TWI838895B - Method for establishing a dual-axis sun-tracking solar power system operating model with shadow mode - Google Patents

Abstract

Disclosed is a method for establishing a dual-axis sun-tracking solar power system operating model with shadow mode, comprising: installing a photosensitive element on a solar power panel so that photosensitive element illumination data is obtained under different shadow modes; using a recurrent fuzzy neural network as a predictor, and establishing a maximum power production predictor module in combination with the photosensitive element; detecting a real power production by the maximum power production predictor module when a time unit passes; and judging sun sets or not; if yes, subsequent steps are executed: judging if the real power production is larger than a threshold value A; if yes, judging what rotation strategy allows the solar panel to maximize its photo-receiving area, and rotating the solar panel correspondingly; if no, the solar panel remains still.

Description

Method for establishing the operation model of a dual-axis sun-tracking solar energy system with shading mode

The present invention relates to a method for establishing a solar power prediction model, and in particular to a method for establishing a model that can adjust the decision-making of solar panel operation under different shading conditions.

In view of the global warming crisis and the rise of environmental awareness, renewable energy has gradually become the mainstream power generation method today. Among them, solar energy is the most common and most easily accessible renewable energy. Therefore, more and more countries and research teams are investing in solar power generation technology. Today, solar power generation has been widely used in agriculture, gardening, and even as an alternative energy source for vehicles or ships, and has broad application prospects. In the prior art of solar tracking systems, the Republic of China Patent Publication No. I697646 provides a floating solar panel tracking system, wherein the solar panel can float on a water surface and the pitch angle of the solar panel can be adjusted to achieve the effect of tracking the sun. However, the solar panel can only be controlled to rotate along a single axis. Since it cannot rotate horizontally, when the sun's orbit moves, the solar panel will not rotate horizontally. When the solar panel is moving, the direct angle of sunlight it receives is limited, so the proportion of its increased power generation is limited. In addition, the case does not take into account the situation when there is a shield blocking the solar panel. Therefore, if the solar panel is operated under a low power generation state, the power consumed by operating the solar panel may be greater than the power obtained by the solar panel receiving light, thereby reducing the total amount of power stored in the entire solar system. In view of the above technical deficiencies, it is necessary to provide a method that can adjust the movement strategy of the solar panel accordingly according to the shading condition of the solar panel to avoid reducing the overall power generation of the solar panel.

The problem that the present invention aims to solve is to provide a method for determining the shading state of a solar panel, and according to the maximum power generation under the current shading state, determine which rotation method can increase the light receiving area when rotating horizontally, vertically, biaxially, or not rotating, and rotate the solar panel in a rotation method that can "increase the maximum light receiving area" so that the entire solar system can obtain the maximum total power generation under various shading states.

In order to achieve the above-mentioned purpose, the present invention provides a method for establishing an operation model of a dual-axis sun-tracking solar system with a shading mode, comprising the following steps: (S1) a photosensitive element is respectively set at at least four positions of a solar panel of a battery module; (S2) a terminal is used to collect illumination data of the photosensitive element when the photosensitive element is not shaded, partially shaded, or completely shaded under a placement time and a related parameter condition, and store the data in a database; (S3) the terminal uses a recursive fuzzy neural network as a predictor to establish a training prediction mathematical model for the illumination data of the photosensitive element in the database, and forms a maximum power generation prediction module; (S4) every time unit, the maximum power generation prediction module detects the actual power generation of the battery module; (S5) according to the movement trajectory of the sun, determine whether the sun has set, or the time or angle for setting the end of the sun tracking has been reached? If so, the solar panel is reset to an initial position, if not, enter step (S6); (S6) determine whether the actual power generation of the battery module is greater than a threshold value A? If yes, proceed to step (S7); if no, the solar panel does not rotate and proceeds to step (S4); (S7) Determine whether the solar panel can reduce the shaded area on the solar panel when rotating? If yes, proceed to step (S8); if no, the solar panel does not rotate and proceeds to step (S4); (S8) Determine in which way the solar panel can rotate to remove more shaded area when operating in the following modes a to c, and rotate in a way that can obtain the highest power generation, and after the solar panel rotates, proceed to step (S4), wherein: mode a is horizontal rotation, mode b is vertical rotation, and mode c is dual-axis rotation.

More preferably, wherein: the placement time includes a first placement time and a second placement time; the relevant parameter condition includes a first relevant parameter condition and a second relevant parameter condition; the photosensitive element illumination data includes a first photosensitive element illumination data and a second photosensitive element illumination data; and the terminal collects the illumination data of the first photosensitive element when the photosensitive element is not shielded, partially shielded, or completely shielded during the first placement time and under the first relevant parameter condition, and the terminal collects the illumination data of the second photosensitive element when the photosensitive element is not shielded, partially shielded, or completely shielded during the second placement time and under the second relevant parameter condition.

Preferably, the relevant parameter condition of step (S2) includes a system-related parameter and an environment-related parameter.

More preferably, the system-related parameters include any of the following data, or a combination thereof: the voltage of the solar panel, the current of the solar panel, the temperature of the solar panel, the total irradiance of the solar panel, the voltage of the solar battery, the current of the solar battery, the temperature of the solar battery, the total irradiance of the solar battery, a horizontal angle of the solar panel relative to the initial position, and a pitch angle of the solar panel relative to the initial position.

Preferably, the environment-related parameter includes any of the following data, or a combination thereof: the temperature of the environment surrounding the solar panel, the relative humidity of the environment surrounding the solar panel, the amount of sunlight at the solar panel installation site throughout the day, the sunshine intensity at the solar panel installation site, the wind speed at the solar panel installation site, the wind intensity at the solar panel installation site, and the air quality index at the solar panel installation site.

，其中，m _ij 、σ _ij,n 、

、

為可調正之控制參數，σ _ij,L 為中心點在m _ij 之歸屬函數左側寬度參數，σ _ij,R 為中心點在m _ij 之歸屬函數右側寬度參數。 More preferably, the mathematical equation of the recursive fuzzy neural network is:

, where m _ij , σ _ij,n ,

,

is an adjustable control parameter, σ _ij,L is the width parameter on the left side of the attribution function with the center _{point at mij} , and σ _ij,R is the width parameter on the right side of the attribution function with the center _{point at mij} .

More preferably, the threshold value A is 30 to 80% of the maximum power generated by the solar panel when the photosensitive element is not shielded.

More preferably, the photosensitive elements are arranged at intervals on the same side of the solar panel and close to the outer edge of the solar panel, and when the number of the photosensitive elements is Q, the angle formed by the line connecting the center of gravity of the solar panel with two adjacent photosensitive elements is 360°/Q.

More preferably, in step (S8), the solar panel is rotated by an azimuth angle of a horizontal angle unit; the solar panel is rotated by a pitch angle of a vertical angle unit; or the solar panel is rotated by an azimuth angle of a horizontal angle unit and a pitch angle of a vertical angle unit respectively.

More preferably, the horizontal angle unit or the vertical angle unit is 1 to 20°.

The effectiveness of the present invention over the prior art is that, in the existing solar tracking model, only the situation that the solar panel rotates corresponding to the movement trajectory of the sun is considered, but the operation strategy when the solar panel generates low power due to the shading effect is not considered. As a result, it is possible that the power generated by the solar panel when it is affected by the shading effect is lower than the power consumed when the solar panel moves corresponding to the movement trajectory of the sun, causing the energy stored in the solar battery to be continuously depleted or even exhausted, and the energy cannot be stored effectively. When the solar panel of the present invention is tracking the sun, it first analyzes the maximum power generation according to the current shading condition of the solar panel, and can calculate which rotation strategy can maximize the total power generation of the solar panel when the solar panel is rotated in four rotation strategies: horizontal rotation, vertical rotation, horizontal and vertical rotation at the same time, or no rotation. Specifically, the present invention can select the best current operation mode under different shading conditions, so that the solar panel can generate the maximum power generation under the corresponding shading condition. Therefore, the solar panel of the present invention does not consume the power in the solar battery during operation, but can store energy stably.

S1~S8: Step number

1: Solar panels

2: Photosensitive element

3: Shaded area

Figures 1A to 1B are a series of block diagrams used to illustrate the method step flow of the present invention;

Figures 2A to 2B are a series of three-dimensional diagrams used to illustrate the implementation of horizontal rotation of solar panels according to the shaded area;

Figures 3A to 3B are a series of three-dimensional diagrams used to illustrate the implementation of vertical rotation of solar panels according to the shaded area;

Figures 4A to 4B are a series of three-dimensional diagrams used to illustrate the implementation of the solar panel rotating horizontally and vertically at the same time according to the shading area;

Figure 5 is a three-dimensional diagram to illustrate the implementation of the solar panel choosing not to rotate according to the shaded area.

In order to make the above and/or other purposes, effects, and features of the present invention more clearly understood, the following specifically provides a preferred implementation method for detailed description:

The purpose of the present invention is to provide a method for establishing an operation model of a dual-axis sun-tracking solar energy system with a shading mode, comprising the following steps: (S1) a photosensitive element (2) is respectively arranged at at least four positions of a solar panel (1) of a battery module; (S2) a terminal is used to collect illumination data of the photosensitive element (2) when the photosensitive element (2) is not shaded, partially shaded, or completely shaded under a placement time and a related parameter condition, and stores the data. to a database; (S3) the terminal uses a recursive fuzzy neural network as a predictor to establish a training prediction mathematical model for the illumination data of the photosensitive element (2) in the database, and forms a maximum power generation prediction module; (S4) every time unit, the maximum power generation prediction module detects the actual power generation of the battery module; (S5) according to the movement trajectory of the sun, it is determined whether the sun has set, or the time or angle for setting the end of the sun tracking has been reached? If so, the solar panel (1) is reset to an initial position, if not, it enters step (S6); (S6) it is determined whether the actual power generation of the battery module is greater than a threshold value A? If yes, proceed to step (S7); if no, the solar panel (1) does not rotate and proceeds to step (S4); (S7) determining whether the solar panel (1) can reduce the shaded area on the solar panel (1) when rotating? If yes, proceed to step (S8); if no, the solar panel (1) does not rotate and proceeds to step (S4); (S8) determines in which manner the solar panel (1) is rotated to remove more shaded area when operating in the following modes a to c, and rotates in a manner that can obtain the highest power generation, and after the solar panel (1) has completed its rotation, proceed to step (S4), wherein: mode a is horizontal rotation, mode b is vertical rotation, and mode c is dual-axis rotation. In a preferred embodiment, in order to prevent the solar panel (1) from consuming the electric energy stored in the solar battery during operation, thereby preventing the total power storage capacity of the solar battery from decreasing, a rotation limit, i.e., a threshold value A, needs to be set for the solar panel (1). Specifically, the threshold value A is 30 to 80%, preferably 40 to 70%, and more preferably 50 to 60%, of the maximum power generated by the solar panel (1) when the photosensitive element (2) is not shielded, but is not limited thereto. In another preferred embodiment, in order to increase the sensitivity of the photosensitive element (2) in sensing the shaded state, the photosensitive elements (2) are arranged at intervals on the same side of the solar panel (1) and close to the outer edge of the solar panel (1), and when the number of the photosensitive elements (2) is Q, the angle formed by the line connecting the center of gravity of the two adjacent photosensitive elements (2) and the solar panel (1) is 360°/Q. In another preferred embodiment, step (S7) is to determine whether the solar panel (1) can increase the light receiving area of the solar panel (1) when rotating along the moving trajectory of the sun, and step (S8) is to make the solar panel (1) rotate accordingly according to the moving trajectory of the sun after selecting the rotation decision.

Preferably, in order to obtain sufficient illumination data of the photosensitive element to optimize the maximum power generation prediction module so that it can more accurately measure the power generation of the solar panel (1), the placement time includes a first placement time and a second placement time; the relevant parameter condition includes a first relevant parameter condition and a second relevant parameter condition; the illumination data of the photosensitive element includes a first illumination data of the photosensitive element and a second illumination data of the photosensitive element; The terminal collects illumination data of the first photosensitive element (2) when it is not shielded, partially shielded, or completely shielded during the first placement time and under the first relevant parameter conditions, and the terminal collects illumination data of the second photosensitive element (2) when it is not shielded, partially shielded, or completely shielded during the second placement time and under the second relevant parameter conditions. Specifically, the terminal can collect multiple sets of illumination data of the photosensitive element at the same time and store them in a database to optimize the maximum power generation prediction module and improve the accuracy of measuring the power generation of the solar panel (1). In a preferred embodiment, the placement time can be 1 day to 1 year, but not limited thereto, wherein: when only one set of photosensitive element illumination data is used to obtain the maximum power generation prediction module, a longer placement time is required to maintain the accuracy of the maximum power generation prediction module in measuring the power generation of the solar panel (1); however, when multiple sets of photosensitive element illumination data are used to form the maximum power generation prediction module, the placement time can be greatly shortened, and the maximum power generation prediction module can accurately measure the power generation of the solar panel (1). In another preferred embodiment, the placement time is one day, one week, one month, one season, half a year, multiples of the above time units, or a combination of the above time units, but not limited thereto.

Preferably, in order to enable the maximum power generation prediction module to measure the maximum power that the "actual" solar panel (1) can generate without making the measured value too idealized and causing a large deviation from the actual value, the system parameters of the solar panel (1) itself and the environmental conditions in which the solar panel (1) is set are taken into consideration. Specifically, the relevant parameter conditions of step (S2) include a system-related parameter and an environment-related parameter. In a preferred embodiment, the system-related parameters include any one of the following data, or a combination thereof: the voltage of the solar panel (1), the current of the solar panel (1), the temperature of the solar panel (1), the total irradiance of the solar panel (1), the voltage of the solar battery, the current of the solar battery, the temperature of the solar battery, the total irradiance of the solar battery, a horizontal angle of the solar panel (1) relative to the initial position, and a pitch angle of the solar panel (1) relative to the initial position. In another preferred embodiment, the environment-related parameter includes any of the following data, or a combination thereof: the temperature of the environment surrounding the solar panel (1), the relative humidity of the environment surrounding the solar panel (1), the amount of sunlight received by the solar panel (1) throughout the day, the intensity of sunlight received by the solar panel (1) at the solar panel (1), the wind speed received by the solar panel (1), the wind strength received by the solar panel (1), and the air quality index received by the solar panel (1).

，其中，m _ij 、σ _ij,n 、

、

為可調正之控制參數，σ _ij,L 為中心點在m _ij 之歸屬函數左側寬度參數，σ _ij,R 為中心點在m _ij 之歸屬函數右側寬度參數。 More preferably, the mathematical equation of the recursive fuzzy neural network is:

, where m _ij , σ _ij,n ,

,

is an adjustable control parameter, σ _ij,L is the width parameter on the left side of the attribution function with the center _{point at mij} , and σ _ij,R is the width parameter on the right side of the attribution function with the center _{point at mij} .

More preferably, when making a rotation decision, the adjustment basis of the "dual-axis sun-tracking solar system operation model with shading mode" of the present invention includes four implementation modes. Among the four implementation modes, with reference to FIG. 2A, the solar panel (1) needs to rotate horizontally to the left or vertically upward so that its rotation trajectory conforms to the movement path of the sun. In the "first implementation", as shown in FIG2A, it can be found that the photosensitive elements (2) on the right half of the solar panel (1) are all shielded by a shade area (3), and the shade area (3) extends to the right half of the solar panel (1). Therefore, in order to maximize the illumination area of the solar panel (1) to increase the power generation, the horizontal angle (azimuth) of the solar panel (1) should be changed to rotate relative to the shade area (3). Therefore, the best rotation decision is to rotate horizontally to the left. As shown in FIG2B, it can be found that: after the solar panel (1) is rotated in the horizontal direction, the photosensitive elements (2) on the right half of the solar panel (1) can receive light to increase the power generation of the solar panel (1). In the "second implementation", as shown in FIG3A, it can be found that the photosensitive elements (2) in the lower half of the solar panel (1) are all shielded by a shade area (3), and the shade area (3) extends to the lower half of the solar panel (1). Therefore, in order to maximize the illumination area of the solar panel (1) to increase the power generation, the pitch angle of the solar panel (1) should be changed to rotate it relative to the shade area (3). Therefore, the best rotation decision at this time is to rotate it vertically upward. As shown in FIG3B, it can be found that when the solar panel (1) is rotated in the vertical direction, the photosensitive elements (2) in the lower half of the solar panel (1) can receive light to increase the power generation of the solar panel (1). In the "third implementation", as shown in FIG. 4A, it can be found that the right half of the solar panel (1) and the photosensitive element (2) in the lower half are both shielded by a shade area (3), and the shade area (3) extends to the right half and the lower half of the solar panel (1). Therefore, in order to maximize the irradiation area of the solar panel (1) to increase the power generation, the azimuth and pitch angles of the solar panel (1) should be changed at the same time so that it rotates relative to the shade area (3). Therefore, the best rotation decision at this time is to rotate to the left horizontally and to the upper vertically at the same time. As shown in FIG. 4B , it can be found that when the solar panel (1) is rotated in the horizontal and vertical directions simultaneously, the right half of the solar panel (1) and the photosensitive element (2) in the lower half can receive light, thereby increasing the power generation of the solar panel (1). In the "fourth implementation", as shown in FIG5, it can be found that the left half of the solar panel (1) and the photosensitive element (2) in the upper half are both shielded by a shade area (3), and the shade area (3) extends to the left half and the upper half of the solar panel (1). Therefore, if the solar panel (1) is rotated at this time, it will cause the solar panel (1) to move toward the shade area (3), so that the light receiving area of the solar panel (1) is reduced. Since the power generated by the solar panel (1) after the rotation is lower than the power generated before the rotation, in order to avoid unnecessary energy consumption, the rotation strategy of the solar panel (1) at this time is not to rotate, and return to step (S4), and after another time unit has passed, the rotation decision is re-determined. Among them, although in the fourth embodiment, the solar panel (1) can be rotated horizontally to the right and vertically downward to increase the light receiving area of the solar panel (1), its rotation direction will be opposite to the actual movement trajectory of the sun, causing a large deviation in the solar irradiation angle and causing the power generation of the solar panel (1) to be greatly reduced. Therefore, in order to avoid the above situation, in the rotation strategy of the solar panel (1), its rotation direction must follow the actual movement trajectory of the sun to rotate, so that the solar panel (1) can stably store energy in both the shaded state and the non-shaded state.

Preferably, the device further comprises a monitoring mechanism disposed on the solar panel (1) for obtaining a geographical coordinate position of the solar panel (1) and calculating the pitch angle and azimuth angle of the sun's illumination of the geographical coordinate position at each moment to obtain solar illumination angle information, so that the solar panel (1) can move accordingly according to the solar illumination angle information, so that the solar panel (1) can receive direct sunlight and generate high power. Specifically, under full sunlight and no shadow environment conditions, the solar panel (1) will rotate horizontally and vertically according to the solar irradiation angle information after each unit time, so that the solar panel (1) remains perpendicular to the solar irradiation angle to generate the maximum power generation. In addition, when the solar panel (1) is affected by the shade state, if the power generation that the solar panel (1) can currently generate is lower than the power required to rotate the solar panel (1), it means that operating the solar panel (1) will cause the total power generation to decrease, and it is not appropriate to rotate the solar panel (1) at this time; if the power generation that the solar panel (1) can currently generate is higher than the power required to rotate the solar panel (1), it means that operating the solar panel (1) will cause the total power generation to decrease, and the solar panel (1) should not be rotated at this time; if the power generation that the solar panel (1) can currently generate is higher than the power required to rotate the solar panel (1), it means that operating the solar panel (1) will cause the total power generation to decrease, and the solar panel (1) should not be rotated at this time. When the power consumed is calculated, it can be calculated: when the solar panel (1) rotates horizontally, vertically, or rotates in both horizontal and vertical directions according to the solar illumination angle information, which operation mode can maximize the increase of the light-receiving area on the solar panel (1), and according to the rotation mode that can maximize the increase of the light-receiving area, the solar panel (1) is rotated according to the solar illumination angle information. Specifically, the present invention takes into account the problem of reduced power generation that the solar panel (1) may face when operating in various shading modes, and maximizes the power generation of the solar panel (1) and prevents the power stored in the solar battery from being lost due to improper operation of the solar panel (1). In a preferred embodiment, the monitoring mechanism can adjust the azimuth and pitch angle of the solar panel (1) to generate the highest power point under the current sun irradiation position, so that the solar panel (1) can continuously generate the highest power when rotating along the sun's moving trajectory. In another preferred embodiment, the geographic coordinate position is a two-dimensional coordinate system composed of longitude and latitude, or a three-dimensional coordinate system composed of longitude, latitude, and altitude, but is not limited thereto.

More preferably, in step (S5), a tracking device is installed on the solar panel (1), and the tracking device is used to track the current position of the sun to confirm whether the solar panel (1) is in a state where it can receive light. Specifically, when the solar panel (1) is only in a shaded state and does not generate power temporarily, since the sun can still shine on the solar panel (1) after the shaded part disappears, it is in a "state where it can receive light". At this time, since the solar panel (1) does not generate power, if the solar panel (1) is rotated, the total power in the solar battery will decrease. Therefore, the rotation strategy of the solar panel (1) is not to rotate, and return to step (S4) to wait for a time unit again. After that, the power generation is re-determined; and when the solar panel (1) does not generate power because the sun has set, the solar panel (1) cannot receive sunlight, which is a certain and unchangeable matter, so it is in a "state that cannot receive light". In addition, since the sun sets, the process of chasing the sun for a day has ended. In order to enable the solar panel (1) to chase the sun again the next day, when the solar panel (1) is in a state that cannot receive light, it will automatically reset to the initial position. In a preferred embodiment, after the solar panel (1) is reset to the initial position, it will sleep for a period of time and restart when it is close to sunrise to reduce the power consumption during the standby time.

More preferably, in step (S8), the solar panel (1) is rotated by an azimuth of a horizontal angle unit; the solar panel (1) is rotated by a pitch angle of a vertical angle unit; or the solar panel (1) is rotated by an azimuth of a horizontal angle unit and a pitch angle of a vertical angle unit. In a preferred embodiment, the horizontal angle unit or the vertical angle unit is 1 to 20°, but is not limited thereto. Specifically, when the solar panel (1) is in a short-term shade state, the solar panel (1) will rotate after each time unit, so it can move to a position corresponding to the direct angle of the sun after rotating a smaller horizontal angle unit or vertical angle unit, so that the solar panel (1) can generate maximum power; and when the solar panel (1) is in a long-term shade state, the solar panel (1) will rotate after multiple time units have passed, so it needs to rotate a larger horizontal angle unit or vertical angle unit before it can move to a position corresponding to the direct angle of the sun, so that the solar panel (1) can generate maximum power.

The benefit of the present invention over the prior art is that, in the existing solar tracking model, only the situation that the solar panel (1) rotates in accordance with the movement trajectory of the sun is taken into consideration, but the operation strategy when the power generation of the solar panel (1) is reduced due to the shading effect is not taken into consideration. As a result, it is possible that the power generation of the solar panel (1) when affected by the shading effect is lower than the power consumed when the solar panel (1) moves in accordance with the movement trajectory of the sun, causing the energy stored in the solar battery to be continuously depleted or even exhausted, and the energy cannot be effectively stored. When the solar panel (1) of the present invention is tracking the sun, it first analyzes the maximum power generation according to the current shading condition of the solar panel (1), and can calculate which rotation strategy can maximize the total power generation of the solar panel (1) when the solar panel (1) is rotated in four rotation strategies, namely horizontal rotation, vertical rotation, simultaneous horizontal and vertical rotation, or no rotation. Specifically, the present invention can select the best current operation mode under different shading conditions, so that the solar panel (1) can generate the maximum power generation under the corresponding shading condition. Therefore, the solar panel (1) of the present invention does not consume the electric energy in the solar battery during operation, but can store energy stably.

However, the above is only the preferred embodiment of the present invention, and it should not be used to limit the scope of the implementation of the present invention. That is, all simple equivalent changes and modifications made according to the scope of the patent application and the content of the invention description of the present invention are still within the scope of the present invention. In addition, any embodiment of the present invention or the scope of the patent application does not need to achieve all the purposes, advantages or features disclosed by the present invention. In addition, the abstract part and the title are only used to assist the search of patent documents, and are not used to limit the scope of the rights of the present invention. In addition, the first, second, etc. mentioned in the specification are only used to indicate the name of the component, and are not used to limit the upper or lower limit of the number of components.

S1~S3: Step number

Claims (10)

A method for establishing an operation model of a dual-axis sun-tracking solar energy system with a shading mode includes the following steps: (S1) A photosensitive element is respectively arranged at at least 4 positions of a solar panel of a battery module; (S2) Using a terminal to collect illumination data of a photosensitive element when the photosensitive element is not shielded, partially shielded, or completely shielded at a certain placement time and under a certain relevant parameter condition, and store the data in a database; (S3) The terminal uses a recursive fuzzy neural network as a predictor to establish a training prediction mathematical model for the illumination data of the photosensitive element in the database, and forms a maximum power generation prediction module; (S4) Every time unit, the maximum power generation prediction module detects the actual power generation of the battery module; (S5) Determine whether the sun has set or the set end time or angle for tracking the sun has been reached according to the sun's movement trajectory? If so, reset the solar panel to an initial position; if not, proceed to step (S6); (S6) Determine whether the actual power generation of the battery module is greater than a threshold value A? If so, proceed to step (S7); if not, the solar panel does not rotate and proceeds to step (S4); (S7) Determine whether the solar panel can reduce the shaded area on the solar panel when it rotates? If so, proceed to step (S8); if not, the solar panel does not rotate and proceeds to step (S4); (S8) Determine which way the solar panel is rotated to remove more shaded area when it is operated in the following modes a to c, and rotate it in a way that can obtain the highest power generation, and enter step (S4) after the solar panel rotates, wherein: mode a is horizontal rotation, mode b is vertical rotation, and mode c is dual-axis rotation. The method as claimed in claim 1, wherein: The placement time includes a first placement time and a second placement time; the related parameter condition includes a first related parameter condition and a second related parameter condition; the photosensitive element illumination data includes a first photosensitive element illumination data and a second photosensitive element illumination data; and The terminal collects illumination data of the first photosensitive element when the photosensitive element is not shielded, partially shielded, or completely shielded during the first placement time and under the first relevant parameter conditions, and the terminal collects illumination data of the second photosensitive element when the photosensitive element is not shielded, partially shielded, or completely shielded during the second placement time and under the second relevant parameter conditions. The method as claimed in claim 1, wherein: the relevant parameter condition of step (S2) includes a system-related parameter and an environment-related parameter. As described in claim 3, the system-related parameters include any of the following data, or a combination thereof: the voltage of the solar panel, the current of the solar panel, the temperature of the solar panel, the total irradiance of the solar panel, the voltage of the solar battery, the current of the solar battery, the temperature of the solar battery, the total irradiance of the solar battery, a horizontal angle of the solar panel relative to the initial position, and a pitch angle of the solar panel relative to the initial position. The method as described in claim 3, wherein the environment-related parameters include any of the following data, or a combination thereof: the temperature of the environment surrounding the solar panel, the relative humidity of the environment surrounding the solar panel, the amount of sunlight at the solar panel installation site throughout the day, the sunlight intensity at the solar panel installation site, the wind speed at the solar panel installation site, the wind intensity at the solar panel installation site, and the air quality index at the solar panel installation site. As described in claim 1, the mathematical equation of the recursive fuzzy neural network is:

, where m _ij , σ _ij,n ,

,

is an adjustable control parameter, σ _ij,L is the width parameter on the left side of the attribution function with the center _{point at mij} , and σ _ij,R is the width parameter on the right side of the attribution function with the center _{point at mij} . As described in claim 1, the threshold value A is 30 to 80% of the maximum power generated by the solar panel when the photosensitive element is not shielded. As described in claim 1, the photosensitive elements are arranged at intervals on the same side of the solar panel and close to the outer edge of the solar panel, and when the number of the photosensitive elements is Q, the angle formed by the line connecting the center of gravity of the solar panel and the two adjacent photosensitive elements is 360°/Q. As described in claim 1, in step (S8), the solar panel is rotated by an azimuth angle of a horizontal angle unit; the solar panel is rotated by a pitch angle of a vertical angle unit; or the solar panel is rotated by an azimuth angle of a horizontal angle unit and a pitch angle of a vertical angle unit respectively. The method as described in claim 9, wherein the horizontal angle unit or the vertical angle unit is 1 to 20°.

Images