KR102577207B1 - System and method for predicting photovoltaics power generation - Google Patents

Abstract

The solar power generation prediction system according to an embodiment of the present invention is a system for predicting the power generation amount of a solar power module, by imaging the sky around the solar power module using at least one image sensor disposed around the solar power module. An image data generation unit that generates image data, a weather data collection unit that collects weather data around the solar module, and an image data analysis unit to generate cloud characteristic data including information on the state of clouds in the sky, and weather data. It generates movement prediction data for clouds in the sky based on the data and cloud characteristic data, and includes a power generation prediction unit that predicts the power generation amount of the solar module based on the movement prediction data and weather data.

Description

Solar power generation prediction system and method {SYSTEM AND METHOD FOR PREDICTING PHOTOVOLTAICS POWER GENERATION}

The present invention relates to a solar power generation prediction system and method, and more specifically, to a solar power generation prediction system and method that can predict real-time power generation in minimum time units using meteorological data and image data captured from the sky. will be.

Solar power generation, a new renewable energy, is expected to play a very important role in achieving greenhouse gas reduction goals along with climate change in the 4th Industrial Revolution. Accordingly, with the steady support policy and technological advancement for solar power generation projects, the lifespan and efficiency of solar panels have improved, solar power generation-related facilities are also becoming more advanced, and not only large-scale solar power plants but also small-scale solar power generation is becoming active. It is becoming. In the case of solar power generation, predicting power generation is very important because it is dependent on external influences.

On the other hand, if the predicted power generation amount is less than the actual power generation amount, if the power generation command (or charging command) is performed as the predicted power generation amount, the insufficient power generation amount will be drawn from the system, which may result in financial loss due to upward adjustment of the power rate in the future. . Accordingly, generally, a power generation command (or charging command) is performed by multiplying the predicted power generation amount by a preset setting ratio (for example, about 0.9). However, the smaller the value of the setting ratio is set, the more the power generation command is executed at a value smaller than the actual power generation amount, which may result in monetary loss, so it is important to set the setting ratio close to 100%.

The problem to be solved by the present invention is to provide a solar power generation prediction system and method that can predict power generation in the minimum time unit.

Another problem to be solved by the present invention is to provide a solar power generation prediction system and method that can predict power generation more accurately.

Another problem to be solved by the present invention is to provide a solar power generation prediction system and method that can perform a power generation command (or charging command) close to the actual power generation amount.

Another problem to be solved by the present invention is to provide a solar power generation prediction system and method that can minimize financial losses.

The problems of the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the above-described problem, the solar power generation prediction system according to embodiments of the present invention includes at least one image sensor disposed around the solar module in the system for predicting the power generation of the solar module. an image data generator that generates image data by imaging the sky around the solar module, a weather data collection unit that collects weather data around the solar module, and a cloud in the sky by analyzing the image data. Generate cloud characteristic data including information on conditions, generate movement prediction data for clouds in the sky based on the weather data and the cloud characteristic data, and generate movement prediction data for clouds in the sky based on the movement prediction data and the weather data. It may include a power generation prediction unit that predicts the power generation amount of the solar module.

In order to solve the above-described problem, the method for predicting the amount of solar power generation according to embodiments of the present invention includes at least one image sensor disposed around the solar module. Generating image data by imaging the sky around the solar module, collecting weather data around the solar module, and analyzing the image data to include information about the state of clouds in the sky. Generating cloud characteristic data, generating movement prediction data for clouds in the sky based on the weather data and the cloud characteristic data, and generating movement prediction data for the clouds in the sky based on the movement prediction data and the weather data. It may include the step of predicting power generation.

In order to solve the problems described above, the computer program according to the embodiments of the present invention is a computer program stored in a computer-readable medium, where the computer program includes instructions, and when executed by a computer system, the instructions may cause the computer system to perform the solar power generation prediction method.

In the case of the solar power generation prediction system and method according to embodiments of the present invention, the power generation is predicted based on image data about the sky around the solar module as well as weather data, so it is more accurate in the minimum time unit (in real time). Power generation can be predicted.

Additionally, in the case of the solar power generation prediction system and method according to embodiments of the present invention, a power generation command (or charging command) can be performed close to the actual power generation amount, thereby minimizing monetary loss.

The effects according to the present invention are not limited to the details exemplified above, and further various effects are included within the present invention.

1 is a block diagram schematically showing an overall system for solar power generation according to embodiments of the present invention.
Figure 2 is a block diagram schematically showing a solar power generation prediction system according to embodiments of the present invention.
FIG. 3 is a block diagram showing an example of the solar power generation prediction system of FIG. 2.
FIG. 4 is a diagram for explaining an example of the operation of the image data generator included in the solar power generation prediction system of FIG. 3.
FIG. 5 is a block diagram showing an example of a power generation prediction unit included in the solar power generation prediction system of FIG. 3.
FIG. 6 is a diagram for explaining an example of the operation of the prediction data generation unit included in the power generation prediction unit of FIG. 5.
FIG. 7 is a diagram illustrating an example of predicted data generated by a solar power generation prediction system according to embodiments of the present invention and prediction data generated by a solar power generation prediction system according to a comparative example.
FIG. 8 is a block diagram showing another example of the solar power generation prediction system of FIG. 2.
FIG. 9 is a diagram for explaining an example of the operation of the image sensor control unit included in the solar power generation prediction system of FIG. 8.
FIG. 10 is a block diagram showing another example of the solar power generation prediction system of FIG. 2.
Figure 11 is a flowchart showing a method for predicting solar power generation according to embodiments of the present invention.

While describing each drawing, similar reference numerals are used for similar components. In the attached drawings, the dimensions of the structures are enlarged from the actual size for clarity of the present invention. Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Additionally, when a part is said to be “connected” to another part, this includes not only the case where it is directly connected, but also the case where it is connected with another element in between.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. The same reference numerals are used for the same components in the drawings, and duplicate descriptions for the same components are omitted.

1 is a block diagram schematically showing an overall system for solar power generation according to embodiments of the present invention.

Referring to FIG. 1, the overall system for solar power generation (hereinafter referred to as “solar power generation system”) according to embodiments of the present invention can provide generated electricity (power) to a power grid system (PGS). there is.

Here, the power grid system (PGS) may refer to a system comprised of power facilities such as transmission lines and substations that transport electricity produced in a solar power generation system to consumers. Meanwhile, this is an example, and the embodiments of the present invention are not limited thereto. For example, electricity (power) generated by a solar power generation system according to embodiments of the present invention can be provided to various systems that require power.

To this end, the solar power generation system according to embodiments of the present invention may include a photovoltaic system (PV), a power control system (PMS), and an energy storage system (ESS).

A photovoltaic system (PV) can generate electricity (electricity) through self-generation using sunlight (sunlight), a natural energy source. To this end, a photovoltaic system (PV) may include a photovoltaic module (PVM) and an inverter (IVT).

A photovoltaic module (PVM) can generate power by converting sunlight (sunlight), a natural energy, into direct current electricity.

To this end, a photovoltaic module (PVM) may include a plurality of photovoltaic cells. Depending on the embodiment, the photovoltaic module (PVM) may include a single crystal silicon photovoltaic cell and/or may be composed of a photovoltaic module including a single crystal silicon photovoltaic cell, but this is merely an example and an embodiment of the present invention It is not limited to this.

Meanwhile, in the above, the photovoltaic module (PVM) has been described as consisting of a photovoltaic module including a plurality of photovoltaic cells, but this is simply an example for convenience of explanation, and in the embodiments of the present invention, the photovoltaic module (PVM) is composed of a photovoltaic module including a plurality of photovoltaic cells. A module (PVM) may be interpreted as consisting of a photovoltaic array including a plurality of photovoltaic modules.

An inverter (IVT) can convert direct current electricity generated from a photovoltaic module (PVM) into alternating current electricity. Electricity (power) converted to alternating current in this way can be provided to an energy storage system (ESS) and/or power grid system (PGS).

The energy storage system (ESS) converts alternating current electricity provided by the photovoltaic system (PV) into direct current electric energy and stores it, and when necessary, converts it back into alternating current electricity and supplies it to the power grid system (PGS). It can perform the role provided. The energy storage system (ESS) may be a battery-type energy storage system (BESS), but this is merely illustrative and embodiments of the present invention are not limited thereto.

To this end, the energy storage system (ESS) may include a power controller (PCS) and a battery (BTR).

The power control unit (PCS) converts alternating current electricity (power) provided from the photovoltaic system (PV) into direct current electricity (power) for storage in the battery (BTR), or It can perform the role of converting electricity (power) in the form of direct current into electricity (power) in the form of alternating current and providing it to the power grid system (PGS). That is, while the above-described inverter (IVT) converts power in one direction, the power control unit (PCS) can convert power in two directions.

Depending on the embodiment, the power control unit (PCS) may perform the role of not only converting alternating current and direct current of power as described above, but also adjusting frequency, voltage, etc.

The battery (BTR) may be a storage device that stores electricity (power) in the form of direct current provided from the power control unit (PCS). For example, the battery (BTR) may be a lithium ion battery, a lithium polymer battery, or a lead battery, but this is merely illustrative and embodiments of the present invention are not limited thereto.

The power control system (PMS) controls the overall operation of the solar power generation system (for example, the photovoltaic system (PV) and energy storage system (ESS) included in the solar power generation system) according to embodiments of the present invention. You can control it.

For example, the Power Management System (PMS) utilizes various communication hardware and software-based Information & Communications Technology (ICT) to control the solar power generation system to optimally manage energy within the solar power system. can do.

The power control system (PMS) collects various data, performs monitoring and analysis, and controls the solar power generation system based on this to manage energy according to the purpose of system installation. For example, a power control system (PMS) can measure energy consumption patterns for each installation location and purpose according to the purpose of system installation and control them appropriately.

In one embodiment, the power control system (PMS) predicts the amount of power generation in the photovoltaic system (PV) and, based on this, the amount of power (electricity) to be provided to the energy storage system (ESS) and/or power grid system (PGS). A power generation command (or charging command) for the value can be provided to the photovoltaic system (PV).

On the other hand, if the predicted power generation amount is less than the actual power generation amount, if the power generation command (or charging command) is performed as the predicted power generation amount, the insufficient power generation amount will be drawn from the system, which may result in financial loss due to upward adjustment of the power rate in the future. .

Accordingly, the power control system (PMS) performs a power generation command (or charging command) by multiplying the predicted power generation amount by a preset setting ratio for a certain margin. Here, it is important to minimize financial losses by setting the value of the set ratio as close to 100% as possible. To achieve this, prediction of power generation needs to be made in minimum time units, and the predicted value of power generation must be close to the actual power generation (i.e. , accurately) needs to be calculated.

To this end, in one embodiment, the power control system (PMS) may include a solar power generation prediction system 100. The solar power generation prediction system 100 uses weather data around the photovoltaic module (PVM) included in the photovoltaic system (PV) and image data captured of the sky around the photovoltaic module (PVM) in the minimum time unit. By predicting real-time power generation, the value according to the power generation command (or charging command) can be set as close as possible to the actual power generation by setting the setting ratio as close to 100% as possible. Accordingly, monetary loss can be minimized.

Figure 2 is a block diagram schematically showing a solar power generation prediction system according to embodiments of the present invention.

Referring to FIGS. 1 and 2 , the solar power generation prediction system 100 according to embodiments of the present invention may include a communication unit 110, a processor 120, and a database 130. Meanwhile, in FIG. 2, the solar power generation prediction system 100 is shown as including a database 130, but this is merely an example and the embodiment of the present invention is not limited thereto. For example, depending on the embodiment, the solar power generation prediction system 100 may be configured without including the database 130.

The solar power generation prediction system 100 can transmit and receive information to and from various systems through the communication unit 110. To this end, the communication unit 110 may be implemented with various communication technologies. For example, the communication unit 110 includes Wi-Fi, Wideband CDMA (WCDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), High Speed Packet Access (HSPA), and Mobile WiMAX. WiMAX), WiBro, LTE (Long Term Evolution), 5G, Bluetooth, IrDA (infrared data association), NFC (Near Field Communication), Zigbee, and wireless LAN technologies will be applied. You can. In addition, when the solar power generation prediction system 100 is connected to the Internet, the communication unit 110 may follow TCP/IP, a standard protocol for information transmission on the Internet, and may also use GPS (Global Positioning System) technology. .

The database 130 may store information for predicting the power generation amount of the solar power generation prediction system 100. For example, the database 130 may store weather data collected to predict power generation, various machine learning data for algorithms and/or machine learning for analyzing weather data and image data, data for determining a setting ratio, etc. However, it is not limited to this.

The processor 120 can access the database 130 through the communication unit 110. On the other hand, when the solar power generation prediction system 100 does not include the database 130 as described above and uses an external database, the solar power generation prediction system 100 connects to the external database through the communication unit 110. You will be able to access it.

Operations for predicting power generation may be performed on the processor 120. Hereinafter, with further reference to FIGS. 3 to 10, the processor 120 of the solar power generation prediction system 100 according to embodiments of the present invention. We will explain in more detail the operations and processes that occur on the screen.

FIG. 3 is a block diagram showing an example of the solar power generation prediction system of FIG. 2.

FIG. 4 is a diagram for explaining an example of the operation of the image data generator included in the solar power generation prediction system of FIG. 3.

FIG. 5 is a block diagram showing an example of a power generation prediction unit included in the solar power generation prediction system of FIG. 3.

FIG. 6 is a diagram for explaining an example of the operation of the prediction data generation unit included in the power generation prediction unit of FIG. 5.

Referring to FIGS. 1 to 3, the solar power generation prediction system 100 according to embodiments of the present invention uses image data (ID) captured of the sky around a photovoltaic module (PVM) of a photovoltaic system (PV). By analyzing the information on the cloud conditions in the sky around the photovoltaic module (PVM), cloud characteristic data (CD, see FIG. 5) is generated, and the cloud characteristic data (CD, see FIG. 5) and the photovoltaic module are analyzed. (PVM) generates movement prediction data (MD, see FIG. 5) about the movement path and movement speed of the clouds in the sky based on surrounding meteorological data (WD), and such movement prediction data (MD, FIG. 5) and weather data (WD), the power generation amount of the photovoltaic module (PVM) can be predicted.

To this end, in one embodiment, the solar power generation prediction system 100 may include an image data generator (IDG), a weather data collection unit (WDG), and a power generation prediction unit (PGP).

The image data generator (IDG) uses at least one image sensor disposed around the photovoltaic module (PVM) of the photovoltaic system (PV) to image the sky around the photovoltaic module (PVM) and generate image data (ID). ) can be created. For example, the image data (ID) generated by the image data generator (IDG) can be used to extract information about the state of clouds in the sky around the photovoltaic module (PVM) as described above.

For example, further referring to FIG. 4, the image data generator (IDG) can capture the sky around the photovoltaic module (PVM) using an image sensor (IMS) disposed around the photovoltaic module (PVM). there is.

For this purpose, the image sensor (IMS) may be installed in the location where the photovoltaic module (PVM) is installed (or in a location nearby), but this is an example and the image sensor (IMS) may be installed in a separate location. there is.

An image sensor (IMS) can generate an image (video) by converting received light into a digital signal. For example, the image sensor (IMS) may include, but is not limited to, a camera, a charge-coupled device (CCD) sensor, or a complementary metal oxide semiconductor (CMOS) sensor, and various other known image capture sensors. The device may be employed as an image sensor (IMS).

Depending on the embodiment, the image sensor (IMS) may be configured to include a fully automatic shutter function capable of acquiring image data (ID) with the light amount adjusted.

Meanwhile, in FIG. 4, a single image sensor (IMS) is shown to capture an image, but this is merely an example and the embodiment of the present invention is not limited thereto. For example, a plurality of image sensors (IMS) may be arranged to capture images.

In one embodiment, the image data generator (IDG) configures the image sensor (IMS) to select a first area (A1) corresponding to the area in which the photovoltaic module (PVM) is placed among the sky surrounding the photovoltaic module (PVM), and Control can be made to capture images for each of the second areas (A2) around the first area (A1).

Meanwhile, the first area (A1) refers to an area in the sky where solar light (SOL) is actually provided from the sun to the photovoltaic module (PVM), depending on the area where the photovoltaic module (PVM) is placed and the current position of the sun. This means that it can actually mean the area where the sun is located in the sky.

In other words, the image data generator (IDG) uses an image sensor (IMS) to generate sunlight according to the amount of sunlight (SOL) according to the cloud conditions in the sky around the solar module (PVM) at the current time, that is, the amount of solar radiation, etc. In addition to the image of the sky in the first area (A1) that affects the power generation of the module (PVM), the second area (A2) around the first area (A1), that is, far from the sun (or solar energy) Image data (ID) can be generated by capturing images of the sky (far away from the module (PVM)).

In one embodiment, the image data generator (IDG) may control the image sensor (IMS) to capture images in preset time units (e.g., seconds, minutes, etc.), but this is merely an example. , the image data generator (IDG) may control the image sensor (IMS) to capture images in real time.

Referring again to FIG. 3, the weather data collection unit (WDG) may collect (or generate) weather data (WD) around the photovoltaic module (PVM).

In one embodiment, the weather data collection unit (WDG) collects weather data (WD) for at least one of solar radiation, temperature, humidity, wind direction, wind speed, sun position, and sun altitude around the photovoltaic module (PVM). You can collect (or create).

However, this is simply an example, and the information included in the weather data (WD) is not limited thereto. For example, the weather data collection unit (WDG) may further collect (or generate) weather data (WD) on precipitation, sunlight hours, fine dust concentration, etc. in addition to the above-described information.

Depending on the embodiment, the weather data collection unit (WDG) may collect the weather data (WD) from a weather station, but this is simply illustrative and the embodiment of the present invention is not limited thereto. For example, the solar power generation prediction system 100 further includes a weather sensor including at least one of an optical sensor for sensing the amount of sunlight, a temperature sensor for sensing the surrounding temperature, and a humidity sensor for sensing humidity. Therefore, the above-described weather data (WD) can be generated independently.

In one embodiment, the weather data collection unit (WDG) may collect (or generate) weather data (WD) in preset time units (e.g., seconds, minutes, etc.), but this is merely an example. In other words, the weather data collection unit (WDG) may collect (or generate) weather data (WD) in real time.

The power generation prediction unit (PGP) may receive image data (ID) from the image data generation unit (IDG) and weather data (WD) from the weather data collection unit (WDG). The power generation prediction unit (PGP) may generate prediction data (GPD) for predicting power generation based on image data (ID) and weather data (WD).

For example, the power generation prediction unit (PGP) analyzes the image included in the image data (ID) and generates cloud characteristic data (CD, see FIG. 5) containing information about the state of clouds in the sky around the photovoltaic module (PVM). ) and generate movement prediction data (MD, see FIG. 5) for the clouds in the sky based on meteorological data (WD) and cloud characteristic data (CD, see FIG. 5), and movement prediction data (MD, Predicted data (GPD) can be generated by predicting the power generation amount of a photovoltaic system (PV) (eg, photovoltaic module (PVM)) based on (see FIG. 5) and weather data (WD).

For a more specific explanation, further referring to FIG. 5, in one embodiment, the power generation prediction unit (PGP) includes a cloud characteristics data generation unit (CDG), a movement prediction data generation unit (MDG), and a prediction data generation unit ( PDG) may be included.

The cloud characteristics data generation unit (CDG) receives image data (ID) and analyzes the state of clouds in the sky around the photovoltaic module (PVM) based on the image data (ID) to generate cloud characteristics data (CD). You can.

In one embodiment, the cloud characteristic data generator (CDG) may extract information about cloud conditions by three-dimensionally processing the image included in the image data (ID). For example, the cloud characteristics data generation unit (CDG) converts the 2D image (two-dimensional image) included in the image data (ID) into a 3D image (three-dimensional image) using simulation, and the converted 3D image. (3D image) can be used to extract information about cloud conditions, but this is simply an example, and the method for the cloud characteristic data generator (CDG) to three-dimensionally process the image included in the image data (ID) is It can be modified in various ways.

For example, according to an embodiment, as described above, when image data (ID) is generated by capturing an image by a plurality of image sensors (IMS) rather than a single image sensor (IMS), cloud characteristics The data generator (CDG) may generate a 3D image (3D image) by merging a plurality of 2D images (multiple 2D images) included in the image data (ID).

The cloud characteristics data generator (CDG) can analyze the state of clouds in the sky around the photovoltaic module (PVM) using this three-dimensionally processed image. For example, the cloud characteristics data generator (CDG) may perform image processing on the three-dimensionally processed image to analyze the state of clouds in the sky around the photovoltaic module (PVM). As an example, the cloud characteristics data generation unit (CDG) performs image processing of chromaticity and RGB value analysis on the three-dimensionally processed image, thereby determining the shape of the cloud, type of cloud, height of the cloud, distribution area of the cloud, and cloud distribution area. The amount of clouds and the location of clouds can be analyzed. However, the above image processing method is merely illustrative, and the embodiment of the present invention is not limited thereto, and the cloud characteristic data generator (CDG) can analyze cloud conditions through various image processing methods.

In one embodiment, as described above, the image data generator (IDG) includes a first area (A1) and a first area (A1) corresponding to the area in which the photovoltaic module (PVM) is disposed among the sky surrounding the photovoltaic module (PVM). Since image data (ID) is generated by capturing all images of the second area (A2) around the area (A1), the cloud characteristic data generator (CDG) generates image data (ID) in the first area of the sky around the solar module (PVM). By analyzing both the cloud conditions in (A1) and the cloud conditions in the second area (A2), cloud characteristic data (CD) can be generated.

Meanwhile, cloud characteristic data (CD) can be used to predict power generation by the prediction data generator (PDG), as will be described later.

For example, condensation nuclei are needed to form clouds. Clouds are made up of small water droplets, and in order for water vapor to condense to form water droplets, small particles that water vapor can stick to, that is, condensation nuclei, are needed. Generally, salt particles or soil grains floating in the air act as condensation nuclei, but when fine dust acts as a condensation nucleus, particles smaller than normal become condensation nuclei. In this case, the size of cloud particles becomes smaller and the surface area of the cloud increases, allowing brighter clouds to form. Here, brighter clouds reflect more solar radiation, which can further reduce solar radiation reaching the ground.

Additionally, when water droplets in a cloud clump together and grow in size, they become the size of raindrops and can start to rain. Here, as described above, the smaller size of cloud particles may mean that a longer time is needed to grow to the size of a raindrop, and thus the cloud can last longer. In other words, it becomes more difficult for clouds to dissipate through precipitation, and the clouds remain longer, further reducing solar radiation.

Additionally, in predicting power generation, it is very important to distinguish the height, shape, and type of clouds. Clouds are generally divided into upper-level clouds, middle-level clouds, and lower-level clouds, and vertically developing clouds include cumulus clouds and cumulonimbus clouds. When encountering vertically developing clouds such as cumulus or cumulonimbus, which are vertically developing clouds rather than upper-level clouds such as cirrostratus, cirrocumulus, etc., power generation may be seriously reduced.

In this way, in order to accurately predict solar power generation, it is necessary to generate cloud characteristic data (CD) about cloud shape, cloud type, cloud height, cloud distribution area, cloud cloud amount, and cloud location. there is.

Meanwhile, cloud characteristic data (CD) may be provided to a movement prediction data generation unit (MDG) and a prediction data generation unit (PDG).

Next, the movement prediction data generator (MDG) can generate movement prediction data (MD) for the movement path and movement speed of clouds in the sky based on weather data (WD) and cloud characteristic data (CD). .

In one embodiment, the movement prediction data generator (MDG) may extract information about wind speed and direction based on weather data (WD). For example, the movement prediction data generator (MDG) may extract information about the wind speed and direction of the wind in the above-described first area A1 and second area A2.

In addition, the movement prediction data generator (MDG) determines the cloud characteristics of the clouds located in the first area (A1) and the second area (A2) based on the cloud characteristic data (CD) provided from the cloud characteristic data generator (CDG). The state (e.g., cloud shape, cloud type, cloud height, cloud distribution area, cloud cloud amount, and cloud location, etc.) is extracted, and the first area extracted based on meteorological data (WD) ( Using information about the wind speed and direction of the wind in the first area (A1) and the second area (A2), extract the expected movement path and expected movement speed of the clouds located in the first area (A1) and the second area (A2), respectively. , Based on this, movement prediction data (MD) can be generated.

For example, clouds move along the wind, and the wind speed and direction may vary depending on the height of the cloud. Accordingly, the movement prediction data generator (MDG) can generate movement prediction data (MD) using information about the state of clouds by height and the wind speed and direction of the wind.

As another example, the movement speed of clouds may be different even if the wind speed is the same, depending on the shape, type, distribution area, and cloud cover of the clouds. Accordingly, the movement prediction data generator (MDG) can generate movement prediction data (MD) by analyzing differences in relative movement speeds depending on the shape, type, distribution area, and cloudiness of clouds.

In one embodiment, the movement prediction data generator (MDG) may extract the expected movement path and expected movement speed for each of the clouds located in the first area (A1) and the clouds located in the second area (A2). .

That is, in the case of the solar power generation prediction system 100 (or power generation prediction unit (PGP)) according to embodiments of the present invention, images and weather of the sky where the sun is located as an area around the solar power module (PVM) In addition to the condition, the image and weather conditions of the sky in the area surrounding the area where the sun is located are analyzed together to determine the clouds located around the photovoltaic module (PVM) and the clouds located in areas far away from the photovoltaic module (PVM). The expected movement path and expected movement speed can be calculated for each cloud.

Finally, the prediction data generation unit (PDG) receives meteorological data (WD), cloud characteristics data (CD), and movement prediction data (MD), and receives meteorological data (WD), cloud characteristics data (CD), and movement prediction data (MD). Based on the prediction data (MD), the power generation amount of a photovoltaic system (PV) (eg, a photovoltaic module (PVM)) may be predicted, and prediction data (GPD) for the predicted power generation amount may be generated.

For example, based on weather data (WD), the predictive data generation unit (PDG) comprehensively considers not only the amount of solar radiation that directly affects solar power generation, but also temperature, humidity, the position of the sun, and the altitude of the sun. Thus, the amount of power generation can be predicted.

In addition, in order to predict solar power generation more accurately, it is necessary to predict not only information on the current solar radiation amount but also changes in solar radiation that change in real time. Here, as described above, the amount of solar radiation varies depending on the shape of the cloud, type of cloud, height of the cloud, distribution area of the cloud, amount of clouds, and location of the cloud, so it changes in real time as well as the current location or state of the cloud. It is necessary to predict changes in solar radiation by comprehensively considering the location and condition of clouds, and predict solar power generation based on this.

Accordingly, the prediction data generation unit (PDG) generates solar energy according to the expected movement path and expected movement speed of clouds in the sky around the solar module (PVM) based on cloud characteristic data (CD) and movement prediction data (MD). Changes in solar radiation for the optical module (PVM) can be predicted in real time, and predicted data (GPD) can be generated based on this.

In one embodiment, the prediction data generator (PDG) may predict changes in solar radiation according to the expected movement path and expected movement speed of clouds located in the first area (A1) and the second area (A2), respectively.

For example, further referring to FIG. 6, in FIG. 6, a first area (A1) corresponding to the area where the photovoltaic module (PVM) is disposed and a second area (A2) around the first area (A1) are shown, respectively. The located clouds (CL1, CL2) are shown. For example, based on the current time (eg, measurement time), first clouds CL1 may be located in the first area A1, and second clouds CL2 may be located in the second area A2. ) can be located.

Meanwhile, in FIG. 6, the right direction, left direction, downward direction, and upward direction are shown as east direction (E), west direction (W), south direction (S), and north direction (N), respectively.

Based on the current time (e.g., measurement time), it is located in the second area (A2) far from the solar module (PVM) (or far from the area on the sky where the sun (SUN) is located). In the case of the second clouds CL2, there may be no substantial influence on solar radiation to the photovoltaic module (PVM), which may affect the power generation amount of the photovoltaic module (PVM). That is, based on the current time (for example, the measurement time), the sun depends on the shape, type, height, distribution area, cloud amount, and location of the first clouds CL1 located in the first area A1. The amount of solar radiation for the optical module (PVM) may be determined.

However, if the location of the clouds changes due to the influence of the wind, the clouds that can affect the amount of solar radiation to the solar photovoltaic module (PVM) may change.

For example, among the first clouds CL1 located in the first area A1, the first cloud CL1a remains in the first area A1 even after a certain period of time due to the influence of the first northwest wind WIN1. ) can be located in. On the other hand, the first cloud (CL1b) among the first clouds (CL1) located in the first area (A1) changes to the second area (A2) after a certain period of time according to the influence of the second wind (WIN2) of the north wind. It may be located in .

In addition, among the second clouds CL2 located in the second area A2, the second cloud CL2a and the second cloud CL2c are the first northwest wind WIN1 and the north wind second wind WIN2, respectively. ), after a certain period of time, it may be located in the first area (A1). On the other hand, among the second clouds CL2 located in the second area A2, the second cloud CL2b still remains in the second area A2 even after a certain period of time due to the influence of the first northwest wind WIN1. ) can be located.

As such, based on the current time, the first clouds (CL1a, CL1b) are located in the first area (A1), so the shape, type, height, distribution area, cloud amount, and location, etc., the amount of solar radiation for the photovoltaic module (PVM) may be determined, but based on a time after the current point (e.g., the predicted time), the surrounding wind (e.g., the first wind (WIN1) and Due to the influence of the second wind (WIN2), some of the clouds (CL1, CL2) (e.g., the first cloud (CL1a) and the second clouds (CL2a, CL2c)) are in the first area ( A1), the amount of solar radiation to the solar module (PVM) can be determined depending on the shape, type, height, distribution area, cloud cover, and location of the corresponding clouds (CL1a, CL2a, CL2c).

Accordingly, the prediction data generator (PDG) generates clouds located in the first area (A1) based on the current time (or measurement time) based on the cloud characteristic data (CD) (e.g., in FIG. 6). The shape, type, height, distribution area, cloud amount, and location of the first clouds (CL1) are extracted, and the expected movement path and expected movement of the clouds (CL1, CL2) are based on movement prediction data (MD). Using the velocity, the shape, type, height, distribution area, and By analyzing cloud cover and location, real-time changes in solar radiation to the photovoltaic module (PVM) are extracted, and based on this, the power generation amount of the photovoltaic system (PV) (or photovoltaic module (PVM)) is predicted in real time. By doing so, prediction data (GPD) can be generated.

Here, the power control system (PMS, see FIG. 1) uses prediction data (GPD) generated by the solar power generation prediction system 100 (or power generation prediction unit (PGP)) according to embodiments of the present invention. Thus, a power generation command (or charging command) is performed by the photovoltaic system (PV).

At this time, as described above, when the power control system (PMS, see FIG. 1) performs a power generation command (or charging command), it multiplies the predicted power generation amount by a preset setting ratio to issue a power generation command (or charging command). In relation to the power generation (i.e., predicted data (GPD)) predicted by the solar power generation prediction system 100 according to embodiments of the present invention, the solar power generation prediction system 100 uses weather data ( Since the power generation amount is calculated (predicted) by calculating the change in insolation amount to the photovoltaic module (PVM) in real time based on the WD) and image data (ID), the power control system (PMS, see FIG. 1) actually calculates the set ratio. Even if is set close to 100%, the problem of the value of the power generation command (or charging command) exceeding the actual power generation does not occur. Accordingly, monetary loss can be minimized.

FIG. 7 is a diagram illustrating an example of predicted data generated by a solar power generation prediction system according to embodiments of the present invention and prediction data generated by a solar power generation prediction system according to a comparative example.

Referring to FIGS. 1 to 7 , FIG. 7 shows prediction data (GPD) generated by the solar power generation prediction system 100 according to embodiments of the present invention and the solar power generation prediction system according to the comparative example. The predicted data (GPD_C) is shown, respectively.

Here, the solar power generation prediction system according to the comparative example is an existing solar power generation prediction system that can predict solar power generation using weather observation data. Here, the weather observation data includes weather data by time zone. , the prediction data (GPD_C) generated by the solar power generation prediction system according to the comparative example cannot help but be generated by time zone (eg, hourly unit). Therefore, since it is difficult to reflect information on solar radiation that changes in real time, the predicted data (GPD_C) according to the comparative example has no choice but to be generated for each time zone.

On the other hand, in the case of prediction data (GPD) generated by the solar power generation prediction system 100 according to embodiments of the present invention, as described above, it is generated by reflecting all solar radiation that changes in real time, so it is predicted in real time. Data (GPD) may be generated, and since it is generated based on image data (ID) as well as weather data (WD), accuracy may be significantly higher than the prediction data (GPD_C) according to the comparative example.

FIG. 8 is a block diagram showing another example of the solar power generation prediction system of FIG. 2.

FIG. 9 is a diagram for explaining an example of the operation of the image sensor control unit included in the solar power generation prediction system of FIG. 8.

FIG. 8 shows a modified embodiment of the embodiment of FIG. 3 with respect to the configuration of an image sensor control unit (ISC).

In FIGS. 8 and 9 , in order to avoid redundant explanation, the explanation is centered on points that are different from the above-described embodiment. Parts not specifically explained follow the above-described embodiment, the same numbers indicate the same components, and similar numbers indicate the same components. represents similar components.

Referring to FIG. 8, the solar power generation prediction system 100_1 may include an image data generator (IDG), a weather data collection unit (WDG), a power generation prediction unit (PGP), and an image sensor control unit (ISC). .

The image sensor control unit (ISC) can adaptively control the position of the sky captured by the image sensor (IMS) in response to the moving orbit (OTS) of the sun.

More specifically, referring to FIG. 9, the orbit (OTS) of the Sun (SUN) may change according to the rotation of the Earth over time.

Here, as described above, the first area A1 refers to the area where the photovoltaic module (PVM) is placed and, depending on the current position of the sun, solar light (SOL) is substantially provided from the sun to the photovoltaic module (PVM). This refers to the area in the sky where the sun (SUN) is located in the sky, so as the orbit (OTS) of the sun changes, the positions of the corresponding areas (A1, A2) also change in the sky. can do.

Accordingly, the image sensor control unit (ISC) can control the image sensor (IMS) to capture images by adaptively controlling the position of the sky where the image sensor (IMS) captures images in response to the moving orbit (OTS) of the sun. You can.

FIG. 10 is a block diagram showing another example of the solar power generation prediction system of FIG. 2.

FIG. 10 shows a modified embodiment of the embodiment of FIG. 3 with respect to the configuration of a power generation command unit (CCU).

In FIG. 10, in order to avoid redundant explanation, the explanation is centered on differences from the above-described embodiment. Parts not specifically explained follow the above-described embodiment, the same numbers indicate the same components, and similar numbers indicate similar components. represents an element.

Referring to FIG. 10, the solar power generation prediction system 100_2 includes an image data generation unit (IDG), a weather data collection unit (WDG), a power generation prediction unit (PGP), and a power generation command unit (CCU) (or charging command). part) may be included.

The power generation command unit (CCU) receives prediction data (GPD) provided from the power generation prediction unit (PGP), and multiplies the predicted power generation amount of the photovoltaic module (PVM) by a set ratio based on the prediction data (GPD). Can be output as a power generation command value (CC) (or charging command value).

Here, in the case of the setting ratio as described above, the higher the prediction accuracy of the power generation, the more likely it is that the value of the power generation command (or charging command) will exceed the actual power generation even if the setting ratio is set close to 100% (or 1). This will not occur, but if the prediction accuracy of power generation is relatively low, a problem may occur in which the value of the power generation command (or charging command) exceeds the actual power generation.

Here, as described above, in the case of the solar power generation prediction system (100, 100_1, 100_2) according to the embodiments of the present invention, the accuracy of power generation prediction is significantly higher than the solar power generation prediction system according to the comparative example. Aside from that, the prediction accuracy may vary depending on weather conditions, etc.

More specifically, as described above, in the solar power generation prediction system (100, 100_1, 100_2) according to the embodiments of the present invention, changes in cloud conditions are monitored in real time at the current time and the predicted time after the current time. In predicting changes in solar radiation to a photovoltaic module (PVM) in real time, depending on weather conditions, the wind speed may be strong, the wind direction may change from moment to moment, and/or the state of clouds (e.g., The accuracy of predicting changes in cloud conditions at the time of prediction may vary due to factors depending on the shape of the cloud, type of cloud, height of the cloud, distribution area of the cloud, cloud amount, and location of the cloud, etc.

For example, in weather conditions where the wind speed is strong and/or the wind direction changes from moment to moment, the accuracy of predicting changes in cloud conditions at the prediction time may be relatively low.

Accordingly, the power generation command unit (CCU) further receives image data (ID) and weather data (WD), and based on the image data (ID) and weather data (WD), determines the wind condition that can affect the prediction accuracy. Extract information about wind speed, wind direction, and/or cloud conditions, and calculate weights with relatively low values if prediction accuracy is judged to be relatively low, and if prediction accuracy is judged to be relatively high. Weights with relatively high values can be calculated. Here, the weight can have a value between 0 and 1.

To this end, the power generation command unit (CCU) may use algorithms, mathematical equations, etc. to calculate the weight value according to information about wind speed, wind direction, and/or cloud status, but is not limited thereto.

Meanwhile, depending on the embodiment, the power generation command unit (CCU) may calculate a weight with a value of 1 when it is determined that the prediction accuracy is significantly high.

Afterwards, the power generation command unit (CCU) calculates the setting ratio by multiplying the standard setting ratio by a weight according to the judgment of prediction accuracy, and calculates the power generation amount of the photovoltaic module (PVM) predicted based on the prediction data (GPD). The value multiplied by the set ratio can be output as a generation command value (CC) (or charging command value).

For example, if the standard setting ratio is set to 100%, that is, a value of 1, and the weight is calculated as 0.97, the setting ratio is determined as the value of 0.97 multiplied by 1 and 0.97, and the generation command value (CC) is predicted. It can be set to 97% of the generated power generation.

As another example, if the standard setting ratio is set to 99%, that is, a value of 0.99, and the weight is calculated as 0.95, the setting ratio is determined to be a value of approximately 0.94 multiplied by 0.99 and 0.95, and the generation command value (CC) is predicted. It can be set to 94% of the generated power generation.

As another example, if the standard setting ratio is set to 100%, that is, a value of 1, and the weight is also calculated to a value of 1, the setting ratio is determined to be a value of 1, and the generation command value (CC) is equal to the predicted power generation amount. Can be set to 100%.

Meanwhile, the above-exampled standard setting ratio values and weight values are merely illustrative for convenience of explanation and are not limited thereto.

In this way, the power generation command unit (CCU) can comprehensively consider the image data (ID) and weather data (WD), determine the prediction accuracy, and calculate the weight based on this to calculate the final setting ratio. Accordingly, the solar power generation prediction system 100_2 according to embodiments of the present invention can adaptively perform power generation commands (or charging commands) depending on weather conditions, etc.

Figure 11 is a flowchart showing a method for predicting solar power generation according to embodiments of the present invention.

Referring to FIGS. 1 to 11, the solar power generation prediction method of FIG. 11 includes the solar power generation prediction system 100 of FIG. 3, the solar power generation prediction system 100_1 of FIG. 8, or the solar power generation prediction system 100 of FIG. 10. It may be performed on system 100_2. Here, since the solar power generation prediction method of FIG. 11 is substantially the same or similar to the operation of the solar power generation prediction system (100, 100_1, 100_2) described with reference to FIGS. 1 to 10, overlapping descriptions will not be repeated. .

First, the solar power generation prediction method of FIG. 11 can generate image data by capturing the sky around the solar module using at least one image sensor disposed around the solar module (S1110).

In addition, the solar power generation prediction method of FIG. 11 can collect weather data around the solar power module (S1120).

Thereafter, the solar power generation prediction method of FIG. 11 analyzes image data to generate cloud characteristic data including information on the state of clouds in the sky (S1130), and predicts cloud characteristics in the sky based on the meteorological data and cloud characteristic data. Movement prediction data can be generated (S1140).

Thereafter, the solar power generation amount prediction method of FIG. 11 can predict the power generation amount of the solar power module based on the movement prediction data and weather data (S1150).

Embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable by those skilled in the computer software field. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. media), and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the invention and vice versa.

As described above, in the case of the solar power generation prediction system and method according to embodiments of the present invention, the power generation is predicted based on image data about the sky around the solar module as well as weather data, so that the power generation amount is predicted in minimum time units. Power generation can be predicted more accurately (in real time).

Additionally, in the case of the solar power generation prediction system and method according to embodiments of the present invention, monetary loss can be minimized by executing a power generation command (or charging command) close to the actual power generation amount.

A solar power generation prediction system according to various embodiments of the present invention can be described as follows.

In order to solve the above-described problem, the solar power generation prediction system according to embodiments of the present invention includes at least one image sensor disposed around the solar module in the system for predicting the power generation of the solar module. an image data generator that generates image data by imaging the sky around the solar module, a weather data collection unit that collects weather data around the solar module, and a cloud in the sky by analyzing the image data. Generate cloud characteristic data including information on conditions, generate movement prediction data for clouds in the sky based on the weather data and the cloud characteristic data, and generate movement prediction data for clouds in the sky based on the movement prediction data and the weather data. It may include a power generation prediction unit that predicts the power generation amount of the solar module.

In one embodiment, the power generation prediction unit includes a cloud characteristics data generator that analyzes the image data to generate the cloud characteristics data, and a movement prediction data that generates the movement prediction data based on the meteorological data and the cloud characteristics data. It may include a generation unit, and a prediction data generation unit that generates prediction data by predicting the power generation amount of the solar module based on the movement prediction data and the weather data.

In one embodiment, the movement prediction data generator extracts information about the wind speed and direction of the wind based on the weather data, and the expected movement path and expected movement speed of the clouds in the sky according to the wind speed and direction of the wind. extracts and generates the movement prediction data, and the power generation prediction unit predicts the change in solar radiation for the solar module according to the expected movement path and expected movement speed of the clouds in the sky, and generates the prediction data based on this. can do.

In one embodiment, the cloud characteristic data generation unit three-dimensionally processes the image of the sky around the solar module included in the image data to determine the shape of the cloud in the sky, the type of cloud, the height of the cloud, and the height of the cloud. Information about the cloud state regarding at least one of distribution area, cloud cover, and cloud location can be extracted.

In one embodiment, the solar power generation prediction system may further include an image sensor control unit that adaptively controls a position in the sky captured by the at least one image sensor in response to the orbit of the sun.

In one embodiment, the solar power generation prediction system receives the image data, the weather data, and the prediction data generated by the power generation prediction unit, and multiplies the predicted power generation amount of the solar module by a set ratio. It may further include a power generation command unit that outputs as a power generation command value. The power generation command unit may calculate a weight based on the weather data and cloud conditions in the sky based on the image data, and calculate the setting ratio by applying the weight to a standard setting ratio.

In one embodiment, the weather data may include at least one of solar radiation, temperature, humidity, wind direction, wind speed, sun position, and sun altitude around the solar module.

A method for predicting solar power generation according to various embodiments of the present invention can be described as follows.

In order to solve the above-described problem, the method for predicting the amount of solar power generation according to embodiments of the present invention includes at least one image sensor disposed around the solar module. Generating image data by imaging the sky around the solar module, collecting weather data around the solar module, and analyzing the image data to include information about the state of clouds in the sky. Generating cloud characteristic data, generating movement prediction data for clouds in the sky based on the weather data and the cloud characteristic data, and generating movement prediction data for the clouds in the sky based on the movement prediction data and the weather data. It may include the step of predicting power generation.

Computer programs according to various embodiments of the present invention can be described as follows.

In order to solve the problems described above, the computer program according to the embodiments of the present invention is a computer program stored in a computer-readable medium, where the computer program includes instructions, and when executed by a computer system, the instructions may cause the computer system to perform the solar power generation prediction method.

Although the present invention has been described above with reference to embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims. You will be able to.

100, 100_1, 100_2: Solar power generation prediction system
CCU: Generation Command
CDG: Cloud characteristic data generation unit
IDG: Image data generation unit
IMS: Image sensor
ISC: Image sensor control section
MDG: Movement prediction data generation unit
PDG: Prediction data generation unit
PGP: Power generation prediction unit
WDG: Meteorological Data Collection Department

Claims (8)

In a system that predicts the power generation of solar modules,
an image data generator that generates image data by capturing the sky around the solar module using at least one image sensor disposed around the solar module;
a weather data collection unit that collects weather data about the solar module surroundings; and
Analyze the image data to generate cloud characteristic data including information on the state of clouds in the sky, generate movement prediction data for the clouds in the sky based on the meteorological data and the cloud characteristic data, and generate movement prediction data for the clouds in the sky, wherein the movement It includes a power generation prediction unit that predicts the power generation amount of the solar module based on the forecast data and the weather data.
go,
The power generation prediction unit,
a cloud characteristic data generator that analyzes the image data to generate the cloud characteristic data;
a movement prediction data generator that generates the movement prediction data based on the weather data and the cloud characteristic data; and
It includes a prediction data generator that generates prediction data by predicting the power generation amount of the solar module based on the movement prediction data and the weather data,
The movement prediction data generator extracts information about the wind speed and direction of the wind based on the weather data, extracts the expected movement path and expected movement speed of the clouds in the sky based on the wind speed and direction of the wind, and extracts the movement prediction data. generate predictive data,
The power generation prediction unit predicts changes in solar radiation to the solar module according to the expected movement path and expected movement speed of the clouds in the sky, and generates the prediction data based on this,
The image data generator controls the image sensor to capture images of each of a first area corresponding to an area in which the solar module is placed in the sky around the solar module and a second area around the first area, ,
The prediction data generator extracts at least one of the shape, type, height, distribution area, cloud amount, and location of the first cloud located in the first area based on the current time,
Among the shape, type, height, distribution area, cloud amount, and location of the second cloud located in the first area at a predicted time after the current time using the expected movement path and expected movement speed of the clouds based on the movement prediction data. A solar power generation prediction system that extracts and analyzes at least one real-time change in solar radiation for the solar module, predicts the power generation of the solar module in real time based on this, and generates the prediction data. delete delete The method of claim 1, wherein the cloud characteristic data generating unit three-dimensionally processes the image of the sky around the solar module included in the image data to determine the shape of the cloud in the sky, the type of the cloud, the height of the cloud, and the cloud. A solar power generation prediction system that extracts information about the cloud state regarding at least one of the distribution area, cloud amount, and cloud location. According to claim 1,
A solar power generation prediction system further comprising an image sensor control unit that adaptively controls a position in the sky captured by the at least one image sensor in response to the orbit of the sun. According to claim 1,
It further includes a power generation command unit that receives the image data, the weather data, and the prediction data generated by the power generation prediction unit, and outputs a value obtained by multiplying the predicted power generation amount of the solar module by a set ratio as a power generation command value; ,
The power generation command unit calculates a weight based on the weather data and cloud conditions in the sky based on the image data, and calculates the set ratio by applying the weight to a standard set ratio. The solar power generation prediction system of claim 1, wherein the weather data includes at least one of solar radiation, temperature, humidity, wind direction, wind speed, sun position, and sun altitude around the solar module. In the method of predicting the power generation of solar modules,
Generating image data by capturing the sky around the solar module using at least one image sensor disposed around the solar module;
Collecting weather data around the solar module;
Analyzing the image data to generate cloud characteristic data including information about cloud conditions in the sky;
generating movement prediction data for clouds in the sky based on the meteorological data and the cloud characteristic data; and
Comprising the step of predicting the amount of power generation of the solar module based on the movement prediction data and the weather data,
Extract information about wind speed and direction based on the meteorological data, extract the expected movement path and expected movement speed of the clouds in the sky according to the wind speed and direction of the wind, and generate the movement prediction data,
Predicting changes in solar radiation for the solar module according to the expected movement path and expected movement speed of clouds in the sky, and generating the prediction data based on this,
Controls the image sensor to capture images of each of a first area in the sky around the solar module, corresponding to an area where the solar module is placed, and a second area around the first area,
Extract at least one of the shape, type, height, distribution area, cloud amount, and location of the first cloud located in the first area based on the current time,
Among the shape, type, height, distribution area, cloud amount, and location of the second cloud located in the first area at a predicted time after the current time using the expected movement path and expected movement speed of the clouds based on the movement prediction data. A solar power generation prediction method that extracts and analyzes at least one to extract real-time changes in solar radiation for the solar power module, and based on this, predicts the power generation of the solar module in real time to generate the prediction data.