CN109345046A - The prediction technique and device of photovoltaic power - Google Patents
The prediction technique and device of photovoltaic power Download PDFInfo
- Publication number
- CN109345046A CN109345046A CN201811480173.2A CN201811480173A CN109345046A CN 109345046 A CN109345046 A CN 109345046A CN 201811480173 A CN201811480173 A CN 201811480173A CN 109345046 A CN109345046 A CN 109345046A
- Authority
- CN
- China
- Prior art keywords
- rain
- day
- irradiation level
- shine
- index
- 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
- 230000003203 everyday effect Effects 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 14
- 230000002354 daily effect Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 230000001052 transient effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 238000005286 illumination Methods 0.000 claims description 2
- 238000010248 power generation Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000005855 radiation Effects 0.000 description 4
- 230000001932 seasonal effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000005201 scrubbing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the present invention provides the prediction technique and device of a kind of photovoltaic power, and wherein method includes: the predicted value in the measured value and each day forecast of historical time for obtain irradiation level of the single photovoltaic plant in historical time about the irradiation level of target date;Calculate the rain or shine index that the same day is actual and predicts;It calculates and corrects rain or shine index and benchmark rain or shine index;According to the benchmark rain or shine index and the amendment rain or shine index, the historical time last day is modified the predicted value of the irradiation level of the target date, target date revised irradiation level is obtained, the power curve of photovoltaic plant is calculated according to the target date revised irradiation level.The embodiment of the present invention improves tradition using the stability of single weather forecast, improves the utilization rate of forecast data, has excavated the key index being hidden in inside data, while improving the utilization rate of data, improves accuracy of the forecast.
Description
Technical field
The present embodiments relate to power grid photovoltaic power generation electric powder predictions, more particularly, to the prediction of photovoltaic power
Method and device.
Background technique
Under the background that photovoltaic power generation grid-connecting capacity steps up, accurately and effectively predict that photovoltaic plant output power is light
The basis of overhead utility power generation, under this demand, photovoltaic power generation Predicting Technique achieves significant progress therewith.To being at present
Only, the predicting power of photovoltaic plant model of mainstream still relies on numerical weather prediction as modeling basis.By numerical weather prediction
In relevant to photovoltaic power generation meteorological element variable as input, prediction in 1-3 days is carried out to generated energy, to obtain photovoltaic
Power curve, so that electric system can be with this will serve as a proof according to progress power scheduling.Wherein numerical weather prediction is commonly known as gas
As source, and the process for calculating power curve is referred to as modeling.
The numerical model period more gentle in weather modification, prediction strategy is higher, when weather modification is violent, in advance
It is lower to survey skill.Mode process and the closely related heat of atmospheric surface, momentum and Water Transport, nonlinear interaction etc.
There is relationship.Since numerical model is made of kinetic equation, forecasting system will cause by the difference of initial fields and generate deviation.Make
The prediction result of photovoltaic power will be seriously affected with the resulting weather system error of single number weather forecasting.
It is the solar radiation flux for reaching ground, usual situation with the maximally related element of photovoltaic plant in numerical prediction
Under, theoretical intensity of solar radiation depends on the variables such as elevation angle, solar distance and the sunshine-duration of the sun, but due to receiving cloud
The influence of layer, aerosol etc., solar radiation flux difference is larger under DIFFERENT METEOROLOGICAL CONDITIONS, and wherein determines that photovoltaic power prediction is quasi-
The key of true rate is correctly predicted level of solar radiation, also referred to as irradiance level.Since apparent diurnal periodicity is presented in irradiation level
Rule, day irradiance level also become one of the index for measuring forecasting accuracy, the index also referred to as rain or shine index.Due to number
The difference of value mode initial fields and parameter setting, the radiancy level predicted also will appear difference, be conventionally based on
The modeling of raw value weather forecasting, it will usually there is a situation where irradiance level predict it is unstable, to reduce this photovoltaic
The precision of power prediction.
Summary of the invention
The embodiment of the present invention provides a kind of photovoltaic power for overcoming the above problem or at least being partially solved the above problem
Prediction technique and device.
First aspect, the embodiment of the present invention provide a kind of prediction technique of photovoltaic power, comprising:
Obtain single photovoltaic plant in each day of the measured value and historical time forecast of the irradiation level of historical time about
The predicted value of the irradiation level of target date;The last day of the historical time is the previous day of the target date;
The same day actual rain or shine index is calculated according to the measured value of same day irradiation level to any one day of the historical time;
According to the forecast on date before the same day to the predicted value of same day irradiation level, the rain or shine index of same day prediction is calculated;
According to every day in the historical time it is actual and it is expected that rain or shine index, calculated using Kalman filter equation
First predicted value of the rain or shine index of the target date, as amendment rain or shine index;
According to the forecast of the historical time last day to the predicted value of the irradiation level of the target date, described in calculating
Second predicted value of the rain or shine index of target date, as benchmark rain or shine index;
According to the benchmark rain or shine index and the amendment rain or shine index, to the historical time last day to described
The predicted value of the irradiation level of target date is modified, and target date revised irradiation level is obtained, according to the target date
Revised irradiation level calculates the power curve of photovoltaic plant.
The second aspect, the embodiment of the present invention provide a kind of prediction meanss of photovoltaic power, comprising:
Historical data obtains module, for obtaining single photovoltaic plant in the measured value of the irradiation level of historical time and going through
Predicted value in each day forecast of history time about the irradiation level of target date;The last day of the historical time is the target
The previous day on date;
Rain or shine index computing module, for being counted to any one day of the historical time according to the measured value of same day irradiation level
Calculate the same day actual rain or shine index;According to the forecast on date before the same day to the predicted value of same day irradiation level, same day prediction is calculated
Rain or shine index;
Amendment rain or shine index computing module, for according to every day in the historical time it is actual and it is expected that rain or shine refer to
Number, the first predicted value of the rain or shine index of the target date is calculated using Kalman filter equation, as amendment rain or shine index;
Benchmark rain or shine index computing module, for according to the forecast of the historical time last day to the target date
Irradiation level predicted value, the second predicted value of the rain or shine index of the target date is calculated, as benchmark rain or shine index;
Photovoltaic power computing module, for according to the benchmark rain or shine index and the amendment rain or shine index, to described
Historical time last day is modified the predicted value of the irradiation level of the target date, obtains target date revised spoke
Illumination calculates the power curve of photovoltaic plant according to the target date revised irradiation level.
The third aspect, the embodiment of the present invention provides a kind of electronic equipment, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, is realized when the processor executes described program as first aspect provides
Method the step of.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, are stored thereon with calculating
Machine program is realized as provided by first aspect when the computer program is executed by processor the step of method.
The prediction technique and device of photovoltaic power provided in an embodiment of the present invention obtain single photovoltaic plant in historical time
Irradiation level measured value and the forecast of each day of historical time in about the target date irradiation level predicted value;Calculating is worked as
Its actual and prediction rain or shine index;It calculates and corrects rain or shine index and benchmark rain or shine index;According to the benchmark rain or shine index
And the amendment rain or shine index, predicted value of the historical time last day to the irradiation level of the target date is carried out
Amendment obtains target date revised irradiation level, calculates photovoltaic plant according to the target date revised irradiation level
Power curve.The embodiment of the present invention improves tradition using the stability of single weather forecast, improves the utilization of forecast data
Rate has excavated the key index being hidden in inside data, while improving the utilization rate of data, improves accuracy of the forecast.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow diagram of the prediction technique of photovoltaic power provided in an embodiment of the present invention;
Fig. 2 is the structural schematic diagram of the prediction meanss of photovoltaic power provided in an embodiment of the present invention;
Fig. 3 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In order to overcome the above problem of the prior art, the embodiment of the invention provides a kind of prediction technique of photovoltaic power and
Device, inventive concept are as follows: the method predicted by history forecast correction photovoltaic is repeatedly forecast for the odd-numbered day, uses Kalman
Filtering method establishes filtering equations, and for the odd-numbered day, rain or shine index carries out Forecast model, to promote whole photovoltaic forecast stability
And accuracy.
Fig. 1 is the flow diagram of the prediction technique of photovoltaic power provided in an embodiment of the present invention, as shown in Figure 1, comprising:
In S101, the measured value for obtaining irradiation level of the single photovoltaic plant in historical time and each day forecast of historical time
The predicted value of irradiation level about target date;The last day of the historical time is the previous day of the target date.
Specifically, the embodiment of the present invention selects the following some day as target date first, such as selects November 1 in 2018
Day it is used as target date, then obtains single photovoltaic plant in historical time, such as October 20 is to day part on October 31
The measured value of irradiation value and October 20 to during October 31 daily to the irradiation value of the November in 2018 of day part on the 1st
Predicted value.
S102, was calculated actual rain or shine the same day according to the measured value of same day irradiation level to any one day of the historical time
Index;According to the forecast on date before the same day to the predicted value of same day irradiation level, the rain or shine index of same day prediction is calculated.
It should be noted that the embodiment of the present invention need to obtain in historical time the predicted value of the rain or shine index of every day and
Actual value, wherein rain or shine the actual value of index is calculated according to the measured value of the same day all period irradiation values, and rain or shine index
Predicted value then have it is multiple, this is because every day can all predict the irradiation value of subsequent certain number of days, for example, for 10
It is pre- due to can daily be carried out to irradiation value on the 25th October 20 to October 24 for the predicted value of the rain or shine index on the moon 25
It surveys, accordingly, there exist 5 predicted values for irradiation value on the 25th.
S103, according to every day in the historical time it is actual and it is expected that rain or shine index, utilize Kalman filtering side
Journey calculates the first predicted value of the rain or shine index of the target date, as amendment rain or shine index.
It should be noted that Kalman filtering (Kalman filtering) is a kind of to utilize linear system state equation, lead to
System input and output observation data are crossed, the algorithm of optimal estimation is carried out to system mode.Due to including in system in observation data
Noise and interference influence, so optimal estimation is also considered as filtering.In embodiments of the present invention, pass through Kalman
The prediction of the rain or shine index to the date where target date may be implemented in filtering, as amendment rain or shine index.
S104, according to the forecast of the historical time last day to the predicted value of the irradiation level of the target date, meter
The second predicted value for calculating the rain or shine index of the target date, as benchmark rain or shine index.
It is understood that since irradiation level of the historical time last day to time zone all periods where target date is equal
It can predict, therefore, the prediction of the rain or shine index to the date where target date also may be implemented according to these irradiation level predicted,
Using predicted value as benchmark rain or shine index.
S105, according to the benchmark rain or shine index and the amendment rain or shine index, to the historical time last day
The predicted value of the irradiation level of the target date is modified, target date revised irradiation level is obtained, according to the mesh
Mark the power curve that date revised irradiation level calculates photovoltaic plant.
It should be noted that passing through benchmark rain or shine index and amendment since rain or shine index is calculated by irradiation level
Rain or shine the otherness between index can be obtained to the historical time last day to the predicted value of the irradiation level of the target date
Obtain the predicted value of revised irradiation level.Belong to known in this neighborhood it should be appreciated that calculating photovoltaic power generation curve using irradiation level
Common sense, details are not described herein.
Compared with prior art, the embodiment of the present invention is utilized more days not be fully utilized in history forecast and forecasts,
It reconstructs data and establishes the best estimate based on kalman filter method, by gathering multiple forecast result, improve traditional use
The stability of single weather forecast improves the utilization of forecast data compared to tradition using the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of multiple meteorologies
Rate, has excavated the key index being hidden in inside data, at the same the embodiment of the present invention it is innovative using rain or shine index as number
The key index of photovoltaic forecast, improves the utilization rate of data, improves the standard of forecast in value simulation weather system translation motion
True property.
On the basis of the various embodiments described above, calculated as a kind of alternative embodiment according to the measured value of same day irradiation level
The same day actual rain or shine index, is calculated with specific reference to following formula:
Wherein,Indicate that the t days actual rain or shine indexes, n indicate the prediction number of irradiation level in one day, x (i) is indicated
The measured value of the irradiation level of i-th of period, x in one daymaxIndicate the maximum value of irradiation level in one day.
On the basis of the various embodiments described above, as a kind of alternative embodiment, according to the forecast on date before the same day to the same day
The predicted value of irradiation level calculates the rain or shine index of same day prediction, is calculated with specific reference to following formula:
Wherein,Indicate that the u days rain or shine indexes to prediction in the t days, n indicate the prediction of irradiation level in one day
Number, xu(i) predicted value of the u days irradiation level to the t days i-th period is indicated,It indicates to predict the t days in the u days
All periods irradiation level maximum value.
It is real according to every day in the historical time as a kind of alternative embodiment on the basis of the various embodiments described above
Border and it is expected that rain or shine index, date prediction rain or shine refers to where calculating target date using Kalman filter equation
Number, specifically:
For kth day in historical time, Kalman's filter is established to the rain or shine index of kth day prediction according to l days before kth day
Wave equation, in conjunction with the actual rain or shine index construction state-transition matrix of kth day;
According to state-transition matrix obtain the actual rain or shine index of kth day and it is expected that rain or shine index between deviation, according to
The deviation is modified the rain or shine index of prediction in kth+1 day, until date prediction where obtaining target date rain or shine refers to
Number.
For example, every daily forecast has a prediction of following 7 days irradiation level, data area was from June 1 to June 30 in 2018
Day, for the purpose of the predicted value of rain or shine index for correcting July 1.Calculated for 16 dates rain or shine to calculate Kalman filter equation
For index, June 10 was calculated to the predicted value of irradiation level on the 16th according to June 10 to every daily forecast on June 15 respectively
To June 15 to the predicted value of rain or shine index on the 16th to establish Kalman filter equation, in conjunction with the reality of irradiation level on the 16th in June
The actual value of the calculated rain or shine index of measured value constructs state-transition matrix, obtains the actual rain or shine index on June 16 and pre-
Deviation between the rain or shine index of meter, is modified, continuous recursion according to predicted value of the deviation to the rain or shine index on June 17,
Finally the predicted value of the rain or shine index on July 1 is modified.
On the basis of the above embodiments, as a kind of alternative embodiment, it is also necessary to single photovoltaic plant in history
Between the measured value of irradiation level carry out seasonal filtering processing, filter out season trend term therein.This is because Various Seasonal
Irradiation level can have apparent difference, since practical predetermined period forecast daily is usually at 7 to 15 days or so, if prediction
Time is in the same moon or season, and the prediction result of irradiation level is also relatively more accurate, but if across seasonal forecasting, irradiation level
Prediction result is unsatisfactory, for example, belong to month at the end of spring and the beginning of summer June, the weather item of weather conditions and 6 the end of month at the beginning of 6 months
Part usually has apparent difference.Specifically seasonal filtering includes: the embodiment of the present invention
To the measured value of irradiation level daily in historical time, made even according to the measured value of certain time length before and after the same day
Mean value, the correction value of the measured value of the irradiation level as the same day.
On the basis of the above embodiments, further include to the data scrubbing of irradiation level and abnormal actual measurement irradiation level is carried out
It screens out.
On the basis of the various embodiments described above, according to benchmark rain or shine index and the amendment rain or shine index, gone through to described
Last day history time is modified the predicted value of the irradiation level of the target date, obtains target date revised irradiation
Degree is calculated with specific reference to following formula:
Wherein,Indicate benchmark rain or shine index,Indicate that amendment rain or shine index, x (r) indicate that historical time is last
The predicted value of one day irradiation level to the target date,Indicate target date revised irradiation level.
Fig. 2 is the structural schematic diagram of the prediction meanss of photovoltaic power provided in an embodiment of the present invention, as shown in Fig. 2, this is pre-
Surveying device includes: that historical data obtains module 201, rain or shine index computing module 202, amendment rain or shine index computing module 203, base
The fine index computing module 204 in Zhunyin, photovoltaic power computing module 205, in which:
Historical data obtain module 201, for obtain single photovoltaic plant the irradiation level of historical time measured value with
And the predicted value in each day forecast of historical time about the irradiation level of the target date;The last day of the historical time is
The previous day of the target date.
Specifically, the historical data acquisition module 201 of the embodiment of the present invention selects the following some day as target day first
Phase, such as select on November 1st, 2018 as target date, single photovoltaic plant is then obtained in historical time, such as October
The measured value of irradiation value to day part on the 31st in October on the 20th and October 20 to during October 31 daily to 2018 11
The predicted value of the irradiation value of month day part on the 1st.
Rain or shine index computing module 202 is used for any one day of the historical time, according to the actual measurement of same day irradiation level
Value calculates the same day actual rain or shine index;According to the forecast on date before the same day to the predicted value of same day irradiation level, the same day is calculated
The rain or shine index of prediction.
It should be noted that the rain or shine index computing module 202 of the embodiment of the present invention obtains every day in historical time
The rain or shine predicted value and actual value of index, wherein rain or shine the actual value of index is the actual measurement according to the same day all period irradiation values
Value calculate, and rain or shine the predicted value of index then have it is multiple, this is because every day all can be to the irradiation value of subsequent certain number of days
It is predicted, for example, for the predicted value of the rain or shine index on October 25, due to average daily meeting in October 20 to October 24
Irradiation value on the 25th is predicted, accordingly, there exist 5 predicted values for irradiation value on the 25th.
Amendment rain or shine index computing module 203, for according to every day in the historical time it is actual and it is expected that yin
Fine index calculates the first predicted value of the rain or shine index of the target date using Kalman filter equation, rain or shine as amendment
Index.
It should be noted that Kalman filtering (Kalman filtering) is a kind of to utilize linear system state equation, lead to
System input and output observation data are crossed, the algorithm of optimal estimation is carried out to system mode.Due to including in system in observation data
Noise and interference influence, so optimal estimation is also considered as filtering.In embodiments of the present invention, amendment rain or shine refers to
The prediction of the rain or shine index to place date target date may be implemented by Kalman filtering for number computing modules 203, as repairing
Just rain or shine index.
Benchmark rain or shine index computing module 204, for according to the forecast of the historical time last day to the target
The predicted value of the irradiation level on date calculates the second predicted value of the rain or shine index of the target date, as benchmark rain or shine index.
It is understood that since irradiation level of the historical time last day to time zone all periods where target date is equal
It can predict, therefore, the prediction of the rain or shine index to the date where target date also may be implemented according to these irradiation level predicted,
Using predicted value as benchmark rain or shine index.
Photovoltaic power computing module 205, for according to the benchmark rain or shine index and the amendment rain or shine index, to institute
Stating historical time last day is modified the predicted value of the irradiation level of the target date, and it is revised to obtain target date
Irradiation level calculates the power curve of photovoltaic plant according to the target date revised irradiation level.
It should be noted that passing through benchmark rain or shine index and amendment since rain or shine index is calculated by irradiation level
Rain or shine the otherness between index can be obtained to the historical time last day to the predicted value of the irradiation level of the target date
Obtain the predicted value of revised irradiation level.Belong to known in this neighborhood it should be appreciated that calculating photovoltaic power generation curve using irradiation level
Common sense, details are not described herein.
The prediction meanss of photovoltaic power provided in an embodiment of the present invention specifically execute the prediction technique of above-mentioned each photovoltaic power
Embodiment process please specifically be detailed in the content of the prediction technique embodiment of above-mentioned each photovoltaic power, and details are not described herein.The present invention
The prediction meanss for the photovoltaic power that embodiment provides are utilized more days not be fully utilized in history forecast and forecast, reconstruct
Data establish the best estimate based on kalman filter method, by gathering multiple forecast result, improve traditional using single
The stability of weather forecast improves the utilization rate of forecast data compared to tradition using the DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of multiple meteorologies, digs
Dug the key index being hidden in inside data, at the same the embodiment of the present invention it is innovative using rain or shine index as numerical simulation
The key index that photovoltaic is forecast in weather system translation motion, improves the utilization rate of data, improves accuracy of the forecast.
Fig. 3 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in Fig. 3, the electronic equipment
It may include: processor (processor) 310,320, memory communication interface (Communications Interface)
(memory) 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 pass through communication bus 340
Complete mutual communication.Processor 310 can call the meter that is stored on memory 330 and can run on processor 310
Calculation machine program, to execute the prediction technique of the photovoltaic power of the various embodiments described above offer, for example, obtain single photovoltaic plant
About the pre- of the irradiation level of the target date in each day forecast of measured value and historical time of the irradiation level of historical time
Measured value;The last day of the historical time is the previous day of the target date;To any one day of the historical time, according to
The measured value of same day irradiation level calculates the same day actual rain or shine index;According to the forecast on date before the same day to same day irradiation level
Predicted value, calculate the same day predict rain or shine index;According to every day in the historical time it is actual and it is expected that rain or shine refer to
Number, the first predicted value of the rain or shine index of the target date is calculated using Kalman filter equation, as amendment rain or shine index;
According to the forecast of the historical time last day to the predicted value of the irradiation level of the target date, the target date is calculated
Rain or shine index the second predicted value, as benchmark rain or shine index;Rain or shine according to the benchmark rain or shine index and the amendment
Index is modified the historical time last day to the predicted value of the irradiation level of the target date, obtains target day
Phase revised irradiation level calculates the power curve of photovoltaic plant according to the target date revised irradiation level.
In addition, the logical order in above-mentioned memory 330 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
The technical solution of the inventive embodiments substantially part of the part that contributes to existing technology or the technical solution in other words
It can be embodied in the form of software products, which is stored in a storage medium, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes the present invention respectively
The all or part of the steps of a embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk
Etc. the various media that can store program code.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, is stored thereon with computer program,
The computer program is implemented to carry out the prediction technique of the photovoltaic power of the various embodiments described above offer when being executed by processor, such as
It include: in the measured value and each day forecast of historical time for obtain irradiation level of the single photovoltaic plant in historical time about described
The predicted value of the irradiation level of target date;The last day of the historical time is the previous day of the target date;To described
Any one day of historical time calculates the same day actual rain or shine index according to the measured value of same day irradiation level;According to the day before yesterday on the same day
The forecast of phase calculates the rain or shine index of same day prediction to the predicted value of same day irradiation level;According to every day in the historical time
It is actual and it is expected that rain or shine index, using Kalman filter equation calculate the rain or shine index of the target date first prediction
Value, as amendment rain or shine index;According to the forecast of the historical time last day to the pre- of the irradiation level of the target date
Measured value calculates the second predicted value of the rain or shine index of the target date, as benchmark rain or shine index;Rain or shine according to the benchmark
Index and the amendment rain or shine index, to the historical time last day to the predicted value of the irradiation level of the target date
It is modified, obtains target date revised irradiation level, photovoltaic electric is calculated according to the target date revised irradiation level
The power curve stood.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (9)
1. a kind of prediction technique of photovoltaic power characterized by comprising
Single photovoltaic plant is obtained in each day forecast of measured value and historical time of the irradiation level of historical time about target
The predicted value of the irradiation level on date;The last day of the historical time is the previous day of the target date;
The same day actual rain or shine index is calculated according to the measured value of same day irradiation level to any one day of the historical time;According to
The forecast on date calculated the rain or shine index of same day prediction to the predicted value of same day irradiation level before the same day;
According to every day in the historical time it is actual and it is expected that rain or shine index, calculated using Kalman filter equation described in
First predicted value of the rain or shine index of target date, as amendment rain or shine index;
According to the forecast of the historical time last day to the predicted value of the irradiation level of the target date, the target is calculated
Second predicted value of the rain or shine index on date, as benchmark rain or shine index;
According to the benchmark rain or shine index and the amendment rain or shine index, to the historical time last day to the target
The predicted value of the irradiation level on date is modified, and obtains target date revised irradiation level, is revised according to the target date
Irradiation level afterwards calculates the power curve of photovoltaic plant.
2. the prediction technique of photovoltaic power according to claim 1, which is characterized in that the reality according to same day irradiation level
Measured value calculates the same day actual rain or shine index, is calculated with specific reference to following formula:
Wherein,Indicate that the t days actual rain or shine indexes, n indicate the prediction number of irradiation level in one day, x (i) is indicated one day
In i-th of period irradiation level measured value, xmaxIndicate the maximum value of irradiation level in one day.
3. the prediction technique of photovoltaic power according to claim 1, which is characterized in that described according to the date before the same day
It forecasts the predicted value to same day irradiation level, calculates the rain or shine index of same day prediction, calculated with specific reference to following formula:
Wherein,Indicate that the u days rain or shine indexes to prediction in the t days, n indicate the prediction number of irradiation level in one day, xu
(i) predicted value of the u days irradiation level to the t days i-th period is indicated,Indicate that owns prediction in t days in u days
The maximum value of the irradiation level of period.
4. the prediction technique of photovoltaic power according to claim 1, which is characterized in that described according in the historical time
Every day it is actual and it is expected that rain or shine index, calculate the of the rain or shine index of the target date using Kalman filter equation
One predicted value, as amendment rain or shine index, specifically:
For kth day in historical time, Kalman filtering side is established to the rain or shine index of kth day prediction according to l days before kth day
Journey, in conjunction with the actual rain or shine index construction state-transition matrix of kth day;
According to state-transition matrix obtain the actual rain or shine index of kth day and it is expected that rain or shine index between deviation, according to described
Deviation is modified the rain or shine index of prediction in kth+1 day, until obtaining the first predicted value of the rain or shine index of target date.
5. the prediction technique of photovoltaic power according to claim 1, which is characterized in that any one to the historical time
It calculates the same day actual rain or shine index, according to the date before the same day according to the measured value of the irradiation level of all periods on the same day
It forecasts the predicted value to the irradiation level of all periods on the same day, calculates the rain or shine index of same day prediction, before further include:
To the measured value of irradiation level daily in historical time, it is averaged according to the measured value of certain time length before and after the same day
Value, the correction value of the measured value of the irradiation level as the same day, and abnormal actual measurement irradiation level is screened out.
6. the prediction technique of photovoltaic power according to claim 1, which is characterized in that described rain or shine to be referred to according to the benchmark
The several and described amendment rain or shine index, to the historical time last day to the predicted value of the irradiation level of the target date into
Row amendment, obtains target date revised irradiation level, calculates with specific reference to following formula:
Wherein,Indicate benchmark rain or shine index,Indicate that amendment rain or shine index, x (r) indicate historical time last day
To the predicted value of the irradiation level of the target date,Indicate target date revised irradiation level.
7. a kind of prediction meanss of photovoltaic power characterized by comprising
Historical data obtains module, for obtaining single photovoltaic plant in the measured value and history of the irradiation level of historical time
Between predicted value in the forecast of each day about the irradiation level of target date;The last day of the historical time is the target date
The previous day;
Rain or shine index computing module, for any one day of the historical time, according to the measured value of same day irradiation level, calculating to be worked as
Its actual rain or shine index;According to the forecast on date before the same day to the predicted value of same day irradiation level, the yin of same day prediction is calculated
Fine index;
Amendment rain or shine index computing module, for according to every day in the historical time it is actual and it is expected that rain or shine index,
The first predicted value that the rain or shine index of the target date is calculated using Kalman filter equation, as amendment rain or shine index;
Benchmark rain or shine index computing module, for the spoke according to the forecast of the historical time last day to the target date
The predicted value of illumination calculates the second predicted value of the rain or shine index of the target date, as benchmark rain or shine index;
Photovoltaic power computing module, for according to the benchmark rain or shine index and the amendment rain or shine index, to the history
Last day time is modified the predicted value of the irradiation level of the target date, obtains target date revised irradiation
Degree calculates the power curve of photovoltaic plant according to the target date revised irradiation level.
8. a kind of electronic equipment characterized by comprising
At least one processor;And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough prediction techniques executed as described in any one of claim 1 to 6.
9. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the prediction as described in any one of claim 1 to 6
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811480173.2A CN109345046B (en) | 2018-12-05 | 2018-12-05 | Photovoltaic power prediction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811480173.2A CN109345046B (en) | 2018-12-05 | 2018-12-05 | Photovoltaic power prediction method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109345046A true CN109345046A (en) | 2019-02-15 |
CN109345046B CN109345046B (en) | 2020-07-07 |
Family
ID=65320121
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811480173.2A Active CN109345046B (en) | 2018-12-05 | 2018-12-05 | Photovoltaic power prediction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109345046B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598335A (en) * | 2019-09-17 | 2019-12-20 | 阳光电源股份有限公司 | Irradiation correction method for ultra-short-term photovoltaic power prediction |
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 |
CN112330032A (en) * | 2020-11-09 | 2021-02-05 | 中国联合网络通信集团有限公司 | Active power output prediction method and device of photovoltaic power plant |
CN113076865A (en) * | 2021-03-31 | 2021-07-06 | 国能日新科技股份有限公司 | Method and system for inverting irradiance based on sky photographing image and satellite cloud image |
CN115115137A (en) * | 2022-07-26 | 2022-09-27 | 国能日新科技股份有限公司 | Photovoltaic power prediction method and device based on matching statistical wavelets |
CN115207923A (en) * | 2022-09-15 | 2022-10-18 | 苏州垚鑫焱科技有限公司 | Data processing method and equipment of power supply system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103390202A (en) * | 2013-07-18 | 2013-11-13 | 华北电力大学 | Output power prediction method based on similarity data selection for photovoltaic plant |
CN105787594A (en) * | 2016-02-29 | 2016-07-20 | 南京航空航天大学 | Irradiation prediction method based on multivariate time series and regression analysis |
JP2017010111A (en) * | 2015-06-17 | 2017-01-12 | 日本電気株式会社 | Device, method, and program for assisting with noise data rejection |
JP2018018329A (en) * | 2016-07-28 | 2018-02-01 | 富士通株式会社 | Power amount prediction program, power amount prediction device and power amount prediction method |
CN108846499A (en) * | 2018-04-13 | 2018-11-20 | 中国电力科学研究院有限公司 | A kind of meteorological element ultra-short term prediction method and device |
-
2018
- 2018-12-05 CN CN201811480173.2A patent/CN109345046B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103390202A (en) * | 2013-07-18 | 2013-11-13 | 华北电力大学 | Output power prediction method based on similarity data selection for photovoltaic plant |
JP2017010111A (en) * | 2015-06-17 | 2017-01-12 | 日本電気株式会社 | Device, method, and program for assisting with noise data rejection |
CN105787594A (en) * | 2016-02-29 | 2016-07-20 | 南京航空航天大学 | Irradiation prediction method based on multivariate time series and regression analysis |
JP2018018329A (en) * | 2016-07-28 | 2018-02-01 | 富士通株式会社 | Power amount prediction program, power amount prediction device and power amount prediction method |
CN108846499A (en) * | 2018-04-13 | 2018-11-20 | 中国电力科学研究院有限公司 | A kind of meteorological element ultra-short term prediction method and device |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598335A (en) * | 2019-09-17 | 2019-12-20 | 阳光电源股份有限公司 | Irradiation correction method for ultra-short-term photovoltaic power prediction |
CN110598335B (en) * | 2019-09-17 | 2023-08-11 | 阳光慧碳科技有限公司 | Irradiation correction method for ultra-short-term photovoltaic power prediction |
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 |
CN112330032A (en) * | 2020-11-09 | 2021-02-05 | 中国联合网络通信集团有限公司 | Active power output prediction method and device of photovoltaic power plant |
CN112330032B (en) * | 2020-11-09 | 2023-01-24 | 中国联合网络通信集团有限公司 | Active power output prediction method and device of photovoltaic power plant |
CN113076865A (en) * | 2021-03-31 | 2021-07-06 | 国能日新科技股份有限公司 | Method and system for inverting irradiance based on sky photographing image and satellite cloud image |
CN115115137A (en) * | 2022-07-26 | 2022-09-27 | 国能日新科技股份有限公司 | Photovoltaic power prediction method and device based on matching statistical wavelets |
CN115207923A (en) * | 2022-09-15 | 2022-10-18 | 苏州垚鑫焱科技有限公司 | Data processing method and equipment of power supply system |
Also Published As
Publication number | Publication date |
---|---|
CN109345046B (en) | 2020-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109345046A (en) | The prediction technique and device of photovoltaic power | |
Liu et al. | Random forest solar power forecast based on classification optimization | |
Behera et al. | Solar photovoltaic power forecasting using optimized modified extreme learning machine technique | |
Wang et al. | Sequence transfer correction algorithm for numerical weather prediction wind speed and its application in a wind power forecasting system | |
Mahmoud et al. | An advanced approach for optimal wind power generation prediction intervals by using self-adaptive evolutionary extreme learning machine | |
CN109615131A (en) | Photovoltaic power prediction technique and device | |
CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
US10956993B2 (en) | Method and device for determining energy system operating scenario | |
CN105576650B (en) | Based on assimilation technique and the wind power forecasting method and system with wind band theory | |
CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
Zhang et al. | Assessment of climate change impacts on the hydro-wind-solar energy supply system | |
CN106485093A (en) | Based on the solar irradiance time series synthetic method for improving Markov chain | |
JP2021531725A (en) | Techniques for estimating and predicting solar power | |
CN113779874B (en) | Multi-objective optimization method for off-grid micro-grid construction | |
Rahimi et al. | Calibration of Angstrom equation for estimating solar radiation using meta-heuristic harmony search algorithm (case study: Mashhad-East of Iran) | |
CN111709569A (en) | Method and device for predicting and correcting output power of wind power plant | |
Laslett et al. | A method for generating synthetic hourly solar radiation data for any location in the south west of Western Australia, in a world wide web page | |
CN112862274A (en) | WRF-LES and Deepar combined wind power prediction method | |
CN110008439A (en) | Rainfall data Spatio-temporal modeling interpolation algorithm based on matrix decomposition | |
WO2017049428A1 (en) | Spinning reserve capacity optimization method based on cost-performance ratio of reserve object | |
Mundra et al. | An efficient model for forecasting renewable energy using ensemble LSTM based hybrid chaotic atom search optimization | |
CN109978277A (en) | Region online load prediction technique and device in photovoltaic power generation | |
CN111967652B (en) | Double-layer collaborative real-time correction photovoltaic prediction method | |
CN111476411B (en) | Photovoltaic power station generating capacity calculation method and server | |
CN117394310A (en) | Method and system for calculating area light Fu Dengxiao light resources affected by multiple weather types |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |