CN105956708A - Grey correlation time sequence based short-term wind speed forecasting method - Google Patents
Grey correlation time sequence based short-term wind speed forecasting method Download PDFInfo
- Publication number
- CN105956708A CN105956708A CN201610310910.9A CN201610310910A CN105956708A CN 105956708 A CN105956708 A CN 105956708A CN 201610310910 A CN201610310910 A CN 201610310910A CN 105956708 A CN105956708 A CN 105956708A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- model
- short
- term
- decision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013277 forecasting method Methods 0.000 title claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000004069 differentiation Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 24
- 230000000694 effects Effects 0.000 claims description 22
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 9
- 230000001932 seasonal effect Effects 0.000 description 6
- 238000000714 time series forecasting Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000013076 uncertainty analysis Methods 0.000 description 1
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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a grey correlation time sequence based short-term wind speed forecasting method, which comprises the steps of (10) forming historical wind speed time sequence data, wherein actually measured wind speeds of a wind power plant are arranged according to a time sequence so as to form a historical wind speed time sequence; (20) acquiring a training sample set, wherein the historical wind speed time sequence is differentiated so as to acquire the training sample set; (30) acquiring a grey correlation optimization wind speed forecasting model, wherein optimized decision-making analysis under multiple targets is carried out on the order number of a time sequence model by applying a grey correlation decision-making analysis method, and grey time sequence model training is carried out by applying the training sample set so as to acquire an optimal wind speed forecasting model; (40) acquiring the differentiated short-term forecast wind speed, wherein short-term wind speed forecasting is carried out on the wind power plant by using the optimal wind speed forecasting model so as to acquire the differentiated short-term forecast wind speed; and (50) acquiring the actual short-term forecast wind speed, wherein inverse differentiation is carried out on the short-term forecast wind speed so as to acquire the short-term forecast wind speed of the wind power plant. The short-term wind speed forecasting method disclosed by the invention is small in forecast error.
Description
Technical field
The invention belongs to predicting wind speed of wind farm technical field, particularly a kind of based on gray relative seasonal effect in time series short-term wind speed forecasting method.
Background technology
Wind-powered electricity generation has good prospect and competitiveness in regenerative resource.But wind energy is affected such as factors such as temperature, air pressure, landform, height above sea level, latitudes by multiple, it is a kind of intermittent, randomness energy, large-scale wind power accesses electrical network, brings severe challenge will certainly to the safe and stable operation of power system, therefore the prediction for wind speed and generated energy is highly desirable to.Wind farm wind velocity and the Accurate Prediction of generated output, beneficially electric power system dispatching department are adjusted the most in time operation plan, thus effectively alleviates the wind-power electricity generation adverse effect to whole electrical network.
The Applied criteria functions such as method many employings AIC criterion of existing employing time series forecasting short-term wind speed carry out forecasting wind speed model and determine rank, determine optimal wind speed forecast model by choosing the model comprising best training fitting data and minimum free parameter.
But this method is limited for the abrupt information disposal ability of prediction of wind speed, when prediction of wind speed and training fluctuations in wind speed situation difference are bigger, it was predicted that model does not catches up with the change of actual measurement wind speed, causes short-term wind speed forecasting error bigger.
Summary of the invention
It is an object of the invention to provide a kind of based on gray relative seasonal effect in time series short-term wind speed forecasting method, it was predicted that error is little.
The technical solution realizing the object of the invention is:
A kind of short-term wind speed forecasting method based on the gray relative time, comprises the steps:
(10) historical wind speed time series data is formed: gather the actual measurement wind speed of wind energy turbine set, arranges according to the order of acquisition time, history of forming wind speed time series；
(20) training sample set obtains: historical wind speed time series is carried out differencing process, obtains the training sample set needed for Grey Time-series model；
(30) gray relative optimizes the acquisition of forecasting wind speed model: use gray-related decision to analyze method and the exponent number of Grey Time-series model carries out the Optimal Decision-making analysis under multiple target, and use training sample set to carry out Grey Time-series model training, obtain optimal wind speed forecast model；
(40) the short-term forecast wind speed of differencing obtains: utilizes optimal wind speed forecast model to carry out wind energy turbine set short-term wind speed forecasting, obtains the short-term forecast wind speed of differencing；
(50) actual short-term forecast wind speed obtains: the short-term forecast wind speed of differencing is carried out contrast differentiation process, obtains wind energy turbine set actual short-term forecast wind speed.
Compared with prior art, its remarkable advantage is the present invention: forecast error is little.
Its reason is:
1, wind speed mutation or fluctuation broadly fall into more greatly and there is the change of more uncertain wind speed, and grey relation theory belongs to gray theory, and gray theory has preferably description and prediction effect for uncertain information.The present invention uses the time series forecasting wind speed method that gray relative optimizes, for the wind speed change that there is bigger uncertain information, there is more preferable precision of prediction, and reduce forecasting wind speed error, the present invention is analyzed first with gray-related decision exponent number uncertain to forecast model, then forecast model is set up according to the training of historical wind speed sequence, decision objective and model quantitative are formed complementation, the foundation making model is more targeted, and the precision predicted the outcome carrying out obtaining during short-term wind speed forecasting is the highest；
2, the optimal decision analysis under gray-related decision can introduce multiple target, uncertainty for following wind speed change, optimization aim can be adjusted flexibly, forecast model is made to have adaptivity for the uncertain Changing Pattern of following wind speed, thus improve versatility and the precision of prediction of forecast model, optimize conventional time series Forecasting Methodology；
3, use the advanced Optimization Modeling mode that time series method and gray-related decision method combine, for the uncertainty analysis decision-making of model order, there is calculating simple, efficiency height and models fitting precision advantages of higher.
The present invention is described in further detail with detailed description of the invention below in conjunction with the accompanying drawings.
Accompanying drawing explanation
Fig. 1 is present invention main flow chart based on gray relative seasonal effect in time series short-term wind speed forecasting method.
Fig. 2 is in Fig. 1 in gray relative optimization forecasting wind speed model obtaining step, and utilization gray-related decision is analyzed method and the exponent number of Grey Time-series model is carried out the flow chart of the decision analysis under multiple target.
Detailed description of the invention
As it is shown in figure 1, present invention short-term wind speed forecasting method based on the gray relative time, comprise the steps:
(10) historical wind speed time series data is formed: gather the actual measurement wind speed of wind energy turbine set, arranges according to the order of acquisition time, history of forming wind speed time series；
In described (10) historical wind speed time series forming step, the acquisition time between adjacent actual measurement wind speed is spaced apart 10min.
(20) training sample set obtains: historical wind speed time series is carried out differencing process, obtains the training sample set needed for Grey Time-series model；
Described (20) training sample set obtaining step includes:
(21) first-order difference: as the following formula historical wind speed time series is carried out first-order difference process,
In formula,For the time series after the wind speed first-order difference of each air speed data point, (1-B) is difference operator, xtRepresent the air speed value of current time air speed data point, xt-1Representing the air speed value of previous moment air speed data point, historical wind speed time series is
X=[xt, t=1,2 ... ..., N],
In formula, X represents the time series of historical wind speed, and xt represents the air speed value in current time time series every 10 minutes air speed data points, and t represents the sequence number after each air speed value is according to time sequence, the air speed data number of samples of N express time sequence.
(22) multistage difference: as the following formula the wind speed time series after first-order difference is carried out multistage differencing process,
Finally obtain the historical wind speed time series after differencing processes,
In formula, d represents difference order,Represent the wind speed time series after d rank calculus of differences processes, XdRepresent the historical wind speed time series after difference processing,For the result after the air speed value differencing of each air speed data point, t represents the sequence number after each air speed value is according to time sequence, the air speed data number of samples of N express time sequence.
(30) the forecasting wind speed model that gray relative optimizes obtains: use gray-related decision to analyze method and the exponent number of Grey Time-series model carries out the Optimal Decision-making analysis under multiple target, and use training sample set to carry out Grey Time-series model training, obtain optimal wind speed forecast model；
As in figure 2 it is shown, in described (30) optimal wind speed forecast model obtaining step, the decision analysis using gray-related decision analysis method to carry out the exponent number of Grey Time-series model under multiple target includes:
(311) gray relative optimal prediction model order schemes of countermeasures collection determines:
Time series predicting model, the most i.e. ARIMA model is
φ(B)(1-B)dXt=θ (B) εt
Wherein, B is delay operator, and d represents difference order,For the autoregressive coefficient multinomial of model, θ (B)=1-θ1B-…θqBqMoving average coefficient polynomial for model；
The order of note forecast model is event a1, then event set A can be expressed as:
A={a1}={ (p, q) },
Determine that countermeasure integrates as model order value in scope [1 4], i.e.
C={bi, i=1,2 ..., 16}={ (po, qj), o=1,2,3,4；J=1,2,3,4},
Wherein, C is the countermeasure collection of event set A, biFor the countermeasure of event set A, po, qjFor game model order,
The schemes of countermeasures collection determining model order event set A is:
S={sj=(a1, bj)|a1∈ A, bj∈ B, j=1 ..., 16},
Wherein, S is the schemes of countermeasures collection of model order, sjFor model order schemes of countermeasures, a1For model order event, bjFor model order countermeasure.
(312)) model order decision objective determines:
Determine three different targets, including, 1. models fitting decision objective, the residual sum of squares (RSS) of models fitting；The simplest model decision target, model order and (p+q), 3. forecast and decision target, it was predicted that wind speed and the fitting degree of actual wind speed；
(313) decision objective Effect value is asked for:
Seek different decision scheme sjEffect value under k targetIt is expressed as:
In formula, u(1)For decision scheme sjResidual sum of squares (RSS) σ of corresponding ARIMA models fittingj 2, u(2)For decision scheme sjCorresponding model order and (p+q), u(3)For decision scheme sjCorresponding prediction of wind speed and the fitting degree of actual wind speed, be represented by:
In formula, f is the fitting degree of prediction of wind speed and actual wind speed, and y is actual measurement wind speed,For prediction of wind speed, this prediction of wind speed is the ARIMA model predication value that "current" model order decision scheme is corresponding；
Obtain
The decision scheme effect sequence of models fitting decision objective
The decision scheme effect sequence of the simplest model decision target
The decision scheme effect sequence of forecast and decision target
(314) average effect sequence is asked for:
Utilize following formula to seek the average picture of k target making policy decision scheme works sequence, obtain average effect sequence
(315) effect vector is asked for:
Decision scheme sjEffect vector uj, j=1 ..., 16, it is expressed as:
(316) optimal effectiveness vector is asked for:
Seek the preferable optimal effectiveness vector under different decision objectiveIt is expressed as
Obtain preferable optimal effectiveness vector
(317) grey absolute correlation degree calculates:
Calculate ujWith uj0Grey absolute correlation degree, be expressed as
In formula (14), εjFor grey absolute correlation degree, hj, hj0It is expressed as
In formula,It is respectively hj, hj0Initial point pulverised picture；
(318) best model order determines:
By max1 ≤ j ≤ 6{εj}=εk, obtain ukFor suboptimum effect vector, sk=(pk, qk) be suboptimum decision scheme, so that it is determined that model ARIMA (p, d, q) in best model order p, q value.
In described (30) optimal wind speed forecast model obtaining step, use training sample set carry out Grey Time-series model training, obtain optimal wind speed forecast model particularly as follows:
Using wind speed training sample sequence as the input signal of ARIMA model, using the output sequence of ARIMA model as output signal, utilize method of least square to pick out the unknown parameter of ARIMA model according to input signal and output signal, the most just obtain optimal grey sequential forecasting models correlation time trained.
(40) the short-term forecast wind speed of differencing obtains: utilizes optimal wind speed forecast model to carry out wind energy turbine set short-term wind speed forecasting, obtains the short-term forecast wind speed of differencing；
Described (40) differencing short-term forecast wind speed obtaining step particularly as follows:
If current time is t, with m the wind-speed sample point predicted composition input optimum ARIMA model of data input before current time, i.e. input data are
The forecasting wind speed value in output next moment, i.e. (t+1) moment
It is wind energy turbine set differencing short-term forecast wind speed.
(50) short-term forecast wind speed obtains: the short-term forecast wind speed of differencing is carried out contrast differentiation process, obtains wind energy turbine set short-term forecast wind speed.
Described (50) short-term forecast wind speed obtaining step particularly as follows:
Differencing short-term forecast wind speed and input data are carried out d cumulative reduction, i.e. obtains wind energy turbine set short-term forecast wind speed.
Wind speed mutation or fluctuation broadly fall into more greatly and there is the change of more uncertain wind speed, and grey relation theory belongs to gray theory, and gray theory has preferably description and prediction effect for uncertain information.So using the time series forecasting wind speed method that gray relative optimizes, for the wind speed change that there is bigger uncertain information, there is more preferable precision of prediction, and reducing forecasting wind speed error.Gray relative is good mainly for uncertain wind speed variation effect, general wind speed forecasting method wind speed change greatly or uncertain change time prediction effect the most poor.
The present invention utilizes gray-related decision exponent number uncertain to forecast model to be analyzed, then forecast model is set up according to the training of historical wind speed sequence, decision objective and model quantitative are formed complementation, the foundation making model is more targeted, and the precision predicted the outcome carrying out obtaining during short-term wind speed forecasting is the highest.
The historical wind speed data obtained with Hebei wind energy turbine set, as initial data, take the wind speed historical data of wherein 5 days, and the acquisition interval time is the historical data that 10min intercepts the dimensions such as 5 sections at random, generates the time series of 5 groups of historical wind speed respectively, is represented sequentially as: X1, X2, X3, X4, X5.Separately verify this 5 groups of seasonal effect in time series precision of predictions, and compared with conventional time series short-term wind speed forecasting method.Wherein, using relative root-mean-square error function (RRMSE) to carry out predictive metrics precision, functional form is as follows:
In above formula (17),The value obtained for prediction, y is wind speed measured value, and n is the number of future position.Obtained relative root-mean-square error functional value is the least, it was demonstrated that prediction effect is the best, it was predicted that precision is the highest.Gained predicts the outcome as shown in table 1:
From the correction data in table 1, relative root-mean-square error based on gray relative seasonal effect in time series Forecasting Methodology proposed by the invention will be less than conventional time series Forecasting Methodology in predicting the outcome of 5 groups of data, and a kind of new short-term wind speed forecasting method of wind farm that i.e. present invention proposes is better than conventional time series short-term forecast method for the forecasting wind speed precision of following uncertain change.
Claims (7)
1. a short-term wind speed forecasting method based on the gray relative time, it is characterised in that comprise the steps:
(10) historical wind speed time series data is formed: gather the actual measurement wind speed of wind energy turbine set, arranges according to the order of acquisition time, history of forming wind speed time series；
(20) training sample set obtains: historical wind speed time series is carried out differencing process, obtains the training sample set needed for Grey Time-series model；
(30) gray relative optimizes the acquisition of forecasting wind speed model: use gray-related decision to analyze method and the exponent number of Grey Time-series model carries out the Optimal Decision-making analysis under multiple target, and use training sample set to carry out Grey Time-series model training, obtain optimal wind speed forecast model；
(40) the short-term forecast wind speed of differencing obtains: utilizes optimal wind speed forecast model to carry out wind energy turbine set short-term wind speed forecasting, obtains the short-term forecast wind speed of differencing；
(50) actual short-term forecast wind speed obtains: the short-term forecast wind speed of differencing is carried out contrast differentiation process, obtains wind energy turbine set actual short-term forecast wind speed.
Short-term wind speed forecasting method the most according to claim 1, it is characterised in that in described (10) historical wind speed time series forming step, the acquisition time between adjacent actual measurement wind speed is spaced apart 10min.
Short-term wind speed forecasting method the most according to claim 1, it is characterised in that described (20) training sample set obtains particularly as follows: as the following formula historical wind speed time series is carried out first-order difference process,
In formula,For the time series after the wind speed first-order difference of each air speed data point, (1-B) is difference operator, xtRepresent the air speed value of current time air speed data point, xt-1Representing the air speed value of previous moment air speed data point, historical wind speed time series is
X=[xt, t=1,2 ... ..., N],
In formula, X represents the time series of historical wind speed, and xt represents the air speed value in current time time series every 10 minutes air speed data points, and t represents the sequence number after each air speed value is according to time sequence, the air speed data number of samples of N express time sequence.
Short-term wind speed forecasting method the most according to claim 1, it is characterized in that, in described (30) optimal wind speed forecast model obtaining step, the decision analysis using gray-related decision analysis method to carry out the exponent number of Grey Time-series model under multiple target includes:
(311) gray relative optimal prediction model order schemes of countermeasures collection determines:
Time series predicting model, i.e. ARIMA model is
φ(B)(1-B)dXt=θ (B) εt
Wherein, B is delay operator, and d represents difference order,For the autoregressive coefficient multinomial of model, θ (B)=1-θ1B-…θqBqMoving average coefficient polynomial for model；
The order of note forecast model is event a1, then event set A can be expressed as:
A={a1}={ (p, q) },
Determine that countermeasure integrates as model order value in scope [1 4], i.e.
C={bi, i=1,2 ..., 16}={ (po, qj), o=1,2,3,4；J=1,2,3,4},
Wherein, C is the countermeasure collection of event set A, biFor the countermeasure of event set A, po, qjFor game model order,
The schemes of countermeasures collection determining model order event set A is:
S={sj=(a1, bj)|a1∈ A, bj∈ B, j=1 ..., 16},
Wherein, S is the schemes of countermeasures collection of model order, sjFor model order schemes of countermeasures, a1For model order event, bjFor model order countermeasure.
(312)) model order decision objective determines:
Determine three different targets, including, 1. models fitting decision objective, the residual sum of squares (RSS) of models fitting；The simplest model decision target, model order and (p+q), 3. forecast and decision target, it was predicted that wind speed and the fitting degree of actual wind speed；
(313) decision objective Effect value is asked for:
Seek different decision scheme sjEffect value under k targetIt is expressed as:
In formula, u(1)For decision scheme sjThe residual sum of squares (RSS) of corresponding ARIMA models fittingu(2)For decision scheme sjCorresponding model order and (p+q), u(3)For decision scheme sjCorresponding prediction of wind speed and the fitting degree of actual wind speed, be represented by:
In formula, f is the fitting degree of prediction of wind speed and actual wind speed, and y is actual measurement wind speed,For prediction of wind speed, this prediction of wind speed is the ARIMA model predication value that "current" model order decision scheme is corresponding；
Obtain
The decision scheme effect sequence of models fitting decision objective
The decision scheme effect sequence of the simplest model decision target
The decision scheme effect sequence of forecast and decision target
(314) average effect sequence is asked for:
Utilize following formula to seek the average picture of k target making policy decision scheme works sequence, obtain average effect sequence
(315) effect vector is asked for:
Decision scheme sjEffect vector uj, j=1 ..., 16, it is expressed as:
(316) optimal effectiveness vector is asked for:
Seek the preferable optimal effectiveness vector under different decision objectiveIt is expressed as
Obtain preferable optimal effectiveness vector
(317) grey absolute correlation degree calculates:
Calculate ujWith uj0Grey absolute correlation degree, be expressed as
In formula, εjFor grey absolute correlation degree, hj, hj0It is expressed as
In formula,It is respectively hj, hj0Initial point pulverised picture；
(318) best model order determines:
By max1 ≤ j ≤ 6{εj}=εk, obtain ukFor suboptimum effect vector, sk=(pk, qk) be suboptimum decision scheme, so that it is determined that model ARIMA (p, d, q) in best model order p, q value.
Short-term wind speed forecasting method the most according to claim 4, it is characterized in that, in described (30) optimal wind speed forecast model obtaining step, use training sample set to carry out Grey Time-series model training, obtain optimal wind speed forecast model, particularly as follows:
Using wind speed training sample sequence as the input signal of ARIMA model, using the output sequence of ARIMA model as output signal, utilize method of least square to pick out the unknown parameter of ARIMA model according to input signal and output signal, obtain optimal grey sequential forecasting models correlation time trained.
Short-term wind speed forecasting method the most according to claim 1, it is characterised in that the short-term forecast wind speed obtaining step of described (40) differencing particularly as follows:
If current time is t, with m the wind-speed sample point predicted composition input optimum ARIMA model of data input before current time, i.e. input data are
The forecasting wind speed value in output next moment, i.e. (t+1) moment
It is wind energy turbine set differencing short-term forecast wind speed.
Short-term wind speed forecasting method the most according to claim 1, it is characterised in that described (50) short-term forecast wind speed obtaining step particularly as follows:
Differencing short-term forecast wind speed and input data are carried out d cumulative reduction, i.e. obtains wind energy turbine set short-term forecast wind speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610310910.9A CN105956708A (en) | 2016-05-12 | 2016-05-12 | Grey correlation time sequence based short-term wind speed forecasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610310910.9A CN105956708A (en) | 2016-05-12 | 2016-05-12 | Grey correlation time sequence based short-term wind speed forecasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105956708A true CN105956708A (en) | 2016-09-21 |
Family
ID=56911290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610310910.9A Pending CN105956708A (en) | 2016-05-12 | 2016-05-12 | Grey correlation time sequence based short-term wind speed forecasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105956708A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845687A (en) * | 2016-12-27 | 2017-06-13 | 河南农业大学 | A kind of cigarette quality research method |
| CN109190845A (en) * | 2018-09-29 | 2019-01-11 | 南京信息工程大学 | A kind of two stages dynamic optimization short-term wind power forecast method |
| WO2019015226A1 (en) * | 2017-07-19 | 2019-01-24 | 厦门理工学院 | Method for rapidly identifying wind speed distribution pattern |
| CN111476439A (en) * | 2020-05-18 | 2020-07-31 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on gray time sequence |
| CN113516320A (en) * | 2021-09-14 | 2021-10-19 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102749471A (en) * | 2012-07-13 | 2012-10-24 | 兰州交通大学 | Short-term wind speed and wind power prediction method |
| CN104376388A (en) * | 2014-12-08 | 2015-02-25 | 国家电网公司 | Ultra-short period wind power prediction method based on wind speed factor control model |
-
2016
- 2016-05-12 CN CN201610310910.9A patent/CN105956708A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102749471A (en) * | 2012-07-13 | 2012-10-24 | 兰州交通大学 | Short-term wind speed and wind power prediction method |
| CN104376388A (en) * | 2014-12-08 | 2015-02-25 | 国家电网公司 | Ultra-short period wind power prediction method based on wind speed factor control model |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845687A (en) * | 2016-12-27 | 2017-06-13 | 河南农业大学 | A kind of cigarette quality research method |
| WO2019015226A1 (en) * | 2017-07-19 | 2019-01-24 | 厦门理工学院 | Method for rapidly identifying wind speed distribution pattern |
| CN109190845A (en) * | 2018-09-29 | 2019-01-11 | 南京信息工程大学 | A kind of two stages dynamic optimization short-term wind power forecast method |
| CN109190845B (en) * | 2018-09-29 | 2022-05-31 | 南京信息工程大学 | Two-stage dynamic optimization short-term wind power prediction method |
| CN111476439A (en) * | 2020-05-18 | 2020-07-31 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on gray time sequence |
| CN111476439B (en) * | 2020-05-18 | 2023-08-04 | 瑞纳智能设备股份有限公司 | Heating valve adjusting method, system and equipment based on gray time sequence |
| CN113516320A (en) * | 2021-09-14 | 2021-10-19 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN113516320B (en) * | 2021-09-14 | 2021-12-10 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
| Korprasertsak et al. | Robust short-term prediction of wind power generation under uncertainty via statistical interpretation of multiple forecasting models | |
| CN105426956B (en) | A kind of ultra-short term photovoltaic prediction technique | |
| CN106529719B (en) | Wind power prediction method based on particle swarm optimization algorithm wind speed fusion | |
| Zhang et al. | GEFCom2014 probabilistic solar power forecasting based on k-nearest neighbor and kernel density estimator | |
| CN105956708A (en) | Grey correlation time sequence based short-term wind speed forecasting method | |
| CN103683274B (en) | Regional long-term wind power generation capacity probability prediction method | |
| CN109636066A (en) | A kind of wind power output power prediction technique based on fuzzy time series data mining | |
| Mangalova et al. | K-nearest neighbors for GEFCom2014 probabilistic wind power forecasting | |
| CN104077632A (en) | Wind power field power prediction method based on deep neural network | |
| Kolhe et al. | GA-ANN for short-term wind energy prediction | |
| CN110991725B (en) | RBF ultra-short-term wind power prediction method based on wind speed frequency division and weight matching | |
| CN113344288B (en) | Cascade hydropower station group water level prediction method and device and computer readable storage medium | |
| CN109636054A (en) | Solar energy power generating amount prediction technique based on classification and error combination prediction | |
| CN104036328A (en) | Self-adaptive wind power prediction system and prediction method | |
| Dong et al. | Wind power prediction based on multi-class autoregressive moving average model with logistic function | |
| Luo et al. | Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine | |
| Chen et al. | Research on wind power prediction method based on convolutional neural network and genetic algorithm | |
| CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
| CN116307240A (en) | Photovoltaic power station short-term power generation power prediction method based on WOA-VMD-OLS | |
| CN111967660B (en) | Ultra-short-term photovoltaic prediction residual error correction method based on SVR | |
| Ansari et al. | Wind power forecasting using artificial neural network | |
| CN112508278A (en) | Multi-connected system load prediction method based on evidence regression multi-model | |
| Khosravi et al. | Wind farm power uncertainty quantification using a mean-variance estimation method | |
| Kartini et al. | Short term forecasting of global solar irradiance by k-nearest neighbor multilayer backpropagation learning neural network algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160921 |
|
| WD01 | Invention patent application deemed withdrawn after publication |