A solar photovoltaic module automatic adjustment system and method for renewable energy power generation

Abstract

The present invention discloses a solar photovoltaic module automatic adjustment system and method for renewable energy power generation, relating to the field of intelligent photovoltaic control technology. The system comprises the following steps: deploying diversified sensors to collect environmental data, preprocessing and extracting features from the environmental data; constructing a photovoltaic performance prediction model based on the processed environmental data set to predict future lighting conditions and optimal module adjustment strategies; generating an adaptive adjustment strategy based on the prediction results; having flexible photovoltaic modules perform preliminary adjustments to the photovoltaic modules in response to instructions from a central processing unit; collecting actual output data from the adjusted photovoltaic modules to evaluate the adjustment effect; and feeding the evaluation results back to the central processing unit to further adjust the photovoltaic modules. The present invention intelligently analyzes environmental data to predict illumination, dynamically optimizes module angles, improves power generation efficiency, provides real-time feedback, enhances system performance, and promotes both renewable energy economic and environmental benefits.

Description

Technical Field

[0001] The present invention relates to the field of intelligent photovoltaic control technology, and in particular to an automatic adjustment system and method for solar photovoltaic components used for renewable energy power generation. Background Art

[0002] With the growing global demand for renewable energy, photovoltaic technology has played a vital role in the transformation of the energy structure. Early solar photovoltaic systems mainly relied on photovoltaic panels installed at fixed angles. Although this design is simple, the photoelectric conversion efficiency is limited by the changes in solar radiation intensity in different seasons and times. In recent years, with the maturity of automation technology and intelligent control systems, the technology of automatically adjusting photovoltaic modules has gradually become a research hotspot. It aims to maximize energy capture efficiency by dynamically adjusting the direction and angle of photovoltaic panels, thereby improving overall power output and economic benefits.

[0003] Although methods for automatically adjusting photovoltaic panels have made significant progress, some challenges and limitations still exist. First, traditional photovoltaic systems mostly rely on a single type of sensor, which makes the system unable to fully perceive environmental factors, which in turn affects the accuracy of prediction models and the refinement of adjustment strategies. Second, most systems use simple mathematical models to predict lighting conditions and panel performance, and lack the ability to deeply mine and extract features from multi-dimensional environmental data, which limits prediction accuracy and adaptability to complex weather patterns. In addition, existing technologies lack sufficient consideration of the physical characteristics of photovoltaic panels in the generation and execution of adjustment strategies, resulting in poor results in extreme weather. Finally, traditional systems often ignore the impact of dynamic changes in panel shape on energy capture and fail to effectively integrate the environmental response matrix and eigenvector, thereby reducing the overall optimization potential and adaptability of the system. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a solar photovoltaic module automatic adjustment system and method for new energy power generation to solve the problems of the existing automatic adjustment photovoltaic module system in environmental perception, prediction accuracy, extreme condition adaptability and overall performance optimization.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for automatically adjusting a solar photovoltaic assembly for renewable energy power generation, which includes deploying a plurality of sensors to collect environmental data, and performing preprocessing and feature extraction on the environmental data;

[0008] A photovoltaic performance prediction model is constructed based on the processed environmental data set to predict future lighting conditions and the optimal component adjustment strategy. Based on the prediction results, an adaptive adjustment strategy is generated. The flexible photovoltaic components preliminarily adjust the photovoltaic components according to the instructions issued by the central processing unit. The actual output data of the adjusted photovoltaic components is collected to evaluate the adjustment effect. The evaluation results are fed back to the central processing unit to adjust the photovoltaic components again.

[0009] As a preferred solution of the method for automatically adjusting solar photovoltaic modules for renewable energy power generation according to the present invention, the steps of deploying diversified sensors to collect environmental data, preprocessing the environmental data and extracting features are as follows:

[0010] Deploy light intensity sensors, temperature sensors, humidity sensors, wind speed sensors, and wind direction sensors at key locations around photovoltaic modules;

[0011] The data is transmitted to the central processing server in real time through the wireless module. After the central processing unit receives the raw data transmitted by the sensor network, it first performs data cleaning to eliminate outliers and noise interference, uses the 3σ principle based on statistics to determine the outlier limit, and applies wavelet transform to extract features;

[0012] Morlet wavelet is selected as the basis function, and the multi-scale features of the signal are extracted through wavelet transform;

[0013] Identify periodic patterns in temperature fluctuations through Fourier transforms;

[0014] Based on the extracted features, a feature vector V is constructed.

