CN106709587A - Direct radiation prediction method based on conventional weather forecast - Google Patents
Direct radiation prediction method based on conventional weather forecast Download PDFInfo
- Publication number
- CN106709587A CN106709587A CN201510777557.0A CN201510777557A CN106709587A CN 106709587 A CN106709587 A CN 106709587A CN 201510777557 A CN201510777557 A CN 201510777557A CN 106709587 A CN106709587 A CN 106709587A
- Authority
- CN
- China
- Prior art keywords
- sample
- fine
- day
- direct radiation
- pattern
- 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
- 230000005855 radiation Effects 0.000 title claims abstract description 97
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000007619 statistical method Methods 0.000 claims abstract description 7
- 238000003064 k means clustering Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 7
- 238000012888 cubic function Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000013145 classification model Methods 0.000 abstract 2
- 238000007635 classification algorithm Methods 0.000 abstract 1
- 238000010248 power generation Methods 0.000 abstract 1
- 230000001932 seasonal effect Effects 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Abstract
The invention provides a direct radiation prediction method based on a conventional weather forecast. According to a weather type classification algorithm, a preferred statistical method is adopted to classify weather types, and a weather type classification model is obtained; according to the weather type classification model and historical direct radiation data, a weather type curve model is built; and according to the weather type curve model and inputted conventional weather forecast data, a direct radiation prediction model is built, and direct radiation prediction data for future 24 hours are obtained. The method provided by the invention overcomes influences on direct radiation prediction by season changes, solves the problem of missing of the direct radiation data to acquire more accurate direct radiation data, and accurately predicts the direct radiation of a photothermal power plant in the future 24 hours; the calculation precision is high, the needed calculation resources are few, good prediction effects can be achieved, and a data basis is laid for power generation power prediction for the photothermal power plant; and further, normal operation of the photothermal power plant can be ensured.
Description
Technical field
The present invention relates to light thermo-power station generated power forecasting technical field, and in particular to a kind of based on the straight of conventional weather forecast
Connect radiation Forecasting Methodology.
Background technology
Solar energy heating generating is different with solar energy power generating, can only utilize solar energy direct radiation (DNI).Therefore,
DNI numerical value is the primary foundation of solar energy heating power station generated power forecasting.Direct solar radiation distribution is determined can
The maximum potential of generating, it is mainly influenceed by astronomy radiation, Atmospheric Absorption and terrain shading.
At present, the prediction on direct solar radiation data relies primarily on computing method of formula, numerical weather forecast predicted method etc..
Wherein, computing method of formula can only qualitatively calculate direct solar radiation data, and its precision is relatively low, and numerical weather forecast is pre-
Survey method needs more observation station data due to computationally intensive.
The content of the invention
In view of this, a kind of direct radiation Forecasting Methodology based on conventional weather forecast that the present invention is provided, the method overcomes
Seasonal variations solve the problems, such as direct radiation shortage of data and obtain more accurately direct for the influence that direct radiation is predicted
Radiation data, direct radiation that can be accurately following 24 hours to light thermo-power station is predicted；Compared to simple public affairs
Formula calculating method accuracy is more preferably, and less compared to computing resource needed for numerical weather forecast method, and can obtain preferable
Prediction effect, for the generated power forecasting of light thermo-power station provides data basis；And then ensure that the normal of light thermo-power station
Operation.
The purpose of the present invention is achieved through the following technical solutions：
A kind of direct radiation Forecasting Methodology based on conventional weather forecast, it is characterised in that methods described comprises the following steps：
Step 1. is classified the weather pattern using preferred statistical method according to weather pattern sorting algorithm, is obtained
Weather pattern disaggregated model；
Step 2. sets up weather pattern curve model according to the weather pattern disaggregated model and history direct radiation data；
Step 3. sets up direct radiation prediction according to the weather pattern curve model and the conventional data of weather forecast of input
Model, obtains following 24 hours direct radiation prediction data.
Preferably, the step 1 includes：
Weather pattern is divided into fine skies sample by 1-1. according to the size and variation tendency of direct radiation by daily mean cluster
Originally with cloudy sample；Obtain fine skies sample pattern and cloudy sample pattern；
1-2. is classified as fine day sample and fine with occasional clouds day in the fine skies sample pattern according to daily difference average
Sample, obtains fine day sample pattern and fine with occasional clouds day sample pattern.
Preferably, the 1-1 includes：
A. every annual average is asked for the radiation data in the range of daily sun set/raise time, using k- means clustering methods,
Obtain fine day sample and cloudy sample；
B. according to the minimum value of the fine day sample average, the classification extreme value of cloudy sample and fine day sample is obtained；And then
Obtain fine skies sample pattern and cloudy sample pattern.
Preferably, the 1-2 includes：
C. difference is carried out to the radiation data in the range of daily sun set/raise time, asks and obtain difference and be worth to daily difference
Average Yj：
In formula (1), Xi+1Represent the direct radiation value at the i+1 moment of jth day；N represents daily direct radiation
Number of samples；XiRepresent the direct radiation value at the i moment of jth day；
D. according to k- means clustering methods, daily difference average is clustered, is obtained fine day sample and fine with occasional clouds day
Sample；
Wherein, the k- means clustering methods be using the k sample for randomly selecting as initial central point, will be in addition to k
Remaining sample be included into similarity highest central point where cluster, then establish the average of sample coordinate in current cluster and be new
Heart point, loop iteration goes down successively, until all sample generics no longer change；
E. the maximum classified according to fine with occasional clouds day sample average, obtain fine day sample and fine with occasional clouds day sample point
Class extreme value；And then obtain fine day sample pattern and fine with occasional clouds day sample pattern.
Preferably, the step 2 includes：
2-1. according to the fine day sample, fine with occasional clouds day sample, cloudy sample curve matching, respectively obtain fine day sample
Originally, fine with occasional clouds day sample and cloudy sample curve；
2-2. is using local weighted recurrence scatterplot exponential smoothing respectively to the fine day sample, fine with occasional clouds day sample and cloudy sample
This curve is fitted, and sets up the weather pattern curve model.
Preferably, the described local weighted recurrence scatterplot exponential smoothing in the 2-2 includes：
F. the initial weight of each direct radiation data point in specified window is calculated, weighting function General Expression is between numerical value
The cubic function of Euclidean distance ratio；
G. regression estimates are carried out using initial weight, sane weight function is defined using the residual error of estimator, calculated new
Weight；
H. according to the new weight, repeat step g numerical simulations, until obtaining convergent multinomial after N steps；
I. the smooth value of arbitrfary point is obtained according to the multinomial and weight.
Preferably, the step 3 includes：
The conventional data of weather forecast of following 24 hours of 3-1. inputs, and according to the weather pattern disaggregated model by its point
It is fine day, fine with occasional clouds and cloudy forecast data；
3-2. sets up straight according to the fine day, fine with occasional clouds and cloudy forecast data and the weather pattern curve model
Radiation forecast model is connect, following 24 hours direct radiation prediction data is obtained.
It can be seen from above-mentioned technical scheme that, the invention provides a kind of direct radiation prediction based on conventional weather forecast
Method, according to weather pattern sorting algorithm, is classified weather pattern using preferred statistical method, obtains weather pattern point
Class model；According to weather pattern disaggregated model and history direct radiation data, weather pattern curve model is set up；According to day
Gas type curve model and the conventional data of weather forecast of input, set up direct radiation forecast model, obtain following 24 hours
Direct radiation prediction data.Method proposed by the present invention overcomes seasonal variations for the influence that direct radiation is predicted, solution
Direct radiation of having determined shortage of data problem and more accurately direct radiation data are obtained, can accurately to light thermo-power station future
The direct radiation of 24 hours is predicted；The accurate computing resource high and required of its calculating is less, and can obtain preferably
Prediction effect, for the generated power forecasting of light thermo-power station provides data basis；And then ensure that the normal fortune of light thermo-power station
OK.
With immediate prior art ratio, the present invention provide technical scheme there is following excellent effect：
1st, in technical scheme provided by the present invention, history direct radiation data are carried out into day first with clustering methodology
Gas classification of type, is divided into fine day, fine with occasional clouds, cloudy three types, and loess then is respectively adopted for three kinds of weather patterns
Recurrence is fitted, and obtains weather pattern curve model, and finally for the conventional weather forecast result of next day, selection is different
Weather pattern curve model so as to obtain the direct radiation data of next day 0-24 hours；For light thermo-power station generated output is pre-
Survey and basis is provided.
