KR20180072954A - Method and apparatus for predicting the generated energy of the solar cell module - Google Patents
Method and apparatus for predicting the generated energy of the solar cell module Download PDFInfo
- Publication number
- KR20180072954A KR20180072954A KR1020160176263A KR20160176263A KR20180072954A KR 20180072954 A KR20180072954 A KR 20180072954A KR 1020160176263 A KR1020160176263 A KR 1020160176263A KR 20160176263 A KR20160176263 A KR 20160176263A KR 20180072954 A KR20180072954 A KR 20180072954A
- Authority
- KR
- South Korea
- Prior art keywords
- generation amount
- power generation
- predicted
- measurement data
- measured
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000010248 power generation Methods 0.000 claims abstract description 143
- 238000005259 measurement Methods 0.000 claims abstract description 84
- 230000005855 radiation Effects 0.000 claims abstract description 47
- 230000006866 deterioration Effects 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims description 31
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000003245 coal Substances 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L31/00—Semiconductor devices sensitive to infrared radiation, light, electromagnetic radiation of shorter wavelength or corpuscular radiation and specially adapted either for the conversion of the energy of such radiation into electrical energy or for the control of electrical energy by such radiation; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof
- H01L31/04—Semiconductor devices sensitive to infrared radiation, light, electromagnetic radiation of shorter wavelength or corpuscular radiation and specially adapted either for the conversion of the energy of such radiation into electrical energy or for the control of electrical energy by such radiation; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof adapted as photovoltaic [PV] conversion devices
- H01L31/042—PV modules or arrays of single PV cells
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
- H02S50/10—Testing of PV devices, e.g. of PV modules or single PV cells
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
- Y02E10/56—Power conversion systems, e.g. maximum power point trackers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Electromagnetism (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Photovoltaic Devices (AREA)
Abstract
A solar cell module generation prediction method and a prediction device capable of predicting the generation amount of the solar cell module more accurately and capable of determining the deterioration rate are also proposed. A method for predicting the generation amount of a solar cell module according to the present invention includes: a first step of obtaining measurement data including a solar radiation amount (A), a module temperature (B), and a power generation amount (C) measured from a solar cell module; A second step of acquiring a plurality of correlations between the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 from the measurement data obtained in the first section of the measurement data; A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section; A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And a predicted generation amount Cp predicted according to an optimal correlation among the predicted generation amount Cp.
Description
The present invention relates to a method and apparatus for predicting the generation rate of a solar cell module, and more particularly, to a method and a device for predicting a generation rate of a solar cell module capable of predicting the generation amount of a solar cell module more accurately .
One of them is the photovoltaic system using solar energy because of the depletion of chemical energy such as coal and petroleum and the environmental pollution problem due to the use of chemical energy. .
Solar power generation is a series of technologies that convert solar energy (solar heat or solar light) into electrical energy. The basic principle is that when a solar cell composed of a pn junction semiconductor is irradiated with sunlight, a pair of electrons and holes due to the light energy are generated, and a photovoltaic effect in which electrons move and current flows across the n- and p- And a result that a current flows to a load connected to the outside is used. In order to convert infinite and pollution-free solar energy into electric energy, it is necessary to develop a solar module for collecting sunlight.
On the other hand, when a solar module is manufactured and released as a product, the generation amount can be predicted using the initial module characteristic value. Through the prediction of the generation amount, the lifetime of the solar cell module can be predicted, and the replacement and monitoring period can be controlled. However, the initial module characteristic value differs from the power generation amount of the solar cell module installed in the actual field, and it is impossible to predict the accurate generation amount considering the measurement error of the measurement data. Therefore, there is a demand for development of a technique for accurately estimating the generation amount of the solar cell module.
SUMMARY OF THE INVENTION It is an object of the present invention to provide a method and a device for predicting the generation rate of a solar cell module capable of predicting the generation amount of the solar cell module more accurately and determining the degradation rate at the same time. .
According to an aspect of the present invention, there is provided a method for predicting the generation amount of a solar cell module, the method comprising: acquiring measurement data including a solar radiation amount (A), a module temperature (B) Stage 1; A second step of acquiring a plurality of correlations between the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 from the measurement data obtained in the first section of the measurement data; A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section; A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And a predicted generation amount Cp predicted according to an optimal correlation among the predicted generation amount Cp.
And a preprocessing step of performing preprocessing on the measurement data in the first step.
The preprocessing can perform at least any one of limiting the irradiation amount (A), limiting the performance ratio (PR) value, and calculating the average value to the measurement data. At this time, only the measurement data having a radiation amount A of 200 W or more can be used. Only the measurement data having a PR value of 0.5 to 1.2 can be used. The average value calculation is performed when the measurement data is measured in 1 minute, . ≪ / RTI >
The second step is a linear regression model method, a random forest analysis method, a support vector regression analysis method, a K nearest neighbors (kNN) analysis method, a gradient boosting method, A machine (Gradient boosting machine) analysis method, and a neural network analysis method (Neural network analysis method).
The fourth step is performed by selecting the correlation obtained by obtaining the correlation value having the smallest value of the measured power generation amount Cm2 and the average value of the root mean squared error (RMSE) of the predicted generation amount Cp as the optimum correlation .
The method of predicting generation of solar cell module according to the present invention comprises the steps of: selecting a value of a mean bias error (MBE) of a predicted generation amount (Cp) predicted according to a measured power generation amount (Cm) and an optimum correlation as a deterioration value of a solar cell module; As shown in FIG.
According to another aspect of the present invention, there is provided a method of controlling a solar cell module, including: a first step of obtaining measurement data including a solar radiation amount A, a module temperature B, and a power generation amount C measured from a solar cell module; A second step of acquiring a plurality of correlations between the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 from the measurement data obtained in the first section of the measurement data; A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section; A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And a fifth step of selecting a predicted power generation amount (Cp) predicted according to an optimal correlation among the predicted power generation amount (Cp) and the predicted generation amount (Cp). The computer readable recording medium A medium is provided.
According to another aspect of the present invention, there is provided a solar cell module including: a storage unit for storing measurement data including a solar radiation amount A, a module temperature B, and a power generation amount C measured from a solar cell module; A correlation acquiring unit for acquiring a plurality of correlations between the solar radiation amount (A1) and the module temperature (B1) and the power generation amount (C1) from the measurement data obtained in the first section of the measurement data; A predicted power generation amount obtaining unit that obtains the predicted generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation acquired by the correlation acquiring unit; An optimal correlation acquiring unit for comparing the measured power generation amount Cm2 measured in the second section with the predicted power generation amount Cp obtained in the predicted power generation amount obtaining unit to obtain the most accurate optimum correlation among the correlations; And a power generation amount predicting unit for selecting the predicted power generation amount Cp according to an optimum correlation among the predicted power generation amount Cp acquired by the predicted power generation amount obtaining unit.
According to another aspect of the present invention, there is provided a solar cell module comprising: a collecting unit for collecting measurement data including a solar radiation amount A, a module temperature B, and a power generation amount C from a solar cell; A storage unit for storing measurement data from the collection unit; A power generation amount predicting unit for predicting a power generation amount of the solar cell module using measurement data from the storage unit; And a transmission unit that transmits the power generation amount predicted from the measured power generation amount and power generation amount predicting unit, wherein the power generation amount predicting unit calculates the power generation amount of the solar cell module based on the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 to obtain a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section, And the predicted generation amount Cp is selected according to the optimum correlation among the predicted generation amount Cp by obtaining the most accurate optimum correlation among the correlation by comparing the measured generation amount Cm2 with the predicted generation amount Cp, A module generation monitoring device is provided.
As described above, according to the method of predicting the generation amount of the solar cell module according to the embodiments of the present invention, it is possible to estimate the power generation amount using the measurement data measured in the field, and to estimate the optimum power generation amount using various big data analysis methods It is possible to predict the most accurate power generation.
It is also possible to estimate the deterioration rate accurately by calculating the deterioration rate based on the prediction of the accurate generation amount.
This makes it possible to properly diagnose the replacement timing and fault diagnosis of the solar cell module and to monitor the real-time generation quantity, thereby avoiding unnecessary labor waste and deteriorating the replacement time of the deteriorated solar cell module. It is effective.
In addition, data on comparative analysis of the current expected generation amount due to the external environmental factors is provided through prediction of the accurate generation amount, so that deterioration of the entire system of the solar cell module can be evaluated by grasping the tendency of the generation amount change for a long time, It is possible.
FIG. 1 is a flowchart illustrating a method of predicting the generation amount of a solar cell module according to an embodiment of the present invention.
2 is a flowchart illustrating a method of predicting the generation amount of a solar cell module according to another embodiment of the present invention.
FIG. 3 is a graph showing the amount of power generation of measurement data of the solar cell module over time.
FIG. 4 is a graph showing the measured data of the solar cell module with respect to time, irradiation dose, module temperature, measured power generation amount, and predicted power generation amount, and FIG. 5 is a graph showing the predicted power generation amount estimated using the SVR analysis method.
FIG. 6 is a table showing average values of RMSE obtained by predicting and generating the power generation amount according to six analysis methods using the annual measurement data among the measurement data of the solar cell module. FIG. And the mean value of RMSE obtained.
8 is a table showing the MBE value obtained by the SVR analysis method of the measurement data of the solar cell module.
9 is a functional block diagram of an apparatus for predicting the generation amount of a solar cell module according to another embodiment of the present invention.
10 is a functional block diagram of an apparatus for monitoring the power generation amount of a solar cell module according to another embodiment of the present invention.
DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the embodiments of the present invention can be modified into various other forms, and the scope of the present invention is not limited to the embodiments described below. The embodiments of the present invention are provided to enable those skilled in the art to more fully understand the present invention. It should be understood that while the present invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, The present invention is not limited thereto.
FIG. 1 is a flowchart illustrating a method of predicting the generation amount of a solar cell module according to an embodiment of the present invention. A method for predicting solar cell module generation amount according to the present invention includes: a first step of obtaining measurement data including a solar radiation amount (A), a module temperature (B), and a power generation amount (C) measured from a solar cell module; A second step of acquiring a plurality of correlations between the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 from the measurement data obtained in the first section of the measurement data; A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section; A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And a predicted generation amount Cp predicted according to an optimal correlation among the predicted generation amount Cp.
In the method of predicting the generation amount of the solar cell module according to the present embodiment, measurement data is directly obtained from the solar cell module installed in the field and processed to estimate the generation amount. The measured data are oblique solar irradiance, module temperature and measured power generation. The data used for predicting the power generation amount are data based on the characteristics of the initial solar cell module, but this is inaccurate because the change depends on the actual field characteristics. However, according to the present invention, stable data collection is possible through accurate measurement from a solar cell module installed in the field, and more accurate prediction is possible.
In the first step, measurement data including the solar radiation amount A, the module temperature B, and the power generation amount C measured from the solar cell module is obtained (S110). Measurement data acquisition is preferably obtained at predetermined time intervals. The closer the time interval is, the more accurate the amount of power generation can be predicted, but the time required for data processing is increased. The solar irradiance (A) measures an oblique solar irradiance and the power generation measures the DC power generation or the AC power generation.
In the second step, a correlation with the power generation amount C is obtained using the irradiation amount A and the module temperature B (S120). A correlation is obtained by using a part of the measurement data obtained in the first step as a learning section. Assuming that the learning section is the first section, the solar radiation amount A and the module temperature B acquired in the first section may be the solar radiation amount A1 and the module temperature B1.
In the second step, a plurality of correlations with the power generation amount C are obtained using the irradiation amount A and the module temperature B, respectively. Correlation acquisition can be performed in various known ways, and one of the big data analysis methods can be used. For example, the analysis methods that can be used in the second step include a linear regression model, a random forest analysis method, a support vector regression analysis method, a k nearest neighbor analysis neighbors, kNN), Gradient boosting machine analysis method, or Neural network analysis method. The analysis method can be analyzed in such a manner that the correlation between the solar radiation amount A and the module temperature B and the power generation amount C is different depending on the type thereof.
In the third step, the predicted generation amount is obtained according to the correlation obtained in the second step (S130). That is, the predicted generation amount Cp is obtained by using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section. Since a different correlation is obtained according to the analysis method in the second step, a plurality of predicted generation amounts Cp are also obtained.
In the fourth step, the most accurate correlation among the correlations acquired in the third step is obtained (S140) in order to obtain the most accurate predicted generation amount Cp among the plurality of obtained predicted generation amounts Cp. In the fourth step, a method for obtaining an optimal correlation, that is, a method for determining a correlation that can optimally predict a power generation amount among correlations obtained according to each analysis method, is an average of root mean squared error ) Value.
That is, in the third step, the measured power generation amount Cm2 measured in the second section is compared with a plurality of predicted power generation amounts Cp, and it is determined that the correlation calculated at the smallest root mean square error average is the most accurate, do. The equation for calculating the root mean square error is as follows.
[Equation 1]
Where Pmeasured is the measured power generation and Ppredicted is the predicted power generation.
When an optimal correlation is obtained, an analysis method for obtaining an optimal correlation is also selected, and it is judged according to which analysis method, the predicted generation amount Cp obtained is the most accurate. Accordingly, if the predicted generation amount Cp predicted based on the optimal correlation is selected, the predicted generation amount value for the solar cell module is obtained in step S150.
2 is a flowchart illustrating a method of predicting the generation amount of a solar cell module according to another embodiment of the present invention. In this embodiment, after the measurement data is acquired in the first step (S210), the preprocessing is performed on the obtained measurement data (S220).
It is possible to increase the accuracy of the power generation prediction through the preprocessing and to reduce the time required for the data processing in case of a large amount of data. The preprocessing can perform at least any one of limiting the irradiation amount (A), limiting the performance ratio (PR) value, and calculating the average value to the measurement data.
The data when the solar radiation amount is too low may be adversely affected by the prediction of the power generation amount, so it is removed. For example, only the measurement data of 200 W or more can be used for the irradiation amount (A).
Another method is to limit the power generation performance coefficient by the preprocessing method. The performance ratio (PR) is expressed by the following equation (2).
&Quot; (2) "
If the PR value is too small or too large, it is removed from the measurement data since it is adversely affecting the power generation prediction. For example, the PR value may be 0.5 to 1.2.
If the data measurement interval is narrow, the average value calculation can use data using the average value because the time required for data processing is long because the data is large. For example, when the measurement data is measured one minute, using the one hour average value of the measurement data can reduce the processing time of the measurement data.
After the preprocessing of the measurement data, a plurality of correlations between the irradiation amount A and the module temperature B and the power generation amount C are acquired (S230), and the predicted generation amount Cp is acquired (240) After obtaining the most accurate optimum correlation among the correlations (S250), the predicted generation amount Cp predicted according to the optimal correlation is selected (S260).
In this embodiment, an optimum correlation that can obtain an accurate predicted power generation amount is obtained and used for calculating the deterioration value. The degradation value is a relative value. The average bias error (MBE) value of the predicted generation amount Cp predicted according to the measured power generation amount Cm and the optimum correlation is selected as the deterioration value of the solar cell module in step S270, . MBE can be calculated by the following equation (3).
&Quot; (3) "
Where Pmeasured is the measured power generation and Ppredicted is the predicted power generation.
The RMSE error rate is expressed as a positive number, but the MBE error rate exists in the + and - values, and the deterioration rate can be quantitatively confirmed by comparing the deterioration of the module and the string with the initial monitoring data after learning.
FIG. 3 is a graph showing the amount of power generation of measurement data of the solar cell module over time. FIG. 3 shows the amount of electricity generated over time in the measurement data acquired for an actual solar cell module. Power generation data located in the red circle among power generation amounts is indicated by erroneous data due to measurement errors. In addition, the power generation amount data located in the blue circle shows a very low value, and this value is a value indicating that the generation amount is 0 because the insolation amount is low in the morning and night. Therefore, it is preferable to perform a method of predicting the generation amount of the solar cell module, excluding the measurement data, in order to accurately predict the generation amount.
Such data can be removed by preprocessing as described above, and can be removed by PR value limitation in case of measurement error. Also, when the amount of solar radiation is low and the amount of generated electricity is low, it is possible to remove measurement data in which the solar radiation amount does not reach a constant value. This preprocessing enables more accurate prediction of power generation.
FIG. 4 is a graph showing the measured data of the solar cell module with respect to time, irradiation dose, module temperature, measured power generation amount, and predicted power generation amount, and FIG. 5 is a graph showing the predicted power generation amount estimated using the SVR analysis method. As shown in FIG. 4, the measurement data of the solar cell module is obtained, and analyzed by the SVR analysis method among the big data analysis models using the statistical program R. FIG. The results of the analysis are shown in Fig. If the outputs of module and string are nonlinear in solar radiation module temperature and module temperature in predicting the power generation amount of solar cell module, SVR model can improve the accuracy because it is the analysis method that linearizes the nonlinear model.
FIG. 6 is a table showing average values of RMSE obtained by predicting and generating the power generation amount according to six analysis methods using the annual measurement data among the measurement data of the solar cell module. FIG. And the mean value of RMSE obtained. That is, in FIG. 6, the test section (the first section) is set to 2014 and the test section (the second section) is set to 2015 and 2016 respectively. When 2015 is set as the learning section, RMSE was obtained according to the analysis method.
When the RMSE obtained according to each analysis method is compared, the SVR analysis method is the lowest. In other words, it is judged that the correlation calculated with the smallest root mean square error is the most accurate, and it is found that the optimal correlation is the correlation obtained in the SVR analysis method. In FIG. 7, it is predicted that the RMSE is lower than that of FIG. 6 predicted on the basis of the month, so that it is possible to predict more accurately by reflecting seasonal factors.
8 is a table showing the MBE value obtained by the SVR analysis method of the measurement data of the solar cell module. In FIG. 6, since it is confirmed that the correlation by the SVR analysis method is an optimal correlation, the MBE value is obtained according to the SVR analysis method. When August 2014 is considered as the learning segment and the MBE value is -2.1 when August 2015 is predicted as TES interval, it is 2.1 higher than the actual measurement value. In other words, the expected 2.1 should be higher, but in fact less power was gained. Therefore, it can be determined that the MBE value has deteriorated.
Similarly, when August 2015 was used as a learning section and August 2016 was used as a test section, the MBE value, that is, the degradation rate, was 2.4. Based on the predicted power generation of 2015 and 2016, it can be judged that the average is deteriorated by 2.25 per year.
9 is a functional block diagram of an apparatus for predicting the generation amount of a solar cell module according to another embodiment of the present invention. In this embodiment, the
10 is a functional block diagram of an apparatus for monitoring the power generation amount of a solar cell module according to another embodiment of the present invention. In this embodiment, the collecting
According to another aspect of the present invention, there is provided a method of controlling a solar cell module, including: a first step of obtaining measurement data including a solar radiation amount A, a module temperature B, and a power generation amount C measured from a solar cell module; A second step of acquiring a plurality of correlations between the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 from the measurement data obtained in the first section of the measurement data; A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section; A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And a fifth step of selecting a predicted power generation amount (Cp) predicted according to an optimal correlation among the predicted power generation amount (Cp) and the predicted generation amount (Cp). The computer readable recording medium A medium is provided.
It goes without saying that the technical idea of the present invention can also be applied to a computer-readable recording medium having a computer program for performing the functions of the apparatus and method according to the present embodiment. In addition, the technical idea according to various embodiments of the present invention may be embodied in computer-readable code form recorded on a computer-readable recording medium. The computer-readable recording medium is any data storage device that can be read by a computer and can store data. For example, the computer-readable recording medium may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical disk, a hard disk drive, or the like. In addition, the computer readable code or program stored in the computer readable recording medium may be transmitted through a network connected between the computers.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, many modifications and changes may be made by those skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims. The present invention can be variously modified and changed by those skilled in the art, and it is also within the scope of the present invention.
Claims (12)
A second step of acquiring a plurality of correlations between the solar radiation amount (A1) and the module temperature (B1) and the power generation amount (C1) from the measurement data obtained in the first section of the measurement data;
A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section;
A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And
And selecting a predicted power generation amount (Cp) predicted according to an optimal correlation among the predicted power generation amount (Cp).
Further comprising: a pre-processing step of performing pre-processing on measurement data in the first step.
Wherein the preprocessing is performed on at least one of limiting the irradiation amount (A), limiting the performance ratio (PR) value, and calculating the average value to the measurement data.
Wherein the solar radiation amount (A) uses only measurement data of 200 W or more.
Wherein the PR value is 0.5 to 1.2.
When the measurement data is measured at the end of one minute,
Wherein the one-hour average value of the measurement data is used.
The second step comprises:
A linear regression model, a random forest analysis method, a support vector regression analysis method, a K nearest neighbors (kNN) analysis method, a Gradient boosting machine ) Analysis method, and a neural network analysis method. The method according to any one of claims 1 to 5,
In the fourth step,
Wherein a correlation value obtained by obtaining a correlation value having a smallest value of the measured power generation amount (Cm2) and an average of root mean squared error value of the predicted generation amount (Cp) is selected as an optimum correlation. Method of estimating power generation.
And selecting a mean bias error (MBE) value of the predicted power generation amount (Cp) predicted according to the measured power generation amount (Cm) and the optimal correlation as a deterioration value of the solar cell module A method for predicting the generation amount of a solar cell module.
A second step of acquiring a plurality of correlations between the solar radiation amount (A1) and the module temperature (B1) and the power generation amount (C1) from the measurement data obtained in the first section of the measurement data;
A third step of obtaining a predicted power generation amount Cp using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained in the first section;
A fourth step of comparing the measured power generation amount (Cm2) measured in the second section with the predicted generation amount (Cp) to obtain the most accurate optimum correlation among the correlations; And
And a fifth step of selecting a predicted power generation amount (Cp) predicted according to an optimum correlation among the predicted power generation amounts (Cp). The computer readable recording medium media.
A correlation acquiring unit for acquiring a plurality of correlations between the solar radiation amount (A1) and the module temperature (B1) and the power generation amount (C1) from the measurement data obtained in the first section of the measurement data;
A predicted power generation amount obtaining unit for obtaining the predicted generation amount Cp by using the solar radiation amount A2 and the module temperature B2 measured in the second section according to the correlation obtained by the correlation obtaining unit;
An optimum correlation acquiring unit that compares the measured power generation amount (Cm2) measured in the second section with the predicted power generation amount (Cp) acquired by the predicted generation power obtaining unit to obtain the most accurate optimum correlation among the correlations; And
And a power generation amount predicting unit for selecting a predicted power generation amount (Cp) predicted according to an optimum correlation among the predicted generation amount (Cp) acquired by the predicted generation amount obtaining unit.
A storage unit for storing measurement data from the collecting unit;
A power generation amount predicting unit for predicting a power generation amount of the solar cell module using measurement data from the storage unit; And
And a transmitter for transmitting the measured power generation amount and a power generation amount predicted from the power generation amount predicting unit,
The power generation amount predicting unit acquires a plurality of correlations between the solar radiation amount A1 and the module temperature B1 and the power generation amount C1 from the measurement data obtained in the first section of the measurement data, The predicted generation amount Cp obtained using the temperature B2 is obtained and the measured generation amount Cm2 measured in the second period is compared with the predicted generation amount Cp to determine the most accurate optimum correlation And selects the predicted power generation amount (Cp) predicted according to the optimum correlation among the predicted generation amount (Cp).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020160176263A KR101882106B1 (en) | 2016-12-22 | 2016-12-22 | Method and apparatus for predicting the generated energy of the solar cell module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020160176263A KR101882106B1 (en) | 2016-12-22 | 2016-12-22 | Method and apparatus for predicting the generated energy of the solar cell module |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| KR20180072954A true KR20180072954A (en) | 2018-07-02 |
| KR101882106B1 KR101882106B1 (en) | 2018-08-24 |
Family
ID=62914123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020160176263A KR101882106B1 (en) | 2016-12-22 | 2016-12-22 | Method and apparatus for predicting the generated energy of the solar cell module |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR101882106B1 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020022624A1 (en) * | 2018-07-26 | 2020-01-30 | (주)에코브레인 | Method for calculating power generation amount reflecting farm environment and detailed technology for predicting solar farm weather, and real-time solar power generation amount prediction system using the method |
| KR102178925B1 (en) * | 2020-01-20 | 2020-11-13 | 영남이공대학교 산학협력단 | Method andapparatus for solar power generation forcatst |
| KR102230548B1 (en) * | 2020-09-02 | 2021-03-22 | 주식회사 케이디티 | Power generation prediction and efficiency diagnosis system of solar power generation facilities using FRBFNN model |
| KR20210062389A (en) * | 2019-11-21 | 2021-05-31 | (주)에코브레인 | A Forecasting System of Photovoltaic Generation Based on Machine-learning Using Realtime Satellite Data and Numerical Modeling Data |
| KR20210079540A (en) * | 2019-12-20 | 2021-06-30 | 한국전자기술연구원 | Comparative Evaluation Method and System of Photovoltaic Power Prediction Model |
| KR20210085315A (en) * | 2019-12-30 | 2021-07-08 | 한국과학기술연구원 | Deep learning based method for estimating output value of power plant and system for performing the same |
| KR102338519B1 (en) * | 2021-04-28 | 2021-12-13 | 주식회사 인코어드 테크놀로지스 | A system for estimating renewable energy generation in real-time |
| KR20220022353A (en) * | 2020-08-18 | 2022-02-25 | 고려대학교 산학협력단 | Interpretable Solar Irradiation Forecasting apparatus and method |
| KR20230048725A (en) * | 2021-10-05 | 2023-04-12 | 한국에너지기술연구원 | Apparatus of data verification for quality evaluation of insolation and power generation data and method thereof |
| KR102587449B1 (en) * | 2023-05-24 | 2023-10-11 | 주식회사 케이디티 | Apparatus and method for predicting solar power generation and diagnosing power generation efficiency using intelligent fuzzy inference system |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102159692B1 (en) * | 2018-11-13 | 2020-09-24 | 주식회사 에코시안 | solar photovoltatic power generation forecasting apparatus and method based on big data analysis |
| KR20210053606A (en) | 2019-11-04 | 2021-05-12 | 주식회사 에스테코 | Apparatus and method for predicting degradation rate of solar power system |
| KR102338515B1 (en) | 2021-04-08 | 2021-12-13 | 주식회사 인코어드 테크놀로지스 | A System For Forecasting Solar Power Generation Based On Artificial Intelligence |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100086298A (en) * | 2009-01-22 | 2010-07-30 | (주)엘지하우시스 | Method for estimating generated energy of the solar cell modules |
-
2016
- 2016-12-22 KR KR1020160176263A patent/KR101882106B1/en active IP Right Grant
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100086298A (en) * | 2009-01-22 | 2010-07-30 | (주)엘지하우시스 | Method for estimating generated energy of the solar cell modules |
Non-Patent Citations (2)
| Title |
|---|
| Mellit, A., A. Massi Pavan, and V. Lughi. "Short-term forecasting of power production in a large-scale photovoltaic plant." Solar Energy 105 (2014): 401-413. 1부. * |
| Yadav, Amit Kumar, and S. S. Chandel. "Solar radiation prediction using Artificial Neural Network techniques: A review." Renewable and Sustainable Energy Reviews 33 (2014): 772-781. 1부. * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020022624A1 (en) * | 2018-07-26 | 2020-01-30 | (주)에코브레인 | Method for calculating power generation amount reflecting farm environment and detailed technology for predicting solar farm weather, and real-time solar power generation amount prediction system using the method |
| KR20200012228A (en) * | 2018-07-26 | 2020-02-05 | (주)에코브레인 | A Forecasting System and Method of Sunlight Generation Using Weather Prediction and Farm Environment |
| KR20210062389A (en) * | 2019-11-21 | 2021-05-31 | (주)에코브레인 | A Forecasting System of Photovoltaic Generation Based on Machine-learning Using Realtime Satellite Data and Numerical Modeling Data |
| KR20210079540A (en) * | 2019-12-20 | 2021-06-30 | 한국전자기술연구원 | Comparative Evaluation Method and System of Photovoltaic Power Prediction Model |
| KR20210085315A (en) * | 2019-12-30 | 2021-07-08 | 한국과학기술연구원 | Deep learning based method for estimating output value of power plant and system for performing the same |
| KR102178925B1 (en) * | 2020-01-20 | 2020-11-13 | 영남이공대학교 산학협력단 | Method andapparatus for solar power generation forcatst |
| KR20220022353A (en) * | 2020-08-18 | 2022-02-25 | 고려대학교 산학협력단 | Interpretable Solar Irradiation Forecasting apparatus and method |
| KR102230548B1 (en) * | 2020-09-02 | 2021-03-22 | 주식회사 케이디티 | Power generation prediction and efficiency diagnosis system of solar power generation facilities using FRBFNN model |
| JP2022042469A (en) * | 2020-09-02 | 2022-03-14 | ケーディーティー カンパニー リミテッド | Power generation prediction and efficiency diagnosis system for photovoltaic power generation facility using frbfnn model |
| KR102338519B1 (en) * | 2021-04-28 | 2021-12-13 | 주식회사 인코어드 테크놀로지스 | A system for estimating renewable energy generation in real-time |
| KR20230048725A (en) * | 2021-10-05 | 2023-04-12 | 한국에너지기술연구원 | Apparatus of data verification for quality evaluation of insolation and power generation data and method thereof |
| KR102587449B1 (en) * | 2023-05-24 | 2023-10-11 | 주식회사 케이디티 | Apparatus and method for predicting solar power generation and diagnosing power generation efficiency using intelligent fuzzy inference system |
Also Published As
| Publication number | Publication date |
|---|---|
| KR101882106B1 (en) | 2018-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101882106B1 (en) | Method and apparatus for predicting the generated energy of the solar cell module | |
| Mellit et al. | Short-term forecasting of power production in a large-scale photovoltaic plant | |
| US9876468B2 (en) | Method, system and program product for photovoltaic cell monitoring via current-voltage measurements | |
| JP2012195495A (en) | Abnormality diagnosis device, method thereof, and computer program | |
| Ventura et al. | Development of models for on-line diagnostic and energy assessment analysis of PV power plants: The study case of 1 MW Sicilian PV plant | |
| KR20190005514A (en) | Method and apparatus for predicting the degradation ratio of the solar cell module | |
| Zhang et al. | A reinforcement learning based approach for on-line adaptive parameter extraction of photovoltaic array models | |
| US20180034411A1 (en) | Method and apparatus for determining key performance photovoltaic characteristics using sensors from module-level power electronics | |
| Shi et al. | Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations | |
| CN115333469A (en) | Photovoltaic module cleaning method and device | |
| Pan et al. | Research on output distribution modeling of photovoltaic modules based on kernel density estimation method and its application in anomaly identification | |
| JP2017027419A (en) | Method and device for expressing temporal change in characteristic of energy conversion means | |
| KR20190037657A (en) | Method and apparatus for measuring degradation property of the solar cell module | |
| CN117172620B (en) | Building photovoltaic potential evaluation method and system based on parameterized analysis | |
| KR101207310B1 (en) | Estimation method on power generation performance of grid-connected photovoltaic system And Apparatus Thereof | |
| CN111814399B (en) | Model parameter optimization extraction method and measurement data prediction method of solar photovoltaic cell system | |
| Aarseth et al. | Detecting permanently activated bypass diodes in utility-scale PV plant monitoring data | |
| Jones et al. | Single diode parameter extraction from in-field photovoltaic IV curves on a single board computer | |
| KR20150076473A (en) | System for forcasting residual life of a solar photovoltaic power generation | |
| JP6190438B2 (en) | Power generation data collection system and solar power generation device | |
| CN116703210B (en) | Renewable energy source utilization method, device, equipment and storage medium | |
| Laayouj et al. | New prognostic framework for degradation assessment and remaining useful life estimation of photovoltaic module | |
| US20230238918A1 (en) | Method for detecting pv anomaly and determining long-term degradation | |
| WO2022054954A1 (en) | Method, system, and program for estimating power generation characteristics of solar cell. | |
| CN117033904A (en) | Distributed photovoltaic electric energy flow and information flow data fusion method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A201 | Request for examination | ||
| E902 | Notification of reason for refusal | ||
| E701 | Decision to grant or registration of patent right | ||
| GRNT | Written decision to grant |