CN106372749A - Ultrashort-term photovoltaic power prediction method based on cloud change analysis - Google Patents
Ultrashort-term photovoltaic power prediction method based on cloud change analysis Download PDFInfo
- Publication number
- CN106372749A CN106372749A CN201610762470.0A CN201610762470A CN106372749A CN 106372749 A CN106372749 A CN 106372749A CN 201610762470 A CN201610762470 A CN 201610762470A CN 106372749 A CN106372749 A CN 106372749A
- Authority
- CN
- China
- Prior art keywords
- represent
- cloud
- image
- photovoltaic power
- photovoltaic plant
- 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 16
- 238000004458 analytical method Methods 0.000 title claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000009499 grossing Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 238000013277 forecasting method Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
Abstract
The invention discloses an ultrashort-term photovoltaic power prediction method based on cloud change analysis and belongs to the technical field of photovoltaic power generation. The method is characterized by, through the real-time image acquisition technology, obtaining image information above a photovoltaic power station in real time, carrying out prediction on meteorological conditions above the photovoltaic power station, and inputting forecast results, serving the as correction parameters, to a photovoltaic power generation model to predicate output power of the photovoltaic power station. The method can reach an effect of carrying out accurate prediction on ultrashort-term photovoltaic power; prediction precision can reach 0-4 hours in the future; and through power grid dispatching, day generating plan can be modified in real time according to the forecast result, thereby improving power generation utilization rate of the photovoltaic power station under the condition of ensuring stable operation of the power grid.
Description
Technical field
The present invention relates to a kind of ultra-short term photovoltaic power Forecasting Methodology becoming analysis based on cloud, belong to photovoltaic power generation technology neck
Domain.
Background technology
At present, Chinese photovoltaic generation enters the scale high speed development stage.But due to photovoltaic generation have intermittent and
The feature of randomness, accesses electrical network with substantial amounts of photovoltaic generation, will certainly be to the safe and stable operation of power system and guarantor
The card quality of power supply brings severe challenge, if the variation tendency of photovoltaic plant output can be prejudged, adjustment electrical network is adjusted in time
Degree operating scheme, solving the photovoltaic generation impact to power grid security for the randomness of exerting oneself just has technical basis.
Photovoltaic generation ultra-short term power prediction is to solve one of effective way of this problem.Existing ultra-short term photovoltaic power is pre-
Survey method mainly has: a class is the Forecasting Methodology based on statistical analysiss, such as support vector machine and neutral net;Another kind of is base
Forecasting Methodology in time series models.
The ultra-short term power prediction that prior art provides typically adopts history generated output to calculate and realizes it is impossible to real-time tracking
Photovoltaic plant overhead cloud layer information, predicts the outcome inaccurate, leads to photovoltaic power station power generation utilization rate low.
Content of the invention
It is an object of the invention to overcoming deficiency of the prior art, provide a kind of ultra-short term photovoltaic becoming analysis based on cloud
Power forecasting method, in solution prior art, photovoltaic plant ultra-short term photovoltaic power prediction accuracy is not high, leads to photovoltaic plant
The low technical problem of capacity factor.
For solving above-mentioned technical problem, the technical solution adopted in the present invention is: becomes the ultra-short term photovoltaic of analysis based on cloud
Power forecasting method, obtains photovoltaic plant overhead image information in real time, photovoltaic plant overhead meteorological condition is predicted, then will
Predict the outcome and be input to, as corrected parameter, the output predicting photovoltaic plant in photovoltaic generation model.
The method specifically includes following steps:
Step one: photovoltaic plant history output, upper null images and weather information are analyzed, calculate different gas
As photovoltaic plant Cloud Over layer data under weather pattern;
Step 2: obtain photovoltaic plant overhead image information in real time, calculate current time photovoltaic plant Cloud Over aspect and amass
And movement velocity;
Step 3: calculate the movement locus of cloud layer, calculate in 0~4 hour 15 minutes spaced points in photovoltaic plant overhead
Cloud layer area;
Step 4: Neural Network model predictive photovoltaic plant output is used according to the meteorologic parameter that weather station provides,
According to step 3 calculate cloud layer areal calculation correction factor, prediction 0~4 hour in ultra-short term power.
Long-pending the specifically comprising the following steps that of photovoltaic plant Cloud Over aspect is calculated in step 2
Step 201: overhead image information is carried out with pretreatment: set current time photovoltaic plant overhead as rgb coloured image,
Rgb coloured image is changed into gray level image, conversion formula is as follows:
Y=0.299r+0.587g+0.114b
In formula: y represents gray value;R represents red color channel value;G represents green channel value;B represents blue channel value;
Step 202: Smoothing of Gray Image is processed, using gaussian filtering, discrete using two-dimentional zero-mean
Gaussian function makees smoothing filter, and two-dimentional gaussian function is:
Wherein: g0(x, y) represents output pixel value;X represents abscissa value;Y represents ordinate value;μxRepresent gaussian kernel letter
The average in x direction for the number;μyRepresent the average in y direction for the gaussian kernel function;σxRepresent the standard deviation in x direction for the gaussian kernel function;
σyRepresent the standard deviation in y direction for the variable gaussian kernel function;Picture noise is removed using corrosion expansion form closed operation;
Step 203: the overhead gray level image under the conditions of selecting clear sky cloudless, will be grey in real time used as normal background difference image
Degree image and normal background difference image carry out difference, detect whether have cloud layer to move in real-time gray level image;
Step 204: carry out rim detection using canny algorithm: judge the second dervative in gradient direction for the point in image
Whether zero crossing: if zero crossing, then this point is exactly the marginal point in image;Otherwise, it is not;
Step 205: obtained the continuous boundary contour curve of Cloud Over tomographic image by step 204, approached using designated precision
The Polygonal Curves of cloud layer, calculate cloud layer area.
It is the movement locus calculating cloud layer using barycenter iterative tracking algorithm in step 3, specific algorithm is as follows:
Step 301: the target area position of previous frame image is defined as the initial position that new search starts, according to formulaObtain initial candidate target area
Represent the similarity between target area and To Template;yiRepresent initial frame target location;xiRepresent with yiFor
Each location of pixels in the present frame place candidate region at center;I=1,2 ..., m;M represents the pixel count of target area;
Step 302: according toCalculate the pixel value on each aspect in current candidate target area and target position
Put the similarity degree of a little upper pixel value;In formula: g (xi) represent be located at x at pixel similarity contribution margin, qu(xi) represent and wait
The u dimension value of favored area, su(xi) represent region of search u dimension value;
Step 303: according to formulaCalculate the pixel on each aspect of next candidate target region
Value;
In formula: yjRepresent loyal target location, y in iterative processj+1Represent next step iterative position;J represents iterationses;xk
Represent with yjCentered on present frame place candidate region in each location of pixels;K=1,2 ..., m;
Step 304: calculate in new candidate target region Represent the new target area of candidate region and mesh
Similarity between mark template;
Step 305: if | | yj+1-yj| | < ε, ε represent any given positive number, then iteration terminates;Otherwise, go to step
302.
Compared with prior art, the beneficial effect that the present invention is reached is: the present invention is defeated according to Neural Network model predictive
Go out power, cloud layer real-time tracking is calculated with the correction factor of prediction output, reaches and Accurate Prediction is carried out to ultra-short term power
Effect, budget precision can reach following 0~4 hour, and dispatching of power netwoks can be according to predicting the outcome, and revising the same day in real time generates electricity meter
Draw, realize, on the premise of ensureing that electrical network can carry out stable operation, improving the capacity factor of photovoltaic plant.
Brief description
Fig. 1 is the flow chart of the present invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following examples are only used for clearly illustrating the present invention
Technical scheme, and can not be limited the scope of the invention with this.
The present invention becomes the ultra-short term photovoltaic power Forecasting Methodology of analysis based on cloud, using real time image collection technology, in real time
Obtain photovoltaic plant overhead image information, photovoltaic plant overhead meteorological condition is predicted, then will predict the outcome as correction
Parameter is input to the output predicting photovoltaic plant in photovoltaic generation model.Dispatching of power netwoks can be according to photovoltaic plant output work
Rate predicts the outcome, and revises in time and works as daily trading planning, ensures power grid operation, improves photovoltaic power station power generation utilization rate.
As shown in figure 1, being the flow chart of the present invention, specifically include following steps:
Step one: photovoltaic plant history output, upper null images and weather information are analyzed, calculate different gas
As photovoltaic plant Cloud Over layer data under weather pattern, i.e. the cloud layer image information in power station overhead, obtain under clear sky to analyze, mark
Quasi- image information runs the normal background image of detection as barycenter.
Step 2: obtain photovoltaic plant overhead image information in real time, calculate current time photovoltaic plant Cloud Over aspect and amass
And movement velocity.
Calculate long-pending the specifically comprising the following steps that of photovoltaic plant Cloud Over aspect
Step 201: overhead image information is carried out with pretreatment: set current time photovoltaic plant overhead as rgb coloured image,
Rgb coloured image is changed into gray level image, conversion formula is as follows:
Y=0.299r+0.587g+0.114b
In formula: y represents gray value;R represents red color channel value;G represents green channel value;B represents blue channel value;
Step 202: Smoothing of Gray Image is processed, using gaussian filtering, discrete using two-dimentional zero-mean
Gaussian function makees smoothing filter, and two-dimentional gaussian function is:
Wherein: g0(x, y) represents output pixel value;X represents abscissa value;Y represents ordinate value;μxRepresent gaussian kernel letter
The average in x direction for the number;μyRepresent the average in y direction for the gaussian kernel function;σxRepresent the standard deviation in x direction for the gaussian kernel function;
σyRepresent the standard deviation in y direction for the variable gaussian kernel function;Picture noise is removed using corrosion expansion form closed operation;
Step 203: the overhead gray level image under the conditions of selecting clear sky cloudless, will be grey in real time used as normal background difference image
Degree image and normal background difference image carry out difference, detect whether have cloud layer to move in real-time gray level image;
Step 204: carry out rim detection using canny algorithm: judge the second dervative in gradient direction for the point in image
Whether zero crossing: if zero crossing, then this point is exactly the marginal point in image;Otherwise, it is not;
Step 205: obtained the continuous boundary contour curve of Cloud Over tomographic image by step 204, approached using designated precision
The Polygonal Curves of cloud layer, calculate cloud layer area.
Step 3: calculate the movement locus of cloud layer, calculate in 0~4 hour 15 minutes spaced points in photovoltaic plant overhead
Cloud layer area.
Cloud layer movement locus are calculated using barycenter iterative tracking algorithm, specifically include following steps:
Step 301: the target area position of previous frame image is defined as the initial position that new search starts, according to formulaObtain initial candidate target area
Represent the similarity between target area and To Template;yiRepresent initial frame target location;xiRepresent with yiFor
Each location of pixels in the present frame place candidate region at center;I=1,2 ..., m;M represents the pixel count of target area;
Step 302: according toCalculate the pixel value on each aspect in current candidate target area and target position
Put the similarity degree of a little upper pixel value;In formula: g (xi) represent be located at x at pixel similarity contribution margin, qu(xi) represent and wait
The u dimension value of favored area, su(xi) represent region of search u dimension value;
Step 303: according to formulaCalculate the pixel on each aspect of next candidate target region
Value;
In formula: yjRepresent loyal target location, y in iterative processj+1Represent next step iterative position;J represents iterationses;xk
Represent with yjCentered on present frame place candidate region in each location of pixels;K=1,2 ..., m;
Step 304: calculate in new candidate target region Represent the new target area of candidate region and mesh
Similarity between mark template;
Step 305: if | | yj+1-yj| | < ε, ε represent any given positive number, then iteration terminates;Otherwise, go to step
302.
Barycenter iterative tracking algorithm can reduce the impact to tracking performance for the background pixel, in complex background and block
In the case of tracking effect also relatively good, and kernel function weighting need not be carried out to image, reduce the complexity of algorithm, improve
Computational efficiency, improves the accuracy of image trace.
Step 4: the meteorologic parameter being provided according to weather station, using Neural Network model predictive photovoltaic plant output,
According to step 3 calculate cloud layer areal calculation correction factor, prediction 0~4 hour in ultra-short term power.Herein, neutral net mould
Type can be selected for rprop neural network model.After correction, the computing formula of pre- power scale is as follows:
P1=p2 ks;
In formula: p1 represents pre- power scale after correction, p2 represents the photovoltaic plant output of neural network prediction, and k represents
Proportionality coefficient, s represents cloud layer area, and k can be drawn using method of least square according to historical data.
The above is only the preferred embodiment of the present invention it is noted that ordinary skill people for the art
For member, on the premise of without departing from the technology of the present invention principle, some improvement can also be made and deform, these improve and deform
Also should be regarded as protection scope of the present invention.
Claims (4)
1. the ultra-short term photovoltaic power Forecasting Methodology of analysis is become it is characterised in that obtaining empty graph on photovoltaic plant in real time based on cloud
As information, photovoltaic plant overhead meteorological condition is predicted, then will predict the outcome and be input to photovoltaic generation as corrected parameter
The output of photovoltaic plant is predicted in model.
2. according to claim 1 the ultra-short term photovoltaic power Forecasting Methodology of analysis is become based on cloud it is characterised in that concrete
Comprise the steps:
Step one: photovoltaic plant history output, upper null images and weather information are analyzed, calculate different meteorology skies
Photovoltaic plant Cloud Over layer data under gas type;
Step 2: obtain photovoltaic plant overhead image information in real time, calculate current time photovoltaic plant Cloud Over aspect and amass and transport
Dynamic speed;
Step 3: calculate the movement locus of cloud layer, calculate in 0~4 hour 15 minutes spaced points cloud layer in photovoltaic plant overhead
Area;
Step 4: Neural Network model predictive photovoltaic plant output is used according to the meteorologic parameter that weather station provides, according to
Step 3 calculate cloud layer areal calculation correction factor, prediction 0~4 hour in ultra-short term power.
3. according to claim 2 the ultra-short term photovoltaic power Forecasting Methodology of analysis is become it is characterised in that step based on cloud
Long-pending the specifically comprising the following steps that of photovoltaic plant Cloud Over aspect is calculated in two
Step 201: overhead image information is carried out with pretreatment: set current time photovoltaic plant overhead as rgb coloured image, will
Rgb coloured image is changed into gray level image, and conversion formula is as follows:
Y=0.299r+0.587g+0.114b
In formula: y represents gray value;R represents red color channel value;G represents green channel value;B represents blue channel value;
Step 202: Smoothing of Gray Image is processed, using gaussian filtering, using two-dimentional zero-mean discrete gaussian letter
Number makees smoothing filter, and two-dimentional gaussian function is:
Wherein: g0(x, y) represents output pixel value;X represents abscissa value;Y represents ordinate value;μxRepresent gaussian kernel function in x
The average in direction;μyRepresent the average in y direction for the gaussian kernel function;σxRepresent the standard deviation in x direction for the gaussian kernel function;σyTable
Show the standard deviation in y direction for the variable gaussian kernel function;Picture noise is removed using corrosion expansion form closed operation;
Step 203: select clear sky cloudless under the conditions of overhead gray level image as normal background difference image, by real-time gray-scale maps
Picture and normal background difference image carry out difference, detect whether have cloud layer to move in real-time gray level image;
Step 204: carry out rim detection using canny algorithm: the point judging in image gradient direction second dervative whether
Zero crossing: if zero crossing, then this point is exactly the marginal point in image;Otherwise, it is not;
Step 205: obtained the continuous boundary contour curve of Cloud Over tomographic image by step 204, cloud layer is approached using designated precision
Polygonal Curves, calculate cloud layer area.
4. according to claim 2 the ultra-short term photovoltaic power Forecasting Methodology of analysis is become it is characterised in that step based on cloud
It is the movement locus calculating cloud layer using barycenter iterative tracking algorithm in three, specific algorithm is as follows:
Step 301: the target area position of previous frame image is defined as the initial position that new search starts, according to formulaObtain initial candidate target area
Represent the similarity between target area and To Template;yiRepresent initial frame target location;xiRepresent with yiCentered on
Present frame place candidate region in each location of pixels;I=1,2 ..., m;M represents the pixel count of target area;
Step 302: according toCalculate the pixel value on each aspect in current candidate target area and source location
The similarity degree of upper pixel value;In formula: g (xi) represent be located at x at pixel similarity contribution margin, qu(xi) represent candidate regions
The u dimension value in domain, su(xi) represent region of search u dimension value;
Step 303: according to formulaCalculate the pixel value on each aspect of next candidate target region;
In formula: yjRepresent loyal target location, y in iterative processj+1Represent next step iterative position;J represents iterationses;xkRepresent
With yjCentered on present frame place candidate region in each location of pixels;K=1,2 ..., m;
Step 304: calculate in new candidate target regionRepresent the new target area of candidate region and target
Similarity between template;
Step 305: if | | yj+1-yj| | < ε, ε represent any given positive number, then iteration terminates;Otherwise, 302 are gone to step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610762470.0A CN106372749B (en) | 2016-08-29 | 2016-08-29 | Ultra-short term photovoltaic power prediction technique based on the analysis of cloud variation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610762470.0A CN106372749B (en) | 2016-08-29 | 2016-08-29 | Ultra-short term photovoltaic power prediction technique based on the analysis of cloud variation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106372749A true CN106372749A (en) | 2017-02-01 |
CN106372749B CN106372749B (en) | 2019-07-02 |
Family
ID=57901334
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610762470.0A Active CN106372749B (en) | 2016-08-29 | 2016-08-29 | Ultra-short term photovoltaic power prediction technique based on the analysis of cloud variation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106372749B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679685A (en) * | 2017-08-25 | 2018-02-09 | 深圳市盛路物联通讯技术有限公司 | A kind of method and server of the energy scheduling based on Internet of Things |
CN107742171A (en) * | 2017-10-31 | 2018-02-27 | 浙江工业大学 | Photovoltaic power station power generation power forecasting method based on mobile shadow image identification |
CN108133182A (en) * | 2017-12-18 | 2018-06-08 | 北京国能日新系统控制技术有限公司 | A kind of generation of electricity by new energy Forecasting Methodology and device based on cloud imaging |
CN108376399A (en) * | 2018-02-11 | 2018-08-07 | 甘肃省电力公司风电技术中心 | The sand and dust influence degree analysis method monitored in real time based on photovoltaic panel |
CN108734331A (en) * | 2018-03-23 | 2018-11-02 | 武汉理工大学 | Short-term photovoltaic power generation power prediction method based on LSTM and system |
CN109217367A (en) * | 2018-09-30 | 2019-01-15 | 国家电网有限公司 | Wind-power electricity generation prediction technique, device and equipment |
CN115441447A (en) * | 2022-10-24 | 2022-12-06 | 佛山职业技术学院 | New energy power generation power prediction method |
CN116260141A (en) * | 2023-05-16 | 2023-06-13 | 国网信息通信产业集团有限公司 | Reconstruction method and system for power of photovoltaic power station and reconstruction terminal |
CN116706906A (en) * | 2023-08-09 | 2023-09-05 | 长江三峡集团实业发展(北京)有限公司 | Photovoltaic power station output power prediction method, device, equipment and medium |
CN117195320A (en) * | 2023-09-11 | 2023-12-08 | 重庆千信新能源有限公司 | Safety method for generating photovoltaic module energy data through big data image |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102915470A (en) * | 2012-09-20 | 2013-02-06 | 中国电力科学研究院 | Cloud cluster movement estimation method facing to photovoltaic power prediction |
CN103353952A (en) * | 2013-05-31 | 2013-10-16 | 国家电网公司 | Photovoltaic power prediction method based on ground-based cloud chart |
CN103605377A (en) * | 2013-10-30 | 2014-02-26 | 浙江工业大学 | Global sky-cloud real-time dynamic monitoring device |
CN104200484A (en) * | 2013-12-16 | 2014-12-10 | 浙江工业大学 | Distributed photovoltaic system ultra-short-term power output prediction method based on cloud cluster characteristic analysis |
-
2016
- 2016-08-29 CN CN201610762470.0A patent/CN106372749B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102915470A (en) * | 2012-09-20 | 2013-02-06 | 中国电力科学研究院 | Cloud cluster movement estimation method facing to photovoltaic power prediction |
CN103353952A (en) * | 2013-05-31 | 2013-10-16 | 国家电网公司 | Photovoltaic power prediction method based on ground-based cloud chart |
CN103605377A (en) * | 2013-10-30 | 2014-02-26 | 浙江工业大学 | Global sky-cloud real-time dynamic monitoring device |
CN104200484A (en) * | 2013-12-16 | 2014-12-10 | 浙江工业大学 | Distributed photovoltaic system ultra-short-term power output prediction method based on cloud cluster characteristic analysis |
Non-Patent Citations (1)
Title |
---|
曹潇 等: "基于地基云图分析的光伏功率预测系统设计", 《电力信息化》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679685A (en) * | 2017-08-25 | 2018-02-09 | 深圳市盛路物联通讯技术有限公司 | A kind of method and server of the energy scheduling based on Internet of Things |
CN107742171B (en) * | 2017-10-31 | 2020-08-21 | 浙江工业大学 | Photovoltaic power station power generation power prediction method based on mobile shadow image recognition |
CN107742171A (en) * | 2017-10-31 | 2018-02-27 | 浙江工业大学 | Photovoltaic power station power generation power forecasting method based on mobile shadow image identification |
CN108133182A (en) * | 2017-12-18 | 2018-06-08 | 北京国能日新系统控制技术有限公司 | A kind of generation of electricity by new energy Forecasting Methodology and device based on cloud imaging |
CN108376399A (en) * | 2018-02-11 | 2018-08-07 | 甘肃省电力公司风电技术中心 | The sand and dust influence degree analysis method monitored in real time based on photovoltaic panel |
CN108734331A (en) * | 2018-03-23 | 2018-11-02 | 武汉理工大学 | Short-term photovoltaic power generation power prediction method based on LSTM and system |
CN108734331B (en) * | 2018-03-23 | 2022-06-03 | 武汉理工大学 | Short-term photovoltaic power generation power prediction method and system based on LSTM |
CN109217367A (en) * | 2018-09-30 | 2019-01-15 | 国家电网有限公司 | Wind-power electricity generation prediction technique, device and equipment |
CN115441447A (en) * | 2022-10-24 | 2022-12-06 | 佛山职业技术学院 | New energy power generation power prediction method |
CN116260141A (en) * | 2023-05-16 | 2023-06-13 | 国网信息通信产业集团有限公司 | Reconstruction method and system for power of photovoltaic power station and reconstruction terminal |
CN116260141B (en) * | 2023-05-16 | 2023-10-20 | 国网信息通信产业集团有限公司 | Reconstruction method and system for power of photovoltaic power station and reconstruction terminal |
CN116706906A (en) * | 2023-08-09 | 2023-09-05 | 长江三峡集团实业发展(北京)有限公司 | Photovoltaic power station output power prediction method, device, equipment and medium |
CN116706906B (en) * | 2023-08-09 | 2024-01-05 | 长江三峡集团实业发展(北京)有限公司 | Photovoltaic power station output power prediction method, device, equipment and medium |
CN117195320A (en) * | 2023-09-11 | 2023-12-08 | 重庆千信新能源有限公司 | Safety method for generating photovoltaic module energy data through big data image |
CN117195320B (en) * | 2023-09-11 | 2024-04-05 | 重庆千信新能源有限公司 | Safety method for generating photovoltaic module energy data through big data image |
Also Published As
Publication number | Publication date |
---|---|
CN106372749B (en) | 2019-07-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106372749A (en) | Ultrashort-term photovoltaic power prediction method based on cloud change analysis | |
CN104200484B (en) | Distributed photovoltaic system ultra-short-term power output prediction method based on cloud cluster characteristic analysis | |
Yao et al. | A support vector machine approach to estimate global solar radiation with the influence of fog and haze | |
CN109308543A (en) | The short-term passenger flow forecasting of subway based on LS-SVM and real-time big data | |
CN104361611B (en) | Group sparsity robust PCA-based moving object detecting method | |
CN108985965A (en) | A kind of photovoltaic power interval prediction method of combination neural network and parameter Estimation | |
CN106779223A (en) | A kind of photovoltaic system electricity generation power real-time predicting method and device | |
CN110210621A (en) | A kind of object detection method based on residual error network improvement | |
CN103886325B (en) | Cyclic matrix video tracking method with partition | |
CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
CN107301657B (en) | A kind of video target tracking method considering target movable information | |
CN109636171A (en) | A kind of comprehensive diagnos and risk evaluating method that regional vegetation restores | |
CN107705556A (en) | A kind of traffic flow forecasting method combined based on SVMs and BP neural network | |
CN107545571A (en) | A kind of image detecting method and device | |
CN109522831B (en) | Real-time vehicle detection method based on micro-convolution neural network | |
CN107038416A (en) | A kind of pedestrian detection method based on bianry image modified HOG features | |
CN107742171A (en) | Photovoltaic power station power generation power forecasting method based on mobile shadow image identification | |
CN104103076A (en) | Nuclear power plant planned restricted zone remote sensing inspecting method based on high-resolution remote sensing images | |
CN116307291B (en) | Distributed photovoltaic power generation prediction method and prediction terminal based on wavelet decomposition | |
CN106780540A (en) | Towards the ground cloud atlas cloud layer tracking of photovoltaic generation and method for early warning | |
CN103853939A (en) | Combined forecasting method for monthly load of power system based on social economic factor influence | |
CN109784228A (en) | A kind of photovoltaic plant identifying system and method based on image recognition technology | |
CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
CN115544889A (en) | Numerical mode precipitation deviation correction method based on deep learning | |
CN106447662A (en) | Combined distance based FCM image segmentation algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Huidalu Nanjing high tech Zone Pukou 210032 Jiangsu province No. 9 Applicant after: Nanjing Guodian Nanzi 710086 Automation Co. Ltd. Address before: 210032 Jiangsu province Nanjing city Pukou high tech Zone Huidalu No. 9 Applicant before: Nanjing Guodian Nanzi Meizhuo Control System Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |