Self-adaptive photovoltaic tracking control method and system

Abstract

The invention discloses a self-adaptive photovoltaic tracking control method and system, and the method comprises the steps: collecting and fusing multi-source data, detecting the operation environment of a photovoltaic system in real time, and carrying out the real-time processing of the collected environment data; constructing a self-adaptive photovoltaic tracking control model, training the self-adaptive photovoltaic tracking control model, and dynamically adjusting a tracking strategy of the photovoltaic panel according to historical data and real-time environment change; a dynamic error compensation mechanism is introduced, errors of a tracking system are corrected in real time, a multi-objective optimization strategy is designed, and tracking modes are automatically switched according to different environmental conditions. The system comprises a multi-source data acquisition module, a photovoltaic tracking control module and a tracking mode switching module. According to the invention, the precision and efficiency of operation monitoring of the photovoltaic system are improved; high-quality data input is provided for a photovoltaic tracking control model, and the decision-making ability of the model is improved; the intelligent and automatic photovoltaic panel tracking strategy is realized, and the power generation efficiency of a photovoltaic system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation equipment, and in particular to an adaptive photovoltaic tracking control method and system. Background Art

[0002] Photovoltaic tracking control systems automatically adjust the angle of photovoltaic panels so that they always face the sun, thereby maximizing the absorption and conversion efficiency of solar energy. This system can significantly improve the power generation efficiency of photovoltaic systems, reduce unit power generation costs, and increase the return on investment. Currently, photovoltaic tracking control systems are mainly divided into the following types: single-axis tracking, which is suitable for tracking in the east-west direction and has low cost but limited accuracy; dual-axis tracking, which has two rotational degrees of freedom and can track the movement of the sun more accurately, and is suitable for environments with a lot of frost, snow, and dust; intelligent tracking systems, which combine sensors, microprocessors, and fuzzy logic control technologies to achieve efficient and accurate tracking control; Although photovoltaic tracking control technology has made significant progress, it still faces some challenges: high-concentration photovoltaic systems have extremely high requirements for tracking accuracy, and existing tracker controllers still have errors in some cases; although active tracking systems can improve power generation efficiency, the motor drive consumes a certain amount of electricity, and the control system needs to be optimized to reduce energy consumption; severe weather conditions place higher demands on the stability of the tracking system.

[0003] Prior art 1, Chinese patent, application number 202110150065.4 discloses a photovoltaic tracking bracket control method, photovoltaic tracking controller and photovoltaic tracking system, obtains photovoltaic tracking related information, photovoltaic tracking related information includes the AC power state of the photovoltaic inverter, electrical parameters and photovoltaic tracking bracket tracking command, when the AC power state is the AC power limit state, and the photovoltaic tracking bracket tracking command is the tracking bracket reverse tracking command, a first control instruction to reduce the light incident angle is generated according to the photovoltaic tracking related information, and the photovoltaic tracking bracket is controlled to reversely track and rotate according to the first control instruction to reduce the light incident angle. Although when the photovoltaic inverter is in the AC power limit state and the DC working voltage of the photovoltaic inverter exceeds the threshold voltage, the photovoltaic tracking bracket is controlled to reversely track and rotate to reduce the light incident angle, so that the power of the photovoltaic module installed on the photovoltaic tracking bracket is appropriately reduced, and the DC voltage of the photovoltaic inverter is reduced at this time, so as to avoid the DC voltage of the photovoltaic inverter being too high; however, the control strategy is not sophisticated enough, which may cause a short power generation interruption or fluctuation of the photovoltaic panel during the adjustment process, thereby affecting the stability of the system.

[0004] Prior art 2, Chinese patent, application number 202311423764.7 discloses a photovoltaic tracking method and photovoltaic tracking system, the photovoltaic tracking method includes obtaining the first solar irradiance and the first photovoltaic power of the photovoltaic module of the control group; obtaining the user load power; determining the upper limit of the irradiance according to the first solar irradiance and the first photovoltaic power and the user load power; obtaining the second solar irradiance of the photovoltaic module of the application group; adjusting the angle of the solar receiving surface of the photovoltaic module of the application group according to the upper limit of the irradiance and the second solar irradiance. Although it solves the problem of reverse flow or negative electricity price when too much energy is sent to the power grid at the same time, affecting the stability of the power grid and the balance of power supply and demand; but the cost is relatively high, and the installation and maintenance are relatively complicated.

[0005] Prior art three, Chinese patent, application number 202111049082.5 discloses a photovoltaic tracking control method, device, tracking controller and photovoltaic tracking system, the tracking controller does not adjust the angle of the tracking bracket at the last preset adjustment moment and the next preset adjustment moment, but adjusts the angle of the tracking bracket to the target tracking angle of the tracking bracket at the next preset adjustment moment at the advance adjustment moment between the last preset adjustment moment and the next preset adjustment moment, so that in the time period between the last preset adjustment moment and the next preset adjustment moment, the degree of sudden change in the power generation of the photovoltaic module is reduced, and the continuity of the power generation change is improved. Compared with the method of adjusting the tracking angle at each preset adjustment moment so that the power generation of the photovoltaic module suddenly changes, the power generation of the photovoltaic module in the time period between the last preset adjustment moment and the next preset adjustment moment can be improved. Although it can reduce the power loss of photovoltaic power generation; however, the angle adjusted in advance may not fully match the actual optimal tracking angle, thereby affecting the efficiency of photovoltaic power generation.

[0006] At present, the control strategies of the prior art 1, prior art 2 and prior art 3 are not sophisticated enough, which may cause a short power generation interruption or fluctuation in the photovoltaic panel during the adjustment process, thereby affecting the stability of the system, and the cost is relatively high, and the installation and maintenance are relatively complicated. The angle adjusted in advance may not fully match the actual optimal tracking angle, thereby affecting the photovoltaic power generation efficiency. Therefore, the present invention provides an adaptive photovoltaic tracking control method and system. Summary of the invention

[0007] The main purpose of the present invention is to provide an adaptive photovoltaic tracking control method and system to solve the problems in the prior art that the control strategy is not sophisticated enough, affecting the stability of the system, the cost is relatively high, and the installation and maintenance are relatively complicated, affecting the efficiency of photovoltaic power generation.

[0008] To achieve the above object, the present invention provides the following technical solutions: An adaptive photovoltaic tracking control method, the adaptive photovoltaic tracking control method comprising: By collecting and fusing multi-source data, the operating environment of the photovoltaic system can be detected in real time, and the collected environmental data can be processed in real time; Build and train an adaptive photovoltaic tracking control model to dynamically adjust the tracking strategy of photovoltaic panels based on historical data and real-time environmental changes; A dynamic error compensation mechanism is introduced to correct the errors of the tracking system in real time, and a multi-objective optimization strategy is designed to automatically switch the tracking mode according to different environmental conditions.

[0009] As a further improvement of the present invention, the process of collecting and fusing multi-source data includes the following steps: At key nodes of the photovoltaic power station, multiple sensors are used to collect meteorological data, ambient light, and cloud coverage data in real time, and the collected data is pre-processed; The pre-processed multi-source data is transmitted to the central data processing platform, and edge computing processing such as hot spot detection, fault diagnosis and environmental adaptability adjustment is performed on the pre-processed multi-source data; The multi-source data processed by edge computing are fused and analyzed and input into the adaptive photovoltaic tracking control model to dynamically adjust the tracking angle of the photovoltaic panel according to environmental changes.

[0010] As a further improvement of the present invention, the process of constructing an adaptive photovoltaic tracking control model includes the following steps: Obtain multi-source data after fusion analysis, collect historical data of photovoltaic output under different weather conditions of the target photovoltaic system, and construct a data set; Construct an adaptive photovoltaic tracking control model to predict the maximum power point position of the photovoltaic panel based on the current environmental conditions; The trained adaptive photovoltaic tracking control model is deployed to the target photovoltaic system for testing. Based on the test results, the effectiveness of the model is evaluated and the parameters of the adaptive photovoltaic tracking control model are further optimized.

[0011] As a further improvement of the present invention, the process of constructing an adaptive photovoltaic tracking control model includes the following steps: Perform feature importance analysis and principal component analysis on the input features in the data set, and select and optimize the input features; An adaptive photovoltaic tracking control model is constructed using a neural network model. The model input variables include light intensity, temperature, current and voltage parameters. The data set is divided into a training set and a validation set. The adaptive photovoltaic tracking control model is trained using the training set, and the weights and biases are adjusted using an optimization algorithm. The validation set is used to evaluate the model performance, and the accuracy of the adaptive photovoltaic tracking control model is measured by calculating indicators such as prediction error and mean square error. A reward function is designed based on the prediction error, and rewards or penalties are given according to the actual power generation efficiency and power output of the photovoltaic panels.

[0012] As a further improvement of the present invention, the process of performing feature importance analysis and principal component analysis on the input features in the data set includes the following steps: Standardize the data in the data set, calculate the correlation coefficient matrix of the data set, decompose the covariance matrix through eigenvalue decomposition, and obtain the eigenvalues ​​and corresponding eigenvectors; According to the size of the obtained eigenvalue or the cumulative contribution rate, the eigenvector corresponding to the largest eigenvalue is selected as the principal component. When the cumulative contribution rate reaches 80%, the principal component extraction is stopped; The selected extracted principal components are used to reduce the dimensionality of the original data to generate a compressed data set.

[0013] As a further improvement of the present invention, the process of training the adaptive photovoltaic tracking control model includes the following steps: The processed data set is divided into a training set and a validation set according to a ratio of 7:3, and the weights and biases of the adaptive photovoltaic tracking control model are initialized by a random initialization method; The adaptive photovoltaic tracking control model is trained using the training set data. During the training process, the weights and biases are updated through the back propagation algorithm, and the parameters of the adaptive photovoltaic tracking control model are continuously adjusted. After the training is completed, the validation set is used to evaluate the performance of the adaptive photovoltaic tracking control model; based on the performance evaluation results, the adaptive photovoltaic tracking control model parameters are further adjusted or the optimization algorithm is optimized.

[0014] As a further improvement of the present invention, the process of designing a reward function based on prediction error includes the following steps: Use the validation set to evaluate the performance of the adaptive photovoltaic tracking control model, calculate the prediction error of the adaptive photovoltaic tracking control model, and design the reward function based on the prediction error; Rewards or penalties are given according to the actual power generation efficiency and power output of the photovoltaic panels; if the power predicted by the adaptive photovoltaic tracking control model is close to the actual power output, a positive reward is given; if the prediction error is large, a negative penalty is given; After each step of training, the adaptive photovoltaic tracking control model is fine-tuned according to the result of the reward function, and the training process is repeated until the prediction error of the adaptive photovoltaic tracking control model reaches the preset target.

[0015] As a further improvement of the present invention, the process of designing a multi-objective optimization strategy includes the following steps: Use sensors to monitor the angle error between the photovoltaic panel and the sun in real time and collect light intensity environmental data; Apply Kalman filtering or particle filtering algorithms to estimate and correct errors in real time; if the system detects that the error exceeds a certain threshold, the drive motor is fine-tuned to keep the photovoltaic panel at the optimal angle at all times; According to real-time environmental data, the tracking strategy is dynamically adjusted through fuzzy control or genetic algorithm, and the use environment of different tracking strategies is set, including the use of fast tracking mode in cloudy weather and stable tracking mode in sunny weather.

[0016] As a further improvement of the present invention, the process of setting the use environment of different tracking strategies includes the following steps: Using fuzzy logic controllers, the tracking strategy is dynamically adjusted according to real-time environmental data; by fuzzifying weather condition variables, the output tracking strategy is determined using preset fuzzy rules; The parameters of the fuzzy controller are optimized by genetic algorithm, and the performance of the fuzzy controller is continuously optimized through iterative selection, crossover and mutation operations, so that it adopts fast tracking mode in cloudy weather and stable tracking mode in sunny weather. The control strategy is further optimized by real-time monitoring of the tracking effect, and the tracking strategy is dynamically adjusted according to changes in environmental data. When the weather and environmental conditions change, the system automatically switches the tracking mode.

[0017] To achieve the above object, the present invention also provides the following technical solutions: An adaptive photovoltaic tracking control system is applied to the adaptive photovoltaic tracking control method. The adaptive photovoltaic tracking control system comprises: Multi-source data acquisition module, used to collect and integrate multi-source data, detect the operating environment of the photovoltaic system in real time, and process the collected environmental data in real time; Photovoltaic tracking control module, used to build an adaptive photovoltaic tracking control model, train the adaptive photovoltaic tracking control model, and dynamically adjust the tracking strategy of photovoltaic panels according to historical data and real-time environmental changes; The tracking mode switching module is used to introduce a dynamic error compensation mechanism to correct the error of the tracking system in real time, and to design a multi-objective optimization strategy to automatically switch the tracking mode according to different environmental conditions.

[0018] The present invention can fully and accurately understand the operating environment of the photovoltaic system by collecting and fusing multi-source data; process environmental data in real time to ensure the timeliness and accuracy of the data and provide a reliable basis for decision-making; design an adaptive photovoltaic tracking control model so that the model can dynamically adjust the strategy according to historical data and real-time environmental changes; conduct training to improve the adaptability and robustness of the model; introduce a dynamic error compensation mechanism to correct the error of the tracking system in real time and improve the tracking accuracy; design a multi-objective optimization strategy to automatically switch the tracking mode according to different environmental conditions, and realize the flexibility and diversity of the tracking strategy BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 A schematic diagram of a step flow chart of an embodiment of an adaptive photovoltaic tracking control method of the present invention; Figure 2 A schematic flow chart of the steps of collecting and fusing multi-source data in one embodiment of the adaptive photovoltaic tracking control method of the present invention; Figure 3 A schematic flow chart of steps for constructing an adaptive photovoltaic tracking control model for an embodiment of the adaptive photovoltaic tracking control method of the present invention; Figure 4 A schematic flow chart of the steps of designing a multi-objective optimization strategy for an embodiment of the adaptive photovoltaic tracking control method of the present invention; Figure 5 A schematic diagram of functional modules of an embodiment of an adaptive photovoltaic tracking control system of the present invention; Figure 6 It is a structural schematic diagram of an embodiment of an electronic device of the present invention; Figure 7 It is a schematic structural diagram of an embodiment of the storage medium of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0021] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] like Figure 1 As shown, this embodiment provides an embodiment of an adaptive photovoltaic tracking control method. In this embodiment, the adaptive photovoltaic tracking control method specifically includes the following steps: Step S100: by collecting and fusing multi-source data, detecting the operating environment of the photovoltaic system in real time, and processing the collected environmental data in real time; Step S200: construct an adaptive photovoltaic tracking control model, train the adaptive photovoltaic tracking control model, and dynamically adjust the tracking strategy of the photovoltaic panel according to historical data and real-time environmental changes; Step S300: Introduce a dynamic error compensation mechanism to correct the error of the tracking system in real time, and design a multi-objective optimization strategy to automatically switch the tracking mode according to different environmental conditions.

[0023] Preferably, step S100 of this embodiment can fully and accurately understand the operating environment of the photovoltaic system by collecting and fusing multi-source data; real-time processing of environmental data ensures the timeliness and accuracy of the data, providing a reliable basis for decision-making; step S200 designs an adaptive photovoltaic tracking control model so that the model can dynamically adjust the strategy according to historical data and real-time environmental changes; training is performed to improve the adaptability and robustness of the model; step S300 introduces a dynamic error compensation mechanism, which can correct the error of the tracking system in real time and improve the tracking accuracy; a multi-objective optimization strategy is designed to automatically switch the tracking mode according to different environmental conditions, thereby achieving flexibility and diversity of the tracking strategy.

[0024] In summary, this embodiment improves the accuracy and efficiency of photovoltaic system operation monitoring; provides high-quality data input for the photovoltaic tracking control model, which helps to improve the decision-making ability of the model; realizes the intelligence and automation of the photovoltaic panel tracking strategy, and improves the power generation efficiency of the photovoltaic system; reduces the power generation loss caused by environmental changes, and improves the economy and reliability of the photovoltaic system; further improves the performance and stability of the photovoltaic tracking system; adapts to the tracking needs under different environmental conditions, and improves the overall power generation capacity and adaptability of the photovoltaic system.

[0025] Furthermore, if Figure 2 As shown, in the adaptive photovoltaic tracking control method of this embodiment, the process of collecting and fusing multi-source data in step S100 specifically includes the following steps: Step S101: using multiple sensors at key nodes of the photovoltaic power station to collect multi-source data such as meteorological data, ambient light, and cloud coverage in real time, and pre-processing the collected data; Step S102: transmitting the preprocessed multi-source data to the central data processing platform, and performing edge computing processing such as hotspot detection, fault diagnosis, and environmental adaptability adjustment on the preprocessed multi-source data; Step S103: The multi-source data processed by edge computing are fused and analyzed, and input into the adaptive photovoltaic tracking control model to dynamically adjust the photovoltaic panel tracking angle according to environmental changes.

[0026] Preferably, in step S101 of this embodiment, multiple sensors are deployed at key nodes of the photovoltaic power station, which can collect multi-source data such as meteorological data, ambient light intensity, and cloud coverage in real time and comprehensively; the collected data is preprocessed to remove noise, fill missing values, etc., to improve the accuracy and availability of the data; step S102 transmits the preprocessed data to the central data processing platform, realizing centralized management and processing of data; edge computing processing such as hotspot detection, fault diagnosis, and environmental adaptability adjustment is performed on the platform, which can timely discover and solve problems and improve the operating efficiency and safety of the photovoltaic power station; step S103 performs fusion analysis on the multi-source data after edge computing, which can comprehensively consider the impact of various factors on the photovoltaic power station; the results of the fusion analysis are input into the adaptive photovoltaic tracking control model, which can dynamically adjust the tracking angle of the photovoltaic panel according to environmental changes, thereby improving the power generation efficiency of the photovoltaic power station.

[0027] In summary, the real-time and accurate data collection of this embodiment provides a solid foundation for subsequent data processing and analysis; the preprocessing step ensures data quality and provides a reliable data source for subsequent edge computing and fusion analysis; edge computing reduces data transmission delays and improves processing speed, enabling photovoltaic power stations to respond to environmental changes more quickly; through hotspot detection and fault diagnosis, potential problems can be discovered in a timely manner to avoid fault expansion and reduce downtime; fusion analysis makes the decision of photovoltaic power stations more intelligent and precise; dynamic adjustment of photovoltaic panel tracking angles can maximize the use of solar energy resources, improve power generation efficiency, and reduce operating costs.

[0028] Furthermore, if Figure 3 As shown, in the adaptive photovoltaic tracking control method of this embodiment, the process of constructing the adaptive photovoltaic tracking control model in step S200 specifically includes the following steps: Step S201: Acquire multi-source data after fusion analysis, collect historical photovoltaic output data of the target photovoltaic system under different weather conditions, and construct a data set; Step S202: construct an adaptive photovoltaic tracking control model to predict the maximum power point position of the photovoltaic panel according to the current environmental conditions; Step S203: deploying the trained adaptive photovoltaic tracking control model to the target photovoltaic system for testing, evaluating the effectiveness of the model based on the test results, and further optimizing the adaptive photovoltaic tracking control model parameters.

[0029] Preferably, step S201 of this embodiment obtains multi-source data after fusion analysis, and constructs a data set containing the output data of the photovoltaic system under different weather conditions; the data set is the basis for training the adaptive photovoltaic tracking control model, and is crucial for the model to accurately predict the maximum power point position of the photovoltaic panel under different environments. The significance lies in providing a rich data environment so that the model can learn how to control the photovoltaic system to maximize the output power under a changing environment. Step S202 constructs an adaptive photovoltaic tracking control model, and creates a model that can predict the maximum power point position of the photovoltaic panel according to the current environmental conditions; the model can dynamically adjust the tracking strategy of the photovoltaic system to adapt to the changing environmental conditions, such as weather, light intensity and temperature. The significance lies in improving the efficiency and reliability of the photovoltaic system, and by dynamically adjusting the tracking strategy, the photovoltaic panel is always kept in the best position to obtain the maximum solar energy. Step S203 deploys and tests the adaptive photovoltaic tracking control model, conducts actual tests on the model, and evaluates the effectiveness of the model based on the test results, including verification of the model performance and further optimization of the model parameters. The significance lies in ensuring that the model can achieve the expected effect in practical applications, and can be further adjusted and optimized according to the actual operation conditions to achieve the best tracking control effect.

[0030] In summary, the three steps of this embodiment together constitute a closed-loop system, which can not only improve the efficiency of the photovoltaic system, but also has the ability of self-learning and self-optimization, which is the key to achieving a high-efficiency, low-cost and environmentally friendly energy system. Through the adaptive control model, solar energy resources can be better utilized and the development of renewable energy technology can be promoted.

[0031] Furthermore, in the adaptive photovoltaic tracking control method of this embodiment, the process of constructing the adaptive photovoltaic tracking control model in step S202 specifically includes the following steps: Step S2021: performing feature importance analysis and principal component analysis on the input features in the data set, and selecting and optimizing the input features; wherein the input features are the photovoltaic output of the target photovoltaic system under different weather conditions; Step S2022: construct an adaptive photovoltaic tracking control model using a neural network model, where the model input variables include light intensity, temperature, current and voltage parameters; divide the data set into a training set and a validation set, use the training set to train the adaptive photovoltaic tracking control model, and use an optimization algorithm to adjust weights and biases; Step S2023: Use the validation set to evaluate the model performance, and measure the accuracy of the adaptive photovoltaic tracking control model by calculating indicators such as prediction error and mean square error; design a reward function based on the prediction error, and give rewards or penalties according to the actual power generation efficiency and power output of the photovoltaic panel.

[0032] Preferably, in step S2021 of this embodiment, feature importance analysis and principal component analysis are performed on the input features in the data set to select and optimize the input features; feature importance analysis can help identify which features have the greatest impact on the model prediction results, thereby retaining important features and removing irrelevant or redundant features; principal component analysis can further reduce feature dimensions, retain the main information in the data, and reduce computational complexity; step S2022 uses a neural network model to build an adaptive photovoltaic tracking control model, trains the model using a training set, and uses an optimization algorithm to adjust weights and biases; the neural network model can handle complex nonlinear relationships, Suitable for building an adaptive photovoltaic tracking control model; using a training set for training can enable the model to learn the relationship between light intensity, temperature, current and voltage parameters and the power generation efficiency of photovoltaic panels; the optimization algorithm can continuously adjust the weights and biases of the model to minimize the prediction error; step S2023 uses a validation set to evaluate the model performance, designs a reward function, and gives rewards or penalties based on the actual power generation efficiency and power output of the photovoltaic panel; by calculating indicators such as prediction error and mean square error, the prediction accuracy of the model can be quantified; the design of the reward function can enable the model to continuously optimize its own performance during the training process to pursue higher power generation efficiency and power output.

[0033] In summary, the optimization of input features in this embodiment can improve the training efficiency and prediction accuracy of the model; by reducing the number of features, the complexity of the model can be reduced, making it easier to train and deploy; the constructed adaptive photovoltaic tracking control model can adjust the working state of the photovoltaic panels in real time according to the current environmental conditions, thereby improving the power generation efficiency; through training and optimization, the model can gradually approach the real photovoltaic power generation process, improving the accuracy and reliability of the prediction; validation set evaluation is a key step to ensure that the model performs well in practical applications; the introduction of the reward function enhances the self-learning ability of the model, enabling it to make adaptive adjustments according to the actual power generation efficiency and power output, thereby improving the overall performance.

[0034] Furthermore, in the adaptive photovoltaic tracking control method of this embodiment, the process of performing feature importance analysis and principal component analysis on the input features in the data set in step S2021 specifically includes the following steps: Step S20211: standardize the data in the data set, calculate the correlation coefficient matrix of the data set, decompose the covariance matrix by eigenvalue decomposition, and obtain eigenvalues ​​and corresponding eigenvectors; Step S20212: According to the size of the obtained eigenvalue or the cumulative contribution rate, the eigenvector corresponding to the largest eigenvalue is selected as the principal component. When the cumulative contribution rate reaches 80%, the principal component extraction is stopped; Step S20213: Use the selected extracted principal components to perform dimensionality reduction processing on the original data to generate a compressed data set.

[0035] Among them, step S20211 performs standardization processing on the data in the data set:

[0036] In the formula, After standardization, i The sample j eigenvalues; Indicates the original data set i The sample j eigenvalues; Indicates that among all samples j The average of the feature values ​​indicates the central tendency of the feature in all samples; Indicates j The standard deviation of an eigenvalue measures the degree of dispersion of the eigenvalue; the formula converts the eigenvalue into a distribution with a mean of 1 and a standard deviation of 1, which helps the algorithm process the eigenvalue more efficiently because the influence of different dimensions is eliminated; the sample represents the photovoltaic output data under different weather conditions (such as the photovoltaic output on a certain day); the feature represents the weather factors that affect the photovoltaic output (such as temperature, light intensity, humidity, etc.); the eigenvalue represents the specific value of a weather factor in a specific sample (such as the temperature is 25℃); Compute the correlation coefficient matrix and perform eigenvalue decomposition:

[0037] In the formula, Representation characteristics and Features The correlation coefficient between them measures the strength of the linear relationship between two features; Indicates a The feature in k The value of samples; Indicates a The average value of a feature in all samples; Indicates a The standard deviation of the feature; Indicates the total sample size; Eigenvalue decomposition:

[0038] In the formula, represents the covariance matrix or correlation coefficient matrix; represents the eigenvector matrix, which contains A Eigenvectors of a matrix; represents the eigenvalue diagonal matrix, and the values ​​on the diagonal are A The eigenvalue of the matrix; extracting the main change direction of the data through eigenvalue decomposition is the key link of principal component analysis; Step S20212 Calculation of principal component contribution rate:

[0039] In the formula, Indicates the cumulative contribution rate, indicating the previous The cumulative contribution ratio of the principal components to the total variance of the data set; represents the eigenvalue of the covariance matrix, corresponding to the Variance contribution in the direction of each principal component; Indicates the number of principal components selected, that is, the number of principal components considered important; Represents the total number of eigenvalues, that is, the number of features in the original data set; Step S20213: Data dimensionality reduction:

[0040] In the formula, Represents a dataset after dimensionality reduction, where the number of features of each sample is reduced; Represents the original dataset, including all samples and features; Represents a matrix composed of eigenvectors corresponding to the selected principal components, which is used to project the original data into a lower-dimensional space; through the above steps, the original data set can be converted into a lower-dimensional version while retaining the key information in the original data as much as possible.

[0041] Preferably, step S20211 of this embodiment scales each feature in the data set to the same scale to ensure that the contribution of each feature to the result is fair and to avoid result deviation caused by different dimensions; measures the linear correlation between the features in the data set to provide a basis for eigenvalue decomposition; decomposes the covariance matrix to obtain eigenvalues ​​and eigenvectors; the eigenvalues ​​reflect the importance of the eigenvectors, while the eigenvectors indicate the main direction of the data; step S20212 selects the principal component according to the size of the eigenvalue or the cumulative contribution rate; the larger the eigenvalue, the larger the variance in the direction represented by the corresponding eigenvector, that is, the higher the degree of dispersion of the data in this direction; when the cumulative contribution rate reaches 80%, the extraction is stopped, which means that the selected principal component can explain 80% of the variance in the original data, achieving better data compression and information retention; step S20213 uses the selected principal component to project the original data to generate a compressed data set; maps the original data from a high-dimensional space to a low-dimensional space, while retaining the structure and information of the original data as much as possible.

[0042] In summary, this embodiment provides the necessary mathematical basis for principal component selection, ensuring the accuracy and effectiveness of the analysis; by selecting the most important principal components, data dimensionality reduction is achieved, the data model is simplified, and the computing efficiency is improved; it is ensured that the data after dimensionality reduction still retains most of the information of the original data, which is helpful for subsequent data analysis and modeling; the dimension of the data is reduced, the complexity and amount of calculation of the data are reduced, and data processing and analysis are facilitated; the visualization effect of the data is improved, making the distribution of the data in the low-dimensional space clearer and easier to understand; it helps to discover potential patterns and trends in the data, and provide more valuable information for data mining and machine learning.

[0043] Furthermore, in the adaptive photovoltaic tracking control method of this embodiment, the process of training the model in step S2022 specifically includes the following steps: Step S20221: Divide the processed data set into a training set and a validation set according to a ratio of 7:3, and initialize the weights and biases of the adaptive photovoltaic tracking control model by a random initialization method; Step S20222: training the adaptive photovoltaic tracking control model using the training set data, updating the weights and biases through the back propagation algorithm during the training process, and continuously adjusting the parameters of the adaptive photovoltaic tracking control model; the back propagation algorithm is based on the chain rule and uses the gradient descent method or other optimization algorithms to update the network weights and biases; Step S20223: After the training is completed, the performance of the adaptive photovoltaic tracking control model is evaluated using the validation set; and according to the performance evaluation result, the adaptive photovoltaic tracking control model parameters or optimization algorithm are further adjusted.

[0044] Preferably, in step S20221 of this embodiment, the processed data set is divided into a training set and a validation set in a ratio of 7:3, which helps to ensure that the model can fully learn the data features during the training process, and at the same time, the generalization ability of the model is evaluated through the validation set to avoid overfitting; the weights and biases of the adaptive photovoltaic tracking control model are set by a random initialization method, which provides a starting point for model training; random initialization can ensure that the model has diversity at the beginning of training, which helps to explore a wider parameter space; step S20222 uses the training set data to train the adaptive photovoltaic tracking control model, and continuously updates the weights and biases through the back propagation algorithm so that the model can gradually approach the distribution of real data; during the training process, the model parameters are continuously adjusted according to the performance of the model, including the learning rate, batch size, etc., to ensure that the model can efficiently and accurately learn the data features; step S20223 uses the validation set to evaluate the performance of the trained adaptive photovoltaic tracking control model, including indicators such as accuracy and recall rate, to measure the generalization ability of the model on unknown data; according to the verification results, the model parameters are further adjusted or the optimization algorithm is optimized to improve the performance of the model.

[0045] In summary, this embodiment provides a reasonable data basis for model training and verification, ensuring that the model can be effectively trained on real data; through random initialization, it provides initial conditions for the optimization of model parameters, laying the foundation for the training process; through training, the model can learn the key features in the data and improve its performance in photovoltaic tracking control tasks; parameter adjustment helps to optimize the training process and improve the convergence speed and accuracy of the model; through verification, the performance of the model can be objectively evaluated, providing direction for model optimization; model optimization can further improve the performance of the model, making it more stable and reliable in practical applications.

[0046] Furthermore, in the adaptive photovoltaic tracking control method of this embodiment, the process of designing a reward function based on the prediction error in step S2023 specifically includes the following steps: Step S20231: using the validation set to evaluate the performance of the adaptive photovoltaic tracking control model, and calculating the prediction error of the adaptive photovoltaic tracking control model, and designing a reward function according to the prediction error; Step S20232: giving rewards or penalties according to the actual power generation efficiency and power output of the photovoltaic panels; if the power predicted by the adaptive photovoltaic tracking control model is close to the actual power output, a positive reward is given; if the prediction error is large, a negative penalty is given; Step S20233: After each step of training, the adaptive photovoltaic tracking control model is fine-tuned according to the result of the reward function, and the training process is repeated until the prediction error of the adaptive photovoltaic tracking control model reaches a preset target.

[0047] The rewards are divided into two parts: intermediate rewards and final rewards. The intermediate rewards are given dynamically according to the performance of the model during the training process to help the model find the optimization direction more quickly. The final rewards are given at the end of the training based on the overall performance of the model to ensure that the model can achieve the preset goals. The design of intermediate rewards combines the performance of the model during training and dynamically adjusts the reward value; intermediate rewards based on power deviation: Set power deviation , intermediate reward Designed for:

[0048] In the formula, and is the intensity coefficient of reward and punishment; and is a smoothing parameter to avoid the denominator being zero; is the deviation threshold, used to distinguish positive rewards from negative penalties; Intermediate rewards based on prediction error trends. The trend of prediction errors can be introduced as a reference for intermediate rewards. Suppose the change in prediction error is , intermediate reward Can be designed as:

[0049] In the formula, and is the intensity coefficient of reward and punishment; It means that the prediction error is decreasing and a positive reward is given; It means that the prediction error is increasing and a negative penalty is given; The design of the final reward needs to be combined with the overall performance of the model to ensure that the model can achieve the preset goals: The final reward based on the prediction error, let the prediction error is the root mean square error RMSE , the final reward Designed for:

[0050] In the formula, and is the weight coefficient used to balance the linear and nonlinear effects of the error; is the decay coefficient, which controls the decay speed of the exponential part; Represents the final reward value. The smaller the error, the greater the reward value. The final reward based on power generation efficiency. In order to further optimize the model, power generation efficiency is introduced as a reference for the final reward. The ratio of actual power generation to theoretical maximum power generation. Designed for:

[0051] In the formula, Indicates power generation efficiency; is the reward intensity coefficient; Combine the intermediate reward and the final reward to form a comprehensive reward function Can be designed as:

[0052] In the formula, and Used to guide the model to gradually optimize during the training process; and Used to ensure that the model reaches the preset target at the end of training; set the initial model parameters and reward function parameters; in each step of training, calculate the intermediate reward based on the power deviation and prediction error trend; update the model parameters according to the comprehensive reward function; at the end of training, calculate the final reward based on the prediction error and power generation efficiency. Repeat the above steps until the prediction error meets the preset target; by introducing the mechanism of intermediate rewards and final rewards, and combining multi-dimensional indicators such as power deviation, prediction error trend and power generation efficiency, it can effectively alleviate the sparse reward problem and improve the learning efficiency and performance of the model.

[0053] Preferably, in step S20231 of this embodiment, the performance of the adaptive photovoltaic tracking control model in the current state can be objectively evaluated through the validation set, which helps to understand the generalization ability of the model and its performance in practical applications; the reward function designed based on the prediction error provides a clear optimization goal for the reinforcement learning process; the smaller the prediction error, the higher the reward, and vice versa. Step S20232 When the power predicted by the model is close to the actual power output, a positive reward is given, which encourages the model to continue to maintain or improve this accuracy; when the prediction error is large, a negative penalty is given, which prompts the model to adjust its parameters to reduce errors in future predictions; step S20233 After each step of training, the model is fine-tuned according to the result of the reward function to ensure that the model can gradually approach the optimal solution; the training process is repeated until the prediction error of the model reaches the preset target, ensuring that the model can reach the required performance level after sufficient training.

[0054] In summary, this embodiment can guide the model to evolve in the direction of improving prediction accuracy through the reward function; through this instant feedback mechanism, the model can continuously learn and adjust during the training process, thereby gradually improving its prediction ability; it is crucial to improving the efficiency and stability of the photovoltaic tracking system; through continuous iterative training and adjustment, the model can gradually adapt to various complex scenarios and improve its performance in practical applications; it is of great significance to improving the overall efficiency and economic benefits of the photovoltaic power generation system.

[0055] Furthermore, if Figure 4 As shown, in the adaptive photovoltaic tracking control method of this embodiment, the process of designing a multi-objective optimization strategy in step S300 specifically includes the following steps: Step S301: using sensors to monitor the angle error between the photovoltaic panel and the sun in real time, and collecting environmental data such as light intensity; Step S302: Apply the particle filter algorithm to estimate and correct the error in real time; if the system detects that the error exceeds a certain threshold, the drive motor is fine-tuned to keep the photovoltaic panel at the optimal angle at all times; Step S303: According to the real-time environmental data, the tracking strategy is dynamically adjusted through fuzzy control or genetic algorithm, and the use environment of different tracking strategies is set, including using a fast tracking mode in cloudy weather and a stable tracking mode in sunny weather.

[0056] Among them, the particle filter algorithm includes: Nonlinear state prediction formula:

[0057] In the formula, Indicates Particles at time The state vector usually contains information such as the angle and angular velocity of the photovoltaic panel; Represents the basic state transfer function, which describes the main dynamic characteristics of the system; for example, it may represent the motion law of a photovoltaic panel in the absence of interference; Represents a high-order nonlinear function, which is used to describe the secondary dynamic characteristics of the system, such as wind disturbance, mechanical vibration, etc. These factors usually lead to nonlinear behavior of the system; Represents the weight coefficient of the nonlinear term, which is used to adjust the impact of each nonlinear term on the state prediction. These coefficients can be determined by experiments or optimization algorithms; It represents the number of nonlinear terms and the types of secondary dynamic characteristics that need to be considered in the system. By introducing high-order nonlinear terms, the state prediction formula can more accurately describe the complex dynamic behavior of the photovoltaic panel system, thereby improving the accuracy of state estimation. Higher-order observation likelihood function:

[0058] In the formula, Indicates time The observation vector usually contains information such as the angle error and light intensity measured by the sensor; Indicates l An observation model describes the mapping relationship between the state vector and the observation vector; for example, it represents the angle error that the sensor should measure in a certain state; represents a Gaussian distribution with a mean of , the covariance matrix is , indicating that in the state Next, observe The probability of Indicates l Gaussian distribution weights satisfy , represents the importance of each observation model in the overall observation likelihood function; LRepresents the number of Gaussian distributions, indicating the type of observation model that needs to be considered; by introducing mixed Gaussian distributions, the observation likelihood function can more accurately describe the uncertainty of the observation data, thereby improving the robustness of the state estimation; Adaptive resampling formula:

[0059] In the formula, Indicates the number of effective particles, which is used to measure the degree of particle degradation. If the number of effective particles is too small, it means that the weights of most particles are concentrated on a few particles, resulting in particle degradation. represents the normalized particle weight, which indicates the matching degree of each particle with the observed data; Represents the resampling threshold, which is usually set to N / 2. If the number of valid particles is lower than this threshold, resampling is performed. The resampling strategy indicates that resampling can adopt stratified resampling or systematic resampling methods to improve the efficiency and accuracy of resampling. The adaptive resampling strategy can effectively avoid particle degradation problems, thereby improving the accuracy and stability of state estimation. The optimization formula for error correction is:

[0060] In the formula, Indicates time Angle error correction amount, used to adjust the angle of the photovoltaic panel; represents the desired photovoltaic panel angle, usually calculated from a sun position model; Indicates Particles at time An estimated value of the angle of represents the regularization coefficient, which is used to balance the error correction amount and the smoothness of the control signal; represents the regularization term, which is used to prevent the correction amount from being too large. By introducing the optimization objective function, the error correction process can calculate the correction amount more accurately, thereby improving the tracking accuracy of the photovoltaic panel. High-level generation formula for motor control signals:

[0061] In the formula, Indicates time The motor control signal is used to drive the motor to adjust the angle of the photovoltaic panel; Represents the proportional gain coefficient, which is used to adjust the response speed of the system; Represents the differential gain coefficient, which is used to adjust the damping characteristics of the system; Represents the integral gain coefficient, which is used to eliminate steady-state errors; Represents the sliding mode gain coefficient, which is used to enhance the robustness of the system; represents the sign function, used for sliding mode control; The integral term representing the error correction amount is used to eliminate the steady-state error. By introducing a high-order controller, the motor control signal can more accurately adjust the angle of the photovoltaic panel, thereby improving the tracking performance and stability of the system. Multi-objective optimization objective function:

[0062] In the formula, represents the multi-objective optimization objective function, which is used to comprehensively consider the angle error, energy consumption and system stability; , , represents the weight coefficient, corresponding to angle error, energy consumption and system stability respectively; represents the optimization time range, indicating the number of time steps to be considered; represents the stability term, which is used to smooth the control signal; by introducing the multi-objective optimization objective function, it can achieve efficient operation under different environmental conditions while ensuring stability and energy efficiency. Through the above complex formulas and optimization strategies, the particle filter algorithm can more accurately estimate and correct the angle error of the photovoltaic panel, while achieving multi-objective optimization to ensure the efficient operation of the system under different environmental conditions.

[0063] Preferably, in step S301 of this embodiment, a sensor is used to monitor the angle error between the photovoltaic panel and the sun in real time, and to collect environmental data such as light intensity. Through real-time monitoring, the system can obtain accurate angle error data and key environmental information such as light intensity. In step S302, a Kalman filter or a particle filter algorithm is used to estimate and correct the error in real time. If the system detects that the error exceeds a certain threshold, the drive motor is fine-tuned to keep the photovoltaic panel at the optimal angle at all times. Through advanced filtering algorithms, the system can estimate and correct the error in real time and accurately to ensure that the photovoltaic panel always maintains the optimal angle, thereby improving the efficiency of light energy conversion. In step S303, the tracking strategy is dynamically adjusted through fuzzy control or genetic algorithms according to real-time environmental data, and the use environment of different tracking strategies is set, including a fast tracking mode in cloudy weather and a stable tracking mode in sunny weather. The system can dynamically adjust the tracking strategy according to environmental changes to adapt to different weather conditions, thereby improving the adaptability and flexibility of the system.

[0064] In summary, this embodiment ensures that the system can operate accurately according to actual conditions, and improves the response speed and accuracy of the system; through real-time correction, the system can adaptively adjust the angle of the photovoltaic panels to adapt to changes in the position of the sun, thereby maximizing power generation efficiency; it enables the system to adapt to complex and changeable environmental conditions more intelligently, and by selecting appropriate tracking strategies, the system can maintain a high power generation efficiency in different weather conditions, thereby improving the overall performance and stability of the system.

[0065] Furthermore, in the adaptive photovoltaic tracking control method of this embodiment, the process of setting the use environment of different tracking strategies in step S303 specifically includes the following steps: Step S3031: using a fuzzy logic controller to dynamically adjust the tracking strategy according to real-time environmental data; by fuzzifying weather condition variables, using preset fuzzy rules to determine the output tracking strategy; Step S3032: Optimizing the parameters of the fuzzy controller by genetic algorithm, and continuously optimizing the performance of the fuzzy controller by iterative selection, crossover and mutation operations, so that the fuzzy controller adopts a fast tracking mode in cloudy weather and a stable tracking mode in sunny weather; Step S3033: The control strategy is further optimized by real-time monitoring of the tracking effect, so that the system can dynamically adjust the tracking strategy according to changes in environmental data. When the weather and environmental conditions change, the system automatically switches the tracking mode.

[0066] Preferably, step S3031 of this embodiment utilizes a fuzzy logic controller to dynamically adjust the tracking strategy according to real-time environmental data; by fuzzifying weather condition variables and using preset fuzzy rules to determine the output tracking strategy, the flexibility and adaptability of the tracking strategy are achieved; fuzzy logic can handle uncertainty and ambiguity, so that the system can make decisions based on incomplete or ambiguous information; step S3032 optimizes the parameters of the fuzzy controller through a genetic algorithm; continuously optimizes the parameters through iterative selection, crossover and mutation operations; improves the performance of the fuzzy controller so that it adopts a fast tracking mode in cloudy weather and a stable tracking mode in sunny weather; step S3033 further optimizes the control strategy by real-time monitoring of the tracking effect; enables the system to dynamically adjust the tracking strategy according to changes in environmental data, and automatically switch the tracking mode when the weather and environmental conditions change; ensures continuous optimization and adaptability of the system.

[0067] In summary, this embodiment can automatically adjust its tracking behavior under different weather conditions, thereby improving tracking efficiency and accuracy; it can automatically adjust its tracking strategy according to changes in weather conditions while maintaining high efficiency and stability. The optimization process of the genetic algorithm ensures that the fuzzy controller can achieve optimal performance for specific application scenarios; it continuously learns and adapts to new environmental conditions, improving its long-term performance and reliability; it can automatically adjust to changing environmental conditions.

[0068] like Figure 5 As shown, this embodiment also provides an embodiment of an adaptive photovoltaic tracking control system. In this embodiment, the adaptive photovoltaic tracking control system is applied to the adaptive photovoltaic tracking control method in the above embodiment. The adaptive photovoltaic tracking control system specifically includes: The multi-source data acquisition module 1 is used to collect and fuse multi-source data, detect the operating environment of the photovoltaic system in real time, and process the collected environmental data in real time; Photovoltaic tracking control module 2 is used to build an adaptive photovoltaic tracking control model, train the adaptive photovoltaic tracking control model, and dynamically adjust the tracking strategy of the photovoltaic panel according to historical data and real-time environmental changes; The tracking mode switching module 3 is used to introduce a dynamic error compensation mechanism, correct the error of the tracking system in real time, and design a multi-objective optimization strategy to automatically switch the tracking mode according to different environmental conditions.

[0069] Preferably, the multi-source data acquisition module 1 of this embodiment can fully and accurately understand the operating environment of the photovoltaic system by collecting and fusing multi-source data; real-time processing of environmental data ensures the timeliness and accuracy of the data, and provides a reliable basis for decision-making; the photovoltaic tracking control module 2 designs an adaptive photovoltaic tracking control model based on machine learning, so that the model can dynamically adjust the strategy according to historical data and real-time environmental changes; training is performed using reinforcement learning or deep learning to improve the adaptability and robustness of the model; the tracking mode switching module 3 introduces a dynamic error compensation mechanism, which can correct the error of the tracking system in real time and improve the tracking accuracy; a multi-objective optimization strategy is designed to automatically switch the tracking mode according to different environmental conditions, thereby achieving the flexibility and diversity of the tracking strategy.

[0070] In summary, this embodiment improves the accuracy and efficiency of photovoltaic system operation monitoring; provides high-quality data input for the photovoltaic tracking control model, which helps to improve the decision-making ability of the model; realizes the intelligence and automation of the photovoltaic panel tracking strategy, and improves the power generation efficiency of the photovoltaic system; reduces the power generation loss caused by environmental changes, and improves the economy and reliability of the photovoltaic system; further improves the performance and stability of the photovoltaic tracking system; adapts to the tracking needs under different environmental conditions, and improves the overall power generation capacity and adaptability of the photovoltaic system.

[0071] like Figure 6 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 4 includes a processor 41 and a memory 42 coupled to the processor 41.

[0072] The memory 42 stores program instructions for implementing the adaptive photovoltaic tracking control system of any of the above embodiments.

[0073] The processor 41 is used to execute program instructions stored in the memory 42 to perform an adaptive photovoltaic tracking control system.

[0074] The processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having the ability to process signals. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0075] Further, Figure 7 The schematic diagram of the structure of the storage medium of an embodiment of the present application is shown in FIG. The storage medium 5 of the embodiment of the present application stores program instructions 51 capable of implementing all the above methods, wherein the program instructions 51 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0076] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0077] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0078] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. An adaptive photovoltaic tracking control method, characterized in that: The adaptive photovoltaic tracking control method comprises: By collecting and fusing multi-source data, the operating environment of the photovoltaic system can be detected in real time, and the collected environmental data can be processed in real time; Build and train an adaptive photovoltaic tracking control model to dynamically adjust the tracking strategy of photovoltaic panels based on historical data and real-time environmental changes; A dynamic error compensation mechanism is introduced to correct the errors of the tracking system in real time, and a multi-objective optimization strategy is designed to automatically switch the tracking mode according to different environmental conditions.

2. The adaptive photovoltaic tracking control method according to claim 1, characterized in that: The process of collecting and fusing multi-source data includes the following steps: At key nodes of the photovoltaic power station, multiple sensors are used to collect meteorological data, ambient light, and cloud coverage data in real time, and the collected data is pre-processed; The pre-processed multi-source data is transmitted to the central data processing platform, and the pre-processed multi-source data is subjected to edge computing processing such as hot spot detection, fault diagnosis and environmental adaptability adjustment; The multi-source data processed by edge computing are fused and analyzed and input into the adaptive photovoltaic tracking control model to dynamically adjust the tracking angle of the photovoltaic panel according to environmental changes.

3. The adaptive photovoltaic tracking control method according to claim 1, characterized in that: The process of building an adaptive photovoltaic tracking control model includes the following steps: Obtain multi-source data after fusion analysis, collect historical data of photovoltaic output under different weather conditions of the target photovoltaic system, and construct a data set; Construct an adaptive photovoltaic tracking control model to predict the maximum power point position of the photovoltaic panel based on the current environmental conditions; The trained adaptive photovoltaic tracking control model is deployed to the target photovoltaic system for testing. Based on the test results, the effectiveness of the model is evaluated and the parameters of the adaptive photovoltaic tracking control model are further optimized.

4. The adaptive photovoltaic tracking control method according to claim 3, characterized in that: The process of building an adaptive photovoltaic tracking control model includes the following steps: Perform feature importance analysis and principal component analysis on the input features in the data set, and select and optimize the input features; An adaptive photovoltaic tracking control model is constructed using a neural network model. The model input variables include light intensity, temperature, current and voltage parameters. The data set is divided into a training set and a validation set. The adaptive photovoltaic tracking control model is trained using the training set, and the weights and biases are adjusted using an optimization algorithm. The validation set is used to evaluate the model performance, and the accuracy of the adaptive photovoltaic tracking control model is measured by calculating the prediction error and mean square error indicators. A reward function is designed based on the prediction error, and rewards or penalties are given according to the actual power generation efficiency and power output of the photovoltaic panels.

5. The adaptive photovoltaic tracking control method according to claim 4, characterized in that: The process of performing feature importance analysis and principal component analysis on the input features in the data set includes the following steps: Standardize the data in the data set, calculate the correlation coefficient matrix of the data set, decompose the covariance matrix through eigenvalue decomposition, and obtain the eigenvalues ​​and corresponding eigenvectors; According to the size of the obtained eigenvalue or the cumulative contribution rate, the eigenvector corresponding to the largest eigenvalue is selected as the principal component. When the cumulative contribution rate reaches 80%, the principal component extraction is stopped; The selected extracted principal components are used to reduce the dimensionality of the original data to generate a compressed data set.

6. The adaptive photovoltaic tracking control method according to claim 4, characterized in that: The process of training the adaptive photovoltaic tracking control model includes the following steps: The processed data set is divided into a training set and a validation set according to a ratio of 7:3, and the weights and biases of the adaptive photovoltaic tracking control model are initialized by a random initialization method; The adaptive photovoltaic tracking control model is trained using the training set data. During the training process, the weights and biases are updated through the back propagation algorithm, and the parameters of the adaptive photovoltaic tracking control model are continuously adjusted. After the training is completed, the validation set is used to evaluate the performance of the adaptive photovoltaic tracking control model; based on the performance evaluation results, the adaptive photovoltaic tracking control model parameters are further adjusted or the optimization algorithm is optimized.

7. The adaptive photovoltaic tracking control method according to claim 4, characterized in that: The process of designing a reward function based on prediction error includes the following steps: Use the validation set to evaluate the performance of the adaptive photovoltaic tracking control model, calculate the prediction error of the adaptive photovoltaic tracking control model, and design the reward function based on the prediction error; Rewards or penalties are given according to the actual power generation efficiency and power output of the photovoltaic panels; if the power predicted by the adaptive photovoltaic tracking control model is close to the actual power output, a positive reward is given; if the