[0015] The photovoltaic performance prediction model is constructed based on the processed environmental data set to predict future lighting conditions and optimal component adjustment strategies. The specific steps are as follows:

[0016] Pair the feature vector V with the output power P of the photovoltaic module to form the data set D required for supervised learning;

[0017] Assuming that the future trends of light intensity, temperature, humidity, wind speed, and wind direction follow the patterns of historical meteorological data, the photovoltaic performance prediction model is used to predict the output power of photovoltaic modules under future light conditions.

[0018] Then, the dataset D is divided into training set D tr and the test set D te , in the test set D te The model performance is evaluated on the ,root mean square error is used as the evaluation metric;

[0019] Based on the predicted future photovoltaic module output power R, a genetic algorithm is used to optimize the tilt angle and azimuth angle of the module by simulating the natural selection and genetic mechanism in the biological evolution process.

[0020] The adaptive adjustment strategy is generated based on the prediction results. The specific steps are as follows:

[0021] A generalized linear model is introduced to integrate the eigenvector V and the environmental response matrix E to establish a sensitivity model for the output power P of photovoltaic modules to changes in environmental conditions. The environmental response matrix E is composed of the power change rate of photovoltaic modules under different environmental conditions in historical data.

[0022] The Lagrange multiplier method is used to optimize the angle of the photovoltaic module, construct the Lagrange function L, and add physical constraints to the photovoltaic module.

[0023] The flexible photovoltaic module preliminarily adjusts the photovoltaic module according to the instruction issued by the central processing unit. The specific steps are as follows:

[0024] Define the shape change function f S (S) Calculate the complex effects of shape changes on power output;

[0025] Where a is the amplitude of the control function, b is the steepness of the control function, and c is the offset;

[0026] Define the angle change function f A (θ, φ) calculates the complex effect of angle transformation on power output;

[0027] Where d is the amplitude coefficient of the sine function, e is the coefficient of θ, f is the coefficient multiplied by the cos(gφ) term, g is the coefficient of φ, and h is a constant term;

[0028] The shape change function f S (S) and angle adjustment function f A (θ, φ) is used as a correction factor and integrated into the power prediction model. n Combined to form the predicted power output P pr，i .

[0029] The specific steps for collecting the actual output data of the adjusted photovoltaic modules and evaluating the adjustment effect are as follows:

[0030] By integrating the environmental response matrix E and the eigenvector V, and considering the physical limitations of the PV modules, an evaluation function Q is constructed based on the output power P of the PV modules, the module change state S, and the module angle (g, φ).

[0031] As a preferred solution of the method for automatically adjusting solar photovoltaic modules for renewable energy power generation according to the present invention, wherein the evaluation result is fed back to the central processing unit to adjust the photovoltaic modules again, the specific steps are as follows:

[0032] A performance evaluation standard η is defined based on the system's design parameters and historical operating data. The system then monitors and calculates a parameter Q, reflecting current performance, in real time. This parameter is then compared with the preset evaluation standard η. When Q < η, the system's current regulation strategy and operating status are within acceptable limits, indicating good system performance and no immediate intervention is required. When Q ≥ η, system performance is deviating from expectations, with declining efficiency and other anomalies, triggering further analysis and response.

[0033] Once it is detected that the system Q≥η, the system will feed this information back to the central processing unit. After receiving the feedback, the central processing unit will start the optimization algorithm to analyze the reasons for the performance deviation. Based on the analysis results, the central processing unit will automatically adjust the angle and shape of the photovoltaic module.

[0034] As a preferred solution of the automatic adjustment method of solar photovoltaic components for renewable energy power generation according to the present invention, wherein:

[0035] The photovoltaic assembly includes a base, a support column, a support seat, a support frame, a mounting frame and a solar panel, wherein the support column is vertically and fixedly mounted on the upper part of the base, the support seat is fixedly mounted on the upper end of the support column, and a vertically arranged rotating shaft is rotatably mounted inside the support seat, a worm gear is fixedly mounted on the rotating shaft, and the worm gear is located inside the support seat, the support frame is vertically and rotatably mounted on the top of the support seat, and the bottom end of the support frame is fixedly connected to the upper end of the rotating shaft, the mounting frame is hinged on the top of the support frame, and the solar panel is fixedly mounted on the upper part of the mounting frame, wherein:

[0036] A motor is fixedly mounted on the outside of the support base through a motor base, a worm is fixedly mounted on the output shaft of the motor, a portion of the worm extends into the interior of the support base and meshes with the worm gear;

[0037] An articulated seat 1 is fixedly mounted on the support frame, a connecting seat 1 is hingedly mounted on the articulated seat 1, an articulated seat 2 is fixedly mounted on the mounting frame, a connecting seat 2 is hingedly mounted on the articulated seat 2, an electric push rod is fixedly mounted between the connecting seat 2 and the connecting seat 1, and the electric push rod and the motor are both controlled by the central processing unit.

[0038] In a second aspect, the present invention provides a solar photovoltaic component automatic adjustment system for renewable energy power generation, comprising an environment collection and preprocessing module, a photovoltaic performance prediction module, a strategy generation module, a component execution and feedback module, and an evaluation and optimization module; the environment collection and preprocessing module is used to collect environmental data through various sensors and clean and preprocess these data; the photovoltaic performance prediction module is used to predict the power generation performance of the photovoltaic system based on the processed environmental data; the strategy generation module is used to generate the optimal energy management and scheduling strategy based on the photovoltaic performance prediction and user needs; the component execution and feedback module is used to execute the operation plan formulated by the strategy generation module, monitor the execution effect in real time, and feed the results back to the system for dynamic adjustment; the evaluation and optimization module is used to evaluate the operating efficiency and performance of the entire system, identify bottlenecks and propose improvement measures, and continuously optimize the system performance to achieve the best state;

[0039] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for automatic adjustment of solar photovoltaic components for new energy power generation as described in the first aspect of the present invention is implemented.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for automatic adjustment of solar photovoltaic components for renewable energy power generation as described in the first aspect of the present invention.

[0041] The beneficial effects of the present invention are as follows: the present invention is an automatic adjustment method and system for solar photovoltaic components for renewable energy power generation. Its core value lies in achieving the optimization of photovoltaic component performance through intelligent means, and collecting environmental data in real time by deploying diversified sensors, and performing preprocessing and feature extraction to provide accurate data for subsequent predictions. Secondly, the processed data is used to build a prediction model to proactively predict lighting conditions and formulate optimal component adjustment strategies. Then, an adaptive adjustment strategy is generated based on the prediction results to dynamically adjust the photovoltaic components to maximize energy capture efficiency. In addition, the system also has a real-time evaluation and feedback mechanism to ensure the effectiveness of the adjustment strategy and continuous optimization of the system. The present invention significantly improves the power generation efficiency of photovoltaic components and the intelligent management level of the system, bringing significant economic benefits and environmental protection contributions to the field of renewable energy power generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is a flow chart of the automatic adjustment method of solar photovoltaic components for renewable energy power generation in Example 1.

[0044] Figure 2 This is a flow chart of the automatic adjustment system for solar photovoltaic components used for renewable energy power generation in Example 1;

[0045] Figure 3 Schematic diagram of the structure of the photovoltaic module in Example 1;

[0046] Figure 4 A schematic diagram of the structure of the photovoltaic module in Example 1 from another perspective Figure 1 ;

[0047] Figure 5 for Figure 4 Schematic diagram of the enlarged structure at A in the middle;

[0048] Figure 6 A schematic diagram of the structure of the photovoltaic module in Example 1 from another perspective Figure 2 ;

[0049] Figure 7 for Figure 6 Schematic diagram of the enlarged structure at point B in the middle. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0053] Example 1, reference Figure 1, which is the first embodiment of the present invention, provides a method for automatically adjusting a solar photovoltaic assembly for renewable energy power generation, comprising the following steps:

[0054] S1. Deploy diversified sensors to collect environmental data and perform preprocessing and feature extraction on the environmental data.

[0055] Furthermore, light intensity sensors, temperature sensors, humidity sensors, wind speed sensors, and wind direction sensors are deployed at key locations around the photovoltaic panels. High-precision, low-power sensor models, such as the BH1750 light intensity sensor, the DHT22 temperature and humidity sensor, and the RS485 wind speed sensor, are selected to ensure data quality and system stability.

[0056] The data is transmitted to the central processing server in real time through the wireless module. After the central processing unit receives the raw data transmitted by the sensor network, it first performs data cleaning to eliminate outliers and noise interference. The outlier limit is determined by the 3σ principle based on statistics. The expression is:

[0057]

[0058] Among them, Z i is the Z-socre of the i-th data point, x i is the original data point, x' is the sample mean, s is the sample standard deviation, and the threshold is set to 3. That is, when |Zi|>3, the data point is marked as an outlier. The outlier correction adopts the cubic spline interpolation method to ensure a smooth transition of the data curve.

[0059] Wavelet transform is applied to extract features to identify the local characteristics of the signal. The expression is:

[0060]

[0061] Among them, W(a, b) is the wavelet coefficient, x(t) is the original analog signal, ψ * is the conjugate of the wavelet basis function,

[0062] a is the scale parameter, b is the translation parameter, and t is a continuous real number;

[0063] Morlet wavelet is selected as the basis function because it has good time-frequency resolution and is suitable for time-frequency analysis of signals. Through wavelet transform, multi-scale features of signals, such as trend, periodicity and transient features, can be extracted.

[0064] The periodic pattern of temperature fluctuations is identified by Fourier transform, which is expressed as:

[0065]

[0066] Where F(k) is the spectral coefficient, x(n) is the original digital signal, N is the signal length, n is the sampling point index in the time domain, and k is the index in the frequency domain;

[0067] Based on the extracted features, construct the feature vector V, which is expressed as:

[0068] V=[W lt ,F tp ,h,v,d];

[0069] Among them, W lt is the characteristic of light intensity change trend, F tp is the temperature fluctuation pattern characteristic, h is the humidity level, v is the wind speed, and d is the wind direction code.

[0070] S2. Build a photovoltaic performance prediction model based on the processed environmental data set to predict future lighting conditions and optimal component adjustment strategies.

[0071] Furthermore, the feature vector V is paired with the output power P of the photovoltaic module to form the data set D required for supervised learning, which is expressed as:

[0072]

[0073] Among them, V i is the feature vector of the i-th observation, P i is the corresponding PV module output power, N is the total number of observations;

[0074] Assuming that the future trends of light intensity, temperature, humidity, wind speed, and wind direction follow the laws of historical meteorological data, the photovoltaic performance prediction model is used to predict the output power of photovoltaic modules under future lighting conditions. The expression is:

[0075]

[0076] in, is the predicted output power under future lighting conditions, V f It represents the feature vector of future lighting conditions;

[0077] Subsequently, the dataset D is divided into a training set D and a training set D according to the ratio of 70% and 30%. tr and the test set D te , to ensure the effectiveness of model training and performance evaluation, on the test set D te The model performance is evaluated on the y-axis, and the root mean square error is used as the evaluation indicator. The expression is:

[0078]

[0079] Based on the predicted future photovoltaic module output power R, a genetic algorithm is used to optimize the tilt angle and azimuth angle of the module to maximize the energy capture efficiency. The genetic algorithm simulates the natural selection and genetic mechanism in the biological evolution process to find the global optimal solution and define the fitness function, which is expressed as:

[0080]

[0081] Where θ is the tilt angle of the photovoltaic module, and φ is the azimuth angle of the photovoltaic module.

[0082] It should also be noted that the range of RMSE is [0, +∞), and a smaller RMSE indicates that the model prediction is more accurate. The range of F(θ, φ) depends on the theoretical maximum output power of the PV module. A larger value means a higher energy capture efficiency. The range of F(θ, φ) also depends on the theoretical maximum output power of the PV module. The maximum value represents the optimal module adjustment strategy.

[0083] S3. Generate an adaptive adjustment strategy based on the prediction results.

[0084] Furthermore, a generalized linear model is introduced to integrate the eigenvector V and the environmental response matrix E to establish a sensitivity model of the PV module output power P to changes in environmental conditions. The environmental response matrix E is composed of the power change rate of the PV module under different environmental conditions in the historical data, and the expression is:

[0085] P(θ, φ, S) = β0 + β V V+β E E+β S S+β θ θ+β φ φ+∈;

[0086] Where β0 is the tilt angle coefficient, β φ is the azimuth coefficient, β V is the coefficient vector of the eigenvector V, β E is the coefficient vector of the eigenvector E, ∈ is the error term, β s is the shape change coefficient, S is a variable that represents the shape change state of the PV module, reflecting the degree to which the module changes its geometric shape in response to external instructions or environmental factors;

[0087] The Lagrange multiplier method is used to optimize the angle of the photovoltaic module, construct the Lagrange function L, and add physical restrictions to the photovoltaic module (such as the maximum tilt angle and azimuth angle range). The expression is:

[0088] L(θ,φ,λ)=P(θ,φ)-λg(θ,φ);

[0089] Where g(θ, φ) is the constraint function, λ is the Lagrange multiplier, and P(θ, φ) is the power prediction model. The optimal solution is found by solving the point where the partial derivatives of L with respect to θ, φ, and λ are equal to 0.

[0090] It should also be noted that when implementing this adaptive adjustment strategy based on a generalized linear model, it is necessary not only to monitor environmental parameters in real time, but also to take into account the physical limitations and long-term durability of photovoltaic modules. This means that although the pursuit of maximum power output is the main goal, it is necessary to dynamically adjust the angle of the module while avoiding exceeding its mechanical design limit to prevent physical damage or shortening its service life. In addition, due to the unpredictability of weather and other environmental conditions, the model should be robust and flexible enough to respond quickly and appropriately in emergencies. Finally, in order to ensure the economy and sustainability of the system, it is also necessary to evaluate and optimize the energy conversion efficiency and energy storage strategy in the energy management system to cope with fluctuations in grid demand.

[0091] S4. The flexible photovoltaic module preliminarily adjusts the photovoltaic module according to the instruction issued by the central processing unit.

[0092] Furthermore, we define the shape change function f S (S) Calculate the complex impact of shape change on power output and ensure a smooth transition of shape change. The expression is:

[0093] fS(S)=ath(bS)+c;

[0094] Where a is the amplitude of the control function, b is the steepness of the control function, and c is the offset;

[0095] Define the angle change function f A (θ, φ) calculates the complex effect of angle transformation on power output, and the expression is:

[0096] f A (θ,φ)=d sin(eθ)+f cos(gφ)+h;

[0097] Where d is the amplitude coefficient of the sine function, e is the coefficient of θ, f is the coefficient multiplied by the cos(gφ) term, g is the coefficient of φ, and h is a constant term;

[0098] The shape change function f S (S) and angle adjustment function f A (θ, φ) is used as a correction factor and integrated into the power prediction model. n Combined to form the predicted power output P pr，i , the expression is:

[0099] Ppr，i =P n ×f S (S)×f A (θ, φ);

[0100] Among them, P n is the power output unaffected by shape change and angle, p pr，i It is the predicted output power of the PV module at the i-th observation time after the shape and angle are adjusted.

[0101] It should also be noted that the adaptive adjustment of flexible photovoltaic modules not only relies on the instructions of the central processing unit, but also deeply integrates multiple links such as environmental monitoring, data preprocessing, feature extraction, performance prediction and strategy generation. This comprehensive system ensures that photovoltaic modules can flexibly adjust their shape and angle according to real-time environmental changes such as light intensity, temperature, humidity, wind speed and direction to pursue the optimal energy capture efficiency. During the adjustment process, the shape change function f S (S) and angle adjustment function f A The careful design of (θ, φ) takes into account both the maximization of power output and the physical limitations and mechanical life of the components, avoiding the damage that may be caused by over-adjustment. In addition, by closely integrating these functions with predictive models, the system can predict the power output at a specific observation moment after adjustment, thereby achieving forward-looking adaptive control.

[0102] S5. Collect the actual output data of the adjusted PV modules and evaluate the adjustment effect. The specific steps are as follows:

[0103] Integrating the environmental response matrix E and the eigenvector V, while considering the physical limitations of the PV modules, an evaluation function Q is constructed based on the output power P of the PV modules, the module change state S, and the module angle (g, φ). The expression is:

[0104]

[0105] Among them, g j (θ, φ) is the physical constraint function of the PV module angle, and M is the dimension of the angle constraint.

[0106] It should also be noted that η is not only a static comparison point, but also one of the key parameters that are dynamically adjusted during system performance monitoring and optimization. As the system ages, technology improves, or external environmental conditions change, the value of η may also need to be adjusted accordingly to maintain its effectiveness as a performance evaluation benchmark.

[0107] S6. Feedback the evaluation results to the central processing unit to adjust the photovoltaic components again.

[0108] Furthermore, a performance evaluation standard η is defined based on the system's design parameters and historical operating data. Subsequently, the system monitors and calculates a parameter Q reflecting current performance in real time. This parameter Q is compared with the preset evaluation standard η. When Q < η, the system's current regulation strategy and operating status are within an acceptable range, indicating good system performance and no need for immediate intervention. When Q ≥ η, system performance begins to deviate from expectations, with declining efficiency and other anomalies, triggering further analysis and response.