2nd, technical scheme provided by the present invention, according to weather pattern sorting algorithm, using preferred statistical method by day
Gas classification of type, obtains weather pattern disaggregated model；According to weather pattern disaggregated model and history direct radiation data, build
Vertical weather pattern curve model；According to weather pattern curve model and the conventional data of weather forecast of input, direct radiation is set up
Forecast model, obtains following 24 hours direct radiation prediction data.Method proposed by the present invention overcomes seasonal variations
For the influence that direct radiation is predicted, solve the problems, such as direct radiation shortage of data and obtain more accurately direct radiation number
According to direct radiation that can be accurately following 24 hours to light thermo-power station is predicted；It calculates accurate high and required
Computing resource is less, and can obtain preferable prediction effect, for the generated power forecasting of light thermo-power station provides data basis；
And then ensure that the normal operation of light thermo-power station.
3rd, the technical scheme that the present invention is provided, is widely used, with significant Social benefit and economic benefit.
Brief description of the drawings
Fig. 1 is a kind of flow chart of direct radiation Forecasting Methodology based on conventional weather forecast of the invention；
Fig. 2 is the flow chart of step 1 in Forecasting Methodology of the invention；
Fig. 3 is the flow chart of step 2 in Forecasting Methodology of the invention；
Fig. 4 is the flow chart of step 3 in Forecasting Methodology of the invention；
Fig. 5 be a kind of direct radiation Forecasting Methodology based on conventional weather forecast of the invention concrete application example in make
With the direct radiation Forecasting Methodology FB(flow block) of conventional weather forecast；
Fig. 6 is the fine day and the classification results schematic diagram at cloudy day in concrete application example of the invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground description, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Base
In embodiments of the invention, those of ordinary skill in the art obtained under the premise of creative work is not made it is all its
His embodiment, belongs to the scope of protection of the invention.
As shown in figure 1, the present invention provides a kind of direct radiation Forecasting Methodology based on conventional weather forecast, including following step
Suddenly：
Step 1. is classified weather pattern using preferred statistical method according to weather pattern sorting algorithm, obtains weather
Classification of type model；
Step 2. sets up weather pattern curve model according to weather pattern disaggregated model and history direct radiation data；
Step 3. sets up direct radiation forecast model according to weather pattern curve model and the conventional data of weather forecast of input,
Obtain following 24 hours direct radiation prediction data.
As shown in Fig. 2 step 1 includes：
Weather pattern is divided into fine skies sample by 1-1. according to the size and variation tendency of direct radiation by daily mean cluster
Originally with cloudy sample；Obtain fine skies sample pattern and cloudy sample pattern；
1-2. is classified as fine day sample and fine with occasional clouds day sample in fine skies sample pattern according to daily difference average,
Obtain fine day sample pattern and fine with occasional clouds day sample pattern.
Wherein, 1-1 includes：
A. every annual average is asked for the radiation data in the range of daily sun set/raise time, using k- means clustering methods,
Obtain fine day sample and cloudy sample；
B. according to the minimum value of fine day sample average, the classification extreme value of cloudy sample and fine day sample is obtained；And then obtain
Fine skies sample pattern and cloudy sample pattern.
Wherein, 1-2 includes：
C. difference is carried out to the radiation data in the range of daily sun set/raise time, asks and obtain difference and be worth to daily difference
Average Yj：
In formula (1), Xi+1Represent the direct radiation value at the i+1 moment of jth day；N represents daily direct radiation
Number of samples；XiRepresent the direct radiation value at the i moment of jth day；
D. according to k- means clustering methods, daily difference average is clustered, is obtained fine day sample and fine with occasional clouds day
Sample；
Wherein, k- means clustering methods are using the k sample for randomly selecting as initial central point, by its in addition to k
Remaining sample be included into similarity highest central point where cluster, then it is new center to establish the average of sample coordinate in current cluster
Point, loop iteration goes down successively, until all sample generics no longer change；
E. the maximum classified according to fine with occasional clouds day sample average, obtain fine day sample and fine with occasional clouds day sample point
Class extreme value；And then obtain fine day sample pattern and fine with occasional clouds day sample pattern.
