A sunlight irradiation angle tracking method and system for energy storage power generation

Abstract

This invention discloses a method and system for tracking solar irradiation angles in energy storage power generation, relating to the field of energy storage power generation technology. The method includes: acquiring real-time environmental data of a photovoltaic system and extracting environmental feature data; analyzing and processing the environmental feature data using an efficiency analysis algorithm to identify key factors affecting power generation efficiency; establishing a tracking control model based on these key factors, and dynamically adjusting the photovoltaic panel angle using the tracking control model to optimize the power generation strategy. This invention identifies key factors affecting power generation efficiency through an efficiency analysis algorithm, thereby establishing a precise angle tracking control model. The model can dynamically adjust the photovoltaic panel angle according to changes in sunlight, ensuring it is always in the optimal receiving state, effectively improving solar energy utilization efficiency. This not only improves the response sensitivity and control accuracy of the photovoltaic power generation system but also optimizes the energy storage power generation strategy, thereby enhancing the overall system stability and energy conversion efficiency.

Description

Technical Field

[0001] This invention relates to the field of energy storage and power generation technology, and more specifically, to a method and system for tracking the angle of sunlight for energy storage and power generation. Background Technology

[0002] Solar tracking technology has significant application value in the development of new energy sources 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 day. The sun's position is affected by multiple factors, including season, time, and geographical location, which places stringent requirements 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 they receive solar radiation at the optimal angle at all times. The system uses high-precision sensors to monitor the sun's position, combines this with control algorithms to calculate the optimal angle, and drives the actuators to adjust the orientation of the photovoltaic panels. By continuously tracking the sun's trajectory, the system can maximize the solar energy conversion rate, providing technical support for the sustainable development of green energy.

[0003] In existing technologies, most adopt static or semi-dynamic adjustment methods, which lack deep perception of environmental data and dynamic response mechanisms. Furthermore, they are not easy to adapt to changes in the angle of solar radiation in real time, resulting in insufficient utilization of solar energy and a lack of intelligent optimization support for power generation strategies, which affects energy storage efficiency and overall system performance.

[0004] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention proposes a method and system for tracking the solar irradiation angle for energy storage power generation. This solves the problems mentioned in the background technology, where most existing technologies adopt static or semi-dynamic adjustment methods, lack deep perception of environmental data and dynamic response mechanisms, and are not easy to adapt to changes in the solar irradiation angle in real time, resulting in insufficient solar irradiation 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 provides the following technical solution:

[0007] According to one aspect of the present invention, a method for tracking the angle of solar radiation for energy storage power generation is provided, comprising:

[0008] S1. Obtain real-time environmental data of the photovoltaic system and extract environmental feature data;

[0009] S2. Utilize performance analysis algorithms to analyze and process environmental characteristic data, and identify key factors affecting power generation efficiency;

[0010] S2 includes:

[0011] S23. Based on the key points of environmental feature data, a fitting algorithm is used to fit the path of environmental feature data to obtain the response relationship between environmental feature data and power generation efficiency.

[0012] S23 includes:

[0013] S234. Based on the target path structure, establish a response function model between key points of environmental feature data and power generation efficiency, and based on the response function model, obtain the response relationship between environmental feature data and power generation efficiency.

[0014] S3. Based on key factors, establish a tracking control model and use the tracking control model to dynamically adjust the angle of the photovoltaic panel and optimize the power generation strategy.

[0015] Furthermore, real-time environmental data of the photovoltaic system is acquired, and environmental feature data is extracted, including:

[0016] S11. Initialize the population of real-time environmental data for the photovoltaic system;

[0017] S12. Initialize the acquisition parameters for each environmental data point and encode the environmental data;

[0018] S13. Compress and decompose the acquired environmental data using nonnegative matrix factorization to extract potential environmental features;

[0019] S14. Use the differential evolution algorithm to update the population of real-time environmental data and optimize the process of extracting environmental features;

[0020] S15. Iteratively execute compression decomposition and evolutionary update until the target environment feature data is extracted.

[0021] Furthermore, prior to S23, it also includes:

[0022] S21. Set the initial parameters of the performance analysis algorithm and set the maximum number of iterations;

[0023] S22. Using the prediction-correction process, calculate the first few key points of environmental feature data along the environmental feature data path and obtain the preliminary trend of power generation efficiency.

[0024] S23 is followed by:

[0025] S24. Based on the response relationship and several known key points of environmental feature data, predict several subsequent environmental feature data points on the environmental feature data path and correct their errors.

[0026] S25. Determine if the maximum number of iterations has been reached. If it has, output the prediction result as a key factor affecting power generation efficiency; otherwise, continue iterating.

[0027] Furthermore, S234 also includes:

[0028] S231. Randomly sample candidate environmental feature data in the environmental feature data space and search for key points of historical environmental feature data in its neighborhood to form a local environmental feature data path to be fitted.

[0029] 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 less than the fitting error of the original environmental feature data path, then perform an effectiveness evaluation; otherwise, switch to other candidate environmental feature data for fitting and updating.

[0030] S233. If the new environmental feature data path passes the validity assessment, it shall be used as the updated target path structure, and the connection relationship of the key points of the environmental feature data in the original environmental feature data path shall be replaced to optimize the path structure.

[0031] Furthermore, based on the target path structure, a response function model is established between key points of environmental feature data and power generation efficiency. Based on the response function model, the response relationship between environmental feature data and power generation efficiency is obtained, including:

[0032] 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.

[0033] S2342. Based on the decomposition algorithm, perform modal decomposition on environmental feature data to obtain multi-scale feature sequences of key points in environmental feature data;

[0034] S2343. Use correlation analysis to screen key modal components, reconstruct the target environment feature dataset, and divide the target environment feature dataset into training set and validation set;

[0035] S2344. Construct a response function model and input it into the training set for training to obtain the response relationship between environmental feature data and power generation efficiency.

[0036] Furthermore, based on the decomposition algorithm, modal decomposition is performed on the environmental feature data to obtain multi-scale feature sequences of key points in the environmental feature data, including:

[0037] S23421. Initialize the parameters of the decomposition algorithm and set the environmental feature data as the candidate parameter group;

[0038] S23422. Based on the candidate parameter group, perform mode decomposition on the environmental feature data and extract several channel mode component sequences;

[0039] S23423. Calculate the envelope entropy of each modal component sequence based on the sequence of each modal component.

[0040] S23424. Use the minimum envelope entropy as the fitness function, update the search state of the environmental feature data, and perform a search for the globally optimal candidate parameter group.

[0041] S23425. Repeat the mode decomposition and search process until the maximum number of iterations is reached, output the optimal candidate parameter set, and perform final mode decomposition on the key points of the environmental feature data based on the optimal candidate parameter set to extract multi-scale feature sequences.

[0042] Furthermore, the formula for calculating the envelope entropy of each modal component sequence is as follows:

[0043] ;

[0044] In the formula, B a Indicates the first a Envelope entropy of a sequence of modal components; A ab Indicates the first a The modal component sequence in b The envelope amplitude at time; n This represents the number of time points in the modal component sequence.

[0045] Furthermore, based on key factors, a tracking control model is established, and this model is used to dynamically adjust the angle of the photovoltaic panels to optimize the power generation strategy, including:

[0046] S31. Based on key factors, design the state vector of the photovoltaic panel and construct a Kalman filter model to dynamically correct the attitude estimate of the photovoltaic panel.

[0047] S32. Establish a tracking control model and calculate the curvature response based on the deviation between the target orientation and the current attitude to generate the angle adjustment decision of the photovoltaic panel.

[0048] S33. Utilize a dynamic adjustment algorithm to optimize and control the forward path distance, and correct the tracking trajectory and action response in real time based on deviation feedback;

[0049] S34. The angle of the photovoltaic panel is updated in real time by tracking the output of the control model, and the angle of sunlight is tracked in real time to optimize the power generation strategy.

[0050] Furthermore, a dynamic adjustment algorithm is used to optimize and control the forward-looking path distance, and the tracking trajectory and motion response are corrected in real time based on deviation feedback, including:

[0051] S331. Initialize the parameters of the dynamic adjustment algorithm, set the state of all forward path points to inactive, and initialize the error response count to non-triggered state;

[0052] S332. Based on real-time error feedback, calculate the ratio of the target response intensity to the adjustment priority of the path point, and select the error clustering area as the starting center of dynamic control.

[0053] S333. Perform forward distance updates on the selected path points, incorporate them into the new response zone, and continue to select path points with the smallest deviation impact ratio from the remaining paths to participate in the regulation.

[0054] 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.

[0055] According to another aspect of the present invention, a solar radiation angle tracking system for energy storage and power generation is also provided, the system comprising:

[0056] The data acquisition module is used to acquire real-time environmental data of the photovoltaic system and extract environmental feature data;

[0057] The factor analysis module is used to analyze and process environmental characteristic data using performance analysis algorithms to identify key factors affecting power generation efficiency.

[0058] The tracking control module is used to establish a tracking control model based on key factors, and to dynamically adjust the angle of the photovoltaic panels using the tracking control model to optimize the power generation strategy.

[0059] The beneficial effects of this invention are as follows:

[0060] 1. This invention acquires real-time environmental data and extracts environmental features, then combines this with performance analysis algorithms to identify key factors affecting power generation efficiency, thereby establishing a precise angle tracking control model. The model dynamically adjusts the photovoltaic panel angle according to changes in sunlight, ensuring it is always in the optimal receiving state, effectively improving solar energy utilization efficiency. This not only enhances the response sensitivity and control precision of the photovoltaic power generation system but also optimizes the energy storage and power generation strategy, strengthening the overall system's stability and energy conversion efficiency.

[0061] 2. This invention uses an efficiency analysis algorithm to perform multi-dimensional modeling and iterative optimization of environmental feature data, thereby achieving accurate identification and prediction of key factors. It also uses a dynamic adjustment algorithm to optimize and control the forward-looking path and correct the tracking trajectory and action response in real time, ensuring that the photovoltaic panel is always at the optimal receiving angle. This allows it to adapt to changes in the angle of solar irradiation, enhance the stability of energy storage and power generation, and ultimately achieve efficient energy management and utilization.

[0062] 3. This invention constructs a tracking control model driven by attitude estimation and curvature response, combines a dynamic adjustment algorithm to optimize the forward-looking path, and uses deviation feedback to correct the tracking trajectory and action response in real time. This achieves high-precision dynamic adjustment of the photovoltaic panel angle, thereby enabling it to adapt to changes in the solar irradiation angle, improve the efficiency of light utilization, optimize the energy storage power generation strategy and operating performance, and enhance the overall system's power generation stability and intelligence level. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a flowchart of a solar radiation angle tracking method for energy storage power generation according to an embodiment of the present invention;

[0065] Figure 2 This is a schematic diagram of a solar illumination angle tracking system for energy storage and power generation according to an embodiment of the present invention.

[0066] In the picture:

[0067] 1. Data acquisition module; 2. Factor analysis module; 3. Tracking and control module. Detailed Implementation

[0068] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0069] In the description of this invention, unless otherwise stated, "a plurality of" means two or more. Furthermore, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0070] According to an embodiment of the present invention, a method and system for tracking the angle of solar radiation for energy storage power generation are provided.

[0071] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, the solar irradiance angle tracking method for energy storage power generation according to an embodiment of the present invention includes:

[0072] S1. Obtain real-time environmental data of the photovoltaic system and extract environmental feature data;

[0073] Specifically, real-time environmental data can be obtained through various 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.

[0074] Specifically, real-time environmental data includes, but is not limited to: illumination information, temperature information, meteorological data, spatiotemporal data, and photovoltaic system operation data.

[0075] 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, and light angle projection ratio.

[0076] S2. Utilize performance analysis algorithms to analyze and process environmental characteristic data, and identify key factors affecting power generation efficiency;

[0077] 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.

[0078] S3. Based on key factors, establish a tracking control model and use the tracking control model to dynamically adjust the angle of the photovoltaic panel and optimize the power generation strategy.

[0079] In this optional embodiment, acquiring real-time environmental data of the photovoltaic system and extracting environmental feature data includes:

[0080] S11. Initialize the population of real-time environmental data for the photovoltaic system;

[0081] S12. Initialize the acquisition parameters for each environmental data point and encode the environmental data;

[0082] S13. Compress and decompose the acquired environmental data using nonnegative matrix factorization to extract potential environmental features;

[0083] S14. Use the differential evolution algorithm to update the population of real-time environmental data and optimize the process of extracting environmental features;

[0084] S15. Iteratively execute compression decomposition and evolutionary update until the target environment feature data is extracted.

[0085] Specifically, firstly, the photovoltaic system collects environmental data in real time through various sensors deployed around the equipment (such as light sensors, thermometers, and hygrometers). Secondly, the environmental data undergoes preprocessing and encoding conversion. Then, the system uses algorithms such as nonnegative matrix factorization to reduce the dimensionality of the data and extract key environmental feature parameters. Finally, the feature extraction process is continuously optimized through differential evolution algorithms, ultimately outputting high-quality environmental feature data that can be used for power generation efficiency analysis.

[0086] 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:

[0087] S21. Set the initial parameters of the performance analysis algorithm and set the maximum number of iterations;

[0088] S22. Using the prediction-correction process, calculate the first few key points of environmental feature data along the environmental feature data path and obtain the preliminary trend of power generation efficiency.

[0089] S23. Based on the key points of environmental feature data, a fitting algorithm is used to fit the path of environmental feature data to obtain the response relationship between environmental feature data and power generation efficiency.

[0090] S24. Based on the response relationship and several known key points of environmental feature data, predict several subsequent environmental feature data points on the environmental feature data path and correct their errors.

[0091] S25. Determine if the maximum number of iterations has been reached. If it has, output the prediction result as a key factor affecting power generation efficiency; otherwise, continue iterating.

[0092] Specifically, first, initial parameters for the performance analysis algorithm are set, such as learning rate and step size, and a maximum number of iterations is determined. Second, using a prediction-correction process, the first few key points on the environmental feature data path are calculated to obtain a preliminary trend in power generation efficiency. Then, based on these key points, a fitting algorithm is used to fit the environmental feature data path, obtaining the response relationship between environmental feature data and power generation efficiency. Next, based on the response relationship and the known key points, the remaining environmental feature data points on the path are predicted, and error correction is performed. Finally, it is determined whether the maximum number of iterations has been reached. If so, the prediction result is output as a key factor affecting power generation efficiency; otherwise, iteration continues. This improves the accuracy and efficiency of key factor identification and optimizes the power generation strategy of the photovoltaic system.

[0093] Specifically, the efficiency analysis algorithm is a homotopy algorithm, a continuously evolving solution method that constructs a "homotopy path" between the easily solvable problem and the target problem, gradually guiding the solution towards the optimal solution. In this invention, initial parameters are first set and a 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; iterative execution continues until convergence, ultimately extracting the key factors affecting power generation efficiency.

[0094] In this optional embodiment, based on key points of environmental feature data, a fitting algorithm is used to fit the path of the environmental feature data to obtain the response relationship between environmental feature data and power generation efficiency, including:

[0095] S231. Randomly sample candidate environmental feature data in the environmental feature data space and search for key points of historical environmental feature data in its neighborhood to form a local environmental feature data path to be fitted.

[0096] 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 less than the fitting error of the original environmental feature data path, then perform an effectiveness evaluation; otherwise, switch to other candidate environmental feature data for fitting and updating.

[0097] S233. If the new environmental feature data path passes the validity assessment, it will be used as the updated target path structure, and the connection relationship of the key points of the environmental feature data in the original environmental feature data path will be replaced to optimize the path structure.

[0098] S234. Based on the target path structure, establish a response function model between key points of environmental feature data and power generation efficiency, and based on the response function model, obtain the response relationship between environmental feature data and power generation efficiency.

[0099] Specifically, firstly, candidate data points are randomly sampled in the environmental feature data space, and historical key points in their neighborhoods are searched 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, its effectiveness is evaluated. Then, if the evaluation is passed, the path structure is updated, and the connection relationships 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 adaptive support for power generation efficiency optimization.

[0100] Specifically, the fitting algorithm is the RRTs (Fast 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 feature data space, and continuously optimize the path structure through error comparison and effectiveness evaluation, ultimately fitting the response relationship between environmental features and power generation efficiency.

[0101] In this optional embodiment, based on the target path structure, a response function model is established between key points of environmental feature data and power generation efficiency. Based on the response function model, the response relationship between environmental feature data and power generation efficiency is obtained, including:

[0102] 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.

[0103] S2342. Based on the decomposition algorithm, perform modal decomposition on environmental feature data to obtain multi-scale feature sequences of key points in environmental feature data;

[0104] S2343. Use correlation analysis to screen key modal components, reconstruct the target environment feature dataset, and divide the target environment feature dataset into training set and validation set;

[0105] S2344. Construct a response function model and input it into the training set for training to obtain the response relationship between environmental feature data and power generation efficiency.

[0106] Specifically, firstly, response signals from key points in the target path structure are collected under various typical environmental conditions and converted into structured feature data. Secondly, a mode decomposition algorithm is used to decompose the environmental feature data at multiple scales, extracting feature sequences in different frequency bands. Then, correlation analysis is used to select mode components with high correlation to power generation efficiency, and 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 features and power generation efficiency. This improves the prediction accuracy and generalization ability of the response model, providing reliable data support for the optimization of photovoltaic system efficiency.

[0107] In this optional embodiment, modal decomposition of environmental feature data based on a decomposition algorithm is performed to obtain a multi-scale feature sequence of key points in the environmental feature data, including:

[0108] S23421. Initialize the parameters of the decomposition algorithm and set the environmental feature data as the candidate parameter group;

[0109] S23422. Based on the candidate parameter group, perform mode decomposition on the environmental feature data and extract several channel mode component sequences;

[0110] S23423. Calculate the envelope entropy of each modal component sequence based on the sequence of each modal component.

[0111] S23424. Use the minimum envelope entropy as the fitness function, update the search state of the environmental feature data, and perform a search for the globally optimal candidate parameter group.

[0112] S23425. Repeat the mode decomposition and search process until the maximum number of iterations is reached, output the optimal candidate parameter set, and perform final mode decomposition on the key points of the environmental feature data based on the optimal candidate parameter set to extract multi-scale feature sequences.

[0113] Specifically, the key parameters of the mode decomposition algorithm are first initialized, including the number of decomposition layers and the convergence threshold, and environmental feature data is set as the initial candidate parameter set. Next, mode decomposition is performed based on the current parameter set to extract modal component sequences across multiple frequency bands. Then, the envelope entropy of each modal component is calculated, with the minimum envelope entropy used as the optimization objective. Next, an iterative search algorithm continuously updates the parameter set to find the optimal decomposition scheme. Finally, when the maximum number of iterations is reached, the optimal parameter set is output and the final decomposition is performed to obtain a multi-scale feature sequence with the best discriminative power. This improves the accuracy and efficiency of feature extraction.

[0114] Specifically, the decomposition algorithm is the Bat Algorithm, an intelligent optimization algorithm that simulates the echolocation behavior of bats, possessing both global search and local fine-tuning capabilities. In this invention, the Bat Algorithm is used for optimal parameter search in the modal decomposition process. By continuously updating the search state and evaluating the envelope entropy, it iteratively obtains the optimal parameter set, ultimately achieving multi-scale modal decomposition of environmental feature data.

[0115] In this optional embodiment, the formula for calculating the envelope entropy of each modal component sequence is:

[0116] ;

[0117] In the formula, B a Indicates the first a Envelope entropy of a sequence of modal components; A ab Indicates the first a The modal component sequence in b The envelope amplitude at time; n This represents the number of time points in the modal component sequence.

[0118] In this optional embodiment, a tracking control model is established based on key factors, and the photovoltaic panel angle is dynamically adjusted using the tracking control model to optimize the power generation strategy, including:

[0119] S31. Based on key factors, design the state vector of the photovoltaic panel and construct a Kalman filter model to dynamically correct the attitude estimate of the photovoltaic panel.

[0120] S32. Establish a tracking control model and calculate the curvature response based on the deviation between the target orientation and the current attitude to generate the angle adjustment decision of the photovoltaic panel.

[0121] S33. Utilize a dynamic adjustment algorithm to optimize and control the forward path distance, and correct the tracking trajectory and action response in real time based on deviation feedback;

[0122] S34. The angle of the photovoltaic panel is updated in real time by tracking the output of the control model, and the angle of sunlight is tracked in real time to optimize the power generation strategy.

[0123] Specifically, firstly, based on identified key environmental factors (such as light intensity and temperature changes), a state vector for the photovoltaic panel is constructed, and a Kalman filter model is introduced to dynamically correct the attitude estimate, improving the accuracy of state prediction. Secondly, a tracking control model is established to calculate the deviation between the current attitude and the sun's orientation, and based on this, a curvature response is generated, outputting preliminary angle adjustment commands. Then, a dynamic adjustment algorithm is introduced to optimize the forward path distance, and a deviation feedback mechanism is used to correct the tracking trajectory and action response in real time. Finally, by continuously outputting angle update commands through the control model, the photovoltaic panel can dynamically align with the sun, achieving real-time tracking and intelligent attitude control, and improving the overall power generation efficiency of the system.

[0124] In this optional embodiment, the forward path distance is optimized and controlled using a dynamic adjustment algorithm, and the tracking trajectory and motion response are corrected in real time based on deviation feedback, including:

[0125] S331. Initialize the parameters of the dynamic adjustment algorithm, set the state of all forward path points to inactive, and initialize the error response count to non-triggered state;

[0126] S332. Based on real-time error feedback, calculate the ratio of the target response intensity to the adjustment priority of the path point, and select the error clustering area as the starting center of dynamic control.

[0127] S333. Perform forward distance updates on the selected path points, incorporate them into the new response zone, and continue to select path points with the smallest deviation impact ratio from the remaining paths to participate in the regulation.

[0128] 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.

[0129] Specifically, first, the parameters of the dynamic adjustment algorithm are initialized, all forward-looking path points are set to inactive, and the error response count is initialized to an untriggered state. Second, based on real-time error feedback, the ratio of the target response intensity to the adjustment priority of each path point is calculated, and the error cluster area is located as the starting center of the control. Then, the forward-looking distance of the selected path points is updated and incorporated into the new response area. At the same time, the path points with the smallest deviation impact ratio are selected from the remaining paths to participate in the control. Finally, the above steps are repeated to gradually complete the response adjustment of all paths, and the tracking trajectory and action execution status are corrected in real time based on error feedback to achieve dynamic and efficient attitude tracking control.

[0130] Specifically, the dynamic adjustment algorithm is an overlapping box covering algorithm, an optimization algorithm for dynamic planning of path regions. It flexibly manages target path adjustments by constructing multiple control boxes with overlapping regions. In this invention, this algorithm is used to initialize the path point state, select the error accumulation area as the starting center based on error feedback, gradually expand the forward-looking path, and dynamically correct the trajectory and action response, ultimately achieving global optimization of path control.

[0131] According to another embodiment of the invention, such as Figure 2 As shown, a solar irradiance tracking system for energy storage power generation is also provided, the system comprising:

[0132] Data acquisition module 1 is used to acquire real-time environmental data of the photovoltaic system and extract environmental feature data;

[0133] Factor analysis module 2 is used to analyze and process environmental characteristic data using efficiency analysis algorithms to identify key factors affecting power generation efficiency;

[0134] Tracking control module 3 is used to establish a tracking control model based on key factors, and to dynamically adjust the angle of the photovoltaic panel using the tracking control model to optimize the power generation strategy.

[0135] The data acquisition module 1 is connected to the factor analysis module 2 and the tracking control module 3.

[0136] In summary, by utilizing the above-mentioned technical solutions of this invention, the present invention performs multi-dimensional modeling and iterative optimization of environmental characteristic data through performance analysis algorithms, achieving accurate identification and prediction of key factors. It optimizes and controls the forward-looking path through dynamic adjustment algorithms, and corrects the tracking trajectory and action response in real time, ensuring that the photovoltaic panel is always at the optimal receiving angle. This allows it to adapt to changes in the solar irradiation angle, enhancing the stability of energy storage power generation and ultimately achieving efficient energy management and utilization. This invention constructs a tracking control model driven by attitude estimation and curvature response, combines it with dynamic adjustment algorithms to optimize and control the forward-looking path, and utilizes deviation feedback to correct the tracking trajectory and action response in real time. This achieves high-precision dynamic adjustment of the photovoltaic panel angle, enabling it to adapt to changes in the solar irradiation angle, improving light utilization efficiency, thereby optimizing the energy storage power generation strategy and operational performance, and enhancing the overall system's power generation stability and intelligence level.

[0137] 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 within the protection scope of the present invention.

Claims

1. A sunlight incidence angle tracking method for energy storage power generation, characterized by, include: Acquire real-time environmental data of the photovoltaic system and extract environmental feature data; The efficiency analysis algorithm is used to analyze and process environmental feature data. Based on the key points of the environmental feature data, the fitting algorithm is used to fit the path of the environmental feature data. Based on the target path structure, a response function model between the key points of the environmental feature data and the power generation efficiency is established. Based on the response function model, the response relationship between the environmental feature data and the power generation efficiency is obtained, and the key factors affecting the power generation efficiency are identified. The process of establishing a response function model between key points of environmental feature data and power generation efficiency based on the target path structure, and obtaining the response relationship between environmental feature data and power generation efficiency based on the response function model, includes: The response signals of key points of environmental feature data in the target path structure are collected under various environmental conditions and converted into environmental feature data for modeling. Modal decomposition of environmental feature data is performed based on decomposition algorithm to obtain multi-scale feature sequences of key points in environmental feature data; Key modal components were screened using correlation analysis, the target environment feature dataset was reconstructed, and the target environment feature dataset was divided into training set and validation set; A response function model is constructed and trained using a training set to obtain the response relationship between environmental feature data and power generation efficiency. The modal decomposition of environmental feature data based on the decomposition algorithm to obtain multi-scale feature sequences of key points in 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 set, mode decomposition is performed on the environmental feature data to extract several channel mode component sequences; Calculate the envelope entropy of each modal component sequence based on the sequence of each modal component. The minimum envelope entropy is used as the fitness function, and the search state of the environmental feature data is updated to perform a search for the globally optimal candidate parameter set. Repeat the mode decomposition and search process until the maximum number of iterations is reached, output the optimal candidate parameter set, and perform final mode decomposition on the key points of the environmental feature data based on the optimal candidate parameter set to extract multi-scale feature sequences; Based on key factors, a tracking control model is established, and the angle of the photovoltaic panel is dynamically adjusted using the tracking control model to optimize the power generation strategy.

2. The method for tracking the angle of solar radiation for energy storage and power generation according to claim 1, characterized in that, The acquisition of real-time environmental data of the photovoltaic system and the extraction of environmental feature data include: Initialize the population of real-time environmental data for the photovoltaic system; Initialize the acquisition parameters for each environmental data point and encode the environmental data; Nonnegative matrix factorization is used to compress and decompose the acquired environmental data to extract potential environmental features. Differential evolution algorithm is used to update the population of real-time environmental data and optimize the process of extracting environmental features; Iteratively perform compression decomposition and evolutionary update until the target environment feature data is extracted.

3. The method for tracking the angle of solar radiation for energy storage and power generation according to claim 1, characterized in that, Before fitting the environmental feature data path using a fitting algorithm based on key points of environmental feature data, the following steps are also included: Set the initial parameters for the performance analysis algorithm and set the maximum number of iterations; Using the prediction-correction process, the key points of the first few environmental feature data along the environmental feature data path are calculated, and the preliminary trend of power generation efficiency is obtained. The process of fitting the environmental feature data path using a fitting algorithm based on key points of environmental feature data further includes: Based on the response relationship and several known key points of environmental feature data, predict several subsequent environmental feature data points on the environmental feature data path and correct their errors. Determine if the maximum number of iterations has been reached. If it has, output the prediction result as a key factor affecting power generation efficiency; otherwise, continue iterating.

4. A sunlight incidence angle tracking method for energy storage power generation according to claim 1, characterized in that, Before establishing a response function model between key points of environmental feature data and power generation efficiency based on the target path structure, and obtaining the response relationship between environmental feature data and power generation efficiency based on the response function model, the following steps are also included: Candidate environmental feature data are randomly sampled in the environmental feature data space, and key points of historical environmental feature data in their neighborhood are searched 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 less than the fitting error of the original environmental feature data path, then perform an effectiveness evaluation; otherwise, switch to other candidate environmental feature data for fitting and updating. If the new environmental feature data path passes the validity assessment, it will be used as the updated target path structure, and the connection relationships of key environmental feature data points in the original environmental feature data path will be replaced to optimize the path structure.

5. A method for tracking the angle of solar radiation for energy storage and power generation according to claim 1, characterized in that, The formula for calculating the envelope entropy of each modal component sequence is as follows: ； In the formula, B a Indicates the first a Envelope entropy of a sequence of modal components; A ab Indicates the first a The modal component sequence in b The envelope amplitude at time; n This represents the number of time points in the modal component sequence.

6. A sunlight incidence angle tracking method for energy storage based power generation as claimed in claim 1, wherein, The process of establishing a tracking control model based on key factors and using this model to dynamically adjust the angle of the photovoltaic panels to optimize the power generation strategy includes: Based on key factors, the state vector of the photovoltaic panel is designed, and a Kalman filter model is constructed to dynamically correct the attitude estimate 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 attitude to generate the angle adjustment decision of the photovoltaic panel. The forward path distance is optimized and controlled using a dynamic adjustment algorithm, and the tracking trajectory and motion response are corrected in real time based on deviation feedback. By tracking the control model output to update the angle of the photovoltaic panel in real time and tracking the angle of sunlight in real time, the power generation strategy can be optimized.

7. A solar irradiance angle tracking method for energy storage power generation according to claim 6, wherein, The method of optimizing and controlling the forward path distance using a dynamic adjustment algorithm, and correcting the tracking trajectory and action response in real time based on deviation feedback, includes: Initialize the parameters of the dynamic adjustment algorithm, set the state of all forward path points to inactive, and initialize the error response count to an inactive state; Based on real-time error feedback, the ratio of the target response intensity to the adjustment priority of the path point is calculated, and the error clustering area is selected as the starting center of dynamic control. The selected path points are updated with forward distances and included in the new response zone. The remaining path points with the smallest deviation impact ratio are then selected for regulation. Repeat the optimization process until all response paths are adjusted, and correct the tracking trajectory and action response in real time based on deviation feedback.

8. A solar irradiance angle tracking system for energy storage power generation for implementing the solar irradiance angle tracking method for energy storage power generation according to any one of claims 1 to 7, characterized in that, The system includes: The data acquisition module is used to acquire real-time environmental data of the photovoltaic system and extract environmental feature data; The factor analysis module is used to analyze and process environmental characteristic data using performance analysis algorithms 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 to dynamically adjust the angle of the photovoltaic panels using the tracking control model to optimize the power generation strategy.

Images