CN106251023A - A kind of photovoltaic power short term prediction method being applicable to small sample - Google Patents
A kind of photovoltaic power short term prediction method being applicable to small sample Download PDFInfo
- Publication number
- CN106251023A CN106251023A CN201610645331.XA CN201610645331A CN106251023A CN 106251023 A CN106251023 A CN 106251023A CN 201610645331 A CN201610645331 A CN 201610645331A CN 106251023 A CN106251023 A CN 106251023A
- Authority
- CN
- China
- Prior art keywords
- period
- earth
- solar radiation
- radiation value
- penetrance
- 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 38
- 206010012373 Depressed level of consciousness Diseases 0.000 claims abstract description 21
- 238000003062 neural network model Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 10
- 230000005855 radiation Effects 0.000 claims description 46
- 238000005259 measurement Methods 0.000 claims description 15
- 230000007935 neutral effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000007619 statistical method Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000013277 forecasting method Methods 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of photovoltaic power short term prediction method being applicable to small sample, comprises the following steps: historical data is screened；Penetrance is added up；Input quantity converts；Neural network model is trained；Neural Network model predictive.Classical forecast model, according to the Decoupling Characteristics of photovoltaic generation each link influence factor, is split by the present invention, makes the network structure of each several part be simplified；By the statistical analysis of weather pattern Yu obnubilation degree corresponding relation, obnubilation factor is effectively integrated in mode input amount.This invention simplifies the input/output relation of neural network prediction model, reduce the complexity of relation between input and output, decrease the demand to training sample.
Description
Technical field
The invention belongs to new forms of energy technical field of photovoltaic power generation, be specifically related to a kind of photovoltaic power being applicable to small sample short
Phase Forecasting Methodology.
Background technology
In recent years, along with socioeconomic development, energy shortage and problem of environmental pollution become increasingly conspicuous, development and utilization can
The renewable sources of energy become the solution energy and the effective way of environmental problem.In generation of electricity by new energy, photovoltaic generation is owing to having safety
Reliably, the advantage such as region limits less, the construction period is short and be rapidly developed, the most possessed bigger industry size.But by
In the impact of the factors such as weather, there is bigger uncertainty, accurately and effectively light in photovoltaic output in short-term time scale
Volt Predicting Technique is significant for effectively utilizing of the safe and stable operation of system and photovoltaic energy.
Carry the photovoltaic short term prediction method of the previous day and be typically necessary the historical data support of abundance, to data integration times
Requirement up to 3 months to 1 year, if photovoltaic plant is in initial operation stage, historical data accumulation deficiency, conventional Forecasting Methodology
Application can be very limited, it is therefore necessary to for small sample situation, conventional method is improved, be applicable to
The power forecasting method of initial operation stage photovoltaic generating system.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, the present invention provides a kind of photovoltaic power short-term being applicable to small sample pre-
Survey method, utilizes the natural Decoupling Characteristics of each influence factor, is split by forecast model, and by weather pattern and obnubilation journey
Degree corresponding relation statistical analysis, obnubilation factor is effectively integrated in mode input amount, simplify network structure, reduce defeated
Enter the complexity of relation between output, thus reduce the Forecasting Methodology demand to historical data.
In order to realize foregoing invention purpose, the present invention adopts the following technical scheme that:
A kind of photovoltaic power short term prediction method being applicable to small sample is provided, said method comprising the steps of:
The first step: historical data is screened
Reject the part that air quality is the best, air humidity is big in the historical data, obtain earth's surface solar radiation value main
The sample affected by cloud amount；
Second step: penetrance is added up
History is utilized to calculate the i-th period of jth sky penetrance k adjacent to day day part earth's surface solar radiation valuei,j, in conjunction with i-th
Period history actual measurement weather pattern w, statistics obtains the penetrance expectation corresponding to i-th period each weather pattern；
On the basis of single period penetrance statistics, account for the penetrance statistics of before and after's period weather pattern, obtain
I-th period of the jth sky penetrance expectation of period weather pattern before and after consideration
3rd step: input quantity converts
According to period to be predicted and the weather pattern of front and back period thereof, in conjunction with the statistical result in second step, obtain treating pre-
Survey the penetrance expectation of period, in conjunction with the average earth's surface solar radiation value of period corresponding under cloudless weather, obtain earth's surface after obnubilation
Solar radiation value, complete input quantity from weather pattern to obnubilation after the conversion of earth's surface solar radiation value；
4th step: neural network model is trained
Historical data is utilized to carry out neural network model training, with earth's surface after the obnubilation corresponding to history actual measurement weather pattern
Solar radiation value, history actual measurement air quality index, history actual measurement ambient temperature are input quantity, and history actual measurement photovoltaic is exerted oneself as defeated
Output, carries out the training of model, and the time interval of all data is 1h；
5th step: Neural Network model predictive
Weather pattern forecast information according to day to be predicted day part obtains earth's surface solar radiation value after corresponding obnubilation, will
It is as the input item of weather pattern influence factor, in conjunction with temperature forecast information, air quality index forecast information, obtains treating pre-
The photovoltaic output surveying day day part predicts the outcome, and the time interval of all data is 1h.
I-th period of jth sky penetrance k in described second stepi,jComputing formula be:
ki,j=Ri,j/R0iI=0,1 ..., 23, j=1,2 ..., n
In formula, Ri,jShow the i-th period of jth sky average earth's surface solar radiation value, R0iRepresent under cloudless weather the flat of corresponding period
All earth's surface solar radiation value, the maximum earth's surface solar radiation value approximate calculation by n neighbouring correspondence day, historical data period:
R0i≈max{Ri,1,Ri,2,…,Ri,j,…,Ri,nJ=1,2 ..., n.
In described 3rd step, after obnubilation, the computing formula of earth's surface solar radiation value is:
In formula,Represent the i-th period of jth sky by cloud amount cut down after earth's surface solar radiation value,Represent jth sky i-th
Period and penetrance expectation corresponding to neighbouring period weather pattern thereof.
The neural network model used in described 4th step is divided into two parts, represents solar radiation respectively and cuts down process and light
Electricity transformation process, wherein, the input quantity of Part I neutral net is earth's surface sun spoke after period to be predicted day to be predicted obnubilation
Penetrate valueAir quality index Ai,j, output is period to be predicted day to be predicted earth's surface solar radiation value Si,j；Part II
The input quantity of neutral net is period to be predicted day to be predicted earth's surface solar radiation value Si,j, ambient temperature Ti,j, output is to treat
Prediction period to be predicted day photovoltaic power Pfi,j。
The described first step is rejected the method for the part that air quality is the best, air humidity is big in the historical data for rejecting
The part that air quality index is more than 100, air humidity is more than 80%.
The present invention is directed to small sample situation conventional method is improved, obtain being applicable to initial operation stage photovoltaic generating system
Power forecasting method.
Accompanying drawing explanation
Fig. 1 is prediction schematic flow sheet；
Fig. 2 is neutral net input/output relation schematic diagram.
Fig. 3 is the control methods figure that predicts the outcome under varying number sample.
Fig. 4 is the inventive method figure that predicts the outcome under varying number sample.
Fig. 5 is the root-mean-square error figure of control methods and the inventive method.
Detailed description of the invention
Below in conjunction with detailed description of the invention, the technical scheme of this patent is described in more detail.
Refer to Fig. 1, a kind of photovoltaic power short term prediction method being applicable to small sample, comprise the following steps:
The first step: historical data is screened
In history earth's surface solar radiation data, history photovoltaic power data, reject corresponding moment air quality index be more than
100, the air humidity part more than 80%, obtains the sample that earth's surface solar radiation value is mainly affected by cloud amount.
Second step: penetrance is added up
From Meteorological Services class website, obtain weather history type, determine according to the weather history type recorded in website
Weather pattern divides, such as fine, cloudy, cloudy, sleet etc..
History is utilized to calculate the penetrance of day part in historical data adjacent to day day part earth's surface solar radiation value, note the
The penetrance of j days the i-th periods is ki,j, in conjunction with the i-th period history actual measurement weather pattern w, the i-th period various weather can be obtained
Penetrance distribution corresponding to type, is calculated the penetrance corresponding to i-th period each weather pattern according to penetrance distribution
Expect.
On the basis of single period penetrance statistics, account for the penetrance statistics of before and after's period weather pattern, obtain
The penetrance expectation of period weather pattern before and after consideration.Such as current i period weather pattern is cloudy, i-1 period weather pattern
It is cloudy for fine, i+1 period weather pattern, then the weather pattern of present period is denoted as (fine)-cloudy-(cloudy).Obtain this shape
Before and after the consideration of formula after the weather pattern of period weather condition, in conjunction with single period penetrance, i.e. can be considered before and after period sky
The penetrance distribution of gas type, is calculated i-th period of jth sky of period weather pattern before and after consideration according to penetrance distribution and wears
Rate expectation thoroughly
3rd step: input quantity converts
According to period to be predicted and the weather pattern of front and back period thereof, by searching the statistical result in second step, obtain
The penetrance expectation of period to be predicted, and time information is incorporated in penetrance, obtain earth's surface solar radiation value after obnubilation, complete
The conversion of earth's surface solar radiation value after becoming input quantity from weather pattern to obnubilation.
4th step: neural network model is trained
Historical data is utilized to carry out neural network model training, with earth's surface after the obnubilation corresponding to history actual measurement weather pattern
Solar radiation value, history actual measurement air quality index, history actual measurement ambient temperature are input quantity, and history actual measurement photovoltaic is exerted oneself as defeated
Output, carries out the training of model, and the time interval of all data is 1h.
5th step: Neural Network model predictive
Weather pattern forecast information according to day to be predicted day part obtains earth's surface solar radiation value after corresponding obnubilation, will
It is as the input item of weather pattern influence factor.In conjunction with temperature forecast information, air quality index forecast information, obtain treating pre-
The photovoltaic output surveying day day part predicts the outcome, and the time interval of all data is 1h.
I-th period of jth sky penetrance k in second stepi,jComputing formula be:
ki,j=Ri,j/R0iI=0,1 ..., 23, j=1,2 ..., n
In formula, Ri,jShow the i-th period of jth sky average earth's surface solar radiation value, R0iRepresent under cloudless weather the flat of corresponding period
All earth's surface solar radiation value, the maximum earth's surface solar radiation value approximate calculation by n neighbouring correspondence day, historical data period:
R0i≈max{Ri,1,Ri,2,…,Ri,j,…,Ri,nJ=1,2 ..., n
In 3rd step, after obnubilation, the computing formula of earth's surface solar radiation value is:
In formula,Represent the i-th period of jth sky by cloud amount cut down after earth's surface solar radiation value,Represent jth sky i-th
Period and penetrance expectation corresponding to neighbouring period weather pattern thereof.
The neural network model used in 4th step is divided into two parts, represents earth's surface solar radiation respectively and cuts down process and light
Electricity transformation process.Wherein, earth's surface sun spoke after the input quantity of Part I neutral net is period to be predicted day to be predicted obnubilation
Penetrate valueAir quality index Ai,j, output is period to be predicted day to be predicted earth's surface solar radiation value Si,j；Part II
The input quantity of neutral net is period to be predicted day to be predicted earth's surface solar radiation value Si,j, ambient temperature Ti,j, output is to treat
Prediction period to be predicted day photovoltaic power Pfi,j, refer to Fig. 2.
By not making the traditional neural network multistep forecasting method method as a comparison of input quantity conversion, in the instruction of varying number
Practice predicting the outcome under sample and refer to Fig. 3.The inventive method predicting the outcome under the training sample of varying number refers to
Fig. 4.The prediction effect of the inventive method is better than control methods under Small Sample Size, along with the increase of sample size, to analogy
The prediction effect of method gradually promotes, both prediction effect convergences.
Control methods and the inventive method be the root-mean-square error average of all prediction days under the training sample of varying number,
Refer to Fig. 5.Control methods is relatively big, along with the increase of sample size, it was predicted that error is gradually reduced to the dependence of training sample.This
Inventive method is preferable to the adaptability of small sample, sample size from 10 increase to 40 during, it was predicted that error change is little,
And it is held in reduced levels.
Claims (5)
1. the photovoltaic power short term prediction method being applicable to small sample, it is characterised in that comprise the steps:
The first step: historical data is screened
Reject the part that air quality is the best, air humidity is big in the historical data, obtain earth's surface solar radiation value mainly by cloud
The sample of amount impact；
Second step: penetrance is added up
History is utilized to calculate the i-th period of jth sky penetrance k adjacent to day day part earth's surface solar radiation valuei,j, in conjunction with the i-th period
History actual measurement weather pattern w, statistics obtains the penetrance expectation corresponding to i-th period each weather pattern；
On the basis of single period penetrance statistics, account for the penetrance statistics of before and after's period weather pattern, considered
The i-th period of jth sky penetrance expectation of period weather pattern front and back
3rd step: input quantity converts
According to period to be predicted and the weather pattern of front and back period thereof, in conjunction with the statistical result in second step, when obtaining to be predicted
The penetrance expectation of section, in conjunction with the average earth's surface solar radiation value of period corresponding under cloudless weather, obtains the earth's surface sun after obnubilation
Radiation value, complete input quantity from weather pattern to obnubilation after the conversion of earth's surface solar radiation value；
4th step: neural network model is trained
Historical data is utilized to carry out neural network model training, with the earth's surface sun after the obnubilation corresponding to history actual measurement weather pattern
Radiation value, history actual measurement air quality index, history actual measurement ambient temperature are input quantity, and history actual measurement photovoltaic is exerted oneself as output
Amount, carries out the training of model, and the time interval of all data is 1h；
5th step: Neural Network model predictive
Weather pattern forecast information according to day to be predicted day part obtains earth's surface solar radiation value after corresponding obnubilation, is made
For the input item of weather pattern influence factor, in conjunction with temperature forecast information, air quality index forecast information, obtain day to be predicted
The photovoltaic output of day part predicts the outcome, and the time interval of all data is 1h.
Photovoltaic power short term prediction method the most according to claim 1, it is characterised in that: jth sky i-th in described second step
Period penetrance ki,jComputing formula be:
ki,j=Ri,j/R0iI=0,1 ..., 23, j=1,2 ..., n
In formula, Ri,jShow the i-th period of jth sky average earth's surface solar radiation value, R0iRepresent that under cloudless weather, the corresponding period is fifty-fifty
Table solar radiation value, the maximum earth's surface solar radiation value approximate calculation by n neighbouring correspondence day, historical data period:
R0i≈max{Ri,1,Ri,2,…,Ri,j,…,Ri,nJ=1,2 ..., n.
Photovoltaic power short term prediction method the most according to claim 1, it is characterised in that: in described 3rd step after obnubilation
The computing formula of table solar radiation value is:
In formula,Represent the i-th period of jth sky by cloud amount cut down after earth's surface solar radiation value,Represent the i-th period of jth sky
And expect adjacent to the penetrance that period weather pattern is corresponding.
Photovoltaic power short term prediction method the most according to claim 1, it is characterised in that: the god used in described 4th step
Being divided into two parts through network model, represent solar radiation respectively and cut down process and photoelectric conversion process, wherein, Part I is neural
The input quantity of network is earth's surface solar radiation value after period to be predicted day to be predicted obnubilationAir quality index Ai,j, output
Amount is period to be predicted day to be predicted earth's surface solar radiation value Si,j；The input quantity of Part II neutral net is to treat day to be predicted
Prediction period earth's surface solar radiation value Si,j, ambient temperature Ti,j, output is period to be predicted day to be predicted photovoltaic power Pfi,j。
Photovoltaic power short term prediction method the most according to claim 1, it is characterised in that: at history number in the described first step
According to the middle part that rejecting air quality is the best, air humidity is big method for reject air quality index more than 100, air humidity
Part more than 80%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610645331.XA CN106251023B (en) | 2016-08-05 | 2016-08-05 | Photovoltaic power short-term prediction method suitable for small sample |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610645331.XA CN106251023B (en) | 2016-08-05 | 2016-08-05 | Photovoltaic power short-term prediction method suitable for small sample |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106251023A true CN106251023A (en) | 2016-12-21 |
| CN106251023B CN106251023B (en) | 2020-01-14 |
Family
ID=58078850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610645331.XA Active CN106251023B (en) | 2016-08-05 | 2016-08-05 | Photovoltaic power short-term prediction method suitable for small sample |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106251023B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102281016A (en) * | 2011-06-09 | 2011-12-14 | 国网电力科学研究院 | Clear-sky photovoltaic super-short-term power forecast method based on real-time radiation acquisition technology |
| US20130166266A1 (en) * | 2007-02-12 | 2013-06-27 | Michael Herzig | Weather and satellite model for estimating solar irradiance |
| CN103971169A (en) * | 2014-04-14 | 2014-08-06 | 国家电网公司 | Photovoltaic super-short-term generated power forecasting method based on cloud cover simulation |
| CN103996082A (en) * | 2014-06-03 | 2014-08-20 | 华北电力大学（保定） | Method for predicating solar radiation intensity based on double-random theory |
| CN105303254A (en) * | 2015-10-26 | 2016-02-03 | 国网浙江省电力公司电力科学研究院 | Method and device for prediction of radiation received by photovoltaic power station |
| CN105512760A (en) * | 2015-12-04 | 2016-04-20 | 北京国电通网络技术有限公司 | Neural network-based calculation method and calculation system for calculating power-generating capacity of photovoltaic station |
-
2016
- 2016-08-05 CN CN201610645331.XA patent/CN106251023B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130166266A1 (en) * | 2007-02-12 | 2013-06-27 | Michael Herzig | Weather and satellite model for estimating solar irradiance |
| CN102281016A (en) * | 2011-06-09 | 2011-12-14 | 国网电力科学研究院 | Clear-sky photovoltaic super-short-term power forecast method based on real-time radiation acquisition technology |
| CN103971169A (en) * | 2014-04-14 | 2014-08-06 | 国家电网公司 | Photovoltaic super-short-term generated power forecasting method based on cloud cover simulation |
| CN103996082A (en) * | 2014-06-03 | 2014-08-20 | 华北电力大学（保定） | Method for predicating solar radiation intensity based on double-random theory |
| CN105303254A (en) * | 2015-10-26 | 2016-02-03 | 国网浙江省电力公司电力科学研究院 | Method and device for prediction of radiation received by photovoltaic power station |
| CN105512760A (en) * | 2015-12-04 | 2016-04-20 | 北京国电通网络技术有限公司 | Neural network-based calculation method and calculation system for calculating power-generating capacity of photovoltaic station |
Non-Patent Citations (4)
| Title |
|---|
| 吴雪莲等: "基于BP神经网络-马尔科夫链的光伏发电预测", 《电工电气》 * |
| 赵书强等: ""基于不确定理论的光伏出力预测研究"", 《电工技术学报》 * |
| 赵书强等: ""基于模糊随机理论的短期太阳辐射强度预测"", 《电力自动化设备》 * |
| 赵书强等: "考虑云量和气溶胶不确定性的太阳辐射值预测", 《电工电能新技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106251023B (en) | 2020-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Forecasting power output of photovoltaic system using a BP network method | |
| CN103996082B (en) | A kind of intensity of solar radiation Forecasting Methodology theoretical based on dual random | |
| Cavallaro | A comparative assessment of thin-film photovoltaic production processes using the ELECTRE III method | |
| CN102930358B (en) | A kind of neural net prediction method of photovoltaic power station power generation power | |
| CN109103926A (en) | Photovoltaic power generation based on more Radiation Characteristics year meteorology scenes receives capacity calculation method | |
| CN104092241B (en) | A kind of wind electricity digestion capability analytical method considering stand-by requirement | |
| CN104361406B (en) | A kind of photovoltaic plant can utilize solar power generation amount Forecasting Methodology | |
| CN102521670A (en) | Power generation output power prediction method based on meteorological elements for photovoltaic power station | |
| CN104463349A (en) | Photovoltaic generated power prediction method based on multi-period comprehensive similar days | |
| CN105426956A (en) | Ultra-short-period photovoltaic prediction method | |
| CN103390200A (en) | Photovoltaic power station electricity generation output power forecasting method based on similar days | |
| CN106682810A (en) | Method for operating cross-basin cascade hydropower station groups under condition of dynamic commissioning of giant hydropower stations for long term | |
| CN104021427A (en) | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN105678397A (en) | Short-term photovoltaic power prediction method based on improved EMD algorithm and Elman algorithm | |
| CN104268659A (en) | Photovoltaic power station generated power super-short-term prediction method | |
| CN104638672A (en) | Determining method of photovoltaic transmission power limit considering variable correlation | |
| CN102479347A (en) | Method and system for forecasting short-term wind speed of wind farm based on data driving | |
| Grossmann et al. | Investment and employment from large-scale photovoltaics up to 2050 | |
| CN104200289A (en) | Distributed photovoltaic installed capacity prediction method based on investment return rate | |
| CN104299173A (en) | Robust optimization day-ahead scheduling method suitable for multi-energy-source connection | |
| Ayoub et al. | ANN model for energy demand and supply forecasting in a hybrid energy supply system | |
| CN111612244A (en) | QRA-LSTM-based method for predicting nonparametric probability of photovoltaic power before day | |
| CN103326394B (en) | Multi-scene probability optimal scheduling method for calculating wind electricity volatility | |
| Zhang et al. | Assessing the integration potential of new energy in river basin clean energy corridors considering energy-power coupled complementary operation modes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |