CN105956685A - Photovoltaic power factor table prediction method - Google Patents

Photovoltaic power factor table prediction method Download PDF

Info

Publication number
CN105956685A
CN105956685A CN201610247301.3A CN201610247301A CN105956685A CN 105956685 A CN105956685 A CN 105956685A CN 201610247301 A CN201610247301 A CN 201610247301A CN 105956685 A CN105956685 A CN 105956685A
Authority
CN
China
Prior art keywords
irradiance
sample
factor table
power factor
power
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
Application number
CN201610247301.3A
Other languages
Chinese (zh)
Other versions
CN105956685B (en
Inventor
吴世伟
李靖霞
檀庭方
刘文彪
纪陵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing SAC Automation Co Ltd
Original Assignee
Nanjing SAC Automation Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing SAC Automation Co Ltd filed Critical Nanjing SAC Automation Co Ltd
Priority to CN201610247301.3A priority Critical patent/CN105956685B/en
Publication of CN105956685A publication Critical patent/CN105956685A/en
Application granted granted Critical
Publication of CN105956685B publication Critical patent/CN105956685B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention discloses a photovoltaic power factor table prediction method. The photovoltaic power factor table prediction method comprises the following steps of: selecting at least two sets of normal power generation data in a clear weather condition as a sample, wherein date, time, irradiance and generation power are included in the sample; normalizing the generation power in the sample by using the running capacity; according to time difference between sunrise and sunset, translating different date data in the sample; using at least two sets of sample data to calculate and obtain a power factor table; correcting predicted irradiance of a prediction day by using actual irradiance from a meteorological observing substation; according to the predicted irradiance of the prediction day, looking up the power factor table and predicting the generation power. The process of the invention is simple and clear, and power variation of photovoltaic power stations can be accurately predicted before and after grid connection of photovoltaic power stations, thereby providing scientific basis for power grid dispatching and improving economical efficiency and safety of power grid operation.

Description

A kind of photovoltaic power factor table Forecasting Methodology
Technical field
The present invention relates to a kind of photovoltaic power factor table Forecasting Methodology, belong to photovoltaic power generation power prediction technology neck Territory.
Background technology
Photovoltaic generation, as a kind of clean energy resource generation technology, currently available develops rapidly and extensive engineer applied. Photovoltaic generation feature be exert oneself (generated energy) with weather conditions fluctuate, have the most intermittent and regular, After extensive centralized photovoltaic electric station grid connection for electrical network impact greatly, the centralized photovoltaic electric of standard gauge is stood firm necessary It is equipped with power prediction functional software.Look-ahead photovoltaic generation is exerted oneself, then be easy to dispatching of power netwoks, reasonable arrangement Formulating generation schedule, regulate exert oneself distribution, economic load dispatching, safe operation etc., therefore accurate forecast photovoltaic is sent out Electrical power is significant.
Luminous power Forecasting Methodology is divided into mathematical model method, statistical model method, model of mind method etc..General algorithm Depending on priori data and training sample, and affected result of calculation by its quality, face is to need to solve The problem that certainly photovoltaic plant lacks service data at initial operation stage.Photovoltaic generation is big by environmental effect, the spring, The environment in season that summer, autumn, the four seasons in winter are different, the DIFFERENT METEOROLOGICAL CONDITIONS such as fine, cloudy, mist, rain, snow descends generating Situation of exerting oneself obvious difference, has the Artificial Neural Network researching and proposing multiple model accordingly, adapts to complexity Meteorological condition is another problem that luminous power prediction needs to solve, and solution process is typically complex.
Summary of the invention
It is an object of the invention to overcome deficiency of the prior art, it is provided that a kind of photovoltaic power factor table is pre- Survey method, solves the precision of prediction reduction caused because of weather pattern change in prior art and puts into operation with grid-connected Initial stage lacks the technical problem of service data.
For solving above-mentioned technical problem, the invention provides a kind of photovoltaic power factor table Forecasting Methodology, it is special Levy and be, comprise the following steps:
Step one, under the conditions of choosing at least two group fair weather, photovoltaic plant normal power generation data are as sample, Sample includes date, time, irradiance and generated output parameter；
Step 2, utilizes the generated output in working capacity normalized sample, and working capacity refers to photovoltaic electric Stand the actual capacity being incorporated into the power networks；
Step 3, in sample, different date datas are translated as centered by irradiance peak；
Step 4, utilizes sample data to be calculated power factor table；
Step 5, utilizes the forecast irradiance of meteorological observation substation actual irradiance correction prediction day；
Step 6, searches power factor table according to prediction day revised irradiance and dopes generated output.
Further, in described step 3, sample translation detailed process is, chooses the flat of sunrise sunset moment All time points are as midpoint, and midpoint is the moment that in one day, irradiance is the highest, and sample is moved to midpoint pair Together.
Further, in described step 4, sample data is utilized to be calculated the detailed process of power factor table For, it is known that function f (x) of irradiance can be launched by normalized generated output P by Taylor's formula,
f ( x ) = f ( a ) 0 ! + f ′ ( a ) 1 ! ( x - a ) + f ′ ′ ( a ) 2 ! ( x - a ) 2 + ... + f ( n ) ( a ) n ! ( x - a ) n + R n ( x )
Wherein, f(n)(a) be the n order derivative of generated output be value during a at irradiance, RnX () is (x-a)n's Higher-order shear deformation；
Retain wherein first order and constant term, for sample L1 and sample L2, at same string (the i.e. sample of alignment In this L1, irradiance is x1, and in sample L2, irradiance is x2) generated output P can be expressed as follows
f ( x 1 ) = f ( x 0 ) 0 ! + f ′ ( x 0 ) 1 ! ( x 1 - x 0 ) + R n ( x )
f ( x 2 ) = f ( x 0 ) 0 ! + f ′ ( x 0 ) 1 ! ( x 2 - x 0 ) + R n ( x )
Can show that coefficient of first order is according to above formulaAt piecewise approximation bar Under part, repeat said process, calculate the piecewise linearity mathematical relationship between generated output and irradiance, composition Power factor table.
Further, in described step 5, the irradiance correction following moving average method computing formula of employing:
x ^ t + 1 = x t + 1 + α ( x ^ t - x t )
WhereinFor actual irradiance value, x after revisingt+1For the irradiance value of initial forecast, xtFor time previous Carve the irradiance value of initial forecast,For the actual irradiance value of previous moment, α is coefficient, and numerical range is 0～1, the calculating process of side reaction coefficient can use method of least square in prior art to calculate, generally at irradiance When data variation is big, α value is less, and in irradiance data change hour, α value is relatively big, α in the application Choose empirical value 0.5.
Further, in described step 6, it is known that prediction day revised irradiance xn, power factor is searched Table, then the generated output computing formula after normalization is: f (xn)=f (x1)+f ' (x0) (xn-x1), will meter The value calculated is multiplied by working capacity and is the generated output of prediction day.
Time before photovoltaic electric station grid connection without relevant historical data, choose the site history data that geographical position is close Calculate power factor table according to above method, predict the generating of this photovoltaic plant according to this power factor table Power；After photovoltaic electric station grid connection, first with the fine day condition data of grid-connected actual motion according to top Method calculates the power factor table of this photovoltaic plant, then carries out generated power forecasting.
Compared with prior art, the present invention is reached to provide the benefit that:
1) historical data under the conditions of the present invention uses fine day is as sample, and sample data is normalized, Translation and correcting process, the station data making geographical position close has similarity, before photovoltaic electric station grid connection In time without relevant historical data, the close site history data in geographical position can be chosen and calculate according to above method Go out power factor table, predict the generated output of this photovoltaic plant according to this power factor table, make photovoltaic plant Power prediction function is just possessed before grid-connected；
2) historical sample under the conditions of the fine day that computational methods of the present invention need is few, runs at photovoltaic electric station grid connection A period of time, utilize two groups of fine day condition data samples of grid-connected actual motion, calculate according to above method The power factor table of this photovoltaic plant, then can carry out generated power forecasting, solve photovoltaic electric station grid connection The problem that initial stage lacks the data sample that effectively generates electricity；
3) process of the present invention is simply clear, accurate forecast photovoltaic plant changed power, provides ginseng for dispatching of power netwoks Examine scientific basis, improve economy and the safety of operation of power networks.
Accompanying drawing explanation
Fig. 1 is the flow chart of the photovoltaic power factor table Forecasting Methodology of the present invention.
Detailed description of the invention
The invention will be further described below in conjunction with the accompanying drawings.Following example are only used for clearly illustrating Technical scheme, and can not limit the scope of the invention with this.
As it is shown in figure 1, a kind of photovoltaic power factor table Forecasting Methodology, it is characterized in that, comprise the following steps:
Step one, under the conditions of choosing at least two group fair weather, photovoltaic plant normal power generation data are as sample, Sample includes date, time, irradiance and generated output parameter；
Under the conditions of choosing at least two group fair weather, photovoltaic plant normal power generation data are as sample, abandon sleet, Generate electricity under the weather of cloudy day and sky cloud effect data, remove ration the power supply, overhaul, the improper (operation of the quality of data Member's locking, test (maintenance) replacement, inaccuracy, inconsistent, legacy data (not refreshing) fault, shake, Bad reference value, the territory that overflows, spilling, invalid, suspicious) when generating data；Sample data gathers Frequency is 15 minutes, every day gather sample include 96 collection points, choose sunny under the conditions of generating Power data should be smoothed curve form；
Step 2, utilizes the generated output in working capacity normalized sample, and working capacity is photovoltaic electric Stand the actual capacity being incorporated into the power networks；
After working capacity refers to photovoltaic electric station grid connection, the capacity can powered to electrical network, i.e. photovoltaic plant reality is also The capacity of network operation, generally less than installed capacity.Active power output is had a direct impact, no by working capacity With the active power output difference that working capacity is corresponding, the working capacity of different photovoltaic plants is the most different, same Power station working capacity also can be with rationing the power supply or the change of the factor such as maintenance；Active power must be considered when using historical data Corresponding with working capacity, by active power to the relative value after working capacity normalization during calculating, at normalization Reason is i.e. power divided by working capacity, draw predict the outcome after be multiplied by working capacity again and draw pre-power scale Absolute value；
Step 3, in sample, different date datas are translated as centered by irradiance peak；
Sun set/raise time changes on an equal basis with seasonal variations, longitude and latitude, and place as same in China is at sunrise Between may several hours of gap in 1 year；And the time period residing for daytime is the most different in 1 year.The most on the same day The synchronization generating output of phase and power generation characteristics are the most variant, and same track of sun position power generation characteristics is relatively Close.Sunrise, high noon, sunset process in observing one day, different track of sun position correspondence photovoltaic arrays Generated output is different, and the generated output that track of sun position same between similar day is corresponding is close.And sample Collection is that with 15 minutes for interval, irradiance peak is not easy accurately to choose, when therefore using sunrise sunset Between difference determine irradiance peak, detailed process is, calculates sunrise sunset moment corresponding to irradiance Average time puts as midpoint, and midpoint is approximately the moment that in one day, irradiance is the highest, in being moved to by sample Point alignment；After multi-group data alignment, the data correspondence sun altitude of same column position is identical.Therefore use Sun set/raise time midpoint alignment thereof, i.e. track of sun aligned in position mode, can be more accurately anti-after translation Reflect the relation between generated output and irradiance；
Step 4, utilizes sample data to be calculated power factor table；
The detailed process utilizing sample data to be calculated power factor table is, it is known that normalized generated output P Function f (x) of irradiance can be launched by Taylor's formula,
f ( x ) = f ( a ) 0 ! + f ′ ( a ) 1 ! ( x - a ) + f ′ ′ ( a ) 2 ! ( x - a ) 2 + ... + f ( n ) ( a ) n ! ( x - a ) n + R n ( x )
Wherein, x is irradiance, and f (x) is generated output function, f(n)A () is the n order derivative of generated output It is value during a at irradiance, RnX () is (x-a)nHigher-order shear deformation；
Retain wherein first order and constant term, according to the sample frequency of every 15 minutes 1 time, within 1 day, have 96 to count According to, for sample L1:(1,2..., 96) and sample L2:(1,2..., 96), at the same string (spoke of alignment In illumination i.e. sample L1, irradiance is x1, and in sample L2, irradiance is x2) power P can be expressed as follows
f ( x 1 ) = f ( x 0 ) 0 ! + f ′ ( x 0 ) 1 ! ( x 1 - x 0 ) + R n ( x )
f ( x 2 ) = f ( x 0 ) 0 ! + f ′ ( x 0 ) 1 ! ( x 2 - x 0 ) + R n ( x )
Can show that coefficient of first order is according to above formulaAt piecewise approximation bar Under part, repeat said process, calculate the piecewise linearity mathematical relationship between generated output and irradiance, composition Power factor table；
Step 5, utilizes the forecast irradiance of meteorological observation substation actual irradiance correction prediction day；
Numerical weather forecast typically carries and obtaining the previous day at home, and relatively accurate in the case of fine day, sleet is cloudy Fractional error is had during change weather；Actual irradiation based on meteorological observation substation, photovoltaic plant scene meteorological data Degree is revised, and can significantly improve the accuracy of numerical weather forecast irradiance；Irradiance correction uses calculated below Formula:
x ^ t + 1 = x t + 1 + α ( x ^ t - x t )
WhereinFor actual irradiance value, x after revisingt+1For the irradiance value of initial forecast, xtFor time previous Carve the irradiance value of initial forecast,For the actual irradiance value of previous moment, α is coefficient, and numerical range is 0～1, the calculating process of side reaction coefficient can use method of least square in prior art to calculate, generally at irradiance When data variation is big, α value is less, and in irradiance data change hour, α value is relatively big, α in the application Choose empirical value 0.5；
Step 6, searches power factor table according to prediction day revised irradiance and dopes generated output；
The same string generated output computing formula of prediction day is: f (xn)=f (x1)+f ' (x0) (xn-x1), its Middle xn is prediction day revised irradiance；Said process is that normalized value calculates, and output result is multiplied by fortune Row capacity is designated as the generated output of prediction.
The present invention use the historical data under the conditions of fine day as sample, and sample data is normalized, Translation and correcting process, the station data making geographical position close has similarity, before photovoltaic electric station grid connection In time without relevant historical data, the close site history data in geographical position can be chosen and calculate according to above method Go out power factor table, predict the generated output of this photovoltaic plant according to this power factor table, make photovoltaic plant Power prediction function is just possessed before grid-connected；After photovoltaic electric station grid connection, run one section at photovoltaic electric station grid connection Time, utilize two groups of fine day condition data samples of grid-connected actual motion, calculate this light according to above method The power factor table of overhead utility, then can carry out generated power forecasting.
The above is only the preferred embodiment of the present invention, it is noted that common for the art For technical staff, on the premise of without departing from the technology of the present invention principle, it is also possible to make some improvement and change Type, these improve and modification also should be regarded as protection scope of the present invention.

Claims (5)

1. a photovoltaic power factor table Forecasting Methodology, is characterized in that, comprises the following steps:
Step one, under the conditions of choosing at least two group fair weather, photovoltaic plant normal power generation data are as sample, Sample includes date, time, irradiance and generated output parameter；
Step 2, utilizes the generated output in working capacity normalized sample, and working capacity refers to photovoltaic electric Stand the actual capacity being incorporated into the power networks；
Step 3, in sample, different date datas are translated as centered by irradiance peak；
Step 4, utilizes sample data to be calculated power factor table；
Step 5, the forecast irradiance of day is predicted in the irradiance correction utilizing meteorological observation substation to measure；
Step 6, searches power factor table according to prediction day revised irradiance and dopes generated output.
A kind of photovoltaic power factor table Forecasting Methodology the most according to claim 1, is characterized in that, described In step 3, sample translation detailed process is, the average time choosing the sunrise sunset moment puts as midpoint, Midpoint is the moment that in one day, irradiance is the highest, and sample moves to midpoint alignment.
A kind of photovoltaic power factor table Forecasting Methodology the most according to claim 2, is characterized in that, described In step 4, the detailed process utilizing sample data to be calculated power factor table is, it is known that normalized Function f (x) of irradiance can be launched by electrical power P by Taylor's formula,
f ( x ) = f ( a ) 0 ! + f ′ ( a ) 1 ! ( x - a ) + f ′ ′ ( a ) 2 ! ( x - a ) 2 + ... + f ( n ) ( a ) n ! ( x - a ) n + R n ( x )
Wherein, f(n)(a) be the n order derivative of generated output be value during a at irradiance, RnX () is (x-a)n's Higher-order shear deformation；
Retain wherein first order and constant term, for sample L1 and sample L2, at same string (the i.e. sample of alignment In this L1, irradiance is x1, and in sample L2, irradiance is x2) generated output P can be expressed as follows
f ( x 1 ) = f ( x 0 ) 0 ! + f ′ ( x 0 ) 1 ! ( x 1 - x 0 ) + R n ( x )
f ( x 2 ) = f ( x 0 ) 0 ! + f ′ ( x 0 ) 1 ! ( x 2 - x 0 ) + R n ( x )
Can show that coefficient of first order is according to above formulaAt piecewise approximation bar Under part, repeat said process, calculate the piecewise linearity mathematical relationship between generated output and irradiance, composition Power factor table.
A kind of photovoltaic power factor table Forecasting Methodology the most according to claim 3, is characterized in that, described In step 5, the irradiance correction following moving average method computing formula of employing:
x ^ t + 1 = x t + 1 + α ( x ^ t - x t )
WhereinFor actual irradiance value, x after revisingt+1For the irradiance value of initial forecast, xtFor time previous Carve the irradiance value of initial forecast,For the actual irradiance value of previous moment, α is coefficient, and numerical range is 0～1, α chooses 0.5.
A kind of photovoltaic power factor table Forecasting Methodology the most according to claim 4, is characterized in that, it is known that Prediction day revised irradiance xn, then the generated output computing formula after normalization is: F (xn)=f (x1)+f ' (x0) (xn-x1), is multiplied by the value calculated working capacity and is the generating of prediction day Power.
CN201610247301.3A 2016-04-20 2016-04-20 A kind of photovoltaic power factor table prediction technique Active CN105956685B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610247301.3A CN105956685B (en) 2016-04-20 2016-04-20 A kind of photovoltaic power factor table prediction technique

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610247301.3A CN105956685B (en) 2016-04-20 2016-04-20 A kind of photovoltaic power factor table prediction technique

Publications (2)

Publication Number Publication Date
CN105956685A true CN105956685A (en) 2016-09-21
CN105956685B CN105956685B (en) 2019-09-10

Family

ID=56917697

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610247301.3A Active CN105956685B (en) 2016-04-20 2016-04-20 A kind of photovoltaic power factor table prediction technique

Country Status (1)

Country Link
CN (1) CN105956685B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108537357A (en) * 2018-02-09 2018-09-14 上海电气分布式能源科技有限公司 Photovoltaic power generation quantity loss forecasting method based on derating factor
CN111414582A (en) * 2020-03-12 2020-07-14 广西电网有限责任公司 Photovoltaic theoretical power calculation method, device, equipment and storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103559561A (en) * 2013-11-13 2014-02-05 上海电气集团股份有限公司 Super-short-term prediction method of photovoltaic power station irradiance

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103559561A (en) * 2013-11-13 2014-02-05 上海电气集团股份有限公司 Super-short-term prediction method of photovoltaic power station irradiance

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
赵欣宇: "光伏发电系统功率预测的研究与实现", 《中国优秀硕士学位论文全文库》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108537357A (en) * 2018-02-09 2018-09-14 上海电气分布式能源科技有限公司 Photovoltaic power generation quantity loss forecasting method based on derating factor
CN108537357B (en) * 2018-02-09 2021-10-01 上海电气分布式能源科技有限公司 Photovoltaic power generation loss prediction method based on derating factor
CN111414582A (en) * 2020-03-12 2020-07-14 广西电网有限责任公司 Photovoltaic theoretical power calculation method, device, equipment and storage medium
CN111414582B (en) * 2020-03-12 2022-12-27 广西电网有限责任公司 Photovoltaic theoretical power calculation method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN105956685B (en) 2019-09-10

Similar Documents

Publication Publication Date Title
De Jong et al. Solar and wind energy production in relation to the electricity load curve and hydroelectricity in the northeast region of Brazil
CN102945508B (en) Model correction based wind power forecasting method
CN103778340B (en) The statistical method of extensive generation of electricity by new energy characteristic
CN104868505B (en) Large solar photovoltaic generating base cluster power producing characteristics analysis method
CN109086928A (en) Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model
CN109978242A (en) The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics
CN113496311A (en) Photovoltaic power station generated power prediction method and system
CN107609697A (en) A kind of Wind power forecasting method
CN108960541A (en) Distributed photovoltaic system effectiveness appraisal procedure and device based on the analysis of cloud data
CN106600060A (en) Method for predicting amount of solar radiation based on similar day sunny coefficient correction
CN102479347A (en) Method and system for forecasting short-term wind speed of wind farm based on data driving
CN103996079A (en) Wind power weighting predication method based on conditional probability
CN104268659A (en) Photovoltaic power station generated power super-short-term prediction method
CN103345585A (en) Wind power prediction correction method and system based on support vector machine
CN103440529A (en) Lateral error translation modification method of wind electricity power forecast system
CN107403015A (en) A kind of short-term luminous power Forecasting Methodology based on Time Series Similarity
CN104362621A (en) Entropy weight method resistance based photovoltaic power station operation characteristic assessment method
CN109960885A (en) A kind of distributed photovoltaic power generation power forecasting method
CN103927597A (en) Ultra-short-term wind power prediction method based on autoregression moving average model
Saranchimeg et al. A novel framework for integration analysis of large-scale photovoltaic plants into weak grids
CN105956685A (en) Photovoltaic power factor table prediction method
CN104239979B (en) A kind of wind power plant generated output ultra-short term prediction method
CN105701556A (en) Photovoltaic power station super-short-time power prediction correcting method
CN104657787B (en) A kind of wind power time series combination forecasting method
CN108268961A (en) A kind of solar radiation ultra-short term prediction method based on weather pattern

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