CN103984986B - The self study arma modeling ultrashort-term wind power prediction method of real time correction - Google Patents
The self study arma modeling ultrashort-term wind power prediction method of real time correction Download PDFInfo
- Publication number
- CN103984986B CN103984986B CN201410186902.9A CN201410186902A CN103984986B CN 103984986 B CN103984986 B CN 103984986B CN 201410186902 A CN201410186902 A CN 201410186902A CN 103984986 B CN103984986 B CN 103984986B
- Authority
- CN
- China
- Prior art keywords
- model
- wind power
- data
- real
- wind
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012937 correction Methods 0.000 title claims abstract description 22
- 241001123248 Arma Species 0.000 title claims abstract 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000005311 autocorrelation function Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 230000009191 jumping Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000005611 electricity Effects 0.000 abstract 1
- 238000010248 power generation Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Landscapes
- Wind Motors (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of self study arma modeling ultrashort-term wind power prediction method of real time correction, including input data to obtain autoregressive moving-average model parameter；Wind-resources monitoring system data and operation monitoring system data are inputted, and according to operational monitoring real-time correction start capacity；Autoregressive moving-average model is established so as to obtain ultrashort-term wind power prediction result；Introduce real-time anemometer tower data and real time correction is carried out to ultrashort-term wind power prediction result.By being predicted to the wind power during wind-power electricity generation, and real time correction is carried out to ultrashort-term wind power prediction result by introducing real-time anemometer tower data, overcome the defects of ultrashort-term wind power precision of prediction is low in existing ARMA technologies, achieve the purpose that high-precision ultrashort-term wind power prediction.
Description
Technical Field
The invention relates to the technical field of wind power prediction in a new energy power generation process, in particular to a self-learning ARMA model wind power ultra-short-term prediction method for wind power, which is used for wind measurement network real-time correction.
Background
Most of large new energy bases generated after wind power enters a large-scale development stage in China are located in the three-north area (northwest, northeast and north China), the large new energy bases are generally far away from a load center, and the power of the large new energy bases needs to be transmitted to the load center for consumption through a long distance and high voltage. Due to the intermittency, randomness and fluctuation of wind and light resources, the wind power and photovoltaic power generation output of a large-scale new energy base can fluctuate in a large range along with the intermittency, randomness and fluctuation of the charging power of a power transmission network, and a series of problems are brought to the operation safety of a power grid.
By 4 months in 2014, the installed capacity of the grid-connected wind power of the Gansu power grid reaches 707 ten thousand watts, occupies about 22 percent of the total installed capacity of the Gansu power grid, and becomes the second main power source which is only inferior to thermal power. At present, the installed capacity of wind power and photovoltaic power generation of a Gansu power grid exceeds 1/3 of the total installed capacity of the Gansu power grid. With the continuous improvement of the new energy grid-connected scale, the uncertainty and the uncontrollable property of wind power generation and photovoltaic power generation bring a plurality of problems to the safe, stable and economic operation of a power grid. Accurate estimation of available power generation wind resources is the basis for large-scale wind power optimization scheduling. The method can predict the wind power in the wind power generation process, and can provide key information for real-time scheduling of new energy power generation, a new energy power generation day-ahead plan, a new energy power generation month plan, new energy power generation capacity evaluation and wind curtailment power estimation.
The ARMA (autoregressive moving average model) is widely applied to wind power ultra-short-term prediction as a mature machine learning method. The ARMA model consists of an autoregressive model (AR) and a moving average Model (MA), and the wind power output in 0-4 hours in the future is predicted by carrying out autoregressive operation on historical power and carrying out moving average on a white noise sequence. The ARMA method has many advantages, so the ARMA method is widely used for ultra-short-term prediction of wind power, but the biggest disadvantage of the ARMA method is the hysteresis of the prediction, namely when the wind power output is changed, the change speed of the result of the ARMA prediction is generally slower than the change speed of the actual wind power output, and therefore the prediction precision of the ARMA is seriously influenced.
Disclosure of Invention
The invention aims to provide a real-time correction self-learning ARMA model wind power ultra-short-term prediction method aiming at the problems so as to realize the advantage of high-precision wind power ultra-short-term prediction.
In order to achieve the purpose, the invention adopts the technical scheme that:
a real-time correction ultra-short-term wind power prediction method for a self-learning ARMA model comprises the steps of inputting data to obtain autoregressive moving average model parameters;
inputting wind resource monitoring system data and operation monitoring system data, and correcting the starting capacity in real time according to the operation monitoring data;
establishing an autoregressive moving average model so as to obtain a wind power ultra-short term prediction result;
and introducing real-time anemometer tower data to correct the wind power ultra-short term prediction result in real time.
According to the preferred embodiment of the present invention, the obtaining of autoregressive moving average model parameters from the input data comprises inputting model training basic data;
determining the order of the model;
and (3) estimating the fixed-order ARMA (p, q) model parameters by adopting a moment estimation method.
According to a preferred embodiment of the invention, the input model trains the underlying data, the input data comprising historical wind speed data and historical power data.
According to the preferred embodiment of the present invention, the model scaling specifically is:
performing model order determination by using a residual variance graph method, specifically setting x t For the term to be estimated, x t-1 ,x t-2 ,...,x t-n For an ARMA (p, q) model, determining the values of parameters p and q in the model by the model in order for the known historical power sequence;
fitting the original sequence with a model with a series of increasing orders, calculating the sum of squares of the residuals each timeThen, the order sum is plottedWhen the order number is increased from small to small,will be obviously reduced and reach the real orderThe value of (b) will gradually become flat, even increase,
= sum of squares of fitting errors/(number of actual observed values-number of model parameters),
the number of actual observation values refers to the number of observation value items actually used in fitting a model, for a sequence with N observation values, an AR (p) model is fitted, the actually used observation values are at most N-p, the number of model parameters refers to the number of parameters actually included in the established model, for a model with a mean value, the number of model parameters is the number of model orders plus 1, and for a sequence with N observation values, the residual error estimation formula of the ARMA model is:
wherein Q is a sum of squares function of the fitting error,and theta j (1. Ltoreq. J. Ltoreq. Q) is the model coefficient, N is the observation sequence length,is a constant term in the model parameters.
According to the preferred embodiment of the present invention, the estimating the fixed-order ARMA (p, q) model parameters by using the moment estimation method specifically comprises the following steps:
utilizing historical power data of wind power plant by using data sequence x 1 ,x 2 ,...,x t Representation with sample autocovariance defined as
Wherein k =0,1,2,. Cndot.n-1, x t And x t-k Are all data sequences x 1 ,x 2 ,...,x t The numerical value of (1);
then
The historical power data sample autocorrelation function is then:
wherein k =0,1,2,. N-1;
the moments of the AR part are estimated as,
order to
Then the covariance function is
By usingInstead of gamma k ，
Available parameters
For MA (q) model coefficientUsing the moment estimate to have
Up to
Wherein k =1,2,. Multidot.m,
and solving the nonlinear equations of the above m +1 equations by an iterative method to obtain the parameters of the autoregressive moving average model.
According to a preferred embodiment of the present invention,
the wind resource monitoring system data comprises real-time wind measurement data monitored by a wind measuring tower related to the wind power plant to be predicted and average wind speed of the wind power plant predicted by numerical weather forecast data, and the operation monitoring system data is real-time monitoring information of a fan of the wind power plant to be predicted and comprises real-time startup and shutdown conditions of the fan and unit pitch angle state information.
According to a preferred embodiment of the present invention, further comprising,
outputting the prediction result;
and post-evaluating the prediction result and modifying the model.
According to a preferred embodiment of the present invention, the autoregressive moving average model is:
wherein,and theta j (1. Ltoreq. J. Ltoreq. Q) is a coefficient, alpha t Is a white noise sequence.
According to the preferred embodiment of the invention, the real-time correction of the wind power ultra-short term prediction result by introducing the real-time anemometer tower data specifically comprises the following steps:
let t 1 At any moment, the average wind speed of the wind power plant obtained by monitoring the anemometer tower is v 1 And the average wind speed of the wind power plant predicted by numerical weather forecast data is u 1 The actual output of the wind farm is p 1 (ii) a The next time t 2 At the moment, the average wind speed of the wind power plant predicted by numerical weather forecast data is u 2 Then the average wind speed v of the wind farm 2 In order to realize the purpose,
v 2 ＝v 1 +(u 2 -u 1 )
the correction quantity of the parameter of the wind power plant power prediction is
(v t Not equal to 0).