As shown in figure 3, step 2 includes：
2-1. according to fine day sample, fine with occasional clouds day sample, cloudy sample curve matching, respectively obtain fine day sample,
Fine with occasional clouds day sample and cloudy sample curve；
2-2. is bent to fine day sample, fine with occasional clouds day sample and cloudy sample respectively using local weighted recurrence scatterplot exponential smoothing
Line is fitted, and sets up weather pattern curve model.
Wherein, the local weighted recurrence scatterplot exponential smoothing in 2-2 includes：
F. the initial weight of each direct radiation data point in specified window is calculated, weighting function General Expression is between numerical value
The cubic function of Euclidean distance ratio；
G. regression estimates are carried out using initial weight, sane weight function is defined using the residual error of estimator, calculated new
Weight；
H. according to new weight, repeat step g numerical simulations, until obtaining convergent multinomial after N steps；
I. the smooth value of arbitrfary point is obtained according to multinomial and weight.
As shown in figure 4, step 3 includes：
Following 24 hours conventional data of weather forecast of 3-1. inputs, and be classified as according to weather pattern disaggregated model fine
My god, fine with occasional clouds and cloudy forecast data；
3-2. sets up direct radiation pre- according to fine day, fine with occasional clouds and cloudy forecast data and weather pattern curve model
Model is surveyed, following 24 hours direct radiation prediction data is obtained.
As shown in figure 5, the present invention provides a kind of concrete application of the direct radiation Forecasting Methodology based on conventional weather forecast
Example, comprises the following steps：
Based on first with history direct radiation data, weather pattern is classified using preferred statistical method；So
Fitting afterwards obtains different weather pattern curves, is finally based on the weather pattern direct spoke following 24 hours to light thermo-power station
Penetrate and be predicted.
Comprise the following steps that：
Step 1:Weather pattern sorting algorithm
According to the size and variation tendency of direct radiation, weather pattern can be divided into fine day, cloudy and fine with occasional clouds day,
Idiographic flow is that weather pattern is divided into fine day and cloudy two class by daily mean cluster, according to daily in fine day sample
Fine day sample is further divided into fine day and fine with occasional clouds day by difference average.
1) fine day, cloudy sorting algorithm
Due to fine day (include fine with occasional clouds day) and the size for differring primarily in that radiation value of cloudy day direct radiation, because
This takes and asks for every annual average to the radiation data in the range of daily sun set/raise time, using k- means clustering methods, obtains
To two classifications, fine day and cloudy day, by the minimum value of fine day sample average, cloudy day, the classification extreme value of fine day are obtained,
If i.e. the radiation average of one day is less than the value, the same day is the cloudy day, is otherwise fine day.
2) fine day, fine with occasional clouds day sorting algorithm
The main distinction of fine day and fine with occasional clouds direct radiation is then in the variation tendency for radiating, therefore to take to daily
Radiation data in the range of sun set/raise time carries out difference, then asks these difference to be worth to daily difference average, as follows
Shown in formula, using k- means clustering methods, after daily difference average is clustered, two classifications are obtained, fine day and fine
Between broken sky, by fine with occasional clouds day sample average classify maximum, obtain the criteria for classification in fine day and fine with occasional clouds day,
If i.e. the average of one day is more than the value, the same day is fine with occasional clouds day, is otherwise fine day.
Wherein Xi+1The direct radiation value at the i+1 moment of jth day is represented, n represents daily direct radiation number of samples, Yj
Represent the difference average of jth day.
The main thought of wherein k- means clustering methods (is preset sample class, selected here 2) with the k for randomly selecting
Individual sample is used as initial central point, the cluster where remaining sample is included into similarity highest central point, then establishes current cluster
The average of middle sample coordinate is new central point, and loop iteration goes down successively, until all sample generics no longer change；
Wherein, cluster result is as shown in Figure 6；Wherein, circle represents fine day, and square represents the cloudy day.
Step 2:Curve matching based on weather pattern
By fine day, fine with occasional clouds day, the curve matching at cloudy day, the weather curve of three types can be obtained, using office
Portion's weighted regression scatterplot exponential smoothing (loess recurrence) is fitted to three kinds of curves respectively.
Loess is returned similar to rolling average technology, is that within specified window, the numerical value of every bit is all with window
The data closed on are weighted recurrence and obtain linear equation, and the method is comprised the following steps：
1) calculate specified window in each direct radiation data point initial weight, weighting function General Expression be numerical value it
Between Euclidean distance ratio cubic function；
2) regression estimates are carried out using initial weight, sane weight function is defined using the residual error of estimator, calculated new
Weight；
3) utilize new weight repeat step 2, ceaselessly numerical simulation, after N step convergences can according to multinomial and
Weight obtains the smooth value of arbitrfary point.
Step 3:Following 24 hours direct radiation forecast models proposed by the invention
1) its weather pattern is judged using step1 methods according to same day direct radiation data.
2) this day direct radiation curve is fitted using step2 methods.
3) next day routine weather forecast is obtained, fine day, fine with occasional clouds and cloudy day is classified as, according to different weather class
Type, selection closes on the direct radiation matched curve of this day, obtains next day 0-24 hours direct radiation and predicts the outcome.
The above embodiments are merely illustrative of the technical solutions of the present invention rather than its limitations, although with reference to above-described embodiment to this
Invention has been described in detail, and those of ordinary skill in the art can still enter to specific embodiment of the invention
Row modification or equivalent, and these are without departing from any modification of spirit and scope of the invention or equivalent, its is equal
Applying within pending claims of the invention.
Claims (7)
1. a kind of direct radiation Forecasting Methodology based on conventional weather forecast, it is characterised in that methods described includes as follows
Step：
Step 1. is classified the weather pattern using preferred statistical method according to weather pattern sorting algorithm, is obtained
Weather pattern disaggregated model；
Step 2. sets up weather pattern curve model according to the weather pattern disaggregated model and history direct radiation data；
Step 3. sets up direct radiation prediction according to the weather pattern curve model and the conventional data of weather forecast of input
Model, obtains following 24 hours direct radiation prediction data.
2. the method for claim 1, it is characterised in that the step 1 includes：
Weather pattern is divided into fine skies sample by 1-1. according to the size and variation tendency of direct radiation by daily mean cluster
Originally with cloudy sample；Obtain fine skies sample pattern and cloudy sample pattern；
1-2. is classified as fine day sample and fine with occasional clouds day in the fine skies sample pattern according to daily difference average
Sample, obtains fine day sample pattern and fine with occasional clouds day sample pattern.
3. method as claimed in claim 2, it is characterised in that the 1-1 includes：
A. every annual average is asked for the radiation data in the range of daily sun set/raise time, using k- means clustering methods,
Obtain fine day sample and cloudy sample；
B. according to the minimum value of the fine day sample average, the classification extreme value of cloudy sample and fine day sample is obtained；And then
Obtain fine skies sample pattern and cloudy sample pattern.
4. method as claimed in claim 2, it is characterised in that the 1-2 includes：
C. difference is carried out to the radiation data in the range of daily sun set/raise time, asks and obtain difference and be worth to daily difference
Average Yj：
In formula (1), Xi+1Represent the direct radiation value at the i+1 moment of jth day；N represents daily direct radiation
Number of samples；XiRepresent the direct radiation value at the i moment of jth day；
D. according to k- means clustering methods, daily difference average is clustered, is obtained fine day sample and fine with occasional clouds day
Sample；
Wherein, the k- means clustering methods be using the k sample for randomly selecting as initial central point, will be in addition to k
Remaining sample be included into similarity highest central point where cluster, then establish the average of sample coordinate in current cluster and be new
Heart point, loop iteration goes down successively, until all sample generics no longer change；
E. the maximum classified according to fine with occasional clouds day sample average, obtain fine day sample and fine with occasional clouds day sample point
Class extreme value；And then obtain fine day sample pattern and fine with occasional clouds day sample pattern.
5. the method for claim 1, it is characterised in that the step 2 includes：
2-1. according to the fine day sample, fine with occasional clouds day sample, cloudy sample curve matching, respectively obtain fine day sample
Originally, fine with occasional clouds day sample and cloudy sample curve；
2-2. is using local weighted recurrence scatterplot exponential smoothing respectively to the fine day sample, fine with occasional clouds day sample and cloudy sample
This curve is fitted, and sets up the weather pattern curve model.
6. method as claimed in claim 5, it is characterised in that the described local weighted recurrence scatterplot in the 2-2
Exponential smoothing includes：
F. the initial weight of each direct radiation data point in specified window is calculated, weighting function General Expression is between numerical value
The cubic function of Euclidean distance ratio；
G. regression estimates are carried out using initial weight, sane weight function is defined using the residual error of estimator, calculated new
Weight；
H. according to the new weight, repeat step g numerical simulations, until obtaining convergent multinomial after N steps；
I. the smooth value of arbitrfary point is obtained according to the multinomial and weight.
7. the method for claim 1, it is characterised in that the step 3 includes：
The conventional data of weather forecast of following 24 hours of 3-1. inputs, and according to the weather pattern disaggregated model by its point
It is fine day, fine with occasional clouds and cloudy forecast data；
3-2. sets up straight according to the fine day, fine with occasional clouds and cloudy forecast data and the weather pattern curve model
Radiation forecast model is connect, following 24 hours direct radiation prediction data is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510777557.0A CN106709587B (en) | 2015-11-13 | 2015-11-13 | Direct radiation prediction method based on conventional weather forecast |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510777557.0A CN106709587B (en) | 2015-11-13 | 2015-11-13 | Direct radiation prediction method based on conventional weather forecast |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106709587A true CN106709587A (en) | 2017-05-24 |
| CN106709587B CN106709587B (en) | 2021-03-02 |
Family
ID=58930695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510777557.0A Active CN106709587B (en) | 2015-11-13 | 2015-11-13 | Direct radiation prediction method based on conventional weather forecast |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106709587B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418558A (en) * | 2020-12-07 | 2021-02-26 | 天津大学 | Total radiation correction method based on multi-source meteorological forecast |
| CN112684519A (en) * | 2020-12-30 | 2021-04-20 | 北京墨迹风云科技股份有限公司 | Weather forecasting method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130262049A1 (en) * | 2012-03-29 | 2013-10-03 | Weihong Zhang | Method for Predicting Outputs of Photovoltaic Devices Based on Two-Dimensional Fourier Analysis and Seasonal Auto-Regression |
| CN103955749A (en) * | 2014-03-19 | 2014-07-30 | 内蒙古电力勘测设计院 | Sun direct radiation value prediction method and system |
| CN104157254A (en) * | 2014-08-18 | 2014-11-19 | 深圳市华星光电技术有限公司 | Gamma voltage generating module and liquid crystal panel |
| CN104573879A (en) * | 2015-01-30 | 2015-04-29 | 河海大学 | Photovoltaic power station output predicting method based on optimal similar day set |
| CN105005825A (en) * | 2015-07-03 | 2015-10-28 | 深圳供电局有限公司 | Method and system for predicting photovoltaic power based on dynamic neural network |
-
2015
- 2015-11-13 CN CN201510777557.0A patent/CN106709587B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130262049A1 (en) * | 2012-03-29 | 2013-10-03 | Weihong Zhang | Method for Predicting Outputs of Photovoltaic Devices Based on Two-Dimensional Fourier Analysis and Seasonal Auto-Regression |
| CN103955749A (en) * | 2014-03-19 | 2014-07-30 | 内蒙古电力勘测设计院 | Sun direct radiation value prediction method and system |
| CN104157254A (en) * | 2014-08-18 | 2014-11-19 | 深圳市华星光电技术有限公司 | Gamma voltage generating module and liquid crystal panel |
| CN104573879A (en) * | 2015-01-30 | 2015-04-29 | 河海大学 | Photovoltaic power station output predicting method based on optimal similar day set |
| CN105005825A (en) * | 2015-07-03 | 2015-10-28 | 深圳供电局有限公司 | Method and system for predicting photovoltaic power based on dynamic neural network |
Non-Patent Citations (1)
| Title |
|---|
| 于炳霞 等: "光伏发电功率预测自适应建模方法研究", 《电网与清洁能源》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418558A (en) * | 2020-12-07 | 2021-02-26 | 天津大学 | Total radiation correction method based on multi-source meteorological forecast |
| CN112418558B (en) * | 2020-12-07 | 2022-03-11 | 天津大学 | Total radiation correction method based on multi-source meteorological forecast |
| CN112684519A (en) * | 2020-12-30 | 2021-04-20 | 北京墨迹风云科技股份有限公司 | Weather forecasting method and device, computer equipment and storage medium |
| CN112684519B (en) * | 2020-12-30 | 2022-07-05 | 北京墨迹风云科技股份有限公司 | Weather forecasting method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106709587B (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Random forest solar power forecast based on classification optimization | |
| Gao et al. | Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM | |
| CN109902874A (en) | A kind of micro-capacitance sensor photovoltaic power generation short term prediction method based on deep learning | |
| CN107194495B (en) | Photovoltaic power longitudinal prediction method based on historical data mining | |
| CN103106544B (en) | A kind of photovoltaic generation prognoses system based on T-S Fuzzy neutral net | |
| CN110942205B (en) | Short-term photovoltaic power generation power prediction method based on HIMVO-SVM | |
| CN104463349A (en) | Photovoltaic generated power prediction method based on multi-period comprehensive similar days | |
| CN104573879A (en) | Photovoltaic power station output predicting method based on optimal similar day set | |
| CN107220723A (en) | A kind of predicting power of photovoltaic plant method | |
| CN104881706A (en) | Electrical power system short-term load forecasting method based on big data technology | |
| CN105574615A (en) | Spatial correlation and genetic algorithm (GA) based wind power forecast method for wavelet-BP neural network | |
| CN112418346B (en) | Numerical weather forecast total radiation system error classification calculation method | |
| CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
| CN106875033A (en) | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting | |
| CN109948281A (en) | It is effectively identified based on weather pattern and the straight of combined prediction dissipates separated modeling method | |
| CN106600060A (en) | Method for predicting amount of solar radiation based on similar day sunny coefficient correction | |
| CN109636054A (en) | Solar energy power generating amount prediction technique based on classification and error combination prediction | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| WO2024051524A1 (en) | Joint prediction method and apparatus for hydraulic, wind and photovoltaic generation power | |
| CN111242355A (en) | Photovoltaic probability prediction method and system based on Bayesian neural network | |
| CN106503833A (en) | Photovoltaic generation short term power rolling forecast method based on algorithm of support vector machine | |
| CN109034475A (en) | A kind of improved substation project cost forecasting method | |
| Aliberti et al. | Forecasting Short-term Solar Radiation for Photovoltaic Energy Predictions. | |
| Yang et al. | Photovoltaic power forecasting with a rough set combination method | |
| CN111062539B (en) | Total electric quantity prediction method based on secondary electric quantity characteristic cluster analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yu Bingxia Inventor after: Chen Zhibao Inventor after: Zhou Qiang Inventor after: Chen Weidong Inventor after: Ju Rongrong Inventor after: Peng Peipei Inventor after: He Jieqiong Inventor after: Lei Da Inventor after: Xiao Ying Inventor after: Li Huipeng Inventor after: Du Huijie Inventor after: Tan Zhiping Inventor after: Zhou Hai Inventor after: Cui Fang Inventor after: Cheng Xu Inventor after: Ding Jie Inventor after: Wang Zhijia Inventor after: Zhu Xiang Inventor after: Ding Huang Inventor before: Yu Bingxia Inventor before: Chen Zhibao Inventor before: Zhou Qiang Inventor before: Chen Weidong Inventor before: Ju Rongrong Inventor before: Peng Peipei Inventor before: He Jieqiong Inventor before: Tan Zhiping Inventor before: Zhou Hai Inventor before: Cui Fang Inventor before: Cheng Xu Inventor before: Ding Jie Inventor before: Wang Zhijia Inventor before: Zhu Xiang Inventor before: Ding Huang |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170803 Address after: Nan Shui Road Gulou District of Nanjing city of Jiangsu Province, No. 8 210003 Applicant after: China Electric Power Research Institute Applicant after: State Grid Corporation of China Applicant after: Electric Power Research Institute of State Grid Shanxi Power Supply Company Applicant after: STATE GRID SHANXI ELECTRIC POWER CO., LTD. Address before: Nan Shui Road Gulou District of Nanjing city of Jiangsu Province, No. 8 210003 Applicant before: China Electric Power Research Institute Applicant before: State Grid Corporation of China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |