CN103617464A - Device for ultra-short-period predication of wind power and predication method - Google Patents
Device for ultra-short-period predication of wind power and predication method Download PDFInfo
- Publication number
- CN103617464A CN103617464A CN201310671431.6A CN201310671431A CN103617464A CN 103617464 A CN103617464 A CN 103617464A CN 201310671431 A CN201310671431 A CN 201310671431A CN 103617464 A CN103617464 A CN 103617464A
- Authority
- CN
- China
- Prior art keywords
- wind power
- ultra
- short term
- short
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a device for ultra-short-period predication of wind power. The device comprises a first unit, a second unit, a third unit and a fourth unit, wherein the first unit is used for collecting an actual observation value of the wind power and a short-period predication value of the wind power; the second unit is used for obtaining an ultra-short-period predication value of the wind power by adopting a preset ultra-short-period predication model of the wind power according to the actual observation value of the wind power and the short-period predication value of the wind power; the third unit is used for determining an optimal ultra-short-period predication model of the wind power according to the ultra-short-period predication value of the wind power; the fourth unit is used for carrying out ultra-short-period predication on the wind power according to the actual observation value of the wind power, the short-period predication value of the wind power and the optimal ultra-short-period predication model of the wind power. The invention also discloses a method for the ultra-short-period predication of the wind power. The device and the method disclosed by the invention have the advantages that as the factors such as change of weather elements and the continuity of the wind power are mainly considered, the ultra-short-period predication value of the wind power is relatively accurate.
Description
Technical field
The present invention relates to electric system prediction and control technology field, specifically, relate to a kind of device and Forecasting Methodology of the prediction of the ultra-short term for wind power.
Background technology
Under the extensive grid-connected background of wind-powered electricity generation, due to undulatory property and the randomness that wind-powered electricity generation has, bring huge challenge to traditional safely and steadily running of electric system.Wind power prediction technology is the important means that help addresses this problem, and wherein, the prediction of the ultra-short term of wind power is generally considered to be the necessary support technology of electrical network Real-Time Scheduling.According to China's electric power energy structure and scheduling level, the time scale of the ultra-short term of wind power prediction is generally following 4 hours, and predicted time resolution is 15 minutes.
The device of the existing ultra-short term for wind power prediction and Forecasting Methodology be less to the combined influence research of the ultra-short term predicted value of wind power for the variation of the Weather Elements of the variation of Weather Elements and the continuity of wind power, makes the error of ultra-short term predicted value of wind power larger.
For weather, want the variation of key element, can be provided by wind power short-term forecasting result.For the continuity of wind power, can be by current measured power as reference.The short-term forecasting value of wind power can be obtained by prior aries such as Mesoscale Simulation system, small scale meteorologic model, generated energy computation model and error correction statistical models.
Summary of the invention
Technical matters to be solved by this invention be the device of the existing ultra-short term for wind power prediction for the variation of the Weather Elements of the variation of Weather Elements and the continuity of wind power less to the combined influence research of the ultra-short term predicted value of wind power, make the error of ultra-short term predicted value of wind power larger.
Technical scheme of the present invention is as follows:
A device of predicting for the ultra-short term of wind power, comprising: first module, for gathering the short-term forecasting value of actual observed value and the wind power of wind power; Second unit, for being obtained the ultra-short term predicted value of wind power by the ultra-short term forecast model of the wind power of presetting according to the short-term forecasting value of the actual observed value of described wind power and described wind power; Unit the 3rd, for determining the ultra-short term forecast model of optimum wind power according to the ultra-short term predicted value of described wind power; Unit the 4th, for carrying out the ultra-short term prediction of wind power according to the ultra-short term forecast model of the wind power of the actual observed value of described wind power, the short-term forecasting value of described wind power, described optimum.
Further, described first module comprises: the first module, and for from initial time t
istart to gather at the same time the actual observed value r of m wind power constantly
e, m, e and i are positive integer, i=1, and 2 ..., m-n; E=1,2 ..., m; With, the second module, for from initial time t
istart to gather at the same time the short-term forecasting value p of m-1 wind power
j, j=i+1, i+2 ..., i+n, n is positive integer, n < m; Wherein, the actual observed value r of m wind power constantly
eshort-term forecasting value p with m-1 wind power
jthe time interval identical.
Further: the ultra-short term forecast model by described default wind power obtains initial time t
ithe ultra-short term predicted value of rear n wind power constantly, the ultra-short term forecast model of described default wind power is k, and k is positive integer, and k>=20 obtain the ultra-short term predicted value that k organizes wind power altogether
Further: when affecting the short-term forecasting value that the factor of the ultra-short term forecast model of wind power is actual observed value and the wind power of wind power, the ultra-short term forecast model of described default wind power is
Wherein, y
rfor weight coefficient.
Further: when k is 1, the y in the ultra-short term forecast model of the 1st group of default wind power
rfor first term is
tolerance is
the arithmetic progression that successively decreases; When k is 2,3 ... time, k organizes the y in the ultra-short term predictive equation of default wind power
rfor first term is
tolerance is
the arithmetic progression that successively decreases.
Further: when to affect the factor of the ultra-short term forecast model of wind power be the actual observed value of wind power,, the short-term forecasting value of wind power and other factors, the ultra-short term forecast model of default wind power is
Wherein, y
rand y
pfor weight coefficient.
Further: when k is 1,2,3 ... time, suppose that k organizes the y in the ultra-short term forecast model of default wind power
rand y
pequate, work as y
r+ y
p>=1 o'clock, y
p=1-y
r,
work as y
r+ y
pduring < 1, y
p=y
r,
Further: described Unit the 3rd is for comparing the mean square of error root sum of the ultra-short term predicted value of k group wind power, and the ultra-short term forecast model of one group of default wind power of the root mean square sum minimum of Select Error is as the ultra-short term forecast model of optimum wind power.
Further: described Unit the 3rd comprises: the 3rd module and four module; Described the 3rd module is for calculating
obtain the error of the ultra-short term predicted value of each wind power
the error of the ultra-short term predicted value of the wind power that the ultra-short term forecast model of k default wind power is obtained
after, by calculating
Obtain the root mean square { ERR of k grouping error
1, ERR
2..., ERR
n, wherein f is positive integer, f=1, and 2 ..., n; By the root mean square summation of every grouping error
the root mean square sum that compares k grouping error
described the second module is used for mean square of error root sum
the y that the minimum corresponding tolerance of a group obtains
rand y
p, as optimal weights coefficient, obtain the ultra-short term predictive equation of optimum wind power.
The ultra-short term Forecasting Methodology that another technical matters to be solved by this invention is existing wind power is less to the combined influence research of the ultra-short term predicted value of wind power for the variation of the Weather Elements of the variation of Weather Elements and the continuity of wind power, makes the error of ultra-short term predicted value of wind power larger.
Another technical scheme of the present invention is as follows:
A ultra-short term Forecasting Methodology for wind power, comprising: gather the actual observed value of wind power and the short-term forecasting value of wind power; According to the short-term forecasting value of the actual observed value of described wind power and described wind power, by the ultra-short term forecast model of the wind power of presetting, obtained the ultra-short term predicted value of wind power; According to the ultra-short term predicted value of described wind power, determine the ultra-short term forecast model of optimum wind power; According to the ultra-short term forecast model of the wind power of described optimum, carry out the ultra-short term prediction of wind power.
Technique effect of the present invention is as follows:
The device of the prediction of the ultra-short term for wind power of some optional embodiments of the present invention and the variation that Forecasting Methodology is mainly considered Weather Elements and the continuity factor of wind power, for weather, want the variation of key element, by wind power short-term forecasting result, provided, and the continuity of wind power by current measured power as reference, the ultra-short term predicted value of wind power is the weighted mean of short-term forecasting result and current real power, makes the ultra-short term predicted value of the wind power that obtains comparatively accurate.
Accompanying drawing explanation
Fig. 1 is the structural representation of device one preferred embodiment of the prediction of the ultra-short term for wind power of the present invention;
Fig. 2 is the comparison diagram of the root mean square error of one embodiment of the present invention.
Embodiment
As shown in Figure 1, be the structural representation of device one preferred embodiment of the ultra-short term for wind power of the present invention prediction.
The device of the prediction of the ultra-short term for wind power of the present invention, comprises as lower unit:
First module 101, for gathering the short-term forecasting value of actual observed value and the wind power of wind power, and is delivered to second unit 102 and the 4th unit 104 by the short-term forecasting value of the actual observed value of wind power and wind power.First module 101 comprises: the first module and the second module.
Second unit 102, for receiving the short-term forecasting value of actual observed value and the wind power of wind power, according to the short-term forecasting value of the actual observed value of wind power and wind power, by the ultra-short term forecast model of the wind power of presetting, obtained the ultra-short term predicted value of wind power, and the ultra-short term predicted value of wind power is delivered to the 3rd unit 103.
The 3rd unit 103, for receiving the ultra-short term predicted value of wind power, and determines the ultra-short term forecast model of optimum wind power, and the ultra-short term forecast model of optimum wind power is delivered to the 4th unit 104 according to the ultra-short term predicted value of wind power.Unit the 3rd comprises: the 3rd module and four module,
The 4th unit 104, for receiving the ultra-short term forecast model of optimum wind power, and receive the actual observed value of wind power and the short-term forecasting value of wind power that first module 101 is transmitted, according to the ultra-short term forecast model of the wind power of the short-term forecasting value of the actual observed value of wind power, wind power, optimum, carry out the ultra-short term prediction of wind power.
The step of the ultra-short term Forecasting Methodology of the wind power of the preferred embodiments of the present invention of employing said apparatus is as follows:
Step S1: gather the actual observed value of wind power and the short-term forecasting value of wind power.
The actual observed value that gathers wind power by the first module, detailed process is:
From initial time t
istart to gather at the same time the actual observed value r of m wind power constantly
e, m, e and i are positive integer, i=1, and 2 ..., m-n; E=1,2 ..., m.The time interval gathering is preferably 15min.
The short-term forecasting value that gathers wind power by the second module, detailed process is:
From initial time t
istart to gather at the same time the short-term forecasting value p of m-1 wind power
j, j=i+1, i+2 ..., i+n, n is positive integer, n < m.The time interval gathering is identical with the time interval of the actual observed value of wind power, is preferably 15min.
Step S2: obtained the ultra-short term predicted value of wind power according to the short-term forecasting value of the actual observed value of wind power and wind power by the ultra-short term forecast model of the wind power of presetting.
Ultra-short term forecast model by the wind power of presetting obtains initial time t
ithe ultra-short term predicted value of rear n wind power constantly, the ultra-short term forecast model of default wind power is k, k is positive integer, obtains altogether the ultra-short term predicted value of k group wind power
Detailed process is as follows:
The difference of the factor of considering according to reality, the ultra-short term forecast model of default wind power has two kinds of situations.
(A) when affecting the factor of the ultra-short term prediction of wind power, be the short-term forecasting value of actual observed value and the wind power of wind power, the ultra-short term forecast model of default wind power is
wherein, y
rand y
pfor weight coefficient.
Step 201A: when k is 1, obtain first group of wind power ultra-short term predicted value according to the ultra-short term forecast model of first default wind power
When k is 1, the y in the ultra-short term forecast model of the wind power that first is default
rfor first term is
tolerance is
the arithmetic progression that successively decreases, i.e. y
rfor
When i is 1, the first moment t
1the actual observed value of wind power be r
1, the short-term forecasting value of wind power is p
j, j=i+1, i+2 ..., i+n.Ultra-short term forecast model by the wind power of presetting obtains the first moment t
1the ultra-short term predicted value of later n wind power constantly, is respectively:
……,
When i is 2, the second moment t
2the actual observed value of wind power be r
2, the short-term forecasting value of wind power is p
j, j=i+1, i+2 ..., i+n.Ultra-short term forecast model by the wind power of presetting obtains the second moment t
2the ultra-short term predicted value of later n wind power constantly, is respectively:
……,
Repeat above-mentioned process until i is m-n, when m-n actual observed value is constantly r
m-n, the short-term forecasting value of wind power is p
j, j=i+1, i+2 ..., i+n.Ultra-short term forecast model by the wind power of presetting obtains the second moment t
2the ultra-short term predicted value of later n wind power constantly, is respectively:
……,
Step 202A: when k is 2,3 ... time, k organizes the y in the ultra-short term forecast model of default wind power
rfor first term is
tolerance is
the arithmetic progression that successively decreases, i.e. y
rfor
Repeating step 201A, obtains being carved into the ultra-short term predicted value of m-n wind power constantly at first o'clock, amounts to k group.
(B) when to affect the factor of the ultra-short term forecast model of wind power be the actual observed value of wind power, the short-term forecasting value of wind power and other factors, the ultra-short term forecast model of default wind power is
Wherein, y
rand y
pfor weight coefficient.
(B) process of the calculating in is identical with the process in (A).But, y
rand y
pthereby can have along with the difference of value different expression formulas makes the ultra-short term forecast model of default wind power different, specific as follows:
Suppose the y in the ultra-short term forecast model of default wind power
rand y
pequate,
Work as y
r+ y
p>=1 o'clock, y
p=1-y
r,
Work as y
r+ y
pduring < 1, y
p=y
r,
Therefore, when to affect the factor of the ultra-short term forecast model of wind power be the actual observed value of wind power, when the short-term forecasting value of wind power and other factors, need first to y
rand y
pjudge, could determine the ultra-short term forecast model that adopts which kind of default wind power.Factor the short-term forecasting value of the actual observed value except wind power that " other factors " refers to and wind power.After determining the ultra-short term forecast model of default wind power, obtaining successively k group initial time t
ithe ultra-short term predicted value of rear n wind power constantly
Step S3: the ultra-short term forecast model of being determined optimum wind power by the ultra-short term predicted value of wind power.
By the 3rd unit 103, determine the ultra-short term forecast model of optimum wind power, the 3rd module is for the mean square of error root sum of the ultra-short term predicted value of k group wind power relatively, and four module is the ultra-short term forecast model as optimum wind power for the ultra-short term forecast model of one group of default wind power of the root mean square sum minimum of Select Error.Specific as follows:
Step S301: the error that obtains the ultra-short term predicted value of each wind power according to formula (1)
……,
……,
……
……,
Step S302: the error of the ultra-short term predicted value of the wind power that the ultra-short term forecast model of k default wind power is obtained
substitution formula (2) obtains the root mean square { ERR of k grouping error
1, ERR
2..., ERR
n,
Specific as follows:
……,
Step S305: by mean square of error root sum
the y that the minimum corresponding tolerance of a group obtains
rand y
p, as optimal weights coefficient, obtain the ultra-short term predictive equation of optimum wind power.
Step S4: the ultra-short term that is carried out wind power by the ultra-short term forecast model of optimum wind power is predicted.
The ultra-short term that carries out wind power by the 4th unit 104 is predicted, specific as follows:
According to the short-term forecasting value of the actual observed value of the ultra-short term predictive equation of optimum wind power, wind power and wind power, just can obtain the ultra-short term predicted value of a certain moment wind power.
With specific embodiment, the present invention is further illustrated below.
Embodiment 1
Adopt apparatus and method of the present invention to obtain the ultra-short term predicted value of wind power.
When affecting the factor of the ultra-short term prediction of wind power, be the short-term forecasting value of actual observed value and the wind power of wind power, the ultra-short term predictive equation of wind power is
the time interval is 15min, and the time scale of ultra-short term prediction is following 4 hours, wherein, m=16, n=240, k=40, the root mean square error before obtaining adopting apparatus and method of the present invention to adjust and after adjusting, as shown in table 1.As shown in Figure 1, be the comparison diagram of the root mean square error of one embodiment of the present invention.From table 1 and Fig. 1, can find out, adopt root-mean-square error after method adjustment of the present invention little compared with the error that does not adopt method of the present invention to adjust, show method of the present invention record in advance more accurately, rationally reliable.
Table 1 do not adopt the device of device of the present invention, method and employing method of the present invention, the error ratio of method prediction
Claims (10)
1. a device of predicting for the ultra-short term of wind power, is characterized in that, comprising:
First module, for gathering the short-term forecasting value of actual observed value and the wind power of wind power;
Second unit, for being obtained the ultra-short term predicted value of wind power by the ultra-short term forecast model of the wind power of presetting according to the short-term forecasting value of the actual observed value of described wind power and described wind power;
Unit the 3rd, for determining the ultra-short term forecast model of optimum wind power according to the ultra-short term predicted value of described wind power;
Unit the 4th, for carrying out the ultra-short term prediction of wind power according to the ultra-short term forecast model of the wind power of the actual observed value of described wind power, the short-term forecasting value of described wind power, described optimum.
2. the device of the prediction of the ultra-short term for wind power as claimed in claim 1, is characterized in that, described first module comprises:
The first module, for from initial time t
istart to gather at the same time the actual observed value r of m wind power constantly
e, m, e and i are positive integer, i=1, and 2 ..., m-n; E=1,2 ..., m; With,
The second module, for starting to gather at the same time the short-term forecasting value p of m-1 wind power from initial time ti
j, j=i+1, i+2 ..., i+n, n is positive integer, n < m;
Wherein, the actual observed value r of m wind power constantly
eshort-term forecasting value p with m-1 wind power
jthe time interval identical.
3. the device of the ultra-short term for wind power as claimed in claim 2 prediction, is characterized in that, by the ultra-short term forecast model of described default wind power, obtains initial time t
ithe ultra-short term predicted value of rear n wind power constantly, the ultra-short term forecast model of described default wind power is k, and k is positive integer, and k>=20 obtain the ultra-short term predicted value that k organizes wind power altogether
4. the device that the ultra-short term for wind power as claimed in claim 3 is predicted, it is characterized in that: when affecting the short-term forecasting value that the factor of the ultra-short term forecast model of wind power is actual observed value and the wind power of wind power, the ultra-short term forecast model of described default wind power is
Wherein, y
rfor weight coefficient.
5. the device that the ultra-short term for wind power as claimed in claim 4 is predicted, is characterized in that:
When k is 1, the y in the ultra-short term forecast model of the 1st group of default wind power
rfor first term is
tolerance is
the arithmetic progression that successively decreases;
6. the device that the ultra-short term for wind power as claimed in claim 3 is predicted, it is characterized in that: when to affect the factor of the ultra-short term forecast model of wind power be the actual observed value of wind power,, the short-term forecasting value of wind power and other factors, the ultra-short term forecast model of default wind power is
Wherein, y
rand y
pfor weight coefficient.
7. the device that the ultra-short term for wind power as claimed in claim 6 is predicted, is characterized in that: when k is 1,2,3 ... time, suppose that k organizes the y in the ultra-short term forecast model of default wind power
rand y
pequate,
Work as y
r+ y
p>=1 o'clock, y
p=1-y
r,
Work as y
r+ y
pduring < 1, y
p=y
r,
8. the device that the ultra-short term for wind power as described in claim 5 or 7 is predicted, it is characterized in that, described Unit the 3rd is for comparing the mean square of error root sum of the ultra-short term predicted value of k group wind power, and the ultra-short term forecast model of one group of default wind power of the root mean square sum minimum of Select Error is as the ultra-short term forecast model of optimum wind power.
9. the device that the ultra-short term for wind power as claimed in claim 8 is predicted, is characterized in that:
Described Unit the 3rd comprises: the 3rd module and four module;
Described the 3rd module is for calculating
obtain the error of the ultra-short term predicted value of each wind power
The error of the ultra-short term predicted value of the wind power that the ultra-short term forecast model of k default wind power is obtained
after, by calculating
By the root mean square summation of every grouping error
The root mean square sum that compares k grouping error
10. a ultra-short term Forecasting Methodology for wind power, is characterized in that, comprising:
Gather the actual observed value of wind power and the short-term forecasting value of wind power;
According to the short-term forecasting value of the actual observed value of described wind power and described wind power, by the ultra-short term forecast model of the wind power of presetting, obtained the ultra-short term predicted value of wind power;
According to the ultra-short term predicted value of described wind power, determine the ultra-short term forecast model of optimum wind power;
According to the ultra-short term forecast model of the wind power of described optimum, carry out the ultra-short term prediction of wind power.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310671431.6A CN103617464B (en) | 2013-12-10 | 2013-12-10 | The device predicted for the ultra-short term of wind power and Forecasting Methodology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310671431.6A CN103617464B (en) | 2013-12-10 | 2013-12-10 | The device predicted for the ultra-short term of wind power and Forecasting Methodology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103617464A true CN103617464A (en) | 2014-03-05 |
CN103617464B CN103617464B (en) | 2016-08-17 |
Family
ID=50168168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310671431.6A Active CN103617464B (en) | 2013-12-10 | 2013-12-10 | The device predicted for the ultra-short term of wind power and Forecasting Methodology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103617464B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334847A (en) * | 2019-05-24 | 2019-10-15 | 广东智造能源科技研究有限公司 | Based on the wind power prediction method for improving K-means cluster and support vector machines |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102102626A (en) * | 2011-01-30 | 2011-06-22 | 华北电力大学 | Method for forecasting short-term power in wind power station |
CN102570453A (en) * | 2012-01-06 | 2012-07-11 | 甘肃省电力公司风电技术中心 | Short-term wind power prediction method and system based on multiple numerical weather prediction sources |
CN102938093A (en) * | 2012-10-18 | 2013-02-20 | 安徽工程大学 | Wind power forecasting method |
CN103065049A (en) * | 2012-12-28 | 2013-04-24 | 东北电力大学 | Real-time prediction and calculation method of wind power and based on coif5 small wave real-time decomposition |
CN103117546A (en) * | 2013-02-28 | 2013-05-22 | 武汉大学 | Ultrashort-term slide prediction method for wind power |
CN103280800A (en) * | 2013-05-27 | 2013-09-04 | 东南大学 | Method for forecasting super-short period wind power based on nonlinear fitting |
CN103390902A (en) * | 2013-06-04 | 2013-11-13 | 国家电网公司 | Photovoltaic power station super short term power prediction method based on least square method |
-
2013
- 2013-12-10 CN CN201310671431.6A patent/CN103617464B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102102626A (en) * | 2011-01-30 | 2011-06-22 | 华北电力大学 | Method for forecasting short-term power in wind power station |
CN102570453A (en) * | 2012-01-06 | 2012-07-11 | 甘肃省电力公司风电技术中心 | Short-term wind power prediction method and system based on multiple numerical weather prediction sources |
CN102938093A (en) * | 2012-10-18 | 2013-02-20 | 安徽工程大学 | Wind power forecasting method |
CN103065049A (en) * | 2012-12-28 | 2013-04-24 | 东北电力大学 | Real-time prediction and calculation method of wind power and based on coif5 small wave real-time decomposition |
CN103117546A (en) * | 2013-02-28 | 2013-05-22 | 武汉大学 | Ultrashort-term slide prediction method for wind power |
CN103280800A (en) * | 2013-05-27 | 2013-09-04 | 东南大学 | Method for forecasting super-short period wind power based on nonlinear fitting |
CN103390902A (en) * | 2013-06-04 | 2013-11-13 | 国家电网公司 | Photovoltaic power station super short term power prediction method based on least square method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334847A (en) * | 2019-05-24 | 2019-10-15 | 广东智造能源科技研究有限公司 | Based on the wind power prediction method for improving K-means cluster and support vector machines |
Also Published As
Publication number | Publication date |
---|---|
CN103617464B (en) | 2016-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10740512B2 (en) | System for tuning a photovoltaic power generation plant forecast with the aid of a digital computer | |
CN103279804B (en) | The Forecasting Methodology of super short-period wind power | |
WO2017054537A1 (en) | Long-time scale photovoltaic output time sequence modelling method and apparatus | |
JP5886407B1 (en) | Prediction device | |
CN102945508B (en) | Model correction based wind power forecasting method | |
CN103927695A (en) | Ultra-short-term wind power prediction method based on self-learning composite data source | |
JP5957372B2 (en) | Solar radiation amount calculation method and supply power determination method | |
Yang et al. | A novel ARX-based multi-scale spatio-temporal solar power forecast model | |
JP2016136001A (en) | Prediction device | |
JP5989754B2 (en) | Prediction device | |
CN103208037B (en) | A kind of power forecasting method based on on-line correction being applied to new energy power station | |
CN104319807A (en) | Method for obtaining multiple-wind farm capacity credit based on Copula function | |
WO2014203431A1 (en) | Prediction system, prediction device, and prediction method | |
CN103996073A (en) | Photometric-network real-time-correction self-learning ARMA model photovoltaic power prediction method | |
CN109150100A (en) | Fault detection method, device, equipment and the storage medium of photovoltaic plant | |
CN105512760A (en) | Neural network-based calculation method and calculation system for calculating power-generating capacity of photovoltaic station | |
CN103996079A (en) | Wind power weighting predication method based on conditional probability | |
CN102664409B (en) | Real-time prediction calculation method based on measured data for wind power of wind power station | |
KR20200040448A (en) | Apparatus and method for predicting solar energy generation amount | |
CN104091077A (en) | Combined force output simulation method of wind power plant and photovoltaic power station | |
CN103984986A (en) | Method for correcting wind power ultra-short-period prediction of self-learning ARMA model in real time | |
CN103927597A (en) | Ultra-short-term wind power prediction method based on autoregression moving average model | |
CN103984988A (en) | Method for correcting super-short-term prediction of photovoltaic power of ARMA module in real time through light metering network | |
CN104200067A (en) | Method and device for determining wind speed probability distribution and method for evaluating power of wind power system | |
CN103617464A (en) | Device for ultra-short-period predication of wind power and predication method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C41 | Transfer of patent application or patent right or utility model | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20160226 Address after: 100083, No. 14, Nanjing Ning building, No. 35, Haidian District, Beijing, Xueyuan Road, China, 1410-007 Applicant after: Northern Great Wind Power Technology (Beijing) Co., Ltd. Address before: 100871 Beijing Haidian District the Summer Palace 5 class 06 Physics Institute graduate dormitory Applicant before: Qian Shengli |
|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |