of wind power time series combination forecasting method provided by the invention, is characterized in that: comprise the following steps:
S1: the wind power generation power data per diem gathering wind energy turbine set to be predicted, i.e. history wind power data, and the history wind power data collected is generated a corresponding time series amount X, as training sample set;
S2: utilize training sample set X is nuclear model with time series predicting model, adopts direct multi-step prediction method, calculates and generates wind power prediction sequence X
dMS;
S3: utilize training sample set X take time series predicting model as nuclear model, adopts rolling multi-step prediction method, calculates and generate wind power prediction sequence X
iMS;
S4: per diem to wind power prediction sequence X
dMS, X
iMScarry out statistical study with training sample set X, under degree of confidence factor alpha, calculate respective high precision predicted time scope T
dMSand T
iMS, wherein ∑ T
dMS+ ∑ T
iMS=24 hours;
S5: adopt time series predicting model as nuclear model, at time range T
dMSthe direct multistep forecasting method of interior employing to day to be predicted at time range T
dMSinterior wind power is predicted, obtains time range T
dMSinterior predicts the outcome; At time range T
iMSinterior employing rolling multistep forecasting method to day to be predicted at time range T
iMSinterior wind power is predicted, obtains time range T
iMSinterior predicts the outcome;
S6: by time range T
dMSinterior predicts the outcome and time range T
iMSin predict the outcome and combine, form complete day to be measured wind power prediction result.
" day " described in above step S1, S4, S5 and S6 is 24 hours.
Wherein, step S4 comprises the following steps:
S4.1: per diem to wind power prediction sequence X
dMScarry out predicated error calculating with training sample set X, under degree of confidence factor alpha, calculate the average error curve E of direct multistep forecasting method predicated error band
dMS;
S4.2: per diem to wind power prediction sequence X
iMScarry out predicated error calculating with training sample set X, under degree of confidence factor alpha, calculate the average error curve E of rolling multistep forecasting method predicated error band
iMS;
S4.3: compare E
dMSwith E
iMSnumerical values recited in 24 hours, chooses E
dMS<E
iMScorresponding time interval is time range T
dMS, II district as shown in Figure 2; Choose E
iMS<E
dMSthe time domain scale T that corresponding time interval is predicted as rolling multistep processes
iMS, I district as shown in Figure 2 and III district.
" day " described in above step S4.1 and S4.2 is 24 hours.
For verifying the prediction effect of the inventive method further, Fig. 3 provides the result that in July, 2012, one, Jiangsu wind energy turbine set was predicted after applying the inventive method and traditional persistence model (persistence model) respectively, and contrast with actual measurement wind power respectively, obviously can find out that predicting the outcome of the inventive method is better with the degree of agreement of surveying wind powertrace.Further, according to measuring and calculating, the prediction effect of the inventive method improves 12.74% than the prediction effect of traditional persistence model (persistencemodel).
Claims (3)
1. a wind power time series combination forecasting method, is characterized in that: comprise the following steps:
S1: the wind power generation power data per diem gathering wind energy turbine set to be predicted, i.e. history wind power data, and the history wind power data collected is generated a corresponding time series amount X, as training sample set;
S2: utilize training sample set X is nuclear model with time series predicting model, adopts direct multi-step prediction method, calculates and generates wind power prediction sequence X
dMS;
S3: utilize training sample set X take time series predicting model as nuclear model, adopts rolling multi-step prediction method, calculates and generate wind power prediction sequence X
iMS;
S4: per diem to wind power prediction sequence X
dMS, X
iMScarry out statistical study with training sample set X, under degree of confidence factor alpha, calculate respective high precision predicted time scope T
dMSand T
iMS, wherein ∑ T
dMS+ ∑ T
iMS=24 hours;
S5: adopt time series predicting model as nuclear model, at time range T
dMSthe direct multistep forecasting method of interior employing to day to be predicted at time range T
dMSinterior wind power is predicted, obtains time range T
dMSinterior predicts the outcome; At time range T
iMSinterior employing rolling multistep forecasting method to day to be predicted at time range T
iMSinterior wind power is predicted, obtains time range T
iMSinterior predicts the outcome;
S6: by time range T
dMSinterior predicts the outcome and time range T
iMSin predict the outcome and combine, form complete day to be measured wind power prediction result;
" day " described in above step S1, S4, S5 and S6 is 24 hours.
2. wind power time series combination forecasting method according to claim 1, is characterized in that: described step S4 comprises the following steps:
S4.1: per diem to wind power prediction sequence X
dMScarry out predicated error calculating with training sample set X, under degree of confidence factor alpha, calculate the average error curve E of direct multistep forecasting method predicated error band
dMS;
S4.2: per diem to wind power prediction sequence X
iMScarry out predicated error calculating with training sample set X, under degree of confidence factor alpha, calculate the average error curve E of rolling multistep forecasting method predicated error band
iMS;
S4.3: compare E
dMSwith E
iMSnumerical values recited in 24 hours, chooses E
dMS<E
iMScorresponding time interval is time range T
dMS, choose E
iMS<E
dMSthe time domain scale T that corresponding time interval is predicted as rolling multistep processes
iMS;
" day " described in above step S4.1 and S4.2 is 24 hours.
3. wind power time series combination forecasting method according to claim 1, is characterized in that: described time series predicting model comprise in arma modeling, AR model, MA model and ANN model any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510056776.XA CN104657787B (en) | 2015-02-03 | 2015-02-03 | A kind of wind power time series combination forecasting method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510056776.XA CN104657787B (en) | 2015-02-03 | 2015-02-03 | A kind of wind power time series combination forecasting method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104657787A true CN104657787A (en) | 2015-05-27 |
CN104657787B CN104657787B (en) | 2018-05-04 |
Family
ID=53248884
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510056776.XA Active CN104657787B (en) | 2015-02-03 | 2015-02-03 | A kind of wind power time series combination forecasting method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104657787B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915736A (en) * | 2015-06-29 | 2015-09-16 | 东北电力大学 | Method for improving accuracy of wind power combined prediction based on improved entropy weight method |
CN105303250A (en) * | 2015-09-23 | 2016-02-03 | 国家电网公司 | Wind power combination prediction method based on optimal weight coefficient |
CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102226903A (en) * | 2011-05-11 | 2011-10-26 | 北方工业大学 | Rolling forecasting combined model method |
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 |
CN102682207A (en) * | 2012-04-28 | 2012-09-19 | 中国科学院电工研究所 | Ultrashort combined predicting method for wind speed of wind power plant |
CN104298859A (en) * | 2014-09-22 | 2015-01-21 | 国电南瑞科技股份有限公司 | Multi-interval-prediction-result weighting integration method |
-
2015
- 2015-02-03 CN CN201510056776.XA patent/CN104657787B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102226903A (en) * | 2011-05-11 | 2011-10-26 | 北方工业大学 | Rolling forecasting combined model method |
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 |
CN102682207A (en) * | 2012-04-28 | 2012-09-19 | 中国科学院电工研究所 | Ultrashort combined predicting method for wind speed of wind power plant |
CN104298859A (en) * | 2014-09-22 | 2015-01-21 | 国电南瑞科技股份有限公司 | Multi-interval-prediction-result weighting integration method |
Non-Patent Citations (1)
Title |
---|
韩爽: "风电场功率短期预测方法研究", 《中国博士学位论文全文数据库》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915736A (en) * | 2015-06-29 | 2015-09-16 | 东北电力大学 | Method for improving accuracy of wind power combined prediction based on improved entropy weight method |
CN105303250A (en) * | 2015-09-23 | 2016-02-03 | 国家电网公司 | Wind power combination prediction method based on optimal weight coefficient |
CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
Also Published As
Publication number | Publication date |
---|---|
CN104657787B (en) | 2018-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cau et al. | Energy management strategy based on short-term generation scheduling for a renewable microgrid using a hydrogen storage system | |
GB2594034A (en) | Optimal control technology for distributed energy resources | |
CN104361406B (en) | A kind of photovoltaic plant can utilize solar power generation amount Forecasting Methodology | |
CN103296701B (en) | Active power control method in wind power plant | |
CN102419394B (en) | Wind/solar power prediction method with variable prediction resolution | |
CN104868505B (en) | Large solar photovoltaic generating base cluster power producing characteristics analysis method | |
CN104268659B (en) | A kind of photovoltaic power station power generation power ultra-short term prediction method | |
CN104951899A (en) | Multi-time-scale optimal scheduling method for power distribution company containing large-scale renewable energy sources | |
CN104574202A (en) | Analysis method of output characteristic of wind power plant | |
CN103345585A (en) | Wind power prediction correction method and system based on support vector machine | |
CN103440529A (en) | Lateral error translation modification method of wind electricity power forecast system | |
CN114362268A (en) | Wind-solar-charge two-stage prediction-based optimized scheduling method for comprehensive energy power supply system | |
CN104143839A (en) | Output-restricted active power distribution method based on power prediction and applied to wind power plant cluster | |
CN105046349B (en) | It is a kind of meter and wake effect wind power forecasting method | |
CN102722760B (en) | Regional power prediction method for photovoltaic power station group | |
CN106257792A (en) | A kind of new forms of energy priority scheduling method based on two benches Unit Combination | |
CN104657787A (en) | Wind power time series combined prediction method | |
CN104657786A (en) | Short-term wind power mixed predicting method based on Boosting algorithm | |
Yuan et al. | An overview on peak regulation of wind power integrated power systems | |
CN104239979B (en) | A kind of wind power plant generated output ultra-short term prediction method | |
CN111931981B (en) | Photovoltaic power generation ultra-short-term prediction method based on machine learning multi-model combination | |
Li et al. | Capacity configuration optimization for stand-alone microgrid considering the uncertainties of wind and solar resource | |
CN103427444A (en) | Control method for reducing wind power grid-connected scheduling plan error | |
CN114825467A (en) | Thermal power generating unit annual maintenance plan standby adequacy evaluation method and system | |
CN104331748A (en) | Method for forecasting continuous power curve of wind power plant group in planning target year |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |