KR20210066642A - Consulting system through big data based prediction of solar power generation - Google Patents

Abstract

The present invention relates to a consulting system through big data-based solar power generation prediction, and more specifically, includes: a data collection unit for collecting existing facility information including facility information, power generation amount information, and weather/climate information for one or more previously installed solar power generation facilities; a database unit for storing the existing facility information collected by the data collection unit and turning the existing facility information into big data; and an information providing unit which analyzes the existing facility information stored in the database unit to generate a power generation prediction model, and provides consulting information including the predicted generation amount for an area where the selected existing solar power generation facility or the selected new solar power generation facility will be installed based on the generated generation amount prediction model.

Description

Consulting system through big data based prediction of solar power generation

The present invention selects an optimal installation area for a new photovoltaic power generation facility through big data analysis of facility information, generation amount information, and weather/climate information of one or more previously installed photovoltaic power generation facilities, or It relates to a consulting system through big data-based solar power generation prediction that provides consulting information so that the rate of return according to the amount of power generation can be referenced.

BACKGROUND ART In general, photovoltaic power generation is a power generation method in which power is produced by converting solar energy into electrical energy using a solar panel in which several solar cells are arranged.

As the demand for renewable energy gradually increases, the production of solar cells and solar cell arrays is also increasing significantly, and the solar power generation-related industry is developing, and recently, the solar power generation system is being built in a grid-connected type. to be.

Thanks to financial incentives/support policies such as the preferential standard price mandatory purchase system for solar electricity and the set-off system, the installation of solar power generation facilities is expanding worldwide, including Korea. .

The solar power generation system is spotlighted as an alternative energy source in the future because it can be used semi-permanently, maintenance is easy by using a solar cell, and uses a pollution-free and limitless solar energy source.

Meanwhile, about 63% of domestic solar power generation facilities are installed in rural areas, and are used in the order of farmland, general land, forests, and plant and animal facilities.

Large-scale photovoltaic power generation facilities often have their own management programs, but as mentioned above, most of the medium and small-scale power generation facilities installed in rural areas are operated in the system at the level of simply monitoring the amount of power generation. The photovoltaic power generation facility is the same as the photovoltaic power generation facility installed in the farmhouse.

Therefore, farmers who lack expertise or individuals who wish to install small-scale power generation facilities are not provided with any data to predict the amount of power generation or to review the business feasibility, such as profitability, when installing new solar power generation facilities. Therefore, for this purpose, it is necessary to provide construction information such as predicted power generation and yield based on accurate information on existing installed facilities.

Republic of Korea Patent No. 10-1525884 (2015.06.03)

Therefore, an object of the present invention is to select an optimal installation area for a new photovoltaic power plant through big data analysis of facility information, power generation amount information, and weather/climate information for one or more pre-installed photovoltaic power facilities, or This is to provide a consulting system through big data-based solar power generation prediction that can provide consulting information so that the profit rate according to the amount of power generation of photovoltaic facilities can be referenced.

As a means for achieving the above object, the consulting system (hereinafter referred to as the 'system of the present invention') through big data-based photovoltaic power generation prediction of the present invention is provided with facility information, power generation information and a data collection unit that collects existing facility information including meteorological/climate information; a database unit for storing the existing facility information collected by the data collection unit and turning it into big data; and generating a power generation prediction model by analyzing the existing facility information stored in the database unit, and the predicted power generation amount for an existing solar power generation facility selected based on the generated power generation prediction model or a selected new solar power generation facility installation area It is characterized in that it includes; an information providing unit that provides consulting information.

As an example, the data collection unit is characterized in that it collects existing facility information from one or more photovoltaic power generation facilities connected in advance through an established network platform.

As an example, the data collection unit is characterized by uploading and collecting existing facility information output from each of one or more solar power generation facilities.

As an example, the data collection unit identifies an area in which one or more solar power generation facilities are installed in conjunction with a Geographic Information System (GIS), and connects to a public data portal or a meteorological service server in which one or more solar power generation facilities are installed. It is characterized by collecting meteorological/climate information about the area.

As an example, the weather/climate information may include one or more than one of insolation, sunlight, temperature, humidity, and air volume.

As an example, the information providing unit, based on the power generation prediction model, to provide to be displayed together with the predicted power generation amount for the planned installation area of the existing solar power generation facility or the selected new solar power generation facility at the same time characteristic.

As an example, the information providing unit may include: a feature deriving module for extracting one or more features for learning from the existing facility information collected from the data collecting unit; a learning module for performing machine learning based on the features extracted from the feature deriving module; a model generation module for receiving the result information learned from the learning module and generating one or more power generation prediction models based on it; and a prediction module for calculating and outputting the predicted generation amount for the selected existing solar power generation facility or the selected new solar power generation facility installation area by applying the generation amount prediction model generated by the model generation unit.

As an example, the information providing unit calculates an error value between the generation amount of the existing facility information and the predicted generation amount based on the generation amount prediction model, and updates the generation amount prediction model generated by the model generation module by reflecting the calculated error value It is characterized by further comprising a correction module to

As such, the system of the present invention selects an optimal installation area for a new solar power generation facility or selects an optimal installation area for a new solar power generation facility through big data analysis such as facility information, generation amount information, and weather/climate information for one or more previously installed solar power generation facilities By providing consulting information so that the profit rate according to the amount of power generation of photovoltaic facilities can be referenced, it is effective in helping farmers who lack expertise or individuals who want to install small-scale power generation facilities to determine the feasibility of the business due to power generation facilities. have

1 is a schematic representation of a system of the present invention;
2 is a block diagram showing the configuration of a system according to an embodiment of the present invention.
3 is a block diagram illustrating a data collection method of a data collection unit according to an embodiment of the present invention.
4 is a block diagram illustrating a method of collecting meteorological/climate information of a data collection unit according to an embodiment of the present invention.
5 is a block diagram illustrating a detailed configuration of an information providing unit according to an embodiment of the present invention.
6 is a view showing a display screen of a user terminal according to an embodiment of the present invention.

Hereinafter, the configuration and operation of the present invention will be described in more detail based on the accompanying drawings. In describing the present invention, the terms or words used in the present specification and claims are based on the principle that the inventor can appropriately define the concept of the term in order to best describe his or her invention. It must be interpreted as a meaning and concept consistent with the technical idea of

1 is a diagram schematically showing a system of the present invention, FIG. 2 is a block diagram showing the configuration of a system according to an embodiment of the present invention, and FIG. 3 is a data collection unit of a data collection unit according to an embodiment of the present invention A block diagram showing the method. 4 is a block diagram illustrating a method of collecting weather/climate information of a data collection unit according to an embodiment of the present invention, and FIG. 5 is a block diagram illustrating a detailed configuration of an information providing unit according to an embodiment of the present invention. , FIG. 6 is a diagram illustrating a display screen of a user terminal according to an embodiment of the present invention.

1 and 2 , the system of the present invention includes a data collection unit 20 , a database unit 25 , an information providing unit 30 , and a user terminal 50 .

The data collection unit 20 collects facility information on one or more pre-installed photovoltaic power generation facilities 10, and existing facility information including generation amount information and weather/climate information, thereby providing an information providing unit 30 to be described below. ) to be used as basic data for model creation.

Here, the facility information may include information such as the installation location, power generation scale, and specifications of the existing photovoltaic power generation facility 10 , and the power generation information includes real-time power generation amount produced in the existing photovoltaic power generation facility 10 as well as the past It can include all the accumulated power generation.

In addition, the weather/climate information may be environmental information including one or more of insolation, sunlight, temperature, humidity, and air volume measured in an area where the existing solar power generation facility 10 is installed.

The data collection unit 20 may present various methods in collecting data from the existing solar power generation facility 10 .

As an example, the data collection unit 20 may collect facility information, generation amount information, weather/climate information, etc. from one or more photovoltaic power generation facilities pre-connected through an established network platform, respectively, as shown in FIG. 3 . .

The established network platform can be applied by selecting any one of a variety of known network platforms, and a detailed description thereof will be omitted. However, in this case, the existing photovoltaic power generation facility 10 receives the sensing means 100 and the sensing means 100 for sensing real-time generation amount information and weather/climate information on its own through a network platform that has been constructed. Communication means for transmitting to the collection unit 20 may be included.

As another example, the data collection unit 20 may upload and collect existing facility information output from each of the one or more solar power generation facilities 10 .

This is a data collection method in the existing photovoltaic power generation facility 10 that is not equipped with communication means, and is downloaded to the data collection unit 20 after accessing the existing photovoltaic power generation facility 10 and downloading the existing facility information. How to upload information directly.

Meanwhile, the data collection unit 20 may separately collect meteorological/climate information for the installation area of the existing solar power generation facility 10 in the existing facility information.

Referring to FIG. 4 , the data collection unit 20 identifies an area in which one or more solar power generation facilities 10 are installed in conjunction with a Geographic Information System (GIS), and a public data portal 45 or a weather service server 40 ) to collect meteorological/climate information for an area where one or more identified solar power generation facilities are installed.

At this time, the weather/climate information provided from the public data portal 45 or the Meteorological Agency server 40 may be information in the form of an OPEN API (Application Programming Interface).

In addition, the meteorological/climate information collected through this embodiment may include the above-mentioned amount of insolation, sunlight, temperature, humidity, and wind volume as well as air pollution information. The air pollution information includes sulfur dioxide concentration, carbon monoxide concentration, ozone concentration, nitrogen dioxide concentration, fine dust concentration, integrated atmospheric environmental value, integrated atmospheric environmental index, sulfur dioxide index, carbon monoxide index, ozone index, nitrogen dioxide index, fine dust index, etc. may include.

In addition, the weather/climate information collected through this embodiment may include not only real-time information, but also past recorded information and future forecast information.

That is, in the data collection unit 20 of the present invention, as shown in FIG. 1 , the meteorological/climate information of the facility, which is measured by itself, is received through the sensing means 100 provided in the existing solar power generation facility 10 . Or, it may be to receive weather/climate information provided from the public data portal 45 or the Automatic Weather System (AWS) of the Meteorological Administration server 40 .

It goes without saying that the collection of such weather/climate information may be performed through the aforementioned individual methods or a plurality of methods may be performed in parallel.

The database unit 25 stores and accumulates the existing facility information collected by the data collection unit 20 to make it big data.

In addition, the database unit 25 statisticizes the existing facility information converted into big data, extracts the statisticalized existing facility information at the request of the user terminal 50, and through the information providing unit 30, the user terminal 50 to be provided as

For example, the statistical information on existing facilities may be electricity generation information for a selected period in the past or changed weather/climate information for a selected period.

The information providing unit 30 analyzes the existing facility information stored in the database unit 25 to generate a generation prediction model, and based on the generated generation prediction model, the selected existing solar power generation facility 10 or the selected new solar Provides consulting information on the area where photovoltaic facilities will be installed.

The consulting information includes the predicted power generation amount predicted by the power generation prediction model and the corresponding predicted yield, so that it can be utilized as reference data in constructing a new solar power generation facility.

In addition, the information providing unit 30 may provide a web or mobile-based service according to the OS environment of the connected user terminal 50 , and a graphical user (GUI) suitable for the web or mobile environment according to the user terminal 50 . interface) so that consulting information can be displayed on the user terminal 50 .

The user terminal 50 is connected to the information providing unit 30 through a wired or wireless communication network to display consulting information provided from the information providing unit 30, or selected existing solar power generation facilities 10 or new solar power plants. Request information for requesting consulting information such as predicted generation amount information for a photovoltaic power generation facility may be input.

The user terminal 50 may be a stationary terminal such as a desktop or a mobile terminal having mobility such as a smart phone or a tablet.

In this case, in the case of a mobile terminal, the user terminal 50 may be a terminal in which a service app for receiving a service is downloaded and installed in advance.

The above-mentioned communication network is an IP network that provides a large-capacity data transmission/reception service and a data service without interruption through the Internet Protocol (IP). It is an IP network structure that integrates different networks based on IP. All IP) network, wired communication network, mobile communication network (CDMA, 2G, 3G, 4G, LTE), Wibro (Wireless Broadband) network, HSDPA (High Speed Downlink Packet Access) network, satellite communication network and Wi-Fi (WI-FI, Wireless Fidelity) ) network can be used.

Meanwhile, the information providing unit 30 may be configured to include a feature deriving module 300 , a learning module 310 , a model generating module 320 , and a prediction module 330 as shown in FIG. 5 .

The feature deriving module 300 extracts one or more features for learning from the existing facility information collected from the data collection unit 20 .

That is, the feature deriving module 300 extracts major factors necessary for learning from the vast amount of information collected in advance to predict the amount of solar power generation, for example, time, solar radiation, temperature, power generation, etc. that affect the power generation amount. features can be extracted.

The learning module 310 performs machine learning based on the features extracted from the feature deriving module 300 .

Machine learning by the learning module 310 may be applied to one or more selected from among various well-known learning algorithms.

For example, the learning module 310 may use a deep learning-based learning algorithm, and preferably perform machine learning using a Convolutional Neural Network (CNN) algorithm belonging to the deep learning learning neural network series. can

The model generation module 320 receives the result information learned by the learning module 310 and generates one or more power generation prediction models based on the received information. The power generation prediction model can be updated in real time by data accumulated in the database unit 25 in real time as a learning model in which a pattern according to the correlation between the amount of power generated by each existing solar power generation facility 10 and meteorological/climate information, etc. is a learning model. have.

The prediction module 330 applies the generation amount prediction model generated by the model generation unit 320 to calculate the predicted generation amount for the selected existing solar power generation facility 10 or the selected new solar power generation facility installation area. print out

That is, the prediction module 330 predicts the future weather/climate information of the expected area based on the generation amount prediction model when the expected installation area of the new solar power generation facility input from the user terminal 50 is input. It will be possible to predict the amount of power generation according to the predicted weather/climate information.

Preferably, the information providing unit 30 provides more reliable information by correcting errors in predicting the amount of power generation based on the power generation prediction model.

Accordingly, the information providing unit 30 may further include a correction module 340, wherein the correction module 340 calculates an error value between the generation amount of the existing facility information and the predicted generation amount based on the generation amount prediction model, The generation amount prediction model generated by the model generation module 320 is updated by reflecting the calculated error value.

The error rate between the generation amount (measured value) of the existing facility information and the predicted generation amount (predicted value) based on the generation amount prediction model can be calculated by using RMSD (Root Mean Square Deviation).

The root mean square deviation (RMSD) is a measure commonly used when dealing with the difference between an estimated value or a value predicted by a model and a value observed in the real environment, and is known to be suitable for expressing precision. , each difference value is also called a residual, and it is known that the root mean square deviation is used to aggregate the residuals into one measure.

As an example, the error rate between the generation amount (measured value) of the existing facility information using the root mean square deviation and the predicted generation amount (prediction value) based on the generation amount prediction model may be calculated through Equation 1 below.

)는 번째 측정된 실시간 태양광 발전량(KW)이며, 예측값(

)는 번째 예측한 태양광 발전량(KW)이다.Here, the measured value (

) is the measured real-time solar power generation (KW), and the predicted value (

) is the predicted solar power generation (KW).

Meanwhile, FIG. 6 is a view showing an example of a screen on which consulting information provided through the information providing unit 30 of the present invention is displayed on the user terminal 50 of the Web environment, as shown in FIG. As mentioned above, the study 30 is a user with the predicted power generation amount and the actual power generation amount at the same time for the existing solar power generation facility 10 or the selected new solar power generation facility selected based on the generation amount prediction model through various GUI environments as mentioned above. By providing to be displayed on the terminal 50, consulting information is provided so that the user can easily compare the amount of power generation (measured value) and the predicted power generation (predicted value).

Those skilled in the art from the above description will be able to see that various changes and modifications are possible without departing from the technical spirit of the present invention. Accordingly, the technical scope of the present invention should not be limited to the contents described in the detailed description of the specification, but should be defined by the claims.

10: solar power generation facility 20: data collection unit
25: database unit 30: information providing unit
40: Meteorological Agency Server 45: Public data portal
50: user terminal 300: feature derivation module
310: learning module 320: model creation module
330: prediction module 330: correction module

Claims (8)

a data collection unit for collecting existing facility information including facility information, generation amount information, and weather/climate information for one or more previously installed solar power generation facilities;
a database unit for storing the existing facility information collected by the data collection unit and turning it into big data; and
The generation amount prediction model is generated by analyzing the existing facility information stored in the database unit, and the predicted generation amount for the existing solar power generation facility selected based on the generated generation amount prediction model or the selected new solar power generation facility installation area is included. A consulting system through big data-based solar power generation prediction, characterized in that it includes; an information providing unit that provides consulting information.
The method of claim 1,
The data collection unit,
A consulting system through big data-based photovoltaic power generation prediction, characterized in that it collects existing facility information from one or more pre-connected photovoltaic power generation facilities through an established network platform.
The method of claim 1,
The data collection unit,
A consulting system through big data-based photovoltaic power generation prediction, characterized by uploading and collecting existing facility information output from each of one or more photovoltaic power generation facilities.
The method of claim 1,
The data collection unit,
By linking with GIS (Geographic Information System), one or more solar power generation facilities are identified, and by accessing a public data portal or the Meteorological Administration server, weather/climate information is collected for the area where one or more solar power generation facilities are installed. A consulting system through big data-based solar power generation prediction, characterized in that.
5. The method of claim 2 to 4,
The weather/climate information is a consulting system through big data-based solar power generation prediction, characterized in that it includes one or more of insolation, sunlight, temperature, humidity, and wind volume.
The method of claim 1,
The information providing unit,
Big data-based photovoltaic power generation prediction, characterized in that the predicted power generation for the selected existing photovoltaic power generation facility or the selected new photovoltaic power plant installation area and the actual power generation amount at the same time are displayed together based on the power generation forecast model consulting system through
The method of claim 1,
The information providing unit,
a feature deriving module for extracting one or more features for learning from the existing facility information collected from the data collection unit;
a learning module for performing machine learning based on the features extracted from the feature deriving module;
a model generation module for receiving the result information learned from the learning module and generating one or more power generation prediction models based on it; and
A prediction module for calculating and outputting the predicted power generation amount for the selected existing solar power generation facility or the selected new solar power generation facility installation area by applying the generation amount prediction model generated by the model generator; Consulting system through data-based solar power generation forecasting.
8. The method of claim 7,
The information providing unit,
A correction module that calculates an error value between the generation amount of the existing facility information and the predicted generation amount based on the generation amount prediction model, and updates the generation amount prediction model generated by the model generation module by reflecting the calculated error value; characterized by further comprising: Consulting system through big data-based solar power generation prediction.

Images