[0109] Once it is detected that the coefficient Q ≥ η, the system will feed this information back to the central processing unit. After receiving the feedback, the central processing unit will start the optimization algorithm to analyze the reasons for the performance deviation, including but not limited to improper component angle, shape changes or changes in environmental factors. Based on the analysis results, the central processing unit automatically adjusts the angle and shape of the photovoltaic module, such as adjusting the tilt angle and azimuth angle of the module through a motor, or fine-tuning the shape of the module (in flexible modules) to optimize the sunlight incident angle, improve lighting efficiency, and ensure that the system returns to an efficient operating state.

[0110] It should also be noted that the setting of the performance evaluation standard η needs to be based on historical data, theoretical models and actual application goals. It is a dynamic threshold that can be adjusted as external conditions change. In winter when the sunlight is weak, η may be lowered to make the system pay more attention to stability and durability. At the same time, the calculation of η should also consider multiple factors such as economic costs, maintenance needs and environmental impacts to ensure that the photovoltaic system maintains an efficient and environmentally friendly operating state throughout its life cycle. In addition, when the central processing unit receives feedback that exceeds the η threshold, it must not only adjust the angle and shape of the photovoltaic module in real time, but also analyze the root cause of the performance degradation, which may be obstruction, pollution, failure or design limitations, and then take targeted optimization measures or trigger maintenance processes to restore and improve system performance.

[0111] Specifically, the photovoltaic assembly provided in this embodiment includes a base 1, a support column 2, a support base 6, a support frame 4, a mounting frame 5 and a solar panel 3, the support column 2 is vertically and fixedly mounted on the upper part of the base 1, the support base 6 is fixedly mounted on the upper end of the support column 2, and a vertically arranged rotating shaft is rotatably mounted inside the support base 6, a worm gear is fixedly mounted on the rotating shaft, and the worm gear is located inside the support base 6, the support frame 4 is vertically and rotatably mounted on the top of the support base 6, and the bottom end of the support frame 4 is fixedly connected to the upper end of the rotating shaft, the mounting frame 5 is hinged at the top of the support frame 4, and the solar panel 3 is fixedly mounted on the upper part of the mounting frame 5, wherein:

[0112] The outside of the support base 6 is fixedly mounted with a motor 7 through a motor base 8, and the output shaft of the motor 7 is fixedly mounted with a worm, a part of the worm extends into the interior of the support base 6 and meshes with the worm gear;

[0113] An articulated seat 401 is fixedly installed on the support frame 4, a connecting seat 901 is hinged on the articulated seat 401, an articulated seat 2 501 is fixedly installed on the mounting frame 5, a connecting seat 2 902 is hinged on the articulated seat 2 501, an electric push rod 9 is fixedly installed between the connecting seat 2 902 and the connecting seat 1 901, and the electric push rod 9 and the motor 7 are both controlled by the central processing unit.

[0114] The photovoltaic assembly adopting the above technical solution is mainly composed of a base 1, a support column 2, a support seat 6, a support frame 4, a mounting frame 5, a solar panel 3, a motor 7, a worm, a worm gear and an electric push rod 9. Among them, the central processing unit can control the motor 7 to automatically adjust the direction of the solar panel 3. At the same time, the central processing unit can control the electric push rod 9 to automatically adjust the inclination angle of the solar panel 3, so that the solar panel 3 can automatically track the movement trajectory of the sun, which can maximize the power generation efficiency.

[0115] This embodiment also provides a solar photovoltaic component automatic adjustment system for renewable energy power generation, including: an environment collection and preprocessing module, a photovoltaic performance prediction module, a strategy generation module, a component execution and feedback module, and an evaluation and optimization module; the environment collection and preprocessing module is used to collect environmental data through various sensors, and clean and preprocess these data; the photovoltaic performance prediction module is used to process the environmental data and predict the power generation performance of the photovoltaic system; the strategy generation module is used to generate the optimal energy management and scheduling strategy based on the photovoltaic performance prediction and user needs; the component execution and feedback module is used to execute the operation plan formulated by the strategy generation module, and monitor the execution effect in real time, and feed the results back to the system for dynamic adjustment; the evaluation and optimization module is used to evaluate the operating efficiency and performance of the entire system, identify bottlenecks and propose improvement measures, and continuously optimize the system performance to achieve the best state.

[0116] This embodiment also provides a computer device, which is suitable for the case of an automatic adjustment method of solar photovoltaic components for renewable energy power generation, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the automatic adjustment method of solar photovoltaic components for renewable energy power generation proposed in the above embodiment.

[0117] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0118] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the automatic adjustment method for solar photovoltaic components for renewable energy power generation proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0119] In summary, the present invention is as follows: the present invention relates to an automatic adjustment method and system for solar photovoltaic components for renewable energy power generation, aiming to improve the power generation efficiency of photovoltaic components through automated means. First, the system collects environmental data by deploying diversified sensors, and performs preprocessing and feature extraction to ensure the accuracy of the data. Secondly, based on the processed data, a photovoltaic performance prediction model is constructed to predict future lighting conditions, thereby generating the optimal component adjustment strategy. Then, the photovoltaic components are adaptively adjusted according to the instructions of the central processing unit, including preliminary adjustment of the angle and shape of the photovoltaic components to adapt to environmental changes. The system also collects the actual output data of the adjusted photovoltaic components, evaluates the adjustment effect, and feeds back the evaluation results to the central processing unit for further optimization and adjustment.

[0120] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of the automatic adjustment method of solar photovoltaic components for renewable energy power generation are provided.

[0121] Two groups of identical photovoltaic modules were used: one group adopted the technical solution of the present invention, and the other group adopted a traditional fixed-angle photovoltaic system as a control. Each group of photovoltaic modules collected light intensity, temperature, humidity, and wind speed respectively.

[0122] First, the sensor deployment and data collection phase involves installing high-precision light intensity sensors BH1750, temperature and humidity sensors DHT22, and wind speed sensors RS485 around the two groups of photovoltaic panels, and sending real-time data to the central processing server via wireless modules.

[0123] Secondly, in the data processing and feature extraction stage, preprocessing operations are performed on the collected raw data to construct a comprehensive feature vector V, which contains the changing trend of light intensity, temperature fluctuation pattern, humidity level, wind speed and wind direction encoding.

[0124] Next, in the performance prediction and adjustment strategy generation step, a supervised learning model is trained based on the feature vector V and the actual output power P to predict the possible output power of the photovoltaic module under different future lighting conditions. The root mean square error (RMSE) is used to evaluate the accuracy of the prediction model on the test set.

[0125] Finally, in the adaptive adjustment and effect evaluation stage, the corresponding adaptive adjustment strategy is generated according to the prediction results, and the angle and shape of the photovoltaic modules are dynamically adjusted. The actual effect of the adjustment strategy is evaluated by continuously monitoring the adjusted output power and calculating the performance evaluation standard η.

[0126] The details are shown in Table 1:

[0127] Table 1 Experimental record table

[0128]

[0129]

[0130] Analysis of the data in the table above shows that, under identical environmental conditions, the photovoltaic system of the present invention consistently outperforms conventional photovoltaic systems in terms of average daily output power. For example, under conditions of 45,000 lux, 25°C temperature, 60% humidity, and 3 m / s wind speed, the average daily output power of the photovoltaic system of the present invention is 5.2 kWh, while the conventional photovoltaic system only achieves 4.8 kWh. Similar trends are also observed in other environments. For example, under conditions of lower light intensity (5,000 lux), lower temperature (15°C), and higher humidity (80%), the output power of the photovoltaic system of the present invention remains at 3.0 kWh, significantly higher than the 2.7 kWh of the conventional system.

[0131] The photovoltaic system of this invention significantly improves the energy capture efficiency of photovoltaic modules through an adaptive regulation strategy, especially under unstable lighting conditions. Compared with traditional photovoltaic systems, it demonstrates significant innovation and advantages. This performance improvement is reflected not only in higher average daily output power, but also in improved system stability and longer module lifespan, providing a more advanced and practical technical solution for the field of solar power generation.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for automatically adjusting solar photovoltaic components for renewable energy power generation, characterized by: include, S1. Deploy diversified sensors to collect environmental data, preprocess and extract features from the environmental data; construct a feature vector V based on the extracted features; Deploy light intensity sensors, temperature sensors, humidity sensors, wind speed sensors, and wind direction sensors at key locations around photovoltaic modules; S2. Build a photovoltaic performance prediction model based on the processed environmental data set to predict future lighting conditions and optimal module adjustment strategies; S3. Generate an adaptive adjustment strategy based on the prediction results; S4, the flexible photovoltaic module preliminarily adjusts the photovoltaic module according to the instruction issued by the central processing unit; S5. Collect the actual output data of the adjusted PV modules and evaluate the adjustment effect; S6. Feedback the evaluation results to the central processing unit to adjust the photovoltaic components again; In S3, a generalized linear model is introduced to integrate the eigenvector V and the environmental response matrix E to establish a sensitivity model of the PV module output power P to changes in environmental conditions. The environmental response matrix E is composed of the power change rate of the PV module under different environmental conditions in the historical data, and the expression is: ； in, is the tilt angle coefficient, is the azimuth coefficient, is the coefficient vector of the eigenvector V, is the coefficient vector of the environmental response matrix E, is the error term, is the shape change coefficient, S is a variable that represents the shape change state of the PV module, reflecting the degree to which the module changes its geometric shape in response to external instructions or environmental factors; The Lagrange multiplier method is used to optimize the angle of the photovoltaic module, construct the Lagrange function L, and add physical constraints to the photovoltaic module. The expression is: ； in, is the constraint function, is the Lagrange multiplier, It is a power prediction model, solving L with respect to θ, and The point where the partial derivative of is equal to 0 to find the optimal solution; In S4, define the shape change function Calculate the complex effects of shape changes on power output and ensure smooth transitions of shape changes. Define the angle change function Calculate the complex effects of angle transformations on power output; Shape change function and angle change function As a correction factor, it is integrated into the power prediction model and combined with the reference power Pn through mathematical operations to form the predicted power output. ; In S5, the environmental response matrix E and the eigenvector V are integrated, and the physical limitations of the photovoltaic modules are considered. Based on the output power P of the photovoltaic modules, the variable S of the photovoltaic module shape change state and the angle of the module , construct an evaluation function Q.

2. The automatic adjustment method for solar photovoltaic components for renewable energy power generation according to claim 1, characterized in that: The deployment of diversified sensors to collect environmental data, preprocess the environmental data and extract features, specifically involves the following steps: Deploy light intensity sensors, temperature sensors, humidity sensors, wind speed sensors, and wind direction sensors at key locations around photovoltaic modules; The data is transmitted to the central processing server in real time through the wireless module. After the central processing unit receives the raw data transmitted by the sensor network, it first performs data cleaning to eliminate abnormal values ​​and noise interference, and uses a statistically based The outlier boundaries were determined based on the principle, and wavelet transform was applied for feature extraction; Morlet wavelet is selected as the basis function, and the multi-scale features of the signal are extracted through wavelet transform; The periodic pattern of temperature fluctuations is identified through Fourier transform.

3. The automatic adjustment method for solar photovoltaic components for renewable energy power generation according to claim 1, characterized in that: Feedback of the evaluation results to the central processing unit to adjust the photovoltaic components again is as follows: A performance evaluation standard η is defined based on the system's design parameters and historical operating data. Subsequently, the system monitors and calculates a parameter Z that reflects the current performance in real time, and compares the real-time calculated performance parameter Z with the preset evaluation standard η. When , it means that the current adjustment strategy and operating status of the system are within the acceptable range, the system performs well and no immediate intervention is required. When the system performance deviates from expectations, there are efficiency drops and other anomalies, which require further analysis and response. Once the system is detected The system feeds this information back to the central processing unit. After receiving the feedback, the central processing unit starts the optimization algorithm to analyze the reasons for the performance deviation. Based on the analysis results, the central processing unit automatically adjusts the angle and shape of the photovoltaic module.

4. A solar photovoltaic module automatic adjustment system for renewable energy power generation, based on the solar photovoltaic module automatic adjustment method for renewable energy power generation according to any one of claims 1 to 3, characterized in that: Including, environmental collection and preprocessing module, photovoltaic performance prediction module, strategy generation module, component execution and feedback module and evaluation and optimization module; The environmental collection and preprocessing module is used to collect environmental data through various sensors and clean and preprocess the data; The photovoltaic performance prediction module is used to process environmental data and predict the power generation performance of the photovoltaic system; The strategy generation module is used to generate the optimal energy management and scheduling strategy based on PV performance prediction and user needs; The component execution and feedback module is used to execute the operation plan formulated by the strategy generation module, monitor the execution effect in real time, and feed the results back to the system for dynamic adjustment; The evaluation and optimization module is used to evaluate the operating efficiency and performance of the entire system, identify bottlenecks and propose improvement measures, and continuously optimize system performance to achieve the best state.

Images