KR102473192B1 - Solar power generation system that controls solar tracking by analyzing big data using artificial neural network - Google Patents

Abstract

Disclosed is a solar power generation system that controls solar tracking by analyzing big data by using an artificial neural network. The solar power generation system comprises: a plurality of solar panels arranged in a plurality of columns and rows; group tracking controllers physically connected to the solar panels to provide power for rotation motion of each of the solar panels; and a central control server for controlling the rotation motion by transmitting a control command to each of the group tracking controllers.

Description

Solar power generation system that controls solar tracking by analyzing big data using an artificial neural network

The present invention relates to a solar power generation system, and more particularly, to a solar power generation system that controls solar tracking by analyzing big data using an artificial neural network.

As part of solving the environmental pollution problem caused by energy production, social interest in the development of eco-friendly alternative energy using solar energy is increasing. Power generation using solar energy is divided into solar power generation that produces power through solar heat using solar cells and solar power generation that produces power using sunlight.

Photovoltaic power generation has been mainly fixed type in which solar panels are installed in a fixed location and the direction cannot be adjusted according to the position of the sun, but recently, as part of improving power generation efficiency, the direction of the solar panel A tracking method (or tracker method) tracking according to the altitude and azimuth is being studied.

As such, in the case of a tracking type that tracks a change in the position of the sun and adjusts the direction of the solar panel in real time, sunlight is set to be perpendicularly incident on the solar panel according to the position of the sun in order to maximize power generation efficiency.

However, when set to maintain normal incidence, shadows may occur between adjacent solar panels because the solar panels installed at regular intervals face the same direction according to the location of the sun according to the time of day.

In addition, when each solar panel is configured to individually install an optical sensor to track the sun, the movement of clouds or various external environmental factors cause shadows that occur frequently in real time. direction is adjusted.

Therefore, in this case, not only can the life span and damage of the equipment be reduced due to frequent adjustment operations, but also the increase in energy consumption according to the control often acts as a factor that lowers the power generation efficiency.

An object of the present invention to solve the above problems is to provide a solar power generation system that controls solar tracking by analyzing big data using an artificial neural network.

One aspect of the present invention for achieving the above object provides a solar power generation system that controls solar tracking by analyzing big data using an artificial neural network.

The photovoltaic power generation system includes a plurality of solar panels arranged in a plurality of columns and rows; Group tracking controllers physically connected to the solar panels to provide power for rotation of each of the solar panels; and a central control server controlling the rotational movement by transmitting a control command to each of the group tracking controllers.

Each of the rows indicates solar panels arranged to be spaced apart from each other by a predetermined spacing in the east-west direction.

Each of the plurality of solar panels may include a plurality of solar panels disposed on a main frame; A secondary frame coupled to the rear surface of the main frame and including a rotation shaft; a support member that is physically connected to the auxiliary frame via the rotating shaft and is fixed perpendicularly to the ground to support a physical load; a solar sensor installed on the main frame to measure the amount of light; and a wire-type thermal sensor installed to pass through the solar panels to measure heat.

The central control server generates learning data by collecting the amount of light, the amount of heat, local weather around the place where the solar panels are installed, and a decrease in power generation according to the local weather, and based on the generated learning data The artificial neural network is supervised and the predicted power generation amount of each of the solar panels is determined using the supervised artificial neural network.

Controlling, by the central control server, a rotation angle of each of the solar panels so that sunlight is incident vertically; determining whether a shaded area exists in the solar panels belonging to each of the columns; and if the shaded area exists, an operation of determining a rotation angle to sequentially remove the shaded area from an easternmost column among the columns.

Each of the group tracking controllers corresponds to each of the columns on a 1:1 basis, and rotates solar panels belonging to corresponding columns at the same rotational angle.

In the case of using the photovoltaic power generation system that controls solar tracking based on big data according to the present invention as described above, power generation efficiency can be maximized by minimizing shadows that may occur between adjacent solar panels.

In addition, by preventing frequent operations that may occur due to movement of clouds or temporary external environment changes, there is an advantage in preventing a decrease in lifespan of equipment and maintaining power generation efficiency.

In addition, since the predicted generation amount is determined based on the amount of light, heat, etc. based on big data, and the optimal rotation angle between adjacent solar panels is determined according to the predicted amount of power generation, very accurate solar tracking as the data accumulates. control is possible

1 is a conceptual diagram for explaining the structure of a solar panel according to an embodiment.
2 is a conceptual diagram illustrating a shading problem occurring in a photovoltaic power generation system according to an exemplary embodiment.
FIG. 3 is a conceptual diagram for explaining an embodiment for maximizing power generation efficiency in consideration of shade according to FIG. 2 .
4 is a block diagram of a solar power generation system that controls solar tracking based on big data according to an embodiment.
5 is a conceptual diagram for explaining the structure of a solar panel according to an embodiment.
6 is a diagram for explaining a process of calculating a ratio of a shaded area in a central control server.
7 is a flowchart illustrating a control operation of a central control server according to an exemplary embodiment.
8 is a diagram showing a hardware configuration of a central control server according to an exemplary embodiment.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. Like reference numerals have been used for like elements throughout the description of each figure.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a conceptual diagram for explaining the structure of a solar panel according to an embodiment.

Referring to FIG. 1 , the solar panel 200 includes a plurality of solar panels 210 disposed on a main frame 220, coupled to a rear surface of the main frame 220, and an auxiliary rotation axis including an AXIS. It may include a frame 230 and a support member 240 that is physically connected to the auxiliary frame 230 via the rotational axis AXIS and is fixed perpendicularly to the ground to support a physical load. The main frame 220 and the auxiliary frame 230 may be configured as separate members, but may be integrally configured according to implementation examples.

Each of the solar panels 210 may be arranged in a lattice form on the main frame 220 .

The solar panel 200 may further include a rotation control unit 250 that rotates the main frame 220 or the auxiliary frame 230 by the rotation angle AGL about the rotation axis AXIS.

The rotation angle AGL may be defined as a value obtained by measuring an angle between the support member 240 fixed perpendicularly to the ground and the main frame 220 or the auxiliary frame 230 in a clockwise direction.

The rotation control unit 250 includes a connecting member 251 that connects the auxiliary frame 230 and the front and rear drive shaft 252 to each other via the rotating shaft AXIS, and the connecting member 251 and the second rotating shaft AXIS2 as a medium. It may include a front and rear drive shaft 252 that is connected and moves linearly in a direction parallel to the ground, and a power member 253 that provides power for linear motion of the front and rear drive shaft 252. For example, the power member 253 may be a power cylinder.

The connecting member 251 may convert the linear motion of the front and rear driving shaft 252 into the rotational motion of the auxiliary frame 230 . Specifically, when the front and rear drive shaft 252 is moved through a linear motion in the west direction, one end of the connecting member 251 is pulled in the west direction through the second rotation shaft AXIS2, and the resulting force is applied to the rotation shaft AXIS. to rotate counterclockwise. Conversely, when the front and rear drive shaft 252 is moved through a linear motion in the east direction, one end of the connecting member 251 is pushed toward the east through the second rotation shaft AXIS2, and the resulting repulsive force moves the rotation shaft AXIS. Let it rotate clockwise.

At this time, the connecting member 251 may be configured to have a variable length so as to stably convert linear motion into rotational motion. For example, when one end of the connecting member 251 is pulled in the west direction through the second rotating shaft AXIS2, the length of the connecting member 251 is increased by a preset length, and one end of the connecting member 251 is When pushed in the east direction through the second rotation axis AXIS2, the length of the connecting member 251 may be reduced again by a preset length. To this end, the connection member 251 may be configured to have a variable length by inserting or withdrawing an extension member (not shown) corresponding to a preset length into or out of the connection member 251 .

Meanwhile, although not shown in the drawings, in one embodiment, the rotation controller 250 may be implemented as a motor that is physically connected to the rotation shaft AXIS to rotate the rotation shaft AXIS. That is, the main frame 210 and the auxiliary frame 220 may be configured to rotate by directly rotating the rotation axis AXIS by the rotational force of the rotation control unit 250 .

The sun moves from east to west every day according to the diurnal direction, and accordingly, the surface of the main frame 220 on which the solar panel 210 is disposed is positioned perpendicular to the sun (hereinafter referred to as a direct solar radiation position) It is most advantageous for power generation efficiency.

Accordingly, the main frame 220 and the auxiliary frame 230 can be controlled to rotate clockwise around the axis of rotation (AXIS) so as to maintain a direct solar radiation position where sunlight can be transmitted vertically according to the sun's rotation. .

In addition, the front and rear driving shafts 252 may be disposed in the east-west direction in order to maintain the direct solar radiation position by rotating the solar panel 200 in a clockwise direction.

2 is a conceptual diagram illustrating a shading problem occurring in a photovoltaic power generation system according to an exemplary embodiment. FIG. 3 is a conceptual diagram for explaining an embodiment for maximizing power generation efficiency in consideration of shade according to FIG. 2 .

Referring to FIG. 2 , a case in which the solar panels 200 are arranged in an east-west direction to follow the circumferential direction of the sun is illustrated.

In this case, the solar panels 200 may be arranged in a plurality of columns (C1 to Cn) and rows to form a group of solar panels 200 for each column.

For convenience of explanation in this specification, each of the rows indicates the solar panels 200 disposed apart from each other by a predetermined spacing (GAP) in the east-west direction, and each of the columns (C1 to Cn) is each other in the north-south direction. It may be defined as indicating the solar panels 200 spaced apart from each other. In this case, the separation distance (GAP) may be a distance along the east-west direction.

For example, in FIG. 2 , the solar panel 200 disposed most eastward may belong to a first group corresponding to the first column C1, and the solar panel 200 disposed most westward may belong to a third group. It may be a third group corresponding to column C3.

On the other hand, when the spacing gap (GAP) is set to be very large, even if the solar panels 200 rotate along the sun's circumferential direction, the solar panels belonging to the front row do not shade the solar panels belonging to the rear row. However, it is difficult to specify a large gap in practice because a large installation area is required.

Therefore, there are many cases in which the spacing gap (GAP) is installed below a certain level, and this causes shading to occur between adjacent columns (more precisely, between adjacent solar panels 200 in the same row). do. In particular, there is less shadowing at noon when the sun is at its zenith, but in the morning or late afternoon before the sun sets, the elevation angle of the sun's incidence (the angle measured from the ground's direction) is small. There is a problem in that the smaller the gap (GAP) is, the larger the shadow occurs, and the power generation efficiency is lowered due to the shadow.

As an example to solve the shading problem, backtracking control may be performed to control the rotation direction of the solar panel 200 to be rotated by a predetermined angle in a direction opposite to the circumferential direction of the sun.

That is, as shown in FIG. 2, the solar panels 200 belonging to the same row may share the same front and rear drive shaft 252, and a single power member 253 for linear movement of the shared front and rear drive shaft 252. ) can be installed. In this case, since it is possible to control the rotational movement of all the solar panels 200 belonging to the same row by controlling only one power member 253, there are advantageous advantages in terms of convenience of control and reduction of construction costs.

On the other hand, in this case, after follow-up control is performed to rotate the solar panels 200 belonging to the same row to correspond to the position of direct solar radiation of the sun, and then a single power member 253 by a predetermined reference angle in the diurnal direction of the sun It is possible to perform backtracking control in which shadows generated between adjacent solar panels 200 in the same row are removed by rotating the same in the reverse direction of (moving direction from east to west).

However, when backtracking control is performed in the above-described manner, all the solar panels 200 are configured to give up the direct solar radiation position in order to remove shading, and the decrease in power generation efficiency due to the abandonment of the direct solar radiation position is a trade-off works as

In addition, if the spacing gap (GAP) is smaller than a certain reference value, shadows are necessarily generated because shadows cannot be completely removed only by backtracking control.

Therefore, in another embodiment of the present invention, with respect to the solar panels 200 belonging to the same row as shown in FIG. 3, based on the rotation angle AGL of the solar panels 200 belonging to the front row, The rotation angle AGL of the solar panel 200 belonging to the front row and the immediately adjacent rear row may be controlled.

For example, among the solar panels 200 belonging to the same row, the solar panel 200 belonging to the first column C1 or the frontmost column (the easternmost column) is set at a first rotation angle ALG1. ), and controls the solar panel 200 belonging to the second column C2 adjacent to the first column C1 at a second rotation angle AGL2 greater than the first rotation angle AGL1, and the second rotation angle AGL2. The solar panel 200 belonging to the third column C3 adjacent to the column C2 may be controlled at a third rotation angle AGL3 greater than the second rotation angle AGL1.

Here, the first rotation angle AGL1 may be an angle determined so that the surface forming the solar panel 210 is perpendicular to sunlight (ie, an angle determined such that the angle of incidence of sunlight becomes 90 degrees), and the elevation angle of the sun. It can be determined arithmetically according to The altitude angle of the sun may be determined according to the location, date, and time of the area where the solar panel 200 is installed, and the arithmetic expression for determining the rotation angle at which sunlight is vertically incident according to the altitude angle is a conventional Since a technician can easily set up with reference to known technologies, detailed descriptions will be omitted.

The second to third rotation angles AGL1 to 3 may be angles at which no shade is generated on the solar panel 200 . Here, the angle at which shading does not occur must be set larger than the rotation angle located in the front row, and can be determined by an arithmetic expression according to the altitude angle of the sun, and a detailed method will be described later.

Meanwhile, when the gap distance (GAP) is smaller than a predetermined reference value, there may be no angle at which no shadow occurs. In this case, it is important to determine the trade-off point between the loss of power generation due to the shaded area, which is an area shaded by the adjacent solar panels in the front row, and the amount of power generation according to the angle of incidence of sunlight in the remaining area other than the shaded area, the power generation area. It is advantageous.

That is, minimizing the shaded area widens the power generation area and increases power generation efficiency, but since the rotation angle AGL needs to be controlled so that the angle of incidence of sunlight is lower than 90 degrees, the amount of power generation per unit area of the power generation area decreases. Therefore, it is necessary to provide a method capable of providing optimal power generation efficiency by clearly setting a trade-off point between reducing the shaded area and maintaining the incident angle of sunlight to the power generation area as close to 90 degrees as possible.

In one embodiment of the present invention, in order to clarify the trade-off point between the size of the shaded area and the power generation efficiency per unit surface of the power generation area, the power generation efficiency according to the area ratio of the shaded area is configured as a data table based on big data. and a method for determining the rotation angle (AGL) corresponding to the optimal shaded area size by referring to the configured data table.

4 is a block diagram of a solar power generation system that controls solar tracking based on big data according to an embodiment.

Referring to FIG. 4 , a photovoltaic power generation system for controlling solar tracking based on big data according to an embodiment includes a plurality of solar panels 200 arranged according to a plurality of columns (C1 to Cn) and rows. ; Group tracking controllers 300 that are physically connected to the solar panels 200 and provide power for rotation of each of the solar panels 200; And it may include a central control server 100 for controlling rotational movement by transmitting a control command to each of the group tracking controllers 300 .

Each of the rows indicates solar panels 200 spaced apart from each other by a predetermined spacing (GAP) in the east-west direction, and each of the columns C1 to Cn is spaced apart from each other in the north-south direction (200). ) can be directed.

Each of the group tracking control units 300 may correspond to each of the columns C1 to Cn in a 1:1 ratio, and may operate rotational motions of the solar panels 200 belonging to the corresponding columns at the same rotational angle.

For example, the group tracking control unit 300 physically connected to the first column C1 may simultaneously operate the rotational movements of the solar panels 200 belonging to the first column C1 to have the same rotational angle. .

In the same way, the group tracking control unit 300 physically connected to the second column C2 can simultaneously operate the rotational movements of the solar panels 200 belonging to the second column C2 at the same rotational angle.

To this end, the group tracking control unit 300 may be physically connected to all of the front and rear drive shafts 252 of each of the solar panels 200 belonging to the corresponding column, and may be composed of one or more power cylinders.

As another example, the group tracking control unit 300 is connected by wire to the motor type rotation control unit 250 included in each of the solar panels 200, so that the rotational movement of the rotation control unit 250 is simultaneously performed at the same rotation angle. You can control it.

That is, since the group tracking control unit 300 is configured to equally control the rotation angles of the solar panels 200 belonging to the same column rather than the same row as shown in FIG. 2, two different group tracking control units ( 300), it is possible to differently control the rotation angles of the front row and the rear row located immediately behind the front row.

Meanwhile, although the group tracking control unit 300 has been illustrated and described as corresponding to each row 1:1, the rotation angle of each of the solar panels 200 is adjusted to the location where each solar panel 200 is installed as needed. It is also possible to operate each individually according to the altitude angle of the sun and the rotation angle of the solar panel 200 located in the front row adjacent to itself.

In this case, the group tracking control unit 300 is used in the same concept as the rotation control unit 250 (ie, motor) included in each of the solar panels 200, and the central control server 100, the solar panels 200 Rotation angles may be individually controlled by remotely (or through a wired network) transmitting a control command to the rotation controllers 250 (ie, motors) included in each rotation control unit 250 .

5 is a conceptual diagram for explaining the structure of a solar panel according to an embodiment. 6 is a diagram for explaining a process of calculating a ratio of a shaded area in a central control server.

Referring to FIG. 5 , the solar panel 200 includes a solar sensor 201 installed on a main frame 220; And it may further include a wire-type thermal sensor 202 installed to pass through the solar panels 210 installed on the main frame 220 in a grid pattern.

The solar sensor 201 may measure the amount of light incident on the solar panel 200 .

The wire-type thermal sensor 202 may measure the amount of heat generated from the solar panel 200 .

The central control server 100, based on the amount of light measured using the solar sensor 201 and the amount of heat measured using the wire-type thermal sensor 202, the unit area of each of the solar panels 200 (eg For example, the predicted power generation per m ² ) can be determined.

For example, the central control server 100 collects the amount of light and heat in the time between sunrise and sunset of the sun, and calculates the amount of power generated per unit area according to the amount of light and heat collected through linear regression analysis. By analyzing, a linear regression equation for determining the predicted amount of power generation can be determined as shown in Equation 1 below.

In Equation 1, Y′ is the predicted power generation per unit area over time between sunrise and sunset, a and b are linear regression coefficients, x1 is the amount of light over time between sunrise and sunset of the sun, and x2 is the amount of light over time between sunrise and sunset of the sun. It may be the amount of heat according to the time between sunrise and sunset.

That is, the central control server 100 continuously measures the amount of power generation per unit area according to the amount of light and heat in the time between sunrise and sunset of the sun (ie, the time according to the change in the altitude angle of the sun) to configure big data, , The linear regression equation according to Equation 1 is determined by analyzing the configured big data using linear regression analysis.

Therefore, each linear regression equation corresponding to each elevation angle may be specified in the form of Equation 1, and the central control server 100 may determine the predicted generation amount through the linear regression equation specified here.

On the other hand, the central control server 100 collects the amount of light, heat, local weather records for the surroundings of the installation place, and/or the amount of power generation reduction according to the local weather to configure big data, and uses the configured big data as learning data An artificial neural network may be supervised and the predicted generation amount of each of the solar panels may be determined using the supervised artificial neural network.

Local weather records may mean sudden climate changes such as clouds, snow, or rain, and may be collected from an external server operated by the Korea Meteorological Administration. In addition, the amount of power generation per unit area can be obtained by collecting the solar panel 200 in real time, and the amount of power generation reduction can be input from a manager or obtained from an external server operated by the Korea Meteorological Administration or a power plant.

In addition, the central control server 100 determines the ratio of the shaded area to the total area of the solar panel cells 210 according to the elevation angle of the sun using a predefined equation, and determines the elevation angle of the sun and the sunrise of the sun. The ratio of the shaded area according to the time between sunrise and sunset of the sun can be determined using a transformation of the relationship between the time between sunsets (ie, the time according to the change in the elevation angle of the sun).

Specifically, referring to FIG. 6 , a separation distance (GAP) between adjacent solar panels 200 among solar panels 200 belonging to the same row is determined by Equation 2 below.

Referring to Equation 2, the separation distance (GAP) is the rotation angle AGL1 of the solar panels 200 disposed in the front row among the solar panels 200 adjacent to each other, and the solar panels 200 disposed in the rear row. ) of the rotation angle (AGL2), the distance (L) from the rotation axis (AXIS) of the solar panel 200 to one end of the solar panel cell 210, the distance (d) of the shaded area, and the elevation angle (SL) of the sun and the horizontal distance T of the shaded area to the ground.

In this case, the horizontal distance T of the shaded area to the ground may be determined by Equation 3 below.

That is, by substituting Equation 3 into Equation 2, it is possible to determine the distance (d) of the shaded area generated in the solar panel 200 disposed in the rear row among the adjacent solar panels 200, If the rotation angle AGL2 of the solar panel 200 disposed in the rear row is obtained when the distance d is 0, the rotation angle AGL2 for not generating shadows can also be calculated.

In addition, the central control server 100 may determine a ratio of the shaded area to the total area of the solar panel cells 210 as shown in Equation 4 below, using the distance d of the shaded area.

In addition, by using the conversion of the relationship between the time between sunrise and sunset of the sun (ie, the time according to the change in the altitude angle of the sun) and the altitude angle according to the location where the solar panels 200 are installed, the sunrise and sunset of the sun It is possible to determine the ratio of the shaded area according to the time in between.

At this time, the time between sunrise and sunset of the sun (that is, the time according to the change in the altitude angle of the sun) and the altitude angle according to the location where the solar panels 200 are installed can be calculated using a well-known formula. , it is obvious that relational conversion is possible based on this formula.

The central control server 100 according to another embodiment of the present invention, when the shaded area cannot be avoided (ie, even if the rotation angles of each of the adjacent solar panels are adjusted because the separation distance GAP is too short, the shaded area If this necessarily exists in the corresponding time zone), it is possible to determine an optimal rotation angle between two adjacent solar panels belonging to the same row.

7 is a flowchart illustrating a control operation of a central control server according to an exemplary embodiment.

Referring to FIG. 7 , the central control server 100 may first control a rotation angle of each of the solar panels 200 so that sunlight enters vertically (S100).

For example, in step S100, the central control server 100 determines the altitude angle of the sun based on the location, date and time at which the solar panels 200 are installed, and the sunlight is vertical based on the determined altitude angle. A rotation angle for incident light may be determined, and the rotation angle of each of the solar panels 200 may be controlled with the determined rotation angle.

In one embodiment, the central control server 100 may determine the altitude angle of the sun by providing the location, date and time to an external weather server (not shown) and receiving the altitude angle from the weather server.

As another example, the central control server 100 may determine the altitude angle of the sun according to a previously input altitude angle calculation formula. Here, since the elevation angle calculation formula is widely known, a detailed description thereof will be omitted.

In step S100, the central control server 100 determines a rotation angle for vertically incident sunlight on each of the solar panels 200 individually, and uses the determined rotation angle to determine each of the solar panels 200. The rotation angle can be controlled. However, when the area occupied by all of the solar panels 200 is located within a preset reference area, all of the solar panels 200 may be controlled at the same rotation angle. (In this case, the rotation angle may be determined based on the altitude angle determined based on the central position within the area occupied by all of the solar panels 200.)

The central control server 100 may determine whether a shaded area exists in the solar panels belonging to each column (S110).

For example, the central control server 100 calculates Equation 3 based on the rotation angle of the first solar panel belonging to the first column and the rotation angle and elevation angle of the second solar panel belonging to the second column disposed to the east. When the distance d of the shaded area determined by substituting into Equation 2 is not 0, it may be determined that the shaded area exists.

If it is determined that the shaded area exists in step S110, the central control server 100 may determine a rotation angle for sequentially removing the shaded area from the solar panels belonging to the second column according to the column (S120).

For example, in step S120, the central control server 100 determines the distance d of the shaded area according to Equations 2 and 3 to be 0 based on the rotation angle and elevation angle of the solar panel belonging to the first column. The rotation angle of the solar panels belonging to the second column can be determined.

In the same way, the central control server 100, based on the rotation angle and elevation angle of the solar panel belonging to the i (i is a natural number greater than or equal to 2 and less than n, n is the total number of columns) th column, shaded area The process of determining the rotation angle of the solar panel belonging to the i+1th column for the distance d of to be 0 may be repeated for each column from the second column.

In this case, the rotation angle determined in step S120 may be determined as the same value for the solar panels belonging to the same column. That is, all solar panels belonging to an arbitrary i-th column may be determined to have the same rotation angle.

Meanwhile, in this case, as shown in FIG. 3 , when the sun is greatly biased toward the east, the rotation angle of the solar panel belonging to the i-th column plus the correction angle for the distance d of the shaded area to be 0 is the i+1th value. The rotation angle of the solar panels belonging to the row can be determined. That is, in order to remove the shaded area due to the solar panel belonging to the front row, the rotation angle of the solar panel belonging to the immediately following column must be increased by the correction angle so that the shaded area can be eliminated.

For example, referring to FIG. 3 again, the rotation angle of the solar panel belonging to the second column C2 is obtained by adding the correction angle to the rotation angle AGL1 of the solar panel belonging to the first column C1. The rotation angle AGL2 of the solar panel belonging to the third column C3 is determined by adding the correction angle to the rotation angle AGL2 of the solar panel belonging to the second column C2. can

In step S130 of sequentially determining rotation angles for each column, the central control server 100 may determine whether there is a reference column in which shaded areas cannot be avoided (S130).

For example, while removing the shaded area by determining the rotation angle of the third column to be greater than that of the second column and determining the rotation angle of the fourth column to be greater than that of the third column, the distance (d) of the shaded area in a specific reference column is 0 The rotation angle may not exist.

That is, in step S120, the central control server 100 determines that the rotation angle of the solar panel belonging to the i+1th column for the distance d of the shaded area according to Equations 2 and 3 to be 0 does not exist. In this case, the i+1th column may be determined as a reference row in which a shaded area cannot be avoided.

When it is determined in step S130 that the reference column exists, the central control server 100 sequentially according to the columns from the solar panels belonging to the reference column to the solar panels belonging to the last columns belonging to each of the two adjacent columns. Rotation angles of the solar panels may be determined (S140).

Specifically, in step S140, the central control server 100, based on the ratio of the shaded area according to the time between sunrise and sunset of the sun and the predicted amount of power generation according to the regression analysis, the solar panels belonging to each of the two adjacent columns ( 200) can be determined.

For example, the central control server 100 gradually decreases the rotation angle of the third solar panels belonging to the reference column by a preset interval from the reference rotation angle (ie, the shaded area of the reference column increases), and in the rear row adjacent to the reference column. While gradually increasing the rotation angles of the fourth solar panels to which they belong by a predetermined interval from the reference rotation angle (ie, reducing the shaded area), the amount of power generation loss defined as the value multiplied by the ratio of the shaded area and the estimated amount of power generation is determined by the third solar panel It can be calculated from one of the four solar panels and one of the fourth solar panels, respectively. Here, the reference rotation angle may be a value obtained by adding a correction angle to a rotation angle determined for solar panels belonging to a front row adjacent to the reference row.

The central control server 100 may determine rotation angles of the third solar panels and the rotation angles of the fourth solar panels such that the sum of the two calculated power generation losses is minimized.

Finally, the central control server 100 controls the rotation angle of each of the solar panels using the rotation angle determined in step S120 and the rotation angle determined in step S140 so that the rotation angle of the solar panel for all rows is optimally efficient. control as much as possible

In summary, the central control server 100 controls the rotation angles of the solar panels so that sunlight is incident vertically (S100), and then, when a shaded area exists (S110), the shaded area sequentially from the easternmost column. The rotation angle is determined to remove (S120), and in the process of determining the rotation angle, if a reference column in which shaded areas cannot be avoided is generated (S130), the rotation angle from the reference column to the last column is shaded area. Rotation angles between solar panels belonging to adjacent columns are determined so that the ratio of and the amount of power generation loss according to predicted power generation are minimized (S140).

On the other hand, the above-described steps are restricted so that they are not performed more than once within a preset time interval (eg, 1 hour or 30 minutes), so that the rotation angle is not frequently controlled according to temporary climate change or external environment change, and mechanical change Losses and malfunctions can be minimized.

8 is a diagram showing a hardware configuration of a central control server according to an exemplary embodiment.

Referring to FIG. 8 , the central control server 100 transmits at least one processor 110 and instructions instructing the at least one processor 110 to perform at least one operation. It may include a memory (memory, 120) for storing.

The at least one operation may include at least some of the operations or functions of the central control server 100 described with reference to FIGS. 1 to 7 , and a detailed description thereof will be omitted to prevent redundant description.

Here, the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor for performing methods according to embodiments of the present invention. can Each of the memory 120 and the storage device 160 may include at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 120 may be one of a read only memory (ROM) and a random access memory (RAM), and the storage device 160 may be a flash-memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, a micro SD card).

In addition, the central control server 100 may include a transceiver 130 that performs communication through a wireless network. In addition, the central control server 100 may further include an input interface device 140, an output interface device 150, a storage device 160, and the like. Each component included in the central control server 100 is connected by a bus 170 to communicate with each other.

For example, the central control server 100 may be a communicable desktop computer, a laptop computer, a notebook, a smart phone, a tablet PC, or a mobile phone. phone), smart watch, smart glass, e-book reader, portable multimedia player (PMP), portable game device, navigation device, digital camera, digital multimedia broadcasting (DMB) ) player, digital audio recorder, digital audio player, digital video recorder, digital video player, personal digital assistant (PDA), and the like.

The methods according to the present invention may be implemented in the form of program instructions that can be executed by various computer means and recorded on a computer readable medium. Computer readable media may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on a computer readable medium may be specially designed and configured for the present invention or may be known and usable to those skilled in computer software.

Examples of computer readable media may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language codes generated by a compiler but also high-level language codes that can be executed by a computer using an interpreter and the like. The hardware device described above may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

In addition, the above-described method or device may be implemented by combining all or some of its components or functions, or may be implemented separately.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the claims below. You will understand that it can be done.

100: central control server
200: solar panel
300: group tracking control unit

Claims (1)

As a solar power generation system that controls solar tracking by analyzing big data using an artificial neural network,
a plurality of solar panels arranged in a plurality of columns and rows;
Group tracking controllers physically connected to the solar panels to provide power for rotation of each of the solar panels; and
A central control server for controlling the rotational motion by transmitting a control command to each of the group tracking controllers;
Each of the rows indicates solar panels spaced apart from each other by a predetermined spacing in the east-west direction,
Each of the plurality of solar panels,
a plurality of solar panels disposed on the main frame;
A secondary frame coupled to the rear surface of the main frame and including a rotation shaft;
a support member that is physically connected to the auxiliary frame via the rotating shaft and is fixed perpendicularly to the ground to support a physical load;
a solar sensor installed on the main frame to measure the amount of light; and
A wire-type thermal sensor installed to pass through the solar panels to measure heat,
The central control server,
controlling a rotation angle of each of the solar panels so that sunlight is incident vertically;
determining whether a shaded area exists in the solar panels belonging to each of the columns;
determining a rotation angle of each of the solar panels to sequentially remove the shaded area from an easternmost column among the columns when the shaded area exists;
determining whether there is a reference column in which the shaded area cannot be avoided among the columns; and
When the reference column exists, a rotation angle of each of the solar panels belonging to two adjacent columns is determined sequentially from the reference column to the last column based on the ratio of the shaded area and the predicted generation amount. but
The operation of determining the rotation angle of each of the solar panels belonging to two adjacent columns based on the ratio of the shaded area and the predicted power generation,
The rotation angle of the solar panels belonging to the reference row is gradually decreased by a preset interval from the preset reference rotation angle, and the rotation angle of the solar panels belonging to the next row adjacent to the reference column is gradually increased by a preset interval from the reference rotation angle. While doing so, the generation loss defined as the value obtained by multiplying the ratio of the shadow area by the predicted generation amount is calculated in the solar panel belonging to the reference row and the solar panel belonging to the back row, respectively, and the sum of the two calculated generation losses is determining a rotation angle of each of the solar panels belonging to the two adjacent columns to be minimized;
The central control server,
Creating learning data by collecting the amount of light, the amount of heat, the local weather around the place where the solar panels are installed, and the amount of power generation reduction according to the local weather,
Based on the generated learning data, an artificial neural network is supervised and trained,
The photovoltaic power generation system for determining the predicted power generation amount of each of the solar panels using the supervised artificial neural network.

Images