Sunlight irradiation angle tracking method and system for energy storage power generation

Abstract

The invention discloses a sunlight irradiation angle tracking method and system for energy storage power generation, and relates to the technical field of energy storage power generation, and the method comprises the steps: obtaining the real-time environment data of a photovoltaic system, and extracting the environment feature data; analyzing and processing the environmental characteristic data by using a performance analysis algorithm, and identifying key factors influencing the power generation efficiency; and based on the key factors, establishing a tracking control model, dynamically adjusting the angle of the photovoltaic panel by using the tracking control model, and optimizing a power generation strategy. Key factors influencing the power generation efficiency are identified through an efficiency analysis algorithm, so that an accurate angle tracking control model is established, the model can dynamically adjust the angle of the photovoltaic panel according to the illumination change, the photovoltaic panel is always in the optimal receiving state, the solar energy utilization efficiency is effectively improved, and the power generation efficiency is improved. The response sensitivity and the control precision of the photovoltaic power generation system are improved, and the energy storage power generation strategy is optimized, so that the stability and the energy conversion efficiency of the whole system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage and power generation, and in particular to a method and system for tracking sunlight angle for energy storage and power generation. Background Art

[0002] Solar tracking technology has important applications in the development of new energy and energy conservation. Currently, the main challenge facing photovoltaic power generation systems is how to accurately track the changing angle of the sun's rays throughout the year and at different times of the day. Changes in the sun's position are affected by multiple factors, including season, time of day, and geographic location, placing strict demands on the efficient collection of solar energy. To achieve more efficient energy collection, an intelligent control system adjusts the angle of the photovoltaic panels in real time to ensure that solar radiation is received at the optimal angle at all times. The system uses high-precision sensors to monitor the sun's position, combines them with control algorithms to calculate the optimal angle, and drives actuators to adjust the orientation of the photovoltaic panels. By continuously tracking the sun's trajectory, the system maximizes the conversion rate of solar energy, providing technical support for the sustainable development of green energy.

[0003] Most existing technologies use static or semi-dynamic adjustment methods, which lack deep perception of environmental data and dynamic response mechanisms, and are not convenient for real-time adaptation to changes in solar angles. This leads to insufficient light utilization and a lack of intelligent optimization support for power generation strategies, affecting energy storage efficiency and overall system performance.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention proposes a method and system for tracking the angle of sunlight for energy storage and power generation, which solves the problems proposed in the above background technology that most of the existing methods adopt static or semi-dynamic adjustment methods, lack deep perception and dynamic response mechanism of environmental data, and are not convenient for real-time adaptation to changes in the angle of sunlight, resulting in insufficient light utilization, lack of intelligent optimization support for power generation strategies, and affecting energy storage efficiency and overall system performance.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: According to one aspect of the present invention, a method for tracking sunlight angle for energy storage power generation is provided, comprising: S1. Obtain real-time environmental data of the photovoltaic system and extract environmental characteristic data; S2. Analyze and process environmental characteristic data using an efficiency analysis algorithm to identify key factors affecting power generation efficiency; S2 includes: S23. Based on the key points of the environmental characteristic data, a fitting algorithm is used to fit the path of the environmental characteristic data to obtain a response relationship between the environmental characteristic data and the power generation efficiency; S23 includes: S234. Based on the target path structure, a response function model is established between key points of the environmental characteristic data and power generation efficiency, and based on the response function model, a response relationship between the environmental characteristic data and power generation efficiency is obtained; S3. Based on key factors, a tracking control model is established, and the tracking control model is used to dynamically adjust the angle of the photovoltaic panels to optimize the power generation strategy.

[0007] Furthermore, real-time environmental data of the photovoltaic system is obtained, and environmental characteristic data is extracted, including: S11, initializing the population of real-time environmental data of the photovoltaic system; S12, initializing the acquisition parameters of each environmental data and encoding the environmental data; S13, compressing and decomposing the acquired environmental data using non-negative matrix decomposition to extract potential environmental features; S14. Use the differential evolution algorithm to perform evolutionary updates on the population of real-time environmental data to optimize the extraction process of environmental features; S15. Iteratively perform compression decomposition and evolutionary update until the target environment feature data is extracted.

[0008] Furthermore, before S23, it also includes: S21. Setting initial parameters of the performance analysis algorithm and setting the maximum number of iterations; S22. Calculate the first several key points of the environmental characteristic data on the environmental characteristic data path using the estimation-correction process, and obtain a preliminary trend of power generation efficiency; S23 and later also include: S24, based on the response relationship and the known key points of the environmental characteristic data, predicting the next several environmental characteristic data points on the environmental characteristic data path, and performing error correction on them; S25. Determine whether the maximum number of iterations has been reached. If so, output the prediction result as a key factor affecting power generation efficiency. Otherwise, continue iterating.

[0009] Furthermore, before S234, it also includes: S231, randomly sampling candidate environmental feature data in the environmental feature data space, and searching for key points of its neighborhood historical environmental feature data to form a local environmental feature data path to be fitted; S232: Calculate the fitting error of the new environmental feature data path and compare it with the fitting error of the original environmental feature data path. If the fitting error of the new environmental feature data path is smaller than the fitting error of the original environmental feature data path, perform validity evaluation; otherwise, switch to other candidate environmental feature data for fitting update. S233. If the new environmental feature data path passes the validity evaluation, it is used as the updated target path structure, and the connection relationship of the environmental feature data key points in the original environmental feature data path is replaced to optimize the path structure.

[0010] Furthermore, based on the target path structure, a response function model between key points of environmental characteristic data and power generation efficiency is established, and based on the response function model, the response relationship between environmental characteristic data and power generation efficiency is obtained, including: S2341. Collect response signals of key points of environmental feature data in the target path structure under various environmental conditions and convert them into environmental feature data for modeling; S2342. Perform modal decomposition on the environmental feature data based on a decomposition algorithm to obtain a multi-scale feature sequence of key points of the environmental feature data; S2343. Filter key modal components using correlation analysis, reconstruct a target environment feature dataset, and divide the target environment feature dataset into a training set and a validation set; S2344. Construct a response function model and input a training set for training to obtain a response relationship between environmental characteristic data and power generation efficiency.

[0011] Furthermore, the environmental feature data is modally decomposed based on the decomposition algorithm to obtain a multi-scale feature sequence of key points of the environmental feature data, including: S23421. Initialize the parameters of the decomposition algorithm and set the environmental feature data as a candidate parameter group; S23422. Based on the candidate parameter group, perform modal decomposition on the environmental feature data to extract a plurality of channel modal component sequences; S23423. Calculate the envelope entropy of each modal component sequence according to each modal component sequence; S23424, using the minimum envelope entropy as the fitness function, updating the search state of the environmental feature data, and performing a search for the global optimal candidate parameter group; S23425. Repeat the modal decomposition and search process until the maximum number of iterations is reached, output the optimal candidate parameter group, and based on the optimal candidate parameter group, perform final modal decomposition on the key points of the environmental feature data to extract the multi-scale feature sequence.

[0012] Furthermore, the formula for calculating the envelope entropy of each modal component sequence is: ; Where, B a Indicates the a Envelope entropy of the modal component sequence; A ab Indicates the a The modal component sequence is b The envelope amplitude at the moment; n The number of time points representing the modal component sequence.

[0013] Furthermore, based on key factors, a tracking control model is established, and the tracking control model is used to dynamically adjust the angle of the photovoltaic panels to optimize the power generation strategy, including: S31. Based on key factors, design the state vector of the photovoltaic panel and build a Kalman filter model to dynamically correct the attitude estimation value of the photovoltaic panel; S32, establishing a tracking control model, and calculating a curvature response based on a deviation between the target orientation and the current posture, to generate an angle adjustment decision for the photovoltaic panel surface; S33, using a dynamic adjustment algorithm to optimize the forward path distance and to modify the tracking trajectory and action response in real time based on deviation feedback; S34. Update the angle of the photovoltaic panel in real time through the tracking control model output, and track the sunlight angle in real time to optimize the power generation strategy.

[0014] Furthermore, a dynamic adjustment algorithm is used to optimize the forward path distance and to modify the tracking trajectory and action response in real time based on the deviation feedback, including: S331, initializing the parameters of the dynamic adjustment algorithm, setting the status of all forward-looking path points to inactive, and initializing the error response times to an untriggered state; S332. Calculate the target response intensity and adjustment priority ratio of the path point based on the real-time error feedback, and select the error concentration area as the starting center of the dynamic control; S333: Update the foresight distance for the selected path point, incorporate it into the new response area, and continue to select the path point with the minimum deviation impact ratio from the remaining paths to participate in the control; S334. Repeat the optimization process until all response paths are adjusted, and correct the tracking trajectory and action response in real time based on the deviation feedback.

[0015] According to another aspect of the present invention, a solar radiation angle tracking system for energy storage and power generation is provided, the system comprising: The data acquisition module is used to obtain the real-time environmental data of the photovoltaic system and extract the environmental characteristic data; The factor analysis module is used to analyze and process environmental characteristic data using the efficiency analysis algorithm to identify key factors affecting power generation efficiency; The tracking control module is used to establish a tracking control model based on key factors, and use the tracking control model to dynamically adjust the angle of the photovoltaic panels and optimize the power generation strategy.

[0016] The beneficial effects of the present invention are: 1. This invention acquires real-time environmental data and extracts environmental characteristics, combining it with an efficiency analysis algorithm to identify key factors affecting power generation efficiency, thereby establishing a precise angle tracking control model. This model dynamically adjusts the angle of the photovoltaic panel based on changes in illumination, ensuring it is always in optimal reception, effectively improving solar energy utilization efficiency. This not only improves the responsiveness and control accuracy of the photovoltaic power generation system, but also optimizes the energy storage and power generation strategy, enhancing overall system stability and energy conversion efficiency.

[0017] 2. The present invention uses an efficiency analysis algorithm to perform multi-dimensional modeling and iterative optimization of environmental feature data to achieve accurate identification and prediction of key factors. It uses a dynamic adjustment algorithm to optimize and control the forward-looking path, and corrects the tracking trajectory and action response in real time to ensure that the photovoltaic panels are always at the optimal receiving angle, thereby being able to adapt to changes in the angle of solar radiation, enhance the stability of energy storage and power generation, and thus achieve efficient energy management and utilization.

[0018] 3. The present invention constructs a tracking control model driven by posture estimation and curvature response, combines it with a dynamic adjustment algorithm to optimize the forward path, and uses deviation feedback to correct the tracking trajectory and action response in real time, thereby achieving high-precision dynamic adjustment of the photovoltaic panel angle, thereby being able to adapt to changes in the angle of solar radiation, improve light utilization efficiency, and further optimize the energy storage power generation strategy and operating performance, thereby enhancing the power generation stability and intelligence level of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in 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.

[0020] Figure 1 is a flow chart of a method for tracking sunlight angle for energy storage and power generation according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a solar radiation angle tracking system for energy storage and power generation according to an embodiment of the present invention.

[0021] In the picture: 1. Data acquisition module; 2. Factor analysis module; 3. Tracking control module. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0023] In the description of the present invention, unless otherwise specified, "plurality" means two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0024] According to an embodiment of the present invention, a method and system for tracking sunlight angle for energy storage and power generation are provided.

[0025] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, the method for tracking sunlight angle for energy storage and power generation according to an embodiment of the present invention includes: S1. Obtain real-time environmental data of the photovoltaic system and extract environmental characteristic data; Specifically, real-time environmental data can be obtained through multiple types of environmental sensors (such as light intensity sensors, temperature and humidity sensors, wind speed and direction sensors, atmospheric pressure sensors, etc.) or through weather forecasts.

[0026] Specifically, real-time environmental data includes but is not limited to: lighting information, temperature information, meteorological data, spatiotemporal data, photovoltaic system operation data, etc.

[0027] Specifically, environmental characteristic data include but are not limited to: average sunshine duration, light fluctuation rate, temperature change rate, radiation growth rate, temperature hysteresis effect, sunshine azimuth deviation, component orientation error, light angle projection ratio, etc.

[0028] S2. Analyze and process environmental characteristic data using an efficiency analysis algorithm to identify key factors affecting power generation efficiency; Specifically, key factors include but are not limited to: light-related factors, temperature-related factors, meteorological disturbance factors, photovoltaic system status and load characteristics, time and space factors, etc.

[0029] S3. Based on key factors, a tracking control model is established, and the tracking control model is used to dynamically adjust the angle of the photovoltaic panels to optimize the power generation strategy.

[0030] In this optional embodiment, acquiring real-time environmental data of the photovoltaic system and extracting environmental characteristic data includes: S11, initializing the population of real-time environmental data of the photovoltaic system; S12, initializing the acquisition parameters of each environmental data and encoding the environmental data; S13, compressing and decomposing the acquired environmental data using non-negative matrix decomposition to extract potential environmental features; S14. Use the differential evolution algorithm to perform evolutionary updates on the population of real-time environmental data to optimize the extraction process of environmental features; S15. Iteratively perform compression decomposition and evolutionary update until the target environment feature data is extracted.

[0031] Specifically, the photovoltaic system first collects real-time environmental data from various sensors deployed around the equipment (such as light sensors, thermometers, and hygrometers). Next, the environmental data undergoes preprocessing and encoding conversion. The system then uses algorithms such as non-negative matrix factorization to reduce the data's dimensionality and extract key environmental characteristic parameters. Finally, the feature extraction process is continuously optimized using a differential evolution algorithm, ultimately outputting high-quality environmental characteristic data that can be used for power generation efficiency analysis.

[0032] In this optional embodiment, the environmental characteristic data is analyzed and processed using an efficiency analysis algorithm to identify key factors affecting power generation efficiency, including: S21. Setting initial parameters of the performance analysis algorithm and setting the maximum number of iterations; S22. Calculate the first several key points of the environmental characteristic data on the environmental characteristic data path using the estimation-correction process, and obtain a preliminary trend of power generation efficiency; S23. Based on the key points of the environmental characteristic data, a fitting algorithm is used to fit the path of the environmental characteristic data to obtain a response relationship between the environmental characteristic data and the power generation efficiency; S24, based on the response relationship and the known key points of the environmental characteristic data, predicting the next several environmental characteristic data points on the environmental characteristic data path, and performing error correction on them; S25. Determine whether the maximum number of iterations has been reached. If so, output the prediction result as a key factor affecting power generation efficiency. Otherwise, continue iterating.

[0033] Specifically, first, the initial parameters of the performance analysis algorithm, such as the learning rate and step size, are set, and the maximum number of iterations is set. Secondly, the prediction-correction process is used to calculate the first several key points on the environmental characteristic data path to obtain the initial trend of power generation efficiency. Then, based on these key points, the environmental characteristic data path is fitted using a fitting algorithm to obtain the response relationship between the environmental characteristic data and power generation efficiency. Next, based on the response relationship and the known key points, the next several environmental characteristic data points on the path are predicted and error correction is performed. Finally, a determination is made as to whether the maximum number of iterations has been reached. If so, the prediction result is output as the key factor affecting power generation efficiency; otherwise, the iteration continues. This improves the accuracy and efficiency of key factor identification and optimizes the power generation strategy of the photovoltaic system.

[0034] Specifically, the efficiency analysis algorithm is a homotopy algorithm, a continuous deformation solution method that gradually guides the solution toward the optimal solution by constructing a "homotopy path" between the easy-to-solve problem and the target problem. In this method, initial parameters are set and the homotopy path is constructed. Then, a prediction-correction mechanism is used to continuously fit the response relationship between environmental characteristic data and power generation efficiency, and error correction is performed. The algorithm is iterated until convergence, ultimately extracting the key factors affecting power generation efficiency.

[0035] In this optional embodiment, based on the key points of the environmental characteristic data, a fitting algorithm is used to fit the path of the environmental characteristic data to obtain a response relationship between the environmental characteristic data and the power generation efficiency, including: S231, randomly sampling candidate environmental feature data in the environmental feature data space, and searching for key points of its neighborhood historical environmental feature data to form a local environmental feature data path to be fitted; S232: Calculate the fitting error of the new environmental feature data path and compare it with the fitting error of the original environmental feature data path. If the fitting error of the new environmental feature data path is smaller than the fitting error of the original environmental feature data path, perform validity evaluation; otherwise, switch to other candidate environmental feature data for fitting update. S233. If the new environmental feature data path passes the validity evaluation, it is used as the updated target path structure, and the connection relationship of the environmental feature data key points in the original environmental feature data path is replaced to optimize the path structure; S234. Based on the target path structure, a response function model between key points of environmental characteristic data and power generation efficiency is established, and based on the response function model, a response relationship between the environmental characteristic data and power generation efficiency is obtained.

[0036] Specifically, the method first randomly samples candidate data points in the environmental feature data space and searches for historical key points in their neighborhood to construct a local path structure. Secondly, the fitting error of this path is calculated and compared with the original path error. If it is better, an effectiveness evaluation is performed. Then, if the evaluation passes, the path structure is updated and the connections between key points are replaced to optimize the overall path. Finally, a response function model is established based on the optimized path structure to obtain the response relationship between environmental feature data and power generation efficiency. This effectively improves the accuracy of response modeling and provides dynamic adaptability support for power generation efficiency optimization.

[0037] Specifically, the fitting algorithm is the RRTs (Rapid Random Tree Search) algorithm, a path construction method based on random sampling, commonly used for path fitting and optimal structure search in high-dimensional spaces. In this invention, RRTs is used to randomly sample candidate paths in the environmental characteristic data space and continuously optimize the path structure through error comparison and effectiveness evaluation, ultimately fitting the response relationship between environmental characteristics and power generation efficiency.

[0038] In this optional embodiment, based on the target path structure, a response function model between key points of environmental characteristic data and power generation efficiency is established, and based on the response function model, a response relationship between environmental characteristic data and power generation efficiency is obtained, including: S2341. Collect response signals of key points of environmental feature data in the target path structure under various environmental conditions and convert them into environmental feature data for modeling; S2342. Perform modal decomposition on the environmental feature data based on a decomposition algorithm to obtain a multi-scale feature sequence of key points of the environmental feature data; S2343. Filter key modal components using correlation analysis, reconstruct a target environment feature dataset, and divide the target environment feature dataset into a training set and a validation set; S2344. Construct a response function model and input a training set for training to obtain a response relationship between environmental characteristic data and power generation efficiency.

[0039] Specifically, the method first collects response signals from key points in the target path structure under various typical environmental conditions and converts them into structured feature data. Secondly, a modal decomposition algorithm is used to perform multi-scale decomposition on the environmental feature data, extracting feature sequences in different frequency bands. Then, through correlation analysis, modal components with high correlation with power generation efficiency are selected. The optimized feature dataset is reconstructed and divided into training and validation sets. Finally, a response function model architecture is constructed, and the training set is used for model training and parameter optimization, ultimately establishing a quantitative response relationship between environmental characteristics and power generation efficiency. This improves the prediction accuracy and generalization ability of the response model, providing reliable data support for optimizing photovoltaic system efficiency.

[0040] In this optional embodiment, performing modal decomposition on the environmental feature data based on a decomposition algorithm to obtain a multi-scale feature sequence of key points of the environmental feature data includes: S23421. Initialize the parameters of the decomposition algorithm and set the environmental feature data as a candidate parameter group; S23422. Based on the candidate parameter group, perform modal decomposition on the environmental feature data to extract a plurality of channel modal component sequences; S23423. Calculate the envelope entropy of each modal component sequence according to each modal component sequence; S23424, using the minimum envelope entropy as the fitness function, updating the search state of the environmental feature data, and performing a search for the global optimal candidate parameter group; S23425. Repeat the modal decomposition and search process until the maximum number of iterations is reached, output the optimal candidate parameter group, and based on the optimal candidate parameter group, perform final modal decomposition on the key points of the environmental feature data to extract the multi-scale feature sequence.

[0041] Specifically, the key parameters of the modal decomposition algorithm, including the number of decomposition levels and convergence threshold, are first initialized, and the environmental feature data is set as the initial candidate parameter set. Next, modal decomposition is performed based on the current parameter set to extract modal component sequences across multiple frequency bands. The envelope entropy index for each modal component is then calculated, with the minimum envelope entropy being the optimization objective. The parameter set is then continuously updated through an iterative search algorithm to find the optimal decomposition solution. Finally, when the maximum number of iterations is reached, the optimal parameter set is output and the final decomposition is performed, resulting in a multi-scale feature sequence with optimal discrimination. This improves the accuracy and efficiency of feature extraction.

[0042] Specifically, the decomposition algorithm is the Bat Algorithm, an intelligent optimization algorithm that simulates bat echolocation behavior and possesses both global search and local fine-tuning capabilities. In this paper, the Bat Algorithm is used to search for optimal parameters in the modal decomposition process. By continuously updating the search state and evaluating the envelope entropy, the optimal parameter set is iteratively obtained, ultimately achieving multi-scale modal decomposition of environmental feature data.

[0043] In this optional embodiment, the formula for calculating the envelope entropy of each modal component sequence is: ; Where, B a Indicates the a Envelope entropy of the modal component sequence; A ab Indicates the a The modal component sequence is b The envelope amplitude at the moment; n The number of time points representing the modal component sequence.

[0044] In this optional embodiment, a tracking control model is established based on key factors, and the tracking control model is used to dynamically adjust the angle of the photovoltaic panels. The power generation strategy optimization includes: S31. Based on key factors, design the state vector of the photovoltaic panel and build a Kalman filter model to dynamically correct the attitude estimation value of the photovoltaic panel; S32, establishing a tracking control model, and calculating a curvature response based on a deviation between the target orientation and the current posture, to generate an angle adjustment decision for the photovoltaic panel surface; S33, using a dynamic adjustment algorithm to optimize the forward path distance and to modify the tracking trajectory and action response in real time based on deviation feedback; S34. Update the angle of the photovoltaic panel in real time through the tracking control model output, and track the sunlight angle in real time to optimize the power generation strategy.

[0045] Specifically, the system first constructs the state vector of the photovoltaic panel based on identified key environmental factors (such as light intensity and temperature fluctuations). A Kalman filter model is then introduced to dynamically correct the attitude estimate, improving state prediction accuracy. Secondly, a tracking control model is established to calculate the deviation between the current attitude and the target solar orientation. This deviation generates a curvature response and outputs preliminary angle adjustment commands. Next, a dynamic adjustment algorithm is introduced to optimize the forward-looking path distance, and a deviation feedback mechanism is used to correct the tracking trajectory and motion response in real time. Finally, the control model continuously outputs angle update commands, enabling the photovoltaic panel to dynamically align with the sun, achieving real-time tracking and intelligent attitude control, and improving the overall power generation efficiency of the system.

[0046] In this optional embodiment, optimizing the forward path distance using a dynamic adjustment algorithm and correcting the tracking trajectory and action response in real time based on deviation feedback include: S331, initializing the parameters of the dynamic adjustment algorithm, setting the status of all forward-looking path points to inactive, and initializing the error response times to an untriggered state; S332. Calculate the target response intensity and adjustment priority ratio of the path point based on the real-time error feedback, and select the error concentration area as the starting center of the dynamic control; S333: Update the foresight distance for the selected path point, incorporate it into the new response area, and continue to select the path point with the minimum deviation impact ratio from the remaining paths to participate in the control; S334. Repeat the optimization process until all response paths are adjusted, and correct the tracking trajectory and action response in real time based on the deviation feedback.

[0047] Specifically, first, initialize the parameters of the dynamic adjustment algorithm, set the status of all forward-looking path points to inactive, and initialize the number of error responses to the untriggered state; second, calculate the target response intensity and adjustment priority ratio of each path point based on real-time error feedback, and locate the error concentration area as the starting center of the control; then, perform forward-looking distance update on the selected path point, incorporate it into the new response area, and continue to select the path points with the smallest deviation impact ratio from the remaining paths to participate in the control; finally, repeat the above steps to gradually complete the response adjustment of all paths, and correct the tracking trajectory and action execution status in real time based on the error feedback to achieve dynamic and efficient posture tracking control.

[0048] Specifically, the dynamic adjustment algorithm is an overlapping box coverage algorithm, an optimization algorithm for dynamic path area planning. By constructing multiple control boxes with overlapping areas, it flexibly manages target path adjustments. In this paper, the algorithm is used to initialize the state of path points, select the error-collecting area as the starting center based on error feedback, gradually expand the forward path, and dynamically correct the trajectory and action response, ultimately achieving global optimization of path control.

[0049] According to another embodiment of the present invention, Figure 2 As shown, a solar radiation angle tracking system for energy storage and power generation is also provided, the system comprising: Data acquisition module 1, used to obtain real-time environmental data of the photovoltaic system and extract environmental feature data; Factor analysis module 2 is used to analyze and process environmental characteristic data using an efficiency analysis algorithm to identify key factors affecting power generation efficiency; The tracking control module 3 is used to establish a tracking control model based on key factors, and use the tracking control model to dynamically adjust the angle of the photovoltaic panels and optimize the power generation strategy.

[0050] The data acquisition module 1 is connected via the factor analysis module 2 and the tracking control module 3 .

[0051] In summary, with the help of the above technical solutions of the present invention, the present invention performs multi-dimensional modeling and iterative optimization on environmental feature data through an efficiency analysis algorithm, realizes accurate identification and prediction of key factors, optimizes and controls the forward-looking path through a dynamic adjustment algorithm, and corrects the tracking trajectory and action response in real time to ensure that the photovoltaic panel is always at the optimal receiving angle, thereby being able to adapt to changes in the angle of solar radiation, enhance the stability of energy storage power generation, and further achieve efficient energy management and utilization. The present invention constructs a tracking control model driven by attitude estimation and curvature response, combines a dynamic adjustment algorithm to optimize and control the forward-looking path, and uses deviation feedback to correct the tracking trajectory and action response in real time, thereby achieving high-precision dynamic adjustment of the photovoltaic panel angle, thereby being able to adapt to changes in the angle of solar radiation, improve light utilization efficiency, and further optimize the energy storage power generation strategy and operating performance, and enhance the power generation stability and intelligence level of the overall system.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for tracking sunlight angle for energy storage and power generation, characterized in that: include: Obtain real-time environmental data of the photovoltaic system and extract environmental characteristic data; The environmental characteristic data is analyzed and processed using an efficiency analysis algorithm. Based on the key points of the environmental characteristic data, a fitting algorithm is used to fit the path of the environmental characteristic data. Based on the target path structure, a response function model is established between the key points of the environmental characteristic data and the power generation efficiency. Based on the response function model, the response relationship between the environmental characteristic data and the power generation efficiency is obtained, and the key factors affecting the power generation efficiency are identified. Based on key factors, a tracking control model is established, and the tracking control model is used to dynamically adjust the angle of photovoltaic panels and optimize the power generation strategy.

2. The method for tracking sunlight angle for energy storage and power generation according to claim 1, characterized in that: The step of obtaining real-time environmental data of the photovoltaic system and extracting environmental characteristic data includes: Initialize the population of real-time environmental data of the photovoltaic system; Initialize the collection parameters of each environmental data and encode the environmental data; Use non-negative matrix decomposition to compress and decompose the acquired environmental data to extract potential environmental features; Use differential evolution algorithm to evolve and update the population of real-time environmental data to optimize the extraction process of environmental features; The compression decomposition and evolutionary update are iteratively performed until the target environment feature data is extracted.

3. The method for tracking sunlight angle for energy storage and power generation according to claim 1, wherein: Before fitting the path of the environmental feature data using a fitting algorithm based on the key points of the environmental feature data, the method further includes: Set the initial parameters of the performance analysis algorithm and set the maximum number of iterations; Using the estimation-correction process, the first several key points of the environmental characteristic data on the environmental characteristic data path are calculated, and the preliminary trend of power generation efficiency is obtained; After fitting the path of the environmental feature data using a fitting algorithm based on the key points of the environmental feature data, the method further includes: Based on the response relationship and several known key points of environmental characteristic data, the next several environmental characteristic data points on the environmental characteristic data path are predicted and their errors are corrected; Determine whether the maximum number of iterations has been reached. If so, output the prediction result as the key factor affecting power generation efficiency. Otherwise, continue iterating.

4. The method for tracking sunlight angle for energy storage and power generation according to claim 1, wherein: Before establishing a response function model between key points of environmental characteristic data and power generation efficiency based on the target path structure and obtaining a response relationship between the environmental characteristic data and power generation efficiency based on the response function model, the method further includes: Randomly sample candidate environmental feature data in the environmental feature data space, and search for key points of its neighborhood historical environmental feature data to form a local environmental feature data path to be fitted; Calculate the fitting error of the new environmental feature data path and compare it with the fitting error of the original environmental feature data path. If the fitting error of the new environmental feature data path is smaller than the fitting error of the original environmental feature data path, perform validity evaluation; otherwise, switch to other candidate environmental feature data for fitting update; If the new environmental feature data path passes the validity evaluation, it will be used as the updated target path structure, and the connection relationship of the environmental feature data key points in the original environmental feature data path will be replaced to optimize the path structure.

5. The method for tracking sunlight angle for energy storage and power generation according to claim 1, characterized in that: The step of establishing a response function model between key points of environmental characteristic data and power generation efficiency based on the target path structure, and obtaining a response relationship between environmental characteristic data and power generation efficiency based on the response function model includes: Collect response signals of key points of environmental characteristic data in the target path structure under various environmental conditions and convert them into environmental characteristic data for modeling; Perform modal decomposition on environmental feature data based on a decomposition algorithm to obtain a multi-scale feature sequence of key points of the environmental feature data; Use correlation analysis to screen key modal components, reconstruct the target environment feature dataset, and divide the target environment feature dataset into a training set and a validation set; A response function model is constructed and input into the training set for training to obtain the response relationship between environmental characteristic data and power generation efficiency.

6. The method for tracking sunlight angle for energy storage and power generation according to claim 5, characterized in that: The method of performing modal decomposition on the environmental feature data based on the decomposition algorithm to obtain a multi-scale feature sequence of key points of the environmental feature data includes: Initialize the parameters of the decomposition algorithm and set the environmental feature data as the candidate parameter group; Based on the candidate parameter group, modal decomposition is performed on the environmental feature data to extract several channel modal component sequences; According to each modal component sequence, the envelope entropy of each modal component sequence is calculated; The minimum envelope entropy is used as the fitness function, and the search state of the environmental feature data is updated to perform the search for the global optimal candidate parameter group; The modal decomposition and search process is repeated until the maximum number of iterations is reached, and the optimal candidate parameter group is output. Based on the optimal candidate parameter group, the final modal decomposition is performed on the key points of the environmental feature data to extract the multi-scale feature sequence.

7. The method for tracking sunlight angle for energy storage and power generation according to claim 6, characterized in that: The formula for calculating the envelope entropy of each modal component sequence is: ； Where, B a Indicates the a Envelope entropy of the modal component sequence; A ab Indicates the a The modal component sequence is b The envelope amplitude at the moment; n The number of time points representing the modal component sequence.

8. The method for tracking sunlight angle for energy storage and power generation according to claim 1, characterized in that: The tracking control model is established based on key factors, and the tracking control model is used to dynamically adjust the angle of the photovoltaic panels to optimize the power generation strategy, including: Based on key factors, the state vector of the photovoltaic panel is designed, and a Kalman filter model is constructed to dynamically correct the estimated attitude of the photovoltaic panel; A tracking control model is established, and the curvature response is calculated based on the deviation between the target orientation and the current posture, generating an angle adjustment decision for the photovoltaic panel. A dynamic adjustment algorithm is used to optimize the forward path distance and to modify the tracking trajectory and action response in real time based on deviation feedback. The output of the tracking control model is used to update the angle of the photovoltaic panel in real time, and the angle of sunlight is tracked in real time to optimize the power generation strategy.

9. The method for tracking sunlight angle for energy storage and power generation according to claim 8, characterized in that: The method of optimizing the forward-looking path distance by using a dynamic adjustment algorithm and correcting the tracking trajectory and action response in real time based on the deviation feedback includes: Initialize the parameters of the dynamic adjustment algorithm, set the status of all forward-looking path points to inactive, and initialize the error response times to untriggered state; Based on real-time error feedback, the ratio of the target response intensity and adjustment priority of the path point is calculated, and the error concentration area is selected as the starting center of dynamic control; Perform foresight distance update on the selected path points, incorporate them into the new response area, and continue to select the path points with the minimum deviation impact ratio from the remaining paths to participate in the regulation; The optimization process is repeated until all response paths are adjusted, and the tracking trajectory and action response are corrected in real time based on the deviation feedback.

10. A sunlight angle tracking system for energy storage power generation, used to implement the sunlight angle tracking method for energy storage power generation according to any one of claims 1 to 9, characterized in that: The system includes: The data acquisition module is used to obtain the real-time environmental data of the photovoltaic system and extract the environmental characteristic data; The factor analysis module is used to analyze and process environmental characteristic data using the efficiency analysis algorithm to identify key factors affecting power generation efficiency; The tracking control module is used to establish a tracking control model based on key factors, and use the tracking control model to dynamically adjust the angle of the photovoltaic panels and optimize the power generation strategy.

Images