KR20210062288A - Server, method and computer program for estimating solar radiation of targer point - Google Patents

Abstract

A server that estimates the amount of insolation at a target point based on satellite data comprises: a regression coefficient derivation unit for deriving a regression coefficient for a meteorological factor based on past satellite data and past weather observation data; a multiple regression model generation unit for generating a multiple regression model based on the regression coefficients for the derived weather factors; and an insolation estimation unit that reflects real-time satellite data and real-time meteorological observation data in the generated multiple regression model to estimate the amount of insolation at a target point from real-time satellite data.

Description

Server, method, and computer program for estimating the amount of insolation at the target point {SERVER, METHOD AND COMPUTER PROGRAM FOR ESTIMATING SOLAR RADIATION OF TARGER POINT}

The present invention relates to a server, a method, and a computer program for estimating the amount of insolation at a target point.

In general, the solar radiation is measured by installing an solar radiation sensor at a specific location to measure the solar radiation.

However, it is impossible to measure the amount of insolation in an area other than the area in which the insolation sensor is installed, and in particular, when the insolation sensor is deteriorated, there is a problem that the accuracy of the insolation measurement value is significantly lowered.

In order to solve this problem, as a method of predicting the amount of insolation, a method of using weather information has been widely used. However, in the case of this method, the weather information of an area belonging to a wide range including the location of the solar power plant can be known, but it is difficult to accurately know the weather information at a specific point where the solar power plant is located. There was a problem in that it was difficult to accurately predict the amount of insolation to the location where it was located.

Japanese Registered Patent Publication No. 5571970 (registered on 2014.07.04.)

The present invention is to solve the problems of the prior art described above, and generates a multiple regression model based on regression coefficients for meteorological factors derived from past satellite data and past weather observation data, and uses the generated multiple regression model. We want to estimate the amount of insolation at the target point from real-time satellite data. However, the technical problem to be achieved by the present embodiment is not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, a server for estimating the amount of insolation at a target point based on satellite data according to the first aspect of the present invention provides a regression for meteorological factors based on past satellite data and past weather observation data. A regression coefficient derivation unit for deriving coefficients; A multiple regression model generator for generating a multiple regression model based on the derived regression coefficients for the meteorological factors; And an insolation estimating unit configured to estimate the insolation amount of the target point from the real-time satellite data by reflecting real-time satellite data and real-time weather observation data in the generated multiple regression model.

A method of estimating solar radiation of a target point based on satellite data according to a second aspect of the present invention includes: deriving a regression coefficient for a meteorological factor based on past satellite data and past meteorological observation data; Generating a multiple regression model based on the derived regression coefficients for the meteorological factors; And estimating the amount of insolation at the target point from the real-time satellite data by reflecting real-time satellite data and real-time weather observation data in the generated multiple regression model.

A computer program stored in a medium including a sequence of instructions for estimating solar radiation of a target point based on satellite data according to the third aspect of the present invention, when executed by a computing device, is based on past satellite data and past weather observation data. Deriving a regression coefficient for a meteorological factor, generating a multiple regression model based on the derived regression coefficient for the meteorological factor, and reflecting real-time satellite data and real-time weather observation data in the generated multiple regression model, the real-time satellite It may include a sequence of instructions for estimating the amount of insolation at the target point from data.

The above-described problem solving means are merely exemplary and should not be construed as limiting the present invention. In addition to the above-described exemplary embodiments, there may be additional embodiments described in the drawings and detailed description of the invention.

According to any one of the above-described problem solving means of the present invention, the present invention generates a multiple regression model based on regression coefficients for meteorological factors derived from past satellite data and past meteorological observation data, and uses the generated multiple regression model. By using, it is possible to estimate the amount of insolation at the target point from real-time satellite data. Through this, the present invention can estimate the insolation amount of the target point through a multiple regression model even if the insolation amount sensor is not installed at the target point.

On the other hand, in the case of the conventional solar radiation estimation method, it was difficult to accurately predict the solar radiation for a specific target point within the corresponding region because the method of estimating the solar radiation of a specific region through meteorological information and satellite data. The conventional problem can be solved, and the reliability of the power generation output of the new renewable power plant can be maximized by estimating the amount of insolation at the target point using a multiple regression model.

1 is a block diagram of an insolation estimation server according to an embodiment of the present invention.
2A to 2C are diagrams for explaining a regression analysis according to an embodiment of the present invention.
3A to 3C are diagrams for explaining an effect in estimating the amount of insolation at a target point according to an embodiment of the present invention.
4 is a diagram illustrating a service method using an estimated amount of insolation at a target point according to an embodiment of the present invention.
5 is a flowchart illustrating a method of estimating solar radiation at a target point according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized by using two or more hardware, or two or more units may be realized by one piece of hardware.

In this specification, some of the operations or functions described as being performed by the terminal or device may be performed instead in a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal or device connected to the server.

Hereinafter, with reference to the accompanying configuration diagram or processing flow chart, it will be described in detail for the implementation of the present invention.

1 is a block diagram of an insolation estimation server 10 according to an embodiment of the present invention.

Referring to FIG. 1, the insolation estimating server 10 may include a regression coefficient derivation unit 100, a multiple regression model generation unit 110, an insolation estimating unit 120, and a generation amount estimating unit 130. However, the insolation estimating server 10 shown in FIG. 1 is only one embodiment of the present invention, and various modifications are possible based on the components shown in FIG. 1.

Hereinafter, it will be described with reference to FIGS. 2A to 4 along with FIG. 1.

The regression coefficient derivation unit 100 may derive a regression coefficient for a meteorological factor based on past satellite data and past weather observation data. Here, the past satellite data includes past insolation for an area including a target point (eg, a point where a renewable power plant is located), and the past weather observation data is historical weather observation data for an area including the target point (eg, , Insolation, temperature, humidity, wind speed, total cloudiness, visibility, etc.).

For example, the regression coefficient derivation unit 100 may calculate a weather factor based on past satellite data for a region including a point where a renewable power plant is located measured during a preset period and past weather observation data observed during a preset period. The regression coefficient for can be derived.

Here, the meteorological factor may include at least one of an insolation factor, a temperature factor, a humidity factor, a wind speed factor, a total cloud factor, and a visibility factor. Regression coefficients for meteorological factors are among the regression coefficients for insolation factors, regression coefficients for temperature factors, regression coefficients for humidity factors, regression factors for wind speed factors, regression factors for total cloud volume factors, and regression factors for visibility factors. It may include at least one.

For example, the regression coefficient derivation unit 100 may provide an insolation factor based on past satellite data for a region including a target point measured during the first period and insolation data included in the past meteorological observation data observed during the first period. We can derive the regression coefficient for For example, the regression coefficient derivation unit 100 is a temperature factor based on past satellite data for a region including a target point measured during the first period and temperature data included in the past weather observation data observed during the first period. We can derive the regression coefficient for

The regression coefficient derivation unit 100 may extract data corresponding to the weather factor from past weather observation data, and derive a regression coefficient for the weather factor through regression analysis between the past satellite data and data corresponding to the weather factor.

Here, the regression analysis may include a linear regression analysis and a regression analysis using a least squares method.

Referring to FIG. 2A, the linear regression analysis refers to a case in which a regression line representing a relationship between a variable X (past weather observation data corresponding to a weather factor) and a variable Y (past satellite data) appears close to a straight line. That is, finding a straight line in which the sum of the distances to all points represented by the coordinates of (X, Y) is the minimum is called linear regression analysis.

By calculating the constants a and b that minimize the sum of squared errors of prediction (SSE), a straight line (linear regression equation) that best represents the relationship between the variables X and Y can be derived. Here, as a method of minimizing SSE, a least squared method may be used.

,

, ...,

이 어떤 다른 측정값

,

, ...,

의 함수라고 추정할 수 있을 때, 측정값

와 함수값 f(

)의 차이를 제곱한 것의 합(

)이 최소가 되도록 하는 함수 f(x)를 구하는 것을 말한다. 이 때, 함수 f(x)는

의 총합(즉, 오차의 총합)이 최소가 되는 직선이라고 할 수 있다. 2B, the regression analysis using the least squares method is a measurement value measured N times.

,

, ...,

Some other measure of this

,

, ...,

When it can be estimated to be a function of

And the function value f(

) The sum of the squared differences (

Refers to finding the function f(x) that makes) the minimum. In this case, the function f(x) is

It can be said that it is a straight line where the sum of (that is, the sum of errors) is the minimum.

On the other hand, in multiple regression analysis with multiple independent variables, the regression coefficient is a direct effect (or net effect) representing the average amount of change in the dependent variable according to the change in the corresponding independent variable when the other independent variable is invariant (i.e., in a controlled state). Effect).

For example, taking the correlation between the data corresponding to the temperature factor and the amount of insolation (satellite data) as an example, the blue coordinate points displayed on the graph 20 of FIG. 2C represent past data (data corresponding to the past temperature factor and past satellites). Insolation corresponding to the data), the red line is the regression line between the temperature factor and the insolation based on past data, and the yellow coordinate point is the currently observed insolation (real-time satellite data), the regression coefficient for the temperature factor is now It plays the role of correcting the observed solar radiation to fit the regression line (refer to reference numeral 22).

The multiple regression model generation unit 110 may generate a multiple regression model based on a regression coefficient for the derived meteorological factor. Here, the multiple regression model can be expressed as Equation 1.

[Equation 1]

은 보정된 위성 데이터의 일사량이고,

은 일사량 인자에 대한 회귀 계수이고,

는 일사량 인자에 대응하는 데이터 변수이고,

는 기온 인자에 대한 회귀 계수이고,

는 기온 인자에 대응하는 데이터 변수이고,

는 습도 인자에 대한 회귀 계수이고,

는 습도 인자에 대응하는 데이터 변수이고,

는 풍속 인자에 대한 회귀 계수이고,

는 풍속 인자에 대응하는 데이터 변수이고,

는 전운량 인자에 대한 회귀 계수이고,

는 전운량 인자에 대응하는 데이터 변수이고,

는 시정 인자에 대한 회귀 계수이고,

는 시정 인자에 대응하는 데이터 변수이다. here,

Is the insolation of the calibrated satellite data,

Is the regression coefficient for the insolation factor,

Is the data variable corresponding to the insolation factor,

Is the regression coefficient for the temperature factor,

Is the data variable corresponding to the temperature factor,

Is the regression coefficient for the humidity factor,

Is the data variable corresponding to the humidity factor,

Is the regression coefficient for the wind speed factor,

Is the data variable corresponding to the wind speed factor,

Is the regression coefficient for the total cloud volume factor,

Is the data variable corresponding to the total cloud volume factor,

Is the regression coefficient for the correction factor,

Is the data variable corresponding to the correction factor.

For example, in the case of a regression coefficient for a temperature factor, it represents an increase in temperature compared to insolation (satellite data). That is, if the regression coefficient for the temperature factor at the target point is a positive (+) coefficient, it indicates the rate of increase of temperature relative to the amount of insolation at the target point, and the regression coefficient for the temperature factor at the target point is negative (- In the case of a coefficient of ), it represents the rate of decrease in temperature relative to the amount of insolation at the target point.

In this way, the regression coefficient for the meteorological factor represents a relationship with the amount of insolation (satellite data), and an error in the amount of insolation may be constantly converged through the meteorological factor. In other words, the present invention provides an increase/decrease trend between past satellite data (past insolation) and past meteorological observation data (data corresponding to the weather factor) for each target point, and current insolation (real-time satellite data) and current weather observation data (real-time weather observation data). ) To correct the error.

Specifically, the insolation estimating unit 120 may estimate the insolation of a target point from real-time satellite data by reflecting real-time satellite data and real-time weather observation data in a multiple regression model generated based on a regression coefficient for a meteorological factor. Here, the real-time satellite data may include real-time solar radiation for an area including the target point. In this case, the insolation amount of the target point estimated based on the multiple regression model is the insolation amount corrected for the real-time insolation amount for the region including the target point.

For example, the insolation estimator 120 substitutes the insolation amount (insolation amount derived from real-time satellite data) to the data variable corresponding to the insolation factor constituting the multiple regression model, and the temperature factor and the humidity factor constituting the multiple regression model , By substituting data corresponding to each meteorological factor extracted from real-time weather observation data into data variables corresponding to each of the wind speed factor, the total cloud volume factor, and the visibility factor, it is possible to estimate the amount of insolation at the target point.

The insolation estimator 120 may estimate the insolation amount of the target point by correcting the real-time insolation amount for the area including the target point based on the generated multiple regression model.

As described above, the present invention generates a multiple regression model for each target point by using the past insolation and past weather observation data for a region including a target point where each of the plurality of renewable power plants is located, and the generated multiple regression model for each target point For each target point, the amount of insolation may be estimated for each target point by reflecting real-time satellite data and real-time weather observation data for an area including each target point.

3A to 3C are diagrams showing the results of verifying the insolation test for each target point to which the present invention is applied. Referring to FIG. 3A, the insolation amount for each target point and the amount of insolation installed at each target point estimated by reflecting real-time satellite data and real-time weather observation data for each target point in a multiple regression model for each target point (19 renewable power plants) It can be seen that the average absolute error (MAPE, Mean Absolute Error) between the insolation amount measured from the sensor is approximately 19.21%, and the Root Mean Square Error (RMSE) is approximately 21.61%.

Referring to FIG. 3B, the amount of insolation (301, real-time insolation corresponding to real-time satellite data before correction) for the Gochang area including the target point, the first renewable power plant, and measured by the insolation sensor installed in the first renewable power plant When comparing the insolation 303 and the insolation 305 of the target point, which is the point where the first renewable power plant is located, the insolation amount 303 measured by the insolation sensor and the multiple It can be seen that the insolation amount 305 of the target point corrected by the regression model shows a similar pattern.

Referring to FIG. 3C, the amount of insolation (307, real-time insolation corresponding to real-time satellite data before correction) for the Chuncheon region including the second renewable power plant as the target point, and measured by the insolation sensor installed in the second renewable power plant When comparing the insolation (309) and the insolation (311, insolation corrected by the present invention) at the target point where the first renewable power plant is located, the insolation amount 309 at the target point measured by the insolation sensor and the multiple regression model It can be seen that the insolation 311 of the target point corrected by is showing a similar pattern.

The power generation predictor 130 may predict the power generation amount of the new and renewable power plant based on the estimated amount of insolation at the target point. Through this, the present invention can maximize the reliability of the power generation amount of the renewable power plant, it is possible to increase the power generation efficiency. In addition, the present invention can diagnose the power generation efficiency of a new and renewable power plant according to the estimated amount of insolation at a target point, and detect a failure situation due to a sudden decrease in power generation efficiency by generating a situation event in which power generation efficiency is lowered.

The power generation predictor 130 may diagnose the power generation performance and failure of the new and renewable power plant by comparing the predicted power generation amount of the new and renewable power plant and the actual power generation amount of the new and renewable power plant based on the estimated amount of insolation at the target point.

For example, referring to FIG. 4, the generation amount prediction unit 130 visualizes and provides information on the amount of insolation at the target point estimated for each target point corresponding to a point in which a plurality of renewable power plants are installed, through an insolation amount distribution interface. I can. For example, the generation amount prediction unit 130 may provide information on the amount of insolation of a specific target point retrieved based on the input date information and the location information of the specific target point through the insolation amount distribution interface.

On the other hand, for those skilled in the art, each of the regression coefficient derivation unit 100, the multiple regression model generation unit 110, the insolation estimating unit 120, and the generation amount prediction unit 130 are implemented separately, or one or more of them are integrated and implemented. I will fully understand that it can be.

5 is a flowchart illustrating a method of estimating solar radiation at a target point according to an embodiment of the present invention.

Referring to FIG. 5, in step S501, the solar radiation estimation server 10 may derive a regression coefficient for a weather factor based on past satellite data and past weather observation data. Here, the past satellite data includes past solar radiation for a region including a target point (eg, a renewable power plant), and the past meteorological observation data may be past weather observation data for a region including the target point.

Here, the meteorological factor includes at least one of an insolation factor, a temperature factor, a humidity factor, a wind speed factor, a total cloud volume factor, and a visibility factor, and the regression coefficient for the meteorological factor is a regression factor for the insolation factor, a regression factor for the temperature factor. , At least one of a regression coefficient for a humidity factor, a regression coefficient for a wind speed factor, a regression coefficient for a total cloud volume factor, and a regression coefficient for a visibility factor.

In step S503, the insolation estimation server 10 may generate a multiple regression model based on a regression coefficient for the derived meteorological factor.

In step S505, the solar radiation estimation server 10 may estimate the solar radiation of the target point from the real-time satellite data by reflecting real-time satellite data and real-time weather observation data in the generated multiple regression model. Here, the real-time satellite data may include real-time solar radiation for an area including the target point.

Although not shown in FIG. 5, in step S501, the solar radiation estimation server 10 extracts data corresponding to the meteorological factor from the past meteorological observation data, and uses a regression analysis between the past satellite data and the data corresponding to the meteorological factor. The regression coefficient for can be derived. Here, the regression analysis may include a linear regression analysis and a regression analysis using a least squares method.

Although not shown in FIG. 5, in step S505, the solar radiation estimation server 10 may estimate the solar radiation of the target point by correcting the real-time solar radiation for the region including the target point based on the generated multiple regression model.

In the above description, steps S501 to S505 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present invention. In addition, some steps may be omitted as necessary, or the order between steps may be changed.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. .

10: Insolation Estimation Server
100: regression coefficient derivation unit
110: Multiple regression model generator
120: insolation estimation unit
130: generation amount prediction unit

Claims (15)

In the server for estimating the amount of insolation at a target point based on satellite data,
A regression coefficient derivation unit for deriving a regression coefficient for a weather factor based on past satellite data and past weather observation data;
A multiple regression model generator for generating a multiple regression model based on the derived regression coefficients for the meteorological factors; And
The server comprising an insolation amount estimating unit for estimating the insolation amount of the target point from the real-time satellite data by reflecting real-time satellite data and real-time weather observation data in the generated multiple regression model.
The method of claim 1,
The target point is a renewable power plant,
The server further comprising a power generation amount predicting unit for predicting the power generation amount of the new and renewable power plant based on the estimated amount of insolation.
The method of claim 1,
The meteorological factor includes at least one of an insolation factor, a temperature factor, a humidity factor, a wind speed factor, a total cloud factor, and a visibility factor,
The regression coefficient for the meteorological factor is a regression coefficient for the insolation factor, a regression coefficient for the temperature factor, a regression coefficient for the humidity factor, a regression coefficient for the wind speed factor, a regression coefficient for the total cloudiness factor, and the The server comprising at least one of the regression coefficients for the correction factor.
The method of claim 3,
The regression coefficient derivation unit
Extracting data corresponding to the meteorological factor from the past weather observation data, and deriving a regression coefficient for the meteorological factor through regression analysis between the past satellite data and the data corresponding to the meteorological factor.
The method of claim 4,
The regression analysis is to include a linear regression analysis and a regression analysis using the least squares method, the server.
The method of claim 1,
The past satellite data includes past solar radiation for an area including the target point,
The past weather observation data is past weather observation data for a region including the target point,
Wherein the real-time satellite data includes real-time insolation for the area.
The method of claim 6,
The insolation amount estimating unit is to estimate the insolation amount of the target point by correcting the real-time insolation amount for the area based on the generated multiple regression model.
In the method of estimating the amount of insolation at a target point based on satellite data,
Deriving a regression coefficient for a weather factor based on past satellite data and past weather observation data;
Generating a multiple regression model based on the derived regression coefficients for the meteorological factors; And
And estimating the amount of insolation at the target point from the real-time satellite data by reflecting real-time satellite data and real-time weather observation data in the generated multiple regression model.
The method of claim 8,
The target point is a renewable power plant,
The method further comprising predicting a power generation amount of the new and renewable power plant based on the estimated amount of insolation.
The method of claim 8,
The meteorological factor includes at least one of an insolation factor, a temperature factor, a humidity factor, a wind speed factor, a total cloud factor, and a visibility factor,
The regression coefficient for the meteorological factor is a regression coefficient for the insolation factor, a regression coefficient for the temperature factor, a regression coefficient for the humidity factor, a regression coefficient for the wind speed factor, a regression coefficient for the total cloudiness factor, and the Including at least one of the regression coefficients for the correction factor, insolation estimation method.
The method of claim 10,
The step of deriving a regression coefficient for the meteorological factor
Extracting data corresponding to the weather factor from the past weather observation data, and
And deriving a regression coefficient for the meteorological factor through regression analysis between the past satellite data and data corresponding to the meteorological factor.
The method of claim 11,
The regression analysis will include a regression analysis using a linear regression analysis and a least squares method, insolation estimation method.
The method of claim 8
The past satellite data includes past solar radiation for an area including the target point,
The past weather observation data is past weather observation data for a region including the target point,
The real-time satellite data includes real-time solar radiation for the area.
The method of claim 13,
Estimating the amount of insolation at the target point
And estimating the amount of insolation at the target point by correcting the amount of insolation in real time for the region based on the generated multiple regression model.
A computer program stored in a medium comprising a sequence of instructions for estimating an amount of insolation at a target point based on satellite data,
When the computer program is executed by a computing device,
Derive regression coefficients for meteorological factors based on past satellite data and past weather observation data,
Generate a multiple regression model based on the regression coefficients for the derived meteorological factors,
A computer program stored in a medium comprising a sequence of instructions for reflecting real-time satellite data and real-time weather observation data to the generated multiple regression model to estimate the amount of insolation at the target point from the real-time satellite data.

Images