According to the preferred embodiment of the present invention, the final prediction result is output as:
wherein X t Is the prediction of the output of the wind power plant at the moment t,and theta j (1. Ltoreq. J. Ltoreq. Q) is a coefficient, alpha t Is a white noise sequence, λ is a weighting coefficient, v t Is the average wind speed of the wind farm at time t.
The technical scheme of the invention has the following beneficial effects:
according to the technical scheme, the wind power in the wind power generation process is predicted, and the wind power ultra-short term prediction result is corrected in real time by introducing real-time wind measuring tower data, so that the defect of low wind power ultra-short term prediction precision in the existing ARMA technology is overcome, and the purpose of high-precision wind power ultra-short term prediction is achieved.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a schematic block diagram of a real-time corrected wind power ultra-short term prediction method for a self-learning ARMA model according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it should be understood that they are presented herein only to illustrate and explain the present invention and not to limit the present invention.
A real-time corrected ultra-short-term wind power prediction method for a self-learning ARMA model comprises the steps of inputting data to obtain autoregressive moving average model parameters;
inputting wind resource monitoring system data and operation monitoring system data, and correcting the starting capacity in real time according to the operation monitoring data;
establishing an autoregressive moving average model so as to obtain a wind power ultra-short term prediction result;
and introducing real-time anemometer tower data to correct the wind power ultra-short term prediction result in real time.
As shown in fig. 1, the ultra-short term prediction of wind power proposed by the technical solution of the present invention can be divided into two stages: a model training phase and a power prediction phase.
Stage 1: model training
Step 1.1: model training basic data input
Input data required by model training of the wind power prediction system mainly comprise historical wind speed data, historical power data and the like. And inputting the basic data into a prediction model for model training.
Step 1.2: order determination of model
Since it is not possible to determine in advance how many terms of the known time series need to be used to build the estimation function, a scaling decision needs to be made on the model.
Let x t For the term to be estimated, x t-1 ,x t-2 ,...,x t-n For the ARMA (p, q) model, the model order is to determine the values of the parameters p and q in the model for the known historical power sequence.
And carrying out model order determination by adopting a residual variance graph method. Assuming that the model is a finite order autoregressive model, if the set order is smaller than the true order, the model is an insufficient fitting, so that the fitted residual sum of squares is necessarily large, and at this time, the residual sum of squares can be remarkably reduced by increasing the order. Conversely, if the order has reached the true value, then increasing the order again is an overfitting, and increasing the order does not significantly reduce the sum of squared residuals, or even slightly increases the sum.
Thus, a series of models with progressively increasing order were fitted to the original sequence, each time the sum of the squares of the residuals were calculatedThen, the order sum is plottedThe pattern of (2). When the order number is increased from small to small,will be obviously reduced and reach the real orderThe value of (a) tends to be gradually gentle and sometimes even to increase. The residual variance is estimated as:
= sum of squares of fitting errors/(number of actual observed values-number of model parameters)
The "number of actual observations" means the number of observation terms actually used in fitting the model, and for a sequence having N observations, fitting the AR (p) model, the actually used observations are at most N-p.
The number of model parameters is the number of parameters actually included in the established model, and for the model with the mean value, the number of model parameters is the number of model orders plus 1. For a sequence of N observations, the residual estimate for the corresponding ARMA model is:
in equation 1, Q is a function of the sum of the squares of the fitting errors,and theta j (1. Ltoreq. J. Ltoreq. Q) is the model coefficient, N is the observation sequence length,is a constant term in the model parameters.
Step 1.3: model parameter estimation
Model parameters of ARMA (p, q) are estimated by a moment estimation method. Firstly, utilizing the historical power data of the wind power plant by a data sequence x 1 ,x 2 ,...,x t Representation with sample autocovariance defined as
(formula 2)
Wherein k =0,1,2 t And x t-k Are all a data sequence x 1 ,x 2 ,...,x t The numerical values in (1).
In particular, it is possible to use, for example,
(formula 3)
Then the historical power data sample autocorrelation function is:
(formula 4)
Wherein k =0,1, 2.
The moments of the AR portion are estimated as
(formula 5)
Order to
(formula 6)
The covariance function is then
(formula 7)
By usingInstead of gamma k Is provided with
(formula 8)
Available parameters
For the MA (q) model coefficient theta 1 ,θ 2 ,...,θ q By using moment estimation have
(formula 9)
………
………
(formula 10)
Wherein k =1,2.
The above equations contain m +1 equations, and for the parameters, the equations are nonlinear and are solved by an iterative method.
The method comprises the following specific steps of transforming the equation into:
(formula 11)
(formula 12)
Given theta 1 ,θ 2 ,...,θ q Anda set of initial values, e.g.
(formula 13)
Substituting the right side of the above two formulas, the value obtained at the left side is the first step iteration value, and recording asThen the value is substituted into the right side of the above two formulas in sequence to obtain a second step iteration value,and analogizing in turn until the results of two adjacent iterations are smaller than a given threshold value, and taking the obtained results as approximate solutions of the parameters.
Finding out through the solving process that the order of the time series model is required to be solved, and obtaining the predicted value of the time series; in order to obtain a predicted value of the time sequence, a specific prediction function must be established first; to build a specific prediction function, the order of the model must be known.
According to practice, the order of the time series model does not generally exceed 5. Therefore, when the algorithm is specifically implemented, the model can be assumed to be 1 order, the parameter of the first-order model is obtained by using the parameter estimation method in the step 1.3, and then an estimation function is established so that the time series model of the first-order model can be estimated to obtain the predicted value of each item, and the residual variance of the first-order model can be obtained; then, assuming that the model is of the second order, the residual error of the second-order model is obtained by the method; by analogy, the residual errors of the models of 1 to 5 orders can be obtained, and the order of the model with the minimum residual error is selected as the order of the final model. After the model order is determined, the parameter theta can be calculated 1 ,θ 2 ,...,θ q The value of (c).
And (2) stage: power prediction
Step 2.1: wind resource monitoring system data input
The wind resource monitoring system data mainly comprises real-time wind measurement data monitored by a wind measuring tower related to the wind farm to be predicted and the average wind speed of the wind farm predicted by NWP (numerical weather forecast data).
Step 2.2: operation monitoring system data input
The operation monitoring system data refers to real-time monitoring information of a wind turbine of the wind power plant to be predicted, and mainly comprises state information such as real-time shutdown and startup conditions of the wind turbine and a turbine set pitch angle.
Step 2.3: real-time correction of boot capacity for operation monitoring data
In the running process of the wind power plant, the wind power plant always has shutdown conditions caused by various reasons, for example, a typical 20-ten-thousand-kilowatt installed wind power plant comprises 134 fans, about 10 fans are in a shutdown state on average, so that the actual starting capacity of the wind power can be known through real-time fan running monitoring data, and the installed capacity of the wind power plant is not used for carrying out the ultra-short-term prediction of the wind power.
Step 2.4: ARMA model-based wind power ultra-short term prediction
After the model parameters are estimated, a time series equation for the ultra-short term prediction of the wind power can be obtained by combining the estimated model orders. The p and q values obtained from the above steps 2 and 3, anθ 1 ,θ 2 ,...,θ q Establishing an autoregressive moving average model;
the autoregressive moving average model is as follows:
(formula 14)
Wherein,and theta j (1. Ltoreq. J. Ltoreq.q) is a coefficient, and α t is a white noise sequence.
Step 2.5: resource monitoring data real-time correction wind power ultra-short term prediction result
According to the ARMA prediction model, the model always has hysteresis for real-time change of the wind power, and the wind power ultra-short term prediction result is corrected in real time by introducing real-time anemometer tower data.
Let t 1 At any moment, the average wind speed of the wind power plant obtained by monitoring the anemometer tower is v 1 And the average wind speed of the NWP predicted wind power plant is u 1 The actual output of the wind farm is p 1 (ii) a The next time t 2 At the moment, the average wind speed of the NWP predicted wind power plant is u 2 Then the average wind speed v of the wind farm 2 In order to realize the purpose,
v 2 ＝v 1 +(u 2 -u 1 ) (formula 15)
The correction quantity of the parameter of the wind power plant power prediction is
(v t Not equal to 0 time) (formula 16)
Step 2.6: outputting and displaying final prediction results
The ultra-short term prediction result of the ARMA model wind power corrected by the wind measuring network in real time is
(formula 17)
Wherein X t Is the prediction of the output of the wind power plant at the moment t,and theta j (1. Ltoreq. J. Ltoreq. Q) is a coefficient, alpha t Is a white noise sequence, λ is a weighting coefficient, v t Is the average wind speed of the wind farm at time t.
By introducing the predicted wind speed corrected by the real-time monitoring data of the anemometer tower, the weighted adjustment can be made on the next prediction of the ARMA model, so that the problem of the hysteresis of the prediction of the ARMA model is solved.
And outputting the prediction result to a database, and displaying the prediction result through a chart and a curve, and displaying the comparison between the prediction result and the actual measurement result.
Step 2.7: post-prediction evaluation and model correction
The step firstly carries out post-evaluation on the prediction result and analyzes the error between the predicted value and the measured value. And if the prediction error is larger than the maximum error allowed, jumping to the model training process, and re-performing the model training.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A real-time correction ultra-short-term wind power prediction method for a self-learning ARMA model is characterized by comprising the steps of inputting data to obtain parameters of an autoregressive moving average model;
inputting wind resource monitoring system data and operation monitoring system data, and correcting the starting capacity in real time according to the operation monitoring data;
establishing an autoregressive moving average model so as to obtain a wind power ultra-short term prediction result;
the method for introducing real-time anemometer tower data to carry out real-time correction on the wind power ultra-short term prediction result specifically comprises the following steps:
let t 1 At any moment, the average wind speed of the wind power plant obtained by monitoring the anemometer tower is v 1 And the average wind speed of the wind power plant predicted by numerical weather forecast data is u 1 The actual output of the wind farm is p 1 (ii) a The next time t 2 At the moment, the average wind speed of the wind power plant predicted by numerical weather forecast data is u 2 Then the average wind speed v of the wind farm 2 In order to realize the purpose,
v 2 ＝v 1 +(u 2 -u 1 )
the correction of the parameter of the wind farm power prediction is
Wherein v is 1 >0，v 2 >, 0 and v 1 Is not equal to v 2 ；
Wherein the post-evaluation and model correction after predicting the result is:
firstly, post-evaluating a prediction result, analyzing errors between a predicted value and an actual measurement value, jumping to a model training process if the prediction error is larger than an allowable maximum error, and re-performing model training;
the method comprises the steps that autoregressive moving average model parameters obtained by the input data are input into model training basic data;
determining the order of the model;
and (3) estimating the ARMA (p, q) model parameters of a fixed order by adopting a moment estimation method, wherein p is the order of an autoregressive model, and q is the order of an autoregressive sliding model.
2. The real-time corrected self-learning ARMA model wind power ultra-short term prediction method as claimed in claim 1, wherein the input model trains basic data, and the input data comprises historical wind speed data and historical power data.
3. The real-time correction self-learning ARMA model wind power ultra-short term prediction method as claimed in claim 2, wherein the model order determination specifically comprises:
performing model order determination by using residual variance diagram method, specifically setting x t For the term to be estimated, x t-1 ,x t-2 ,...,x t-n For the known historical power sequence, for an ARMA (p, q) model, determining the order of the model, namely determining the values of parameters p and q in the model;
fitting the original sequence with a series of models of increasing order, each time calculating the sum of squares of the residualsThen, the order sum is plottedWhen the order number is increased from small to small,will be obviously reduced and reach the real orderWill gradually change toGradually tend to be gentle and even to be bigger,
= sum of squares of fitting errors/(number of actual observed values-number of model parameters),
the number of actual observation values refers to the number of observation value items actually used in fitting a model, for a sequence with N observation values, an AR (p) model is fitted, the actually used observation values are at most N-p, the number of model parameters refers to the number of parameters actually included in the established model, for a model with a mean value, the number of model parameters is the number of model orders plus 1, and for a sequence with N observation values, the residual error estimation formula of the ARMA model is:
wherein Q is a sum of squares function of the fitting error,and theta j Is a model coefficient, wherein i is more than or equal to 1 and less than or equal to p, j is more than or equal to 1 and less than or equal to q, N is the length of an observation sequence,is a constant term in the model parameters.
4. The real-time correction self-learning ARMA model wind power ultra-short term prediction method as claimed in claim 3, wherein the specific steps of estimating fixed-order ARMA (p, q) model parameters by using a moment estimation method are as follows:
utilizing historical power data of wind power plant by data sequence x 1 ,x 2 ,...,x t Representation with sample autocovariance defined as
Wherein k1=0,1,2 t And x t -k1 are all data sequences x 1 ,x 2 ,...,x t The numerical value of (1);
then
The historical power data sample autocorrelation function is then:
wherein k1=0,1,2,. Cndot.n-1;
the moment of the AR part is estimated as,
order to
The covariance function is then
By usingInstead of gamma k2 ，
Available parameters
For the MA (q) model coefficient theta 1 ,θ 2 ,...,θ q Using the moment estimate to have
Up to
Wherein k2=1,2, ·, m,
solving the nonlinear equations of the above m +1 equations by using an iterative method to obtain autoregressive moving average model parameters.
5. The real-time corrected self-learning ARMA model wind power ultra-short term prediction method as claimed in claim 4,
the wind resource monitoring system data comprises real-time wind measurement data monitored by a wind measurement tower related to the wind power plant to be predicted and the average wind speed of the wind power plant predicted by numerical weather forecast data, and the operation monitoring system data is real-time monitoring information of a fan of the wind power plant to be predicted and comprises real-time startup and shutdown conditions of the fan and unit pitch angle state information.
6. The real-time corrected self-learning ARMA model wind power ultra-short term prediction method as recited in claim 5, further comprising,
outputting the prediction result;
and post-evaluating the prediction result and modifying the model.
7. The real-time corrected self-learning ARMA model wind power ultra-short term prediction method as claimed in claim 6, wherein the autoregressive moving average model is:
wherein,and theta j Is a model coefficient, wherein i is more than or equal to 1 and less than or equal to p, j is more than or equal to 1 and less than or equal to q, alpha t Is a white noise sequence, p is the order of the autoregressive model, q is the order of the autoregressive sliding model, X t Represents the value of the autoregressive moving average model function at the moment t, X t-i Represents the value of the autoregressive moving average model function at the t-i moment, alpha t-j Representing the white noise value at time t-j.
8. The real-time correction self-learning ARMA model wind power ultra-short term prediction method as recited in claim 1, wherein the output final prediction result is:
wherein, X t Is the prediction of the output of the wind power plant at the moment t,and theta j Is a model coefficient, wherein i is more than or equal to 1 and less than or equal to p, j is more than or equal to 1 and less than or equal to q, alpha t Is a white noise sequence, λ is a weighting coefficient, v t The average wind speed of the wind power plant at the time t, p is the order of the autoregressive model, q is the order of the autoregressive sliding model, and k is the wind power plant output value at the time t-1 after being corrected by the actually measured wind speed data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410186902.9A CN103984986B (en) | 2014-05-06 | 2014-05-06 | The self study arma modeling ultrashort-term wind power prediction method of real time correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410186902.9A CN103984986B (en) | 2014-05-06 | 2014-05-06 | The self study arma modeling ultrashort-term wind power prediction method of real time correction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103984986A CN103984986A (en) | 2014-08-13 |
| CN103984986B true CN103984986B (en) | 2018-04-27 |
Family
ID=51276947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410186902.9A Active CN103984986B (en) | 2014-05-06 | 2014-05-06 | The self study arma modeling ultrashort-term wind power prediction method of real time correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103984986B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104820146B (en) * | 2015-04-24 | 2018-08-14 | 中国电力科学研究院 | Transformer fault prediction technique based on Gases Dissolved in Transformer Oil monitoring data |
| US11242842B2 (en) | 2016-05-23 | 2022-02-08 | General Electric Company | System and method for forecasting power output of a wind farm |
| CN106844594A (en) * | 2017-01-12 | 2017-06-13 | 南京大学 | A kind of electric power Optimal Configuration Method based on big data |
| CN109274110A (en) * | 2018-11-23 | 2019-01-25 | 国网上海市电力公司 | A kind of electric system unbalance factor prediction technique based on error transfer factor |
| CN111192163B (en) * | 2019-12-23 | 2023-03-28 | 明阳智慧能源集团股份公司 | Generator reliability medium-short term prediction method based on wind turbine generator operating data |
| CN112070320B (en) * | 2020-09-21 | 2023-06-16 | 西安交通大学 | Ultra-short-term wind power prediction method and system based on dynamic harmonic regression |
| CN118381010A (en) * | 2024-04-19 | 2024-07-23 | 浙江大学 | Two-stage short-term wind power prediction method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102945508A (en) * | 2012-10-15 | 2013-02-27 | 风脉（武汉）可再生能源技术有限责任公司 | Model correction based wind power forecasting system and method |
| CN103208037A (en) * | 2013-04-26 | 2013-07-17 | 国电南瑞南京控制系统有限公司 | Online correction based power prediction method applicable to new energy power station |
| CN103473322A (en) * | 2013-09-13 | 2013-12-25 | 国家电网公司 | Photovoltaic generation power ultra-short term prediction method based on time series model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030184307A1 (en) * | 2002-02-19 | 2003-10-02 | Kozlowski James D. | Model-based predictive diagnostic tool for primary and secondary batteries |
| CN201813161U (en) * | 2010-07-16 | 2011-04-27 | 北京中科伏瑞电气技术有限公司 | Wind power forecasting system |
-
2014
- 2014-05-06 CN CN201410186902.9A patent/CN103984986B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102945508A (en) * | 2012-10-15 | 2013-02-27 | 风脉（武汉）可再生能源技术有限责任公司 | Model correction based wind power forecasting system and method |
| CN103208037A (en) * | 2013-04-26 | 2013-07-17 | 国电南瑞南京控制系统有限公司 | Online correction based power prediction method applicable to new energy power station |
| CN103473322A (en) * | 2013-09-13 | 2013-12-25 | 国家电网公司 | Photovoltaic generation power ultra-short term prediction method based on time series model |
Non-Patent Citations (1)
| Title |
|---|
| 甘肃电网风电功率超短期预测预报系统建设;赵龙等;《甘肃省电机工程学会2012年学术年会》;20120930;第430-434页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103984986A (en) | 2014-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103984986B (en) | The self study arma modeling ultrashort-term wind power prediction method of real time correction | |
| CN103996073B (en) | Light-metering network real time correction self study arma modeling photovoltaic power Forecasting Methodology | |
| CN103927695B (en) | Ultrashort-term wind power prediction method based on self study complex data source | |
| CN103117546B (en) | A kind of Ultrashort-term slide prediction method for wind power | |
| CN103984988B (en) | Light-metering network real time correction arma modeling photovoltaic power ultra-short term prediction method | |
| CN103984987B (en) | A kind of arma modeling ultrashort-term wind power prediction method of wind measurement network real time correction | |
| CN105048499A (en) | Wind power integration real-time scheduling method and device based on model prediction and control | |
| CN104573876A (en) | Wind power plant short-period wind speed prediction method based on time sequence long memory model | |
| CN103473322A (en) | Photovoltaic generation power ultra-short term prediction method based on time series model | |
| CN108053048A (en) | A kind of gradual photovoltaic plant ultra-short term power forecasting method of single step and system | |
| CN102562469A (en) | Short-term wind driven generator output power predicting method based on correction algorithm | |
| CN103996079B (en) | Wind power weighting predication method based on conditional probability | |
| CN104220951A (en) | Maximum power point tracking (mppt) | |
| CN103106314A (en) | Time sequence probability modeling method for output power of solar photovoltaic power supply | |
| EP3741991A1 (en) | Method for dynamic real-time optimization of the performance of a wind park and wind park | |
| CN103927597A (en) | Ultra-short-term wind power prediction method based on autoregression moving average model | |
| CN117117819A (en) | Photovoltaic power generation short-term power prediction method, system, equipment and medium | |
| JP6086875B2 (en) | Power generation amount prediction device and power generation amount prediction method | |
| CN105956708A (en) | Grey correlation time sequence based short-term wind speed forecasting method | |
| Chen et al. | Research on wind power prediction method based on convolutional neural network and genetic algorithm | |
| CN114819385A (en) | Wind power prediction method and device, electronic equipment and storage medium | |
| CN105741192B (en) | Short-term wind speed combined forecasting method for wind turbine engine room of wind power plant | |
| Ding et al. | Forecast of pv power generation based on residual correction of markov chain | |
| CN117371581A (en) | New energy generated power prediction method, device and storage medium | |
| Dong et al. | Studies on wind farms ultra-short term NWP wind speed correction methods |
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 |