CN113065982A - System and method for predicting power of dust-accumulated photovoltaic panel based on dense residual error network - Google Patents
System and method for predicting power of dust-accumulated photovoltaic panel based on dense residual error network Download PDFInfo
- Publication number
- CN113065982A CN113065982A CN202110435777.0A CN202110435777A CN113065982A CN 113065982 A CN113065982 A CN 113065982A CN 202110435777 A CN202110435777 A CN 202110435777A CN 113065982 A CN113065982 A CN 113065982A
- Authority
- CN
- China
- Prior art keywords
- data
- photovoltaic panel
- power
- monitoring center
- photovoltaic
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 16
- 230000009467 reduction Effects 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims abstract description 3
- 239000000428 dust Substances 0.000 claims description 16
- 230000004913 activation Effects 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008021 deposition Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000003287 optical effect Effects 0.000 abstract description 2
- 238000010248 power generation Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000004071 soot Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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"
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Abstract
A system and a method for predicting the power of a dust-deposition photovoltaic panel based on a dense residual error network comprise a data acquisition system and a data monitoring center, wherein data information acquired by the data acquisition system is sent to the data monitoring center through a data transmitter and a data receiver, the data monitoring center calculates the power of the photovoltaic panel, and the prediction method comprises the steps that the data acquisition system acquires electrical data and meteorological data of the photovoltaic panel; the invention discloses a photovoltaic panel gray image monitoring method, which comprises the steps of carrying out dimension reduction processing on a photovoltaic panel gray image by a data monitoring center, and finally calculating the power of a photovoltaic panel by the data monitoring center through an intensive residual error network. The method can provide important reference for a power grid dispatching plan, and has important significance for full grid-connected operation of optical volt-ampere.
Description
Technical Field
The invention relates to the technical field of solar photovoltaic power generation, in particular to a system and a method for predicting the power of a dust-accumulated photovoltaic panel based on a dense residual error network.
Background
In recent years, in order to solve the global warming problem, many countries have concentrated on energy conversion, and have been focusing on the development of renewable energy. Solar photovoltaic power generation is taken as a power generation technology with development prospect in the field of new energy, and new vitality is released under the background of transformation and upgrading of global energy structures by virtue of the industrial characteristics of wide distribution, rich reserves and mature technology. However, photovoltaic power generation has the problems of intermittency, randomness, fluctuation and the like, and challenges are brought to planning and operation of the existing power system. The traditional solution of the power grid dispatching department can only limit power by passive switching-off, and a photovoltaic power prediction system becomes more important along with the increase of the penetration rate of a power grid power supply structure of a photovoltaic power station. The method realizes accurate prediction of photovoltaic power generation, and has important significance for providing high-quality electric energy for terminal users and improving the operation reliability of the power system.
Disclosure of Invention
The invention aims to solve the problem of insufficient accuracy of the conventional power prediction and provides a system and a method for predicting the power of a gray-deposited photovoltaic panel based on a dense residual error network.
The purpose of the invention is realized by the following technical scheme:
the utility model provides an area grey photovoltaic board power prediction system based on intensive residual error network, includes data acquisition system and data monitoring center, data acquisition system includes visible light camera, meteorological detector, smart electric meter and paster temperature sensor, the visible light camera is used for shooing photovoltaic board area grey image, meteorological detector is used for detecting the meteorological data of worn-out fur, smart electric meter is used for collecting the electrical data of photovoltaic board, paster temperature sensor is used for detecting photovoltaic board temperature, and the data information that data acquisition system gathered sends to data monitoring center through data transmitter and data receiver, and data monitoring center calculates photovoltaic board power at last.
Further, the meteorological data of the photovoltaic panel comprise irradiation data, environment temperature data, atmospheric humidity data, wind speed data, wind direction data and air pressure data.
Further, the intelligent electric meter is installed in a distribution box of the photovoltaic panel, and the electrical data of the photovoltaic panel comprises output voltage data, output current data and photovoltaic panel conversion efficiency of the photovoltaic panel;
further, the voltage range of the intelligent electric meter is direct current 0-1000V, and the current range is 0-10A.
Furthermore, the data monitoring center is an upper computer.
Further, the data acquisition interval of the upper computer is 15 min.
Further, the data transmitter and the data receiver transmit the dust deposition images and the operation parameters of the photovoltaic panel to the upper computer through two data transmission channels.
A prediction method of a power prediction system of a soot photovoltaic panel based on a dense residual error network specifically comprises the following steps:
s1, collecting electrical data and meteorological data of the photovoltaic panel by the data collection system, wherein the electrical data comprise a photovoltaic panel dust deposition image, photovoltaic panel output voltage, photovoltaic panel output current and photovoltaic panel temperature; meteorological data including irradiation, ambient temperature, atmospheric humidity, wind speed, wind direction, and barometric pressure;
s2, sending the data information acquired by the data acquisition system to a data monitoring center through a data transmitter and a data receiver;
s3, the data monitoring center performs dimensionality reduction processing on the voltage board accumulated dust image, and specifically comprises the following steps:
(1) subjecting the collected photovoltaic panel dust image to perspective transformation to obtain a corrected photovoltaic panel image;
(2) enhancing the characteristic information of the dust concentration by using an Adaptive Contrast Enhancement (ACE) algorithm;
(3) transforming the histogram of the image of the photovoltaic panel, and carrying out three-class classification on the basis of the value at the highest point of the ordinate, and sorting av from high to low1,av2,av3;
(4) Calculating the average pixel value av of each equal division, wherein the calculation formula is as follows:
wherein, in the above formula; k is an equal classification number; n is the total pixel number of the picture; n is a radical ofkIs the total number of pixels in the k classes, nkThe number of pixel values in the k classes; x is the number ofiIs the ith pixel value, p, of class kiThe probability of this pixel value in the whole picture;
s4, calculating the power of the photovoltaic panel by the data monitoring center by using an intensive residual error network, wherein: the hidden layer between the input layer and the output layer of the dense residual network has N (A, B, C …) scales, and each scale has N (N)1,N2,N3…) layers of nThe output of each layer is added to the output of the first layer in the activation function, and the neuron vectorization in each scale of the hidden layer can be expressed as:
Ni=activation(Ni-1·wi-1+b+N1)。
further, in step S1, the photovoltaic panel temperature is obtained by averaging N different position measurements of the photovoltaic back panel, and the calculation formula is:
the invention has the beneficial effects that: according to the system and the method for predicting the power of the gray-deposited photovoltaic panel based on the dense residual error network, the output power of the photovoltaic panel is predicted by using the monitoring data, and compared with the situation that only environmental and electrical parameters are considered, dimension-reduced image gray-deposited information is introduced, the dense residual error network is provided, the network depth is increased, and the problem of network degradation such as gradient disappearance is solved. The method can provide important reference for a power grid dispatching plan, and has important significance for full grid-connected operation of optical volt-ampere.
Drawings
FIG. 1 is a block diagram of a power prediction system for a soot photovoltaic panel according to the present invention;
FIG. 2 is a flow chart of the dimension reduction of the gray image information according to the present invention;
FIG. 3 is a schematic block diagram of a power prediction system for a soot photovoltaic panel according to the present invention;
FIG. 4 is a diagram of the intensive residual network architecture of the present invention;
FIG. 5 is a simplified diagram of the dense residual network structure according to the present invention.
In the figure, 1-a visible light camera, 2-a meteorological detector, 3-a smart meter, 4-a patch temperature sensor, 5-a data transmitter, 6-a data receiver and 7-a data monitoring center.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Example 1:
the system comprises a data acquisition system and a data monitoring center 7, wherein the data acquisition system comprises a visible light camera 1, a meteorological detector 2, an intelligent ammeter 3 and a patch temperature sensor 4, the visible light camera 3 is used for shooting a dust image of the photovoltaic panel, the meteorological detector 2 is used for detecting meteorological data of a light panel, the intelligent ammeter 3 is used for collecting electrical data of the photovoltaic panel, the patch temperature sensor 4 is used for detecting the temperature of the photovoltaic panel, data information acquired by the data acquisition system is sent to the data monitoring center 7 through a data emitter 5 and a data receiver 6, and the data monitoring center 7 calculates the power of the photovoltaic panel finally.
In the above embodiment, the meteorological data of the photovoltaic panel includes irradiation data, ambient temperature data, atmospheric humidity data, wind speed data, wind direction data, and air pressure data.
In the above embodiment, the smart meter 3 is installed in a distribution box of a photovoltaic panel, and the electrical data of the photovoltaic panel includes output voltage data, output current data and conversion efficiency of the photovoltaic panel;
in the above embodiment, the voltage range of the intelligent ammeter 3 is dc 0-1000V, and the current range is 0-10A.
In the above embodiment, the data monitoring center 7 is an upper computer, a Visual Studio-based software management system is pre-installed in the upper computer 7, the upper computer 7 collects the operation data and the meteorological data of the photovoltaic panel through the software management system, the collected data interval is 15min, and then the data is processed to calculate the power of the photovoltaic panel, and meanwhile, the upper computer also provides data storage and historical data query functions.
In the above embodiment, the data transmitter 5 and the data receiver 7 transmit the photovoltaic panel dust deposition image and the operation parameters to the upper computer through two data transmission channels, so as to guarantee the quality of data transmission.
It should be noted that for the above embodiments, the data acquisition system should be arranged by following:
(1) and (3) overall coverage: all photovoltaic panels of a photovoltaic plant should be monitored and should target sufficient spatial coverage, should be evenly distributed in the monitored area, and should be balanced between a sufficient number of points and costs.
(2) Dust multi-zone focus: due to different environmental conditions, the area of a photovoltaic power plant is strongly affected by dust. The best acquisition point should be selected based on location and wind conditions.
(3) Law of rational utilization of resources and cost effectiveness: the power supply of the equipment should be considered when the existing resources are used, and the equipment is easy to deploy and maintain.
Example 2:
referring to fig. 3, a prediction method of a power prediction system of a gray photovoltaic panel based on a dense residual error network specifically includes the following steps:
s1, collecting electrical data and meteorological data of the photovoltaic panel by the data collection system, wherein the electrical data comprise a photovoltaic panel dust deposition image, photovoltaic panel output voltage, photovoltaic panel output current and photovoltaic panel temperature; meteorological data including irradiation, ambient temperature, atmospheric humidity, wind speed, wind direction, and barometric pressure;
s2, sending the data information acquired by the data acquisition system to a data monitoring center through a data transmitter and a data receiver;
s3, the data monitoring center performs a dimension reduction process on the voltage board gray image, specifically, as shown in fig. 2, the method includes the following steps:
(1) the image of the photovoltaic panel has a certain inclination due to the problem of shooting angle, the inclination angle is obtained by searching the edge slope, the collected image of the accumulated dust of the photovoltaic panel is subjected to perspective transformation to obtain a corrected image of the photovoltaic panel, and the inclination angle is adjusted to zero;
(2) enhancing the characteristic information of the dust concentration by using an Adaptive Contrast Enhancement (ACE) algorithm, specifically, dividing an image into a low-frequency part (unsharp mask) and a high-frequency part, wherein the low-frequency part is obtained by smoothing and other operations of a low-pass filter on the image; the high frequency part is obtained by subtracting the low frequency part from the original image, and then the high frequency part is enlarged (the enlargement factor is CG). Finally, adding the high-frequency part and the low-frequency part after the gain to obtain an enhanced image;
(3) transforming the histogram of the image of the photovoltaic panel, and carrying out three-class classification on the basis of the value at the highest point of the ordinate, and sorting av from high to low1,av2,av3;
(4) Calculating the average pixel value av of each equal division, wherein the calculation formula is as follows:
wherein, in the above formula; k is an equal classification number; n is the total pixel number of the picture; n is a radical ofkIs the total number of pixels in the k classes, nkThe number of pixel values in the k classes; x is the number ofiIs the ith pixel value, p, of class kiThe probability of this pixel value in the whole picture;
and S4, calculating the power of the photovoltaic panel by the data monitoring center by using an intensive residual error network.
In the above embodiment, the hidden layer between the input layer and the output layer of the dense residual network has N (a, B, C …) scales, and each scale has N (N)1,N2,N3…) layers, where the output of each layer is within the activation functionAdding the output of the first layer, specifically referring to fig. 4 and 5, the dimension of the input layer is (1 × 13), corresponding to 13 parameters in the data set; the hidden layer has 3 sizes of A (8 × 64), B (8 × 16) and C (8 × 4), which can be expressed as that the hidden layer of the scale A has 8 layers, each layer has 64 neurons, the hidden layer of the scale B has 8 layers, each layer has 16 neurons, the hidden layer of the scale C has 8 layers, and each layer has 4 neurons; the output layer is a photovoltaic panel output power parameter.
Within each scale, the output of each layer is added to the output of the first layer within the activation function. The neuron vectorization in each scale of the hidden layer is represented as:
Ni=activation(Ni-1·wi-1+bi-1+N1)
the RELU activation function is chosen for each layer, and the neuron vector for each layer is expressed as:
A1=re(X·w0+b)0
wherein w0The scale is (13X 64), b0Is (1 × 64), the input parameter X is transformed and activated, and then output A1
A2=re(A1·w1+b1)
A3=re(A2·w2+b2+A1)
A4=re(A3·w3+b3+A1)
Likewise, a transformation is made up to the last layer of dimension a:
A8=re(A7·w7+b+7A)
wherein w1~w7The scale is (64X 64), b1~b7Is (1 × 64);
B1=re(A8·w8+b)8
B1and (4) for the first layer of the hidden layer B scale, obtaining the transformation formulas of all the layers according to the rule. W8The scale is (64X 16), b8Is (1X 16). Wherein w9~w15The scale is (16 is multiplied by 16),b9~b15Is (1X 16). The same applies to the dimension C.
In the above facts, preferably, in step S1, the photovoltaic panel temperature is obtained by averaging N different position measurements of the photovoltaic back panel, and the calculation formula is:
the above-mentioned embodiments only express the specific embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (9)
1. The utility model provides an area grey photovoltaic board power prediction system based on intensive residual error network, its characterized in that, includes data acquisition system and data monitoring center, data acquisition system includes visible light camera, meteorological detector, smart electric meter and paster temperature sensor, the visible light camera is used for shooing photovoltaic board area grey image, meteorological detector is used for detecting the meteorological data of worn-out fur, smart electric meter is used for collecting the electric data of photovoltaic board, paster temperature sensor is used for detecting photovoltaic board temperature, and the data information that data acquisition system gathered sends to data monitoring center through data transmitter and data receiver, and data monitoring center calculates photovoltaic board power.
2. The system of claim 1, wherein the meteorological data of the photovoltaic panel comprises irradiation data, ambient temperature data, atmospheric humidity data, wind speed data, wind direction data, and barometric pressure data.
3. The system of claim 1, wherein the smart meter is installed in a power distribution box of a photovoltaic panel, and the electrical data of the photovoltaic panel comprises output voltage data, output current data and photovoltaic panel conversion efficiency of the photovoltaic panel.
4. The system of claim 3, wherein the smart meter has a voltage range of 0-1000V DC and a current range of 0-10A.
5. The system for predicting the power of the gray-deposited photovoltaic panel based on the dense residual error network as claimed in claim 1, wherein the data monitoring center is an upper computer.
6. The system for predicting the power of the soot-deposited photovoltaic panel based on the dense residual error network as claimed in claim 5, wherein the interval of the data collected by the upper computer is 15 min.
7. The system for predicting the power of the gray-deposited photovoltaic panel based on the dense residual error network as claimed in claim 6, wherein the data transmitter and the data receiver transmit the gray-deposited image and the operation parameters of the photovoltaic panel to the upper computer through two data transmission channels.
8. The prediction method of the dense residual error network-based power prediction system for the gray-covered photovoltaic panel is characterized by comprising the following steps:
s1, collecting electrical data and meteorological data of the photovoltaic panel by the data collection system, wherein the electrical data comprise a photovoltaic panel dust deposition image, photovoltaic panel output voltage, photovoltaic panel output current and photovoltaic panel temperature; meteorological data including irradiation, ambient temperature, atmospheric humidity, wind speed, wind direction, and barometric pressure;
s2, sending the data information acquired by the data acquisition system to a data monitoring center through a data transmitter and a data receiver;
s3, the data monitoring center performs dimensionality reduction processing on the voltage board accumulated dust image, and specifically comprises the following steps:
(1) subjecting the collected photovoltaic panel dust image to perspective transformation to obtain a corrected photovoltaic panel image;
(2) enhancing the characteristic information of the dust concentration by using an Adaptive Contrast Enhancement (ACE) algorithm;
(3) transforming the histogram of the image of the photovoltaic panel, and carrying out three-class classification on the basis of the value at the highest point of the ordinate, and sorting av from high to low1,av2,av3;
(4) Calculating the average pixel value av of each equal division, wherein the calculation formula is as follows:
wherein, in the above formula; k is an equal classification number; n is the total pixel number of the picture; n is a radical ofkIs the total number of pixels in the k classes, nkThe number of pixel values in the k classes; x is the number ofiIs the ith pixel value, p, of class kiThe probability of this pixel value in the whole picture;
s4, calculating the power of the photovoltaic panel by the data monitoring center by using an intensive residual error network, wherein: the hidden layer between the input layer and the output layer of the dense residual network has N (A, B, C …) scales, and each scale has N (N)1,N2,N3…) layers, where the output of each layer is added to the output of the first layer within the activation function, the neuron vectorization in each scale of the hidden layer can be expressed as:
Ni=activation(Ni-1·wi-1+b+N1)。
9. the prediction method of the ash deposition photovoltaic panel power prediction system based on the dense residual error network as claimed in claim 8, wherein in step S1, the photovoltaic panel temperature is obtained by averaging N different position measurements of the photovoltaic back panel, and the calculation formula is:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110435777.0A CN113065982A (en) | 2021-04-22 | 2021-04-22 | System and method for predicting power of dust-accumulated photovoltaic panel based on dense residual error network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110435777.0A CN113065982A (en) | 2021-04-22 | 2021-04-22 | System and method for predicting power of dust-accumulated photovoltaic panel based on dense residual error network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113065982A true CN113065982A (en) | 2021-07-02 |
Family
ID=76567543
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110435777.0A Pending CN113065982A (en) | 2021-04-22 | 2021-04-22 | System and method for predicting power of dust-accumulated photovoltaic panel based on dense residual error network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113065982A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341566A (en) * | 2017-06-19 | 2017-11-10 | 东北电力大学 | Photovoltaic system electricity generation power prediction meanss and its method based on meteorologic parameter Yu solar panel running state parameter |
CN109615629A (en) * | 2018-12-24 | 2019-04-12 | 东北电力大学 | Photovoltaic panel dust stratification status image identifying system and its analysis regulation method based on convolutional neural networks |
CN111539355A (en) * | 2020-04-27 | 2020-08-14 | 东北电力大学 | Photovoltaic panel foreign matter detection system and detection method based on deep neural network |
CN112116171A (en) * | 2020-09-29 | 2020-12-22 | 山东建筑大学 | Novel photovoltaic power generation power prediction method based on neural network |
-
2021
- 2021-04-22 CN CN202110435777.0A patent/CN113065982A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341566A (en) * | 2017-06-19 | 2017-11-10 | 东北电力大学 | Photovoltaic system electricity generation power prediction meanss and its method based on meteorologic parameter Yu solar panel running state parameter |
CN109615629A (en) * | 2018-12-24 | 2019-04-12 | 东北电力大学 | Photovoltaic panel dust stratification status image identifying system and its analysis regulation method based on convolutional neural networks |
CN111539355A (en) * | 2020-04-27 | 2020-08-14 | 东北电力大学 | Photovoltaic panel foreign matter detection system and detection method based on deep neural network |
CN112116171A (en) * | 2020-09-29 | 2020-12-22 | 山东建筑大学 | Novel photovoltaic power generation power prediction method based on neural network |
Non-Patent Citations (3)
Title |
---|
SIYUAN FAN等: "A master-slave residual network-based classification method for PV panels dust accumulation", 《2020 CHINESE AUTOMATION CONGRESS(CAC)》 * |
从光杰: "建筑光伏组件的积灰检测与输出功率预测模型研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
廖坤: "基于深度学习的光伏板积灰状态图像识别与分析", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Puri et al. | A hybrid artificial intelligence and internet of things model for generation of renewable resource of energy | |
AU2017261849A1 (en) | "Solar power forecasting" | |
CN108205717A (en) | A kind of photovoltaic generation power Multiple Time Scales Forecasting Methodology | |
CN103971169A (en) | Photovoltaic super-short-term generated power forecasting method based on cloud cover simulation | |
CN110514298A (en) | A kind of solar irradiation strength calculation method based on ground cloud atlas | |
Nguyen et al. | Automated quantification of solar photovoltaic potential in cities Overview: A new method to determine a city's solar electric potential by analysis of a distribution feeder given the solar exposure and orientation of rooftops. | |
WO2017193172A1 (en) | "solar power forecasting" | |
CN111815021A (en) | Photovoltaic power prediction method based on solar radiation climate characteristic identification | |
CN110781458A (en) | Method for predicting surface solar irradiance based on mixed regression model | |
Yang et al. | Ultra-short-term multi-step wind power prediction based on fractal scaling factor transformation | |
Dissawa et al. | Cross-correlation based cloud motion estimation for short-term solar irradiation predictions | |
CN115329667A (en) | Method, device and equipment for determining point location of fan and storage medium | |
CN108008633A (en) | Irradiation level comprising a variety of Changes in weather and photovoltaic module coordinate incidence relation method for building up | |
CN111047076A (en) | Photovoltaic short-term power forecasting method based on sunflower number 8 satellite cloud picture | |
Dhanalakshmi et al. | Application of machine learning in multi-directional model to follow solar energy using photo sensor matrix | |
CN113408785B (en) | Method, device, equipment and storage medium for predicting optical power | |
CN103927598A (en) | Photovoltaic generation power prediction method based on self-learning radial basis function | |
CN113065982A (en) | System and method for predicting power of dust-accumulated photovoltaic panel based on dense residual error network | |
CN115587326B (en) | Noise environment wind power plant data correction method | |
CN116029440A (en) | Ultra-short-term power prediction method and device for photovoltaic power station | |
CN111160602A (en) | Photovoltaic ultra-short term power forecasting method based on sunflower number 8 satellite cloud picture | |
CN114971081A (en) | Irradiation prediction method based on time series analysis and daily statistics | |
CN112116569A (en) | Photovoltaic power station power generation power prediction method based on shadow recognition | |
Arosh et al. | Composite imagery-based non-uniform illumination sensing for system health monitoring of solar power plants | |
CN112016390B (en) | Radiation fluctuation calculation method based on cloud cover and neural network |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210702 |