WO2021066259A1

WO2021066259A1 - System and method for analyzing data of photovoltaic power plant

Info

Publication number: WO2021066259A1
Application number: PCT/KR2020/000444
Authority: WO
Inventors: 백경석; 오재철
Original assignee: 주식회사 아이온커뮤니케이션즈
Priority date: 2019-10-02
Filing date: 2020-01-10
Publication date: 2021-04-08
Also published as: KR102065443B1

Abstract

Disclosed in one embodiment of the present invention is a method for analyzing data of a photovoltaic power plant, the method comprising the steps of: calculating a theoretical estimated power generation amount of a photovoltaic power plant; obtaining a measured power generation amount actually collected from the photovoltaic power plant; determining whether power generation loss of the photovoltaic power plant occurs, depending on a result of comparing the estimated power generation amount and the measured power generation amount; and determining a cause of loss on the basis of a lost power generation amount when it is determined that power generation loss of the photovoltaic power plant has occurred.

Description

Solar power plant data analysis method and system

The present invention relates to a data analysis method and system of a solar power plant, and to a data analysis method and system of a solar power plant for detecting a decrease in output of the solar power plant and analyzing the cause of the decrease in output.

In modern society, as environmental problems such as global warming become serious due to excessive use of fossil fuels, internationally, it is urgent to prepare measures to reduce carbon dioxide emissions, and interest in renewable energy is increasing as an alternative.

In addition, green energy sources, including solar cells, have great advantages in that they do not use fossil fuels, which are limited to the earth, and that they do not emit carbon dioxide gas, so that environmental pollution can be minimized. These advantages are inevitably very important when considering the position of modern people who must prepare for the near future when global warming and fossil fuel depletion are serious.

In the case of Korea, in recent years, in order to regulate carbon dioxide emissions, a policy to encourage the supply of new and renewable energy, led by solar power generation, has been institutionalized and implemented. Accordingly, the solar power generation system has been recommended as a priority power generation system for major new and renewable energy in recent years, and numerous power generation facilities and infrastructure facilities necessary for its operation have been developed. Currently, photovoltaic power generation facilities with a capacity of thousands of KW are installed and operated in the field. have.

On the other hand, if the solar module is shaded by external environments such as clouds, shadows, and fallen leaves in a set of string-type solar modules connected in series, it causes an unstable state in which voltage and current change every moment, and the corresponding string type There is a problem of lowering the total power generation of the solar module.

To solve this problem, solar power plants collect and monitor data generated by inverters through a solar monitoring system.

As for inverters, there is a centralized type in which one or two inverters are installed according to the capacity of one solar power plant consisting of a plurality of solar module strings, and there is a string inverter type that is installed in units of solar module strings.

The latter has a disadvantage of having a high installation cost because it requires relatively more equipment than the former. A solar power plant built with a string inverter method can compensate to some extent from the photovoltaic partial shading problem by utilizing the MPPT (Maximum Power Point Tracking) function provided by the inverter.

However, most of the solar power plants built in Korea are centralized inverters, and recently, cases of introducing string inverters in newly constructed power plants have arisen. In a solar power plant with an existing centralized inverter, it is extremely rare to replace the inverter with a string inverter due to the problem of investment cost.

For a solar power plant with a basic centralized inverter installed, if the power loss can be recognized by detecting some of the solar power loss based on the power generation data monitored by the photovoltaic monitoring system, it is cheaper than replacing the inverter with a string inverter. By installing the MPPT control device on the string solar module, which does not affect the existing power plant with simple installation, it will be possible to solve the problem and minimize the amount of power loss.

Since the economics of a solar power plant are important, a solution that provides an economic effect against the minimum investment in lost power generation is urgently needed.

The present invention was conceived to solve the problems of the prior art, and the data analysis method of a solar power plant according to an embodiment of the present invention is an inexpensive and simple method in a solar power plant equipped with a centralized inverter. And try to find out the cause of the power generation loss.

In addition, the data analysis method of a solar power plant according to an embodiment of the present invention is used to make a decision on applying a method that can minimize the amount of power generation loss according to the amount of power generation loss and the cause of the loss of the solar power plant. I would like to provide reference material.

A method of analyzing data of a solar power plant according to an embodiment of the present invention includes calculating a theoretical predicted power generation amount of the solar power plant, obtaining the measured power generation amount actually collected from the solar power plant, the predicted power generation amount and the measurement Determining whether or not power generation loss of the solar power plant has occurred according to a result of comparing the difference in power generation amount, and determining a cause of the loss based on the amount of power loss when it is determined that power generation loss of the solar power plant has occurred. I can.

In one embodiment, in the calculating of the estimated power generation, the estimated power generation amount is calculated through a mathematical operation that reflects real-time meteorological data and calculates the power generation amount by a predetermined time unit of a solar panel unit. Panel properties can be reflected as variable values.

In one embodiment, the determining of the power generation loss of the solar power plant includes determining that power generation of the solar power plant is lost when the difference between the estimated power generation amount and the measured power generation amount is greater than or equal to a preset first reference value. And extracting a first distribution graph indicating a difference value in which the difference between the estimated power generation amount and the measured power generation amount is equal to or greater than the first reference value in a predetermined time unit.

In one embodiment, the step of determining the cause of the loss based on the amount of power loss comprises: when the amount of power loss is greater than or equal to a predetermined first reference value, a similarity to weather data of an adjacent time zone corresponding to the first distribution graph is preset. 1 Determining whether there is a past that is greater than or equal to the similarity criterion, and when there is a past whose meteorological data is greater than or equal to the first similarity criterion, a second distribution graph of the past having a similarity of the first distribution graph and a predetermined second similarity criterion or more Determining whether or not there is, and when the second distribution graph having a similarity greater than or equal to the second similarity criterion exists, determining whether the second distribution graph exists above a preset second reference value, and the second distribution If the graph exists below the second reference value, determining that some shades have occurred in the solar power plant may be included.

In an embodiment, when the amount of power loss is less than the first reference value, determining that the cause of the loss of the amount of power loss of the solar power plant is that white noise has occurred.

In one embodiment, if there is no past having a similarity with weather data of an adjacent time zone corresponding to the first distribution graph equal to or greater than the first similarity criterion, periodically recording power generation information of the corresponding solar power plant. Can include.

In an embodiment, when the second distribution graph having the similarity greater than or equal to the second similarity criterion does not exist, the step of periodically recording power generation information of a corresponding solar power plant may be further included.

In one embodiment, if the second distribution graph exists above the second reference value, determining that a physical defect has occurred in the solar power plant, and performing a detailed inspection related to the solar power plant. I can.

In one embodiment, after the step of determining whether or not shadowing of the solar power plant has occurred, acquiring location information of the solar panel determined to have shadowed, an area adjacent to the solar panel corresponding to the location information Flying a flying object, obtaining an image by photographing the solar panel through at least one camera provided on the flying object, analyzing the acquired image, and analyzing the acquired image, based on the analyzed image It may further include the step of re-checking whether or not the light panel is shaded.

The data analysis system of a solar power plant according to an embodiment of the present invention compares the difference between a solar power plant that collects power produced from a plurality of solar panels, and the theoretical predicted power generation amount of the solar power plant and the actual measured power generation amount collected. It may include a central server that determines whether or not the solar power plant has power generation loss based on a result, and analyzes the cause of the loss based on the amount of power loss.

In one embodiment, the central server calculates the theoretical predicted power generation amount through a mathematical operation that reflects real-time weather data and calculates the power generation amount for each predetermined time unit of the solar panel unit, but the mathematical operation is the solar panel The property of can be reflected as a variable value.

In one embodiment, the central server, when the difference between the estimated power generation amount and the measured power generation amount is greater than or equal to a preset first reference value, determines that power generation of the solar power plant has been lost, and the estimated power generation amount and the estimated power generation amount in a predetermined time unit. A first distribution graph indicating a difference value in which the difference in the measured power generation amount is equal to or greater than the first reference value may be extracted.

In one embodiment, the central server, when the amount of power loss is greater than or equal to the first reference value, whether or not there exists a past that has a similarity of weather data of an adjacent time zone corresponding to the first distribution graph equal to or greater than a preset first similarity criterion. Is determined, and when there is a past in which the meteorological data is greater than or equal to the first similarity criterion, it is determined whether or not a second distribution graph in the past with a similarity of the first distribution graph or higher than a preset second similarity criterion exists, and the similarity is When the second distribution graph that is greater than or equal to the second similarity criterion exists, it is determined whether the second distribution graph is greater than or equal to a preset second criterion value, and when the second distribution graph is less than the second criterion value, It can be determined that some shading has occurred in the solar power plant.

In an embodiment, when the amount of power loss is less than the first reference value, the central server may determine the cause of the loss of the amount of power loss of the solar power plant as white noise.

In one embodiment, the central server, when there is no past in which the similarity to weather data of an adjacent time zone corresponding to the first distribution graph is equal to or greater than the first similarity criterion does not exist, the power generation information of the corresponding solar power plant is periodically Can be recorded.

In an embodiment, the central server may periodically record power generation information of a corresponding solar power plant when the second distribution graph having the similarity greater than or equal to the second similarity criterion does not exist.

In an embodiment, when the second distribution graph exists above the second reference value, it is determined that a physical defect has occurred in the solar power plant, and a detailed inspection related to the solar power plant may be performed.

In one embodiment, the central server acquires location information of the solar power plant determined to have some shades, and makes the flying object fly to an area adjacent to the solar power plant corresponding to the location information, and the flying object The photovoltaic panels included in the photovoltaic power plant are photographed through at least one camera provided in the photovoltaic power plant to acquire an image, the acquired image is analyzed, and whether or not the corresponding photovoltaic panel is shaded is determined again based on the analyzed image. I can confirm.

A computer-readable recording medium or a computer program stored in a recording medium according to an embodiment of the present invention is a computer-readable recording medium or recording medium in which a program for performing the data analysis method of a solar power plant described above is recorded. It characterized in that it is a computer program stored in.

According to the data analysis method of a solar power plant according to an embodiment of the present invention as described above, the inverter is replaced with a string inverter by recognizing the power generation loss based on the power generation data for a solar power plant in which a centralized inverter is installed. It is cheaper and simpler to monitor solar power plants.

In addition, according to the data analysis method of a solar power plant according to an embodiment of the present invention, it is used to make a decision on applying a method that can minimize the amount of power generation loss depending on the amount of power generation loss and the cause of the loss of the solar power plant. You can provide reference materials.

1 is a diagram showing a schematic configuration of a data analysis system of a solar power plant according to an embodiment of the present invention.

2 is a photograph showing an example in which some shades have occurred in a solar power plant due to surrounding environment.

3 is a flowchart schematically illustrating a data analysis method of a solar power plant according to an embodiment of the present invention.

4 is a flow chart for explaining in more detail a data analysis method of a solar power plant according to an embodiment of the present invention.

5 is a flowchart illustrating a method of analyzing solar power plant data after periodically recording power generation information of a solar panel according to an embodiment of the present invention.

6 is a diagram showing an example in which a flying object is applied to the configuration of a data analysis system of a solar power plant according to the present invention.

7 is a photovoltaic panel and is a diagram showing unit panels constituting the photovoltaic panel.

8 is a block diagram schematically showing the configuration of a central server according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to clarify the technical idea of the present invention. In describing the present invention, when it is determined that a detailed description of a related known function or component may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted. Constituent elements having substantially the same functional configuration among the drawings are assigned the same reference numerals and reference numerals as much as possible, even though they are indicated on different drawings. For convenience of explanation, if necessary, the device and the method will be described together.

FIG. 1 is a diagram showing a schematic configuration of a data analysis system of a solar power plant according to an embodiment of the present invention, and FIG. 2 is a photograph showing an example in which some shades are generated in a solar power plant due to surrounding environment. .

As shown in FIG. 1, the data analysis system 10 of a solar power plant according to an embodiment of the present invention may include a central server 100 and a solar power plant 300.

Prior to the description, the data analysis system 10 of a solar power plant according to an embodiment of the present invention detects when and for how long some shadows have occurred through time-series data analysis for a solar power plant equipped with a centralized inverter. And, by calculating the power loss estimate and the loss amount, we want to help you make decisions about applying a method that can minimize the power loss.

1 and 2, the solar power plant 300 may be composed of a plurality of solar panels M1 to M3, and the solar panels M1 to M3 collect sunlight incident from the outside to It can produce electricity. The solar power plant 300 is a general configuration known to a person skilled in the art, and a detailed description thereof will be omitted.

The central server 100 is connected to the photovoltaic power plant 300 through a wired or wireless network, receives power generation amount from the photovoltaic power plant 300, determines whether it is operating normally, and manages the operating state of the photovoltaic power plant. .

That is, the central server 100 determines whether or not there is a loss of power generation of the photovoltaic power plant 300 based on the result of comparing the difference between the theoretical estimated power generation amount of the solar power plant 300 and the actual collected measured power generation amount, and Based on this, the cause of the loss can be analyzed.

Furthermore, the central server 100 may provide reference material used for making a decision on applying a method that can minimize the amount of power loss according to the amount of power generation loss of the solar power plant 300 and the cause of the loss. .

Hereinafter, a data analysis method of a solar power plant according to an embodiment of the present invention will be schematically described with reference to FIG. 3.

Referring to FIG. 3, in the data analysis method of a solar power plant according to an embodiment of the present invention, first, a theoretical predicted power generation amount of the solar power plant may be calculated (S410).

To this end, the central server may calculate the expected power generation amount through a mathematical operation that reflects real-time weather data and calculates the power generation amount for each predetermined time unit of the solar panel unit. Here, the mathematical operation may reflect the property of the solar panel as a variable value.

In one embodiment, the mathematical calculation for calculating the expected power generation amount of a solar power plant is based on at least one of the number of panels of the power plant, the power reduction rate according to the life of the panel, the power reduction rate according to the panel surface temperature, and the maximum amount of power generation information. Can be calculated.

In addition, the mathematical calculation for calculating the expected power generation amount of the solar power plant may calculate the output reduction rate according to the panel surface temperature by reflecting weather data including the current amount of insolation, temperature, humidity, and wind speed in real time. To this end, the meteorological data may be stored in a certain time unit, for example, in a few minutes, and the estimated power generation amount in minutes may be calculated.

In an embodiment, the power generation amount is measured in units of solar panels constituting a solar power plant, and the total amount of power generation measured for each solar panel unit may be summed to calculate the total amount of power generation of the solar power plant. Alternatively, in another embodiment, the expected power generation amount may be calculated for each solar panel in units of solar panels.

Next, it is possible to obtain the measured power generation amount actually collected from the solar power plant (S420). Likewise, the measured power generation amount may be obtained in units of a solar power plant, or the measured power generation amount may be obtained for each solar panel.

Since the technology in which the central server receives the actual measured power generation amount from the solar power plant is general, a detailed description will be omitted.

Next, it is possible to determine whether or not there is a power loss of the solar power plant according to a result of comparing the difference between the estimated power generation amount and the measured power generation amount (S430).

To this end, the central server may compare the difference between the estimated power generation amount calculated in step S410 and the measured power generation amount obtained in step S420 to determine whether or not the solar power plant loses power according to whether the difference value is equal to or greater than a preset reference value.

In one embodiment, when the difference between the estimated power generation amount and the measured power generation amount is greater than or equal to a preset first reference value, it may be determined that power generation has been lost, whereas, if it is less than the first reference value, it may be determined as white noise.

Next, when it is determined that the power generation loss of the solar power plant has occurred, the cause of the loss may be determined based on the amount of power loss (S440). In one embodiment, it is determined whether some shading has occurred in the solar power plant or whether a physical problem has occurred in the solar power plant according to whether the amount of power loss is greater than or equal to a preset reference value, the frequency at which the amount of power loss occurs, and whether the loss continues to occur. can do. If it is determined that a physical problem has occurred in the solar power plant, a detailed inspection can be performed to uncover specific problems such as panel failure, junction box failure, electrical wiring problem, and inverter failure.

Hereinafter, a data analysis method of a solar power plant according to an embodiment of the present invention will be described in detail with reference to FIGS. 4 and 5.

Referring to FIG. 4, in the method for analyzing data of a solar power plant according to an embodiment of the present invention, first, an estimated amount of power generation and a measured amount of power generation may be compared (S510). In one embodiment, the estimated power generation amount calculated in minutes for a certain time period for a solar power plant may be summed, and the sum of the measured power generation amount for the same time period may be compared.

Since the method of calculating the estimated power generation amount and the measured power generation amount has been described with reference to FIG. 3, detailed descriptions will be omitted.

In addition, when the loss generation amount, which is the difference between the estimated generation amount and the measured generation amount, is equal to or greater than a preset first reference value (S520), a first distribution graph indicating a difference value between the expected generation amount and the measured generation amount may be extracted (S540).

Specifically, when the difference between the estimated power generation amount and the measured power generation amount is greater than or equal to a preset first reference value, it may be determined that power generation of the solar power plant is lost. On the other hand, if it is less than the first reference value, it may be determined that the difference value is due to white noise (S530).

Here, the first distribution graph may be extracted by a predetermined time unit, and the predetermined time unit may be a minute unit. The meteorological data and the panel surface temperature are continuously recorded in the predetermined time unit, and can be applied in real time to calculate the expected power generation amount. In addition, the first distribution graph may be stored in the database along with information such as year, date, time, and weather data.

Next, it may be determined whether or not the past exists in which the similarity to the weather data of the adjacent time zone corresponding to the extracted first distribution graph is greater than or equal to a preset first similarity criterion (S550).

Here, the adjacent time zone may include the same time zone corresponding to the first distribution graph (eg, the same time zone a week ago), and may include a time interval corresponding to within a predetermined interval before and after the same time zone.

The meteorological data may be data representing weather conditions, including climate, weather, insolation, temperature, humidity, and wind speed, in numerical values, graphs, and the like.

In one embodiment, the first similarity criterion is set to a predetermined similarity range based on a numerical value for each meteorological data expressed as a numerical value, or a degree of similarity in the form, flow, and numerical value of the graph for the meteorological data expressed as a graph. It can be set as a similarity range.

The first similarity criterion may be a criterion for determining whether each of the climate, weather, insolation, temperature, humidity, and wind speed falls within a predetermined similarity range. Alternatively, the first similarity criterion may be a criterion for determining whether at least what percentage of climate, weather, insolation, temperature, humidity, and wind speed each fall within a predetermined similarity range.

And, if there are at least how many past cases in which the similarity to the data of the adjacent time period corresponding to the first distribution graph is equal to or greater than the first similarity criterion should be at least, that is, if the past case is more than the preset reference number, it is assumed that there are similar past cases. It can be set to judge.

On the other hand, when a past case with a similarity greater than or equal to the first similarity criterion exists less than the preset reference number, it may be determined that no past case exists.

Next, when there is a past that has a similarity greater than or equal to a preset first similarity criterion with meteorological data corresponding to the first distribution graph, a second distribution in the past with a similarity greater than or equal to a preset second similarity criterion. It is possible to determine whether the graph exists (S570).

Here, the second distribution graph may be a graph generated by the same method as the first distribution graph when the first distribution graph is generated when the season, month, day, time, etc. are the same or adjacent to each other. That is, the second distribution graph is information that was created in the past and stored in the database in the same way as the method of creating and storing the first distribution graph, but the season, weather, insolation, temperature, humidity, and wind speed at which the first distribution graph was generated. It may be a graph of meteorological data generated at a time when the weather data and the like are similar in time.

Assuming that there are 10 past cases similar to the meteorological data corresponding to the first distribution graph, the second distribution graphs are extracted for each of the 10 cases, and the similarity to the first distribution graph is a second similarity among the second distribution graphs. Graphs that are more than the standard can be extracted. The second similarity criterion is a reference value for determining the similarity between the first distribution graph and the second distribution graph. For example, the second similarity criterion is based on the first distribution graph and falls within a similarity range of at least 80% or more. It may be a criterion for extracting the second distribution graph. The similarity comparison of the distribution graph can be performed by applying an algorithm that compares the patterns of the distribution graph.

On the other hand, when there is no past case in which the similarity to the weather data of the time zone corresponding to the first distribution graph is greater than or equal to the first similarity criterion, power generation information of the corresponding solar power plant may be periodically recorded (S560).

This means that although it was determined that there is a loss in the amount of power generated by the solar power plant, but there are no similar cases in the past in this regard, by periodically recording and storing the power generation information of the solar power plant in the future, at some point in the future. Through the first distribution graph stored in advance, it may be suitable for the purpose of using it to determine the cause of the power generation loss of the solar power plant.

Next, when the second distribution graph having a similarity greater than or equal to the second similarity criterion exists, it may be determined whether or not the second distribution graph is greater than or equal to a preset second reference value (S580).

For example, there are 10 past cases in which the similarity to the weather data of an adjacent time zone corresponding to the first distribution graph is equal to or higher than a preset first similarity criterion, and the past second has similarity to the first distribution graph equal to or higher than the second similarity criterion. When it is assumed that there are 7 distribution graphs, if the second reference value is set to at least 5 or more, it may be determined that the second distribution graph exists above the second reference value in step S580.

That is, the second reference value may be an absolute value preset with respect to the number of second distribution graphs whose similarity is greater than or equal to the second similarity reference based on the first distribution graph. Alternatively, the second reference value may be set as a ratio occupied by the second distribution graph whose similarity is greater than or equal to the second similarity criterion with respect to the total number of the second distribution graphs.

Here, when the second distribution graph exists above the second reference value, that is, when it is determined that the second distribution graph has been continuously occurring to some extent from the past, solar power is not generated by a change in weather or season. It can be determined that power generation losses are continuously occurring due to physical failure of the power plant. Accordingly, a detailed inspection for detecting physical defects of the solar power plant may be performed (S590).

Here, when the second distribution graph exists below the second reference value, that is, when the second distribution graph intermittently exists, it may be determined that some shades have occurred in the solar power plant (S600).

In other words, as a result of analysis based on the fact that the power generation loss of the solar power plant occurred intermittently (less than the second reference value) at the same time or similar time period from the past, and the past and present weather data, the power generation loss of the current solar power plant It can be judged to be caused by some shades caused by this season or weather.

On the other hand, in an embodiment of the present invention, since it is possible to analyze the estimated power generation amount and the measured power generation amount in minutes, a site where some shadows are generated in real time or within a short time from the time when it is determined that some shadows have occurred in the solar power plant or The environment that caused some shades can be acquired as an image.

To this end, according to an embodiment of the present invention, after the step of determining whether or not shadowing of a solar power plant has occurred, location information of the solar panel determined to have shadowed may be obtained. In an embodiment of the present invention, since it is possible to determine whether or not power generation loss occurs even in units of solar panels constituting a solar power plant, it is possible to identify location information of a solar panel in which power generation loss has occurred.

A flying object having at least one camera mounted thereon may be made to fly to an area adjacent to the solar panel corresponding to the location information obtained by this method. In addition, an image may be obtained by photographing a solar panel corresponding to the location information and the surrounding environment through a camera provided on the flying object.

Here, the camera may be at least one of an infrared camera, a visible ray camera, and an EL camera.

In addition, by analyzing the acquired image, it is possible to confirm whether or not a shadow around the corresponding solar panel is generated based on the analyzed image. 6 shows an example in which the flying object 200 is applied to the configuration of the data analysis system 10 of a solar power plant of the present invention, and FIG. 7 is a solar panel M, showing a solar panel M It shows the unit panels 310 constituting.

5 is a flowchart illustrating a method of analyzing solar power plant data after periodically recording power generation information of a solar panel according to an embodiment of the present invention. That is, FIG. 5 is a flowchart illustrating a method of analyzing solar power plant data after step S560 of FIG. 4.

Referring to FIG. 5, after step S560 of periodically recording power generation information of a solar panel, a first distribution graph and a third distribution graph at a future point in time may be compared (S561).

The third distribution graph is the same method as the method of generating the first distribution graph, and may be generated based on a difference value between the estimated generation amount and the measured generation amount for the solar power plant. The third distribution graph may be extracted in a certain time unit, and the certain time unit may be in a minute unit, but is not limited thereto. Meteorological data and panel surface temperature are continuously recorded in a certain time unit and can be applied to calculate the expected power generation, and the third distribution graph can be stored in a database along with information such as year, date, time, and meteorological data. have.

Next, it may be determined whether or not there is a third distribution graph whose similarity to the weather data of an adjacent time zone corresponding to the first distribution graph is greater than or equal to a preset first reference (S562).

Here, the adjacent time zone includes the same time zone corresponding to the first distribution graph, and may include a time interval corresponding to within a predetermined interval before and after the same time zone. The meteorological data may be data that expresses weather conditions in numerical form, graphs, etc., including solar radiation, temperature, humidity, and wind speed.

And, the number of cases in the future (based on the first distribution graph) in which the similarity to the data in the adjacent time zone corresponding to the first distribution graph is equal to or higher than the first similarity criterion should be at least. A case that is more than the set reference number can be set as determining that a similar case exists.

On the other hand, when a future case having a similarity greater than or equal to the first similarity criterion exists less than the preset reference number, it may be determined that there is no future case. When it is determined that a future case in which the similarity to the weather data in the time zone corresponding to the first distribution graph is greater than or equal to the first similarity criterion does not exist at a future point in time, power generation information of the corresponding solar power plant may be continuously tracked (S563). .

This means that although it was determined that there is a loss in the amount of power generated by the solar power plant, in this regard, similar cases have not yet occurred in the future, so by continuously recording and storing the power generation information of the solar power plant in the future, At some point, it can be used to determine the cause of the power generation loss of the solar power plant through the first distribution graph stored in advance.

When there is a future case in which the similarity of the weather data of the adjacent time zone corresponding to the first distribution graph is equal to or greater than the preset first similarity criterion, the first distribution graph and the third distribution graph at a future point in which the similarity is equal to or greater than the second similarity criterion It can be determined whether or not (S562). If the first distribution graph and the third distribution graph at a future point in which the similarity is greater than or equal to the preset second similarity criterion do not exist, it is determined that it is not clear whether it is a partial shade or a physical defect, and the power generation information of the solar power plant is continuously displayed. It can be traced (S563).

Next, when there is a third distribution graph having a similarity greater than or equal to the second similarity criterion, it may be determined whether or not the third distribution graph is greater than or equal to a preset third reference value (S564).

Here, when the third distribution graph exists above the third reference value, that is, when it is determined that the third distribution graph is continuously occurring to some extent in the future based on the creation time of the first distribution graph, weather, season, etc. It can be judged that power generation loss is continuously occurring not due to a change in power generation but by a physical defect of the solar power plant. Accordingly, a detailed inspection for detecting a physical defect of the solar power plant may be performed (S565).

In addition, when the third distribution graph exists below the third reference value, that is, when the third distribution graph intermittently exists, it may be determined that some shades have occurred in the solar power plant (S566).

In other words, the fact that the power generation loss of the solar power plant occurred intermittently (less than the third reference value) at the same time or similar time period from the time when the first distribution graph was generated to the future time point, and the future time point and the first distribution graph. As a result of analyzing based on the corresponding meteorological data, it can be determined that the power generation loss of the solar power plant at the time corresponding to the first distribution graph is caused by some shades caused by the season or weather.

8 is a block diagram schematically showing the configuration of a central server according to an embodiment of the present invention. Referring to FIG. 8, the central server 100 according to an embodiment of the present invention may include an output reduction section detection unit 110, a shadow generation determination unit 120, and a loss information statistics unit 130. .

The output reduction section detection unit 110 calculates the theoretical expected power generation amount of the solar power plant, obtains the measured power generation amount actually collected from the solar power plant, and compares the difference between the estimated power generation amount and the measured power generation amount of the solar power plant. It is possible to determine whether or not there is a loss of power generation. At this time, since the power generation data and the meteorological data are operated in the same time unit, the power generation data and the meteorological data can have characteristics of time-series data, so whether the solar power plant is lost can be detected in units of time-series power generation loss intervals. .

The shade generation determination unit 120 may determine the cause of the loss based on at least one of the calculated loss generation amount, the past time point and the future time point in which the meteorological data are similar, and frequency information at which the power loss occurs. For a method of determining the cause of the power generation loss of the solar power plant, reference will be made to the description described with reference to FIGS. 3 to 5 above.

The loss information statistics unit 130 may calculate and store a cost conversion of the frequency of occurrence of some shades, the amount of power loss, and the amount of power loss, respectively. In addition, statistics may be calculated for each solar power plant in units of a certain period of time, for example, year/month/week/day, for the cost conversion information of the frequency of occurrence of some shades, the amount of power loss, and the amount of power loss. The information thus calculated may be provided to the solar power plant manager and the solar power plant owner's terminal.

The data analysis method of the solar power plant as described above can be executed by a computer program stored in a recording medium. The present invention can also be implemented as a computer-readable code on a computer-readable recording medium. Computer-readable recording media include all storage media such as magnetic storage media and optical reading media. The exemplary structures according to the present invention include program instructions executed by a processor, a software module, a microcode, a computer program product recorded on a recording medium that can be read by a computer (including all devices having an information processing function), It can be implemented in a variety of ways, such as logic circuits, application specific semiconductors, or firmware. Examples of the computer-readable recording medium include ROM, RAM, CD, DVD, magnetic tape, hard disk, floppy disk, hard disk, and optical data storage device. Further, the computer-readable recording medium is distributed over a computer system connected through a network, so that computer-readable codes can be stored and executed in a distributed manner.

Also, for example, various embodiments may be embodied or encoded on a computer-readable medium containing instructions. Instructions embodied or encoded on a computer-readable medium may cause a programmable processor or other processor to perform a method, eg, when the instructions are executed. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. The storage medium may be any available medium that can be accessed by a computer. For example, such computer-readable media may be RAM, ROM, EEPROM, CD-ROM, or other optical disk storage medium, magnetic disk storage medium or other magnetic storage device, or instructions accessible by a computer with the desired program code or It may include any other medium that can be used to carry or store in the form of data structures.

Such hardware, software, firmware, and the like may be implemented within the same device or within separate devices to support the various operations and functions described herein. Additionally, components, units, modules, components, and the like described as "units" in the present invention may be implemented together or separately as interoperable logic devices. The description of different features for modules, units, etc. is intended to highlight different functional embodiments, and does not necessarily imply that they must be realized by separate hardware or software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware or software components or may be integrated within common or separate hardware or software components.

Although the operations are shown in the figures in a specific order, it should not be understood that these operations are performed in the specific order shown, or in a sequential order, or that all illustrated operations need to be performed to achieve the desired result. . In any environment, multitasking and parallel processing can be advantageous. Moreover, the division of various components in the above-described embodiments should not be understood as requiring such division in all embodiments, and the described components are generally integrated together into a single software product or packaged into multiple software products. It should be understood that you can.

So far, the present invention has been looked at in detail centering on the preferred embodiments shown in the drawings. These embodiments are not intended to limit the present invention, but are merely illustrative, and should be considered from a descriptive point of view rather than a restrictive point of view. The true technical protection scope of the present invention should be determined not by the above description, but by the technical spirit of the appended claims. Although specific terms have been used in the present specification, they are used only for the purpose of describing the concept of the present invention, and not for limiting the meaning or limiting the scope of the present invention described in the claims. Each step of the present invention does not necessarily have to be performed in the order described, and may be performed in parallel, selectively or individually. Those of ordinary skill in the art to which the present invention pertains will understand that various modifications and other equivalent embodiments are possible without departing from the essential technical idea of the present invention claimed in the claims. It is to be understood that equivalents include not only currently known equivalents, but also equivalents to be developed in the future, that is, all components invented to perform the same function regardless of the structure.

Claims

Calculating a theoretical predicted power generation amount of the solar power plant;

Obtaining a measured amount of generation actually collected from the solar power plant;

Determining whether a power generation loss of the solar power plant is based on a result of comparing the difference between the estimated power generation amount and the measured power generation amount; And

And determining the cause of the loss based on the amount of power loss when it is determined that the power generation loss of the photovoltaic power plant has occurred.
The method of claim 1,

The step of calculating the expected power generation amount,

The solar panel, characterized in that the predicted power generation amount is calculated through a mathematical operation that reflects real-time weather data and calculates the amount of power generated by a predetermined time unit of the solar panel unit, wherein the mathematical operation reflects the property of the solar panel as a variable value. Data analysis method of photovoltaic power plant
The method of claim 1,

The step of determining whether the solar power plant has power generation loss,

Determining that power generation of the solar power plant is lost when the difference between the estimated power generation amount and the measured power generation amount is greater than or equal to a preset first reference value; And

And extracting a first distribution graph indicating a difference value in which the difference between the estimated power generation amount and the measured power generation amount in a predetermined time unit is equal to or greater than the first reference value.
The method of claim 3,

The step of determining the cause of the loss based on the amount of power generated by the loss,

When the amount of power loss is greater than or equal to a preset first reference value,

Determining whether there is a past that has a similarity of weather data of an adjacent time zone corresponding to the first distribution graph and is greater than or equal to a preset first similarity criterion;

Determining whether or not a second distribution graph in the past having a similarity of the first distribution graph and a second similarity criterion having a similarity higher than or equal to a preset second similarity criterion exists when there is a past in which the meteorological data is greater than or equal to the first similarity criterion;

Determining whether the second distribution graph has a similarity greater than or equal to the second similarity criterion when the second distribution graph having a similarity greater than or equal to the second similarity criterion exists; And

And determining that some shades have occurred in the solar power plant when the second distribution graph is less than the second reference value.
The method of claim 4,

And when the amount of power loss is less than the first reference value, determining that the cause of the loss of the power loss amount of the solar power plant is that white noise has occurred.
The method of claim 4,

If there is no past having a similarity with weather data of an adjacent time zone corresponding to the first distribution graph equal to or greater than the first similarity criterion, periodically recording power generation information of a corresponding solar power plant. Data analysis method of solar power plant.
The method of claim 4,

And if the second distribution graph having the similarity greater than or equal to the second similarity criterion does not exist, periodically recording power generation information of a corresponding solar power plant.
The method of claim 4,

If the second distribution graph exists above the second reference value, determining that a physical defect has occurred in the solar power plant, and performing a detailed inspection related to the solar power plant. Power plant data analysis method.
The method of claim 1,

After the step of determining whether the solar power plant is shaded or not,

Acquiring location information of the solar panel determined to be shaded;

Flying a flying object to an area adjacent to the solar panel corresponding to the location information;

Obtaining an image by photographing the solar panel through at least one camera provided in the flying object; And

Analyzing the acquired image, and based on the analyzed image data analysis method of a solar power plant further comprising the step of re-checking whether or not shade has occurred in the solar panel.
A solar power plant that collects power produced from a plurality of solar panels; And

Comprising a central server that determines whether or not there is a power loss of the solar power plant based on a result of comparing the difference between the theoretically expected power generation amount of the solar power plant and the actual measured power generation amount collected, and analyzes the cause of the loss based on the amount of power loss. Data analysis system of a solar power plant, characterized in that.
The method of claim 10,

The central server,

The theoretical predicted power generation amount is calculated through a mathematical operation that reflects real-time meteorological data and calculates the power generation amount by a predetermined time unit of the solar panel unit, wherein the mathematical operation reflects the property of the solar panel as a variable value. Data analysis system of a solar power plant.
The method of claim 10,

The central server,

When the difference between the estimated power generation amount and the measured power generation amount is greater than or equal to a preset first reference value, it is determined that power generation of the solar power plant is lost,

A data analysis system for a solar power plant, characterized in that extracting a first distribution graph indicating a difference value in which the difference between the estimated power generation amount and the measured power generation amount is equal to or greater than the first reference value in a predetermined time unit.
The method of claim 12,

The central server,

When the amount of power loss is greater than or equal to the first reference value,

It is determined whether or not a past exists in which the degree of similarity to the meteorological data of an adjacent time zone corresponding to the first distribution graph is greater than or equal to a preset first similarity criterion, and when there is a past in which the meteorological data is greater than the first similarity criterion, the first It is determined whether there is a second distribution graph in the past having a distribution graph and a similarity greater than or equal to a preset second similarity criterion, and when the second distribution graph having a similarity greater than or equal to the second similarity criterion exists, a second similarity or greater Data analysis of a solar power plant, characterized in that it is determined whether the second distribution graph exists, and when the second distribution graph is less than the second reference value, it is determined that some shades have occurred in the solar power plant. system.
The method of claim 13,

The central server,

When the amount of power loss is less than the first reference value, the data analysis system of a solar power plant is characterized in that it is determined that the cause of the loss of the power loss amount of the solar power plant is that white noise has occurred.
The method of claim 13,

The central server,

Data of a solar power plant, characterized in that, when there is no past that has a similarity greater than or equal to the first similarity criterion with meteorological data of an adjacent time zone corresponding to the first distribution graph, power generation information of the corresponding solar power plant is periodically recorded. Analysis system.
The method of claim 13,

The central server,

When the second distribution graph having the similarity greater than or equal to the second similarity criterion does not exist, power generation information of a corresponding solar power plant is periodically recorded.
The method of claim 13,

When the second distribution graph exists above the second reference value, it is determined that a physical defect has occurred in the solar power plant and a detailed inspection related to the solar power plant is performed. .
The method of claim 10,

The central server,

Acquires location information of a solar power plant determined to have some shading, and makes a flying object fly to an area adjacent to the solar power plant corresponding to the location information, and sunlight through at least one camera provided in the flying object Data of a solar power plant, characterized in that by photographing the solar panels included in the power plant to acquire an image, analyzing the acquired image, and reconfirming whether or not a shadow has occurred in the corresponding solar panel based on the analyzed image Analysis system.
A computer program stored in a medium for executing the method of any one of claims 1 to 9 on a computer.