CN110365053A - Short-term wind power forecast method based on delay optimisation strategy - Google Patents
Short-term wind power forecast method based on delay optimisation strategy Download PDFInfo
- Publication number
- CN110365053A CN110365053A CN201910732490.7A CN201910732490A CN110365053A CN 110365053 A CN110365053 A CN 110365053A CN 201910732490 A CN201910732490 A CN 201910732490A CN 110365053 A CN110365053 A CN 110365053A
- Authority
- CN
- China
- Prior art keywords
- power
- data
- wind speed
- wind
- prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000000630 rising effect Effects 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000012937 correction Methods 0.000 claims abstract description 19
- 238000005070 sampling Methods 0.000 claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 7
- 230000001174 ascending effect Effects 0.000 claims description 28
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000002045 lasting effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 13
- 238000011160 research Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 238000009499 grossing Methods 0.000 description 2
- 238000004940 physical analysis method Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- H02J3/386—
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
Abstract
The invention discloses a kind of short-term wind power forecast methods based on delay optimisation strategy, comprising: obtains wind speed-power data；The data of acquisition are sampled；Reject the abnormal data in sampled data；Choose continuous sampling data；Training prediction model；Utilize trained prediction model prediction power；Delay function is defined for the wind speed of lasting rising and carries out power correction.Method of the invention is quantitatively described the size and speed of fluctuations in wind speed by defining fluctuations in wind speed rate；Analysis is used to measure the correlation between the amplitude and angle and prediction lag of fluctuations in wind speed rate, in conjunction with wind energy replacement theory, proposes Deferred Correction function, is modified to prediction power, the wind power prediction precision of the violent section of fluctuations in wind speed can be improved.
Description
Technical Field
The invention relates to wind power prediction, in particular to a short-term wind power prediction method based on a delay optimization strategy.
Background
With the development of the wind power generation industry, the wind power grid-connected quantity is increased year by year, and large-scale wind power grid-connected has higher requirements on wind power prediction. However, due to wind instability, and the power generated by the turbine is proportional to the cube of the wind speed, the fluctuation of the wind speed in a specific time period necessarily affects the energy conversion rate of the wind driven generator. Nowadays, wind power prediction methods are roughly divided into physical analysis methods, statistical learning methods and combination of the physical analysis methods and the statistical learning methods. The physical method is suitable for the physical process of wind change, and the wind power plant geographic information and the characteristics of the wind turbine generator are analyzed, modeled and predicted to form a wind turbine generator or a wind power plant power curve to predict power. The statistical learning method is based on historical data such as NWP data, wind driven generator and anemometer tower collected data and the like, a model of wind-to-power conversion is obtained through a trend analysis method for prediction, but the method has high requirements on the historical data, and the prediction result with higher precision can be obtained from data which fluctuate smoothly and have certain regularity. Therefore, the problems of instability of wind power generation, low wind energy utilization rate and the like caused by factors such as sudden change and volatility of wind still need to be improved, and high-precision short-term wind power prediction is still the focus of research.
Regarding the research on the influence of the wind speed characteristics on the power generation power of a fan in the prior art, the power fluctuation characteristics of the fan under an equivalent wind speed model are researched by establishing an equivalent wind speed model containing wind shear and tower shadow effects in wind power fluctuation characteristic analysis based on equivalent wind speed by Wan Booth and the like, but the influence difference of each component of the equivalent wind speed on the power characteristics of a unit is obvious only by comparing simulation data with actual operation data of a wind field. Yangmang et al qualitatively analyzed the incidence relation between the wind speed and the power fluctuation series in wind power real-time prediction research based on probability distribution quantization index and grey correlation decision, and meanwhile selected the power fluctuation sequence and the grey correlation degree of the wind speed fluctuation sequence as decision variables to enter the decision, and the final predicted power is formed by combining the power obtained through the standard wind speed power curve of the fan and the power of the same wind speed section found by grey correlation decision analysis. However, the above research does not quantitatively analyze the influence of wind speed fluctuation on power prediction, and due to the inertia of the wind turbine itself in the process from receiving wind energy to converting wind energy into electric energy, a delay phenomenon exists between predicted power and actual power when the wind speed changes, especially continuously changes, so that the accuracy of power prediction is further reduced.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a short-term wind power prediction method based on a delay optimization strategy, and solves the problem that in the prior art, when the wind speed changes, the prediction accuracy is reduced due to delay between the predicted power and the actual power.
The technical scheme is as follows: the invention provides a short-term wind power prediction method based on a delay optimization strategy, which comprises the following steps:
(1) acquiring wind speed-power data: acquiring wind speed and power data in a specific time period by utilizing a wind measuring tower and a wind driven generator of a wind power plant according to a set time resolution to obtain sampling data;
(2) eliminating abnormal data in the sampled data to obtain normal sampled data, wherein the abnormal data comprises data which are detected at specific time points and error data;
(3) selecting continuous sampling data: in normal sampling data, selecting continuous N groups of sampling data without abnormality as continuous sampling data, wherein x groups of continuous data are used as training data, y groups of continuous data are used as prediction data, and x + y is equal to N;
(4) training a prediction model: training the prediction model by using training data, taking wind speed data as input and power data as output, so that the prediction model is suitable for a conversion rule from wind speed to power;
(5) and predicting power by using the trained prediction model: taking wind speed data in the data for prediction as input, and predicting through a prediction model to obtain predicted power;
(6) defining a delay function aiming at the continuously rising wind speed and correcting the power, wherein the delay function f (v) is related to the wind speed, v represents the wind speed, and v (t) represents the wind speed at the time t; according toCorrecting the power to obtain the corrected power PXWhereinRepresenting the predicted power.
Further, the prediction model may employ a bp neural network or an Xgboost algorithm model.
Further, the method comprises the following step (6):
(61) taking the data for prediction as a test set wind speed sequence, and performing EMD reconstruction to realize smooth processing on the data;
(62) selecting a wind speed continuous ascending section from the wind speed sequence reconstructed by the EDM, searching an extreme point of the wind speed sequence in the ascending section, and quantitatively describing the size and speed of wind speed change through an amplitude value and an included angle;
(63) data normalization: normalizing the amplitude and the included angle of the wind speed of the continuous rising section;
(64) constructing a delay function f (v) with the expression:
f(v)＝ωv3
ω＝-(αU+βθ)
wherein v is the wind speed of the continuous ascending section, omega is a correction coefficient, U and theta are the amplitude and the included angle of the wind speed of the ascending section after normalization, alpha and beta are proportionality factors between U and theta and the correction coefficient omega, and lambda and mu are respectively correlation coefficients between U and theta and the power prediction error;
(65) according to predicted powerAnd a delay function f (v) to obtain a corrected power PX：
Further, the step (63) includes:
calculating the difference between the predicted power and the actual power, i.e.Wherein the content of the first and second substances,to predict power, P is actual power;
selecting an amplitude set A of n wind speed rising sections as { U ═ U1,U1,...,UnAn included angle set B of n wind speed rising sections is { theta ═ theta1,θ1,...,θnPower error set Z ═ p of n wind speed rising segments1,p2,...,pnNormalizing the sets into a, b and z, and respectively calculating correlation coefficients lambda and mu between the sets a, b and z;
wherein,ΔPithe difference between the predicted power and the actual power is predicted for the ith point, m is the number of data points of the nth rising segment, pnIs the average of the power errors of the nth rising segment.
Further, in step (4), the number of data for training is larger than the number of data for prediction, that is, x > y.
Has the advantages that: compared with the prior art, the invention quantitatively defines the continuous fluctuation of the wind speed through two variables of the amplitude and the included angle, and analyzes the relationship between the wind speed rising section and the power delay in different degrees; the prediction error caused by the continuous rising of the wind speed is corrected by defining the delay function, so that the accuracy of power prediction is improved.
Drawings
FIG. 1 is a graph of up-down wind versus fitted power;
FIG. 2 is a flow chart of power prediction and correction;
FIG. 3 is a schematic view of the wind speed fluctuation rate;
FIG. 4 is a diagram of the EMD data smoothing process results;
FIG. 5 is a normalized index for different interval rise segments;
FIG. 6 is a comparative graph of the correction results.
Detailed Description
The invention is further described below with reference to the following figures and examples:
roughly dividing the wind speed into ascending wind and descending wind according to a method of the difference between the wind speed and the wind speed, and comparing the wind speed with a wind speed power curve fitted by a Bien method, wherein the actual power of the ascending wind is almost all below the fitted power curve, and the deviation degree is increased along with the rising of the wind speed as shown in figure 1; although part of the actual power of the downwind is also located above the fitted power curve, most of the data are close to the power curve, and as the wind speed increases, the phenomenon becomes more obvious, and even the actual power of the downwind is located below the curve. The wind power generation is affected differently by the rise and fall of the wind speed, and the correction method is different, and the invention only considers the influence of the continuous rise of the wind speed on the power prediction accuracy and corrects the influence.
The invention provides a short-term wind power prediction method based on a delay optimization strategy, the flow of which is shown in figure 2, and the method comprises the following steps:
(1) acquiring wind speed-power data: acquiring wind speed and power data in a specific time period by utilizing a wind measuring tower and a wind driven generator of a wind power plant according to a set time resolution to obtain sampling data; the wind speed and power data comprise cut-in wind speed, rated wind speed, cut-out wind speed, rated power and time resolution of the wind turbine.
(2) And eliminating abnormal data in the sampled data to obtain normal sampled data, wherein the abnormal data comprises data which are not detected at a certain moment and error data such as the wind speed and the power which are less than 0 or other data which are not consistent with common knowledge, caused by faults of a wind measuring tower and a wind driven generator collecting system or external factors.
(3) Selecting continuous sampling data: in normal sampling data, selecting continuous N groups of sampling data without abnormality as continuous sampling data, wherein x groups of continuous data are used as training data, y groups of continuous data are used as prediction data, and x + y is equal to N; in an embodiment of the invention, the number of data for training is larger than the number of data for prediction, i.e. x > y.
(4) Training a prediction model: training the prediction model by using training data, taking wind speed data as input and power data as output, so that the prediction model is suitable for a conversion rule from wind speed to power; the prediction model can adopt a bp neural network or an Xgboost algorithm model.
(5) And predicting power by using the trained prediction model: taking wind speed data in the data for prediction as input, predicting through the prediction model to obtain predicted power
(6) Defining a delay function aiming at the continuously rising wind speed and correcting the power, wherein the delay function f (v) is related to the wind speed, v represents the wind speed, and v (t) represents the wind speed at the time t;
(61) taking the data for prediction as a test set wind speed sequence, and performing EMD reconstruction to realize smooth processing on the data;
(62) selecting a wind speed continuous ascending section from the wind speed sequence reconstructed by the EDM, searching an extreme point of the wind speed sequence in the ascending section, and quantitatively describing the size and speed of the wind speed change through an amplitude value and an included angle, as shown in FIG. 3. Starting from the first data point, the extreme point of the wind speed sequence is found: if v (t) satisfies v (t-1) < v (t) and v (t) > v (t +1), v (t) is the maximum value point; if v (t) satisfies v (t-1) > v (t) and v (t) < v (t +1), v (t) is the minimum point. The amplitude U is the difference value between the wind speeds corresponding to the maximum value max and the minimum value min point, and the included angle theta is the included angle between the hypotenuse of the triangle drawn on the way and the horizontal axis. In order to better reflect and analyze the influence of the continuous rising of the wind speed on the power, after the wind speed sequence extreme point is identified, maximum values and minimum value points with reasonable intervals are selected to describe the continuous rising of the wind speed.
(63) Data normalization: the amplitude and the included angle of the wind speed of the continuous rising section are normalized by the following method:
calculating the difference between the predicted power and the actual power, i.e.Wherein the content of the first and second substances,to predict power, P is actual power;
selecting an amplitude set A of n wind speed rising sections as { U ═ U1,U1,...,UnAn included angle set B of n wind speed rising sections is { theta ═ theta1,θ1,...,θnPower error set Z ═ p of n wind speed rising segments1,p2,...,pnNormalizing the sets into a, b and z, and respectively calculating correlation coefficients lambda and mu between the sets a, b and z;
wherein,ΔPithe difference between the predicted power and the actual power is predicted for the ith point, m is the number of data points of the nth rising segment, pnIs the average of the power errors of the nth rising segment.
(64) Constructing a delay function f (v) with the expression:
f(v)＝ωv3 (1)
ω＝-(αU+βθ) (2)
wherein v is the wind speed of the continuous ascending section, omega is a correction coefficient, U and theta are the amplitude and the included angle of the wind speed of the ascending section after normalization, alpha and beta are proportionality factors between U and theta and the correction coefficient omega, and lambda and mu are respectively correlation coefficients between U and theta and the power prediction error;
(65) according to predicted powerAnd a delay function f (v) to obtain a corrected power PXThe expression is as follows:
in the embodiment of the invention, in order to explore the relationship among the amplitude, the included angle and the delay phenomenon, the Xgboost algorithm and the bp neural network algorithm are respectively used for preliminary prediction.
At present, the Xgboost algorithm is often used in a classification or regression problem, and in the training process, a plurality of classifiers are learned by changing the weight of a training sample, so that an optimal classifier is finally obtained. After each round of training is finished, the weight of the correctly classified training samples is reduced, the weight of the samples with wrong classification is increased, after multiple times of training, some training samples with wrong classification can get more attention, the weight of the correct training samples approaches to 0, a plurality of simple classifiers are obtained, and a final model is obtained by combining the classifiers. The objective function is:
where i denotes the ith sample,represents the prediction error of the ith sample, ΣkΩ(fk) A function representing the complexity of the tree.
The bp neural network is most widely and typically applied to short-term wind power prediction, has strong nonlinear mapping capability and high flexibility and is characterized by error back propagation.
A certain wind power plant is taken as a research object by Chongming from the sea, the wind power plant is positioned in the east Asia monsoon region, and 30 fans are provided in total. The cut-in wind speed of the fan is 3m/s, the rated wind speed is 12m/s, the cut-out wind speed is 25m/s, the rated power is 2MW, the time resolution is 5min, and data are derived from data collected by the anemometer tower and the wind driven generator in 9 months-2015 9 months in 2014. A 2000 series of data were extracted from fan 2014 in 9 months to 2015 in 9 months and one year, with 70% used as training and 30% used as testing.
For the fluctuating wind speed sequence, to better identify the extreme points, the data is smoothed by EMD, and the smoothing result is shown in fig. 4. It can be seen that the mutation point of the wind speed sequence reconstructed by EMD is better captured, that is, the extreme point of the continuous change of the wind speed is better identified, the reconstructed wind speed sequence keeps the characteristics of the original sequence, and the reconstructed sequence can be used for identifying the extreme point.
After the reconstructed wind speed sequence is identified by extreme points, four ascending sections with different degrees, namely, the number epsilon of interval data among the extreme points is more than or equal to 1, the epsilon is more than or equal to 2, the epsilon is more than or equal to 3, and the epsilon is more than or equal to 4, are respectively selected for selecting the continuous ascending sequence with reasonable interval length, and the ascending sections are determined according to the correlation. Fig. 5 is a line graph of the included angle, amplitude and power of 4 kinds of ascending segments, and in order to more clearly illustrate the correlation between the included angle, amplitude and power of the ascending segments at different intervals, the corresponding correlation coefficients are shown in table 1.
TABLE 1 correlation coefficient of ascending segments at different intervals
As can be seen from table 1, the correlation coefficient increases as the interval between rise data increases, but there is a problem that the interval increases and the number of rises required becomes smaller. Therefore, the number of data intervals between extreme points of the ascending section and the number of the ascending sections are comprehensively considered, a wind speed section in which 5 or more data points continuously ascend (i.e. an ascending section with epsilon larger than or equal to 3) is selected as a continuous ascending wind speed section, and the amplitude U and the included angle theta of the 5 qualified ascending sections in fig. 4 are obtained as shown in table 2:
TABLE 2 fluctuation of wind speed in the ascending section
The set A, B, Z is normalized to obtain sets a, b, and z, and the correlation coefficients between the set a and the set z, and between the set b and the set z are obtained, and the results are shown in table 3:
TABLE 3 variable normalization
Since both the amplitude and the angle have a certain correlation with the power delay error, it is feasible to define the correction factor ω with these two variables. Wherein alpha and beta in the formula (2) are set according to the correlation coefficient of the amplitude and the included angle, and the values of the alpha and the beta are calculated by the formula (3). In this example, α is 0.63 and β is 0.37.
Aiming at the delay phenomenon of the prediction result of the wind speed sequence at the ascending segment, a delay function is provided to correct the prediction result, and in order to avoid the contingency, the prediction results of the 2 prediction methods of the Xgboost neural network and the bp neural network are respectively corrected, and the results are shown in FIG. 6.
Fig. 6 shows that the power correction for the ascending section has a certain effect, and most of data points are more fit with the actual curve than before correction, but there is a problem that the power corresponding to the extreme point of the wind speed change does not achieve a good correction effect, and a reasonable guess about this problem is an influence caused by the own regulation strategy of the fan when dealing with the sudden change of the wind speed, and the latter research can use this as an entry point. To more clearly illustrate the effect after the delay correction, MAE and RMSE were used as evaluation indexes of the correction result, and compared with those before the correction, the results are shown in table 4.
TABLE 4 error comparison
It can be seen that, no matter what method and what error index, the power corrected by the delay correction function is greatly improved in accuracy compared with the original predicted power, wherein the average absolute error (MAE) reflects the amplitude of the predicted error, and the Root Mean Square Error (RMSE) reflects the dispersion degree of the error.
Claims (5)
1. A short-term wind power prediction method based on a delay optimization strategy is characterized by comprising the following steps:
(1) acquiring wind speed-power data: acquiring wind speed and power data in a specific time period by utilizing a wind measuring tower and a wind driven generator of a wind power plant according to a set time resolution to obtain sampling data;
(2) rejecting abnormal data in the sampled data to obtain normal sampled data, wherein the abnormal data comprises data which are detected at specific time points and error data;
(3) selecting continuous sampling data: in normal sampling data, selecting continuous N groups of sampling data without abnormality as continuous sampling data, wherein x groups of continuous data are used as training data, y groups of continuous data are used as prediction data, and x + y is equal to N;
(4) training a prediction model: training a model by using the training data, taking wind speed data as input and power data as output, and training a prediction model to adapt to a conversion rule from wind speed to power;
(5) and predicting power by using the trained prediction model: taking wind speed data in the data for prediction as input, and predicting through the prediction model to obtain predicted power;
(6) defining a delay function for the continuously rising wind speed and correcting the power, wherein the delay function f (v) is related to the wind speed, v represents the wind speed, and v (t) represents the wind speed at the time t; according toCorrecting the power to obtain the corrected power PX, wherein Representing the predicted power.
2. The short-term wind power prediction method according to claim 1, characterized in that the prediction model can adopt a bp neural network or an Xgboost algorithm model.
3. The short-term wind power prediction method according to claim 1, characterized in that said step (6) comprises:
(61) taking the data for prediction as a test set wind speed sequence, and performing EMD reconstruction to realize smooth processing on the data;
(62) selecting a wind speed continuous ascending section from the wind speed sequence reconstructed by the EDM, searching an extreme point of the wind speed sequence in the ascending section, and quantitatively describing the size and speed of wind speed change through an amplitude value and an included angle;
(63) data normalization: normalizing the amplitude and the included angle of the wind speed of the continuous rising section;
(64) constructing a delay function f (v) with the expression:
f(v)＝ωv3
ω＝-(αU+βθ)
wherein v is the wind speed of the continuous ascending section, omega is a correction coefficient, U and theta are the amplitude and the included angle of the wind speed of the ascending section after normalization, alpha and beta are proportionality factors between U and theta and the correction coefficient omega, and lambda and mu are respectively correlation coefficients between U and theta and the power prediction error;
(65) according to predicted powerAnd a delay function f (v) to obtain a corrected power PX：
4. The short term wind power prediction method according to claim 3, characterized in that said step (63) comprises:
calculating the difference between the predicted power and the actual power, i.e. wherein ,to predict power, P is actual power;
n pieces to be sorted outAmplitude set A ═ U of wind speed rising section1,U1,...,UnAn included angle set B of n wind speed rising sections is { theta ═ theta1,θ1,...,θnPower error set Z ═ p of n wind speed rising segments1,p2,...,pnNormalizing the sets into a, b and z, and respectively calculating correlation coefficients lambda and mu between the sets a, b and z;
wherein ,ΔPithe difference between the predicted power and the actual power is predicted for the ith point, m is the number of data points of the nth rising segment, pnIs the average of the power errors of the nth rising segment.
5. The short-term wind power prediction method according to claim 1, characterized in that in step (4), the number of training data is greater than the number of prediction data, i.e. x > y.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910732490.7A CN110365053B (en) | 2019-08-09 | 2019-08-09 | Short-term wind power prediction method based on delay optimization strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910732490.7A CN110365053B (en) | 2019-08-09 | 2019-08-09 | Short-term wind power prediction method based on delay optimization strategy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110365053A true CN110365053A (en) | 2019-10-22 |
| CN110365053B CN110365053B (en) | 2023-04-25 |
Family
ID=68223504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910732490.7A Active CN110365053B (en) | 2019-08-09 | 2019-08-09 | Short-term wind power prediction method based on delay optimization strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110365053B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414354A (en) * | 2020-03-12 | 2020-07-14 | 广西电网有限责任公司 | Wind power plant data processing method and device and computer readable storage medium |
| CN111476402A (en) * | 2020-03-16 | 2020-07-31 | 云南电网有限责任公司 | Wind power generation capacity prediction method coupling meteorological information and EMD technology |
| CN116317169A (en) * | 2023-05-17 | 2023-06-23 | 三峡智控科技有限公司 | Remote intelligent comparison platform and method for wind power prediction system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496927A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Wind power station power projection method based on error statistics modification |
| CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
| CN108092319A (en) * | 2017-12-13 | 2018-05-29 | 国家电网公司 | A kind of Uncertainty Analysis Method and device of short-term wind-electricity power prediction |
| 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 |
-
2019
- 2019-08-09 CN CN201910732490.7A patent/CN110365053B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496927A (en) * | 2011-12-16 | 2012-06-13 | 中国电力科学研究院 | Wind power station power projection method based on error statistics modification |
| CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
| CN108092319A (en) * | 2017-12-13 | 2018-05-29 | 国家电网公司 | A kind of Uncertainty Analysis Method and device of short-term wind-electricity power prediction |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 叶小岭等: "基于小波分析和PSO优化神经网络的短期风电功率预测", 《可再生能源》 * |
| 叶小岭等: "基于风速升降特征的短期风电功率预测", 《电力系统保护与控制》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414354A (en) * | 2020-03-12 | 2020-07-14 | 广西电网有限责任公司 | Wind power plant data processing method and device and computer readable storage medium |
| CN111476402A (en) * | 2020-03-16 | 2020-07-31 | 云南电网有限责任公司 | Wind power generation capacity prediction method coupling meteorological information and EMD technology |
| CN116317169A (en) * | 2023-05-17 | 2023-06-23 | 三峡智控科技有限公司 | Remote intelligent comparison platform and method for wind power prediction system |
| CN116317169B (en) * | 2023-05-17 | 2023-08-04 | 三峡智控科技有限公司 | Remote intelligent comparison platform and method for wind power prediction system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110365053B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109802430B (en) | Wind power grid control method based on LSTM-Attention network | |
| CN106447098B (en) | Photovoltaic ultra-short-term power prediction method and device | |
| CN111369070B (en) | Multimode fusion photovoltaic power prediction method based on envelope clustering | |
| CN110365053A (en) | Short-term wind power forecast method based on delay optimisation strategy | |
| CN111488896A (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN110601250B (en) | Method for evaluating stability of static voltage of access point based on new energy power station | |
| CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
| CN114004139A (en) | Photovoltaic power generation power prediction method | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| CN114792156A (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN112580874A (en) | Short-term wind power prediction method based on random forest algorithm and TCN | |
| CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| CN113505938A (en) | Ultra-short-term wind power combined prediction method and system | |
| CN114399081A (en) | Photovoltaic power generation power prediction method based on weather classification | |
| CN109767353B (en) | Photovoltaic power generation power prediction method based on probability distribution function | |
| CN113659630B (en) | Wind power plant power optimal scheduling method and system based on fatigue damage value estimation | |
| CN112598148A (en) | Fan variable pitch motor temperature fault early warning method based on collaborative expression and LightGBM algorithm | |
| CN111553400A (en) | Accurate diagnosis method for vibration fault of wind generating set | |
| CN111242371A (en) | Photovoltaic power generation short-term prediction correction method based on non-iterative multi-model | |
| CN114281846B (en) | New energy power generation prediction method based on machine learning | |
| CN115577854A (en) | Quantile regression wind speed interval prediction method based on EEMD-RBF combination | |
| CN112329987A (en) | Short-term wind power plant power prediction method based on Adaboost-EMD-SVM | |
| CN111178601B (en) | Wind turbine generator power prediction method based on meteorological data post-processing | |
| CN113505909A (en) | Error compensation method for short-term wind power trend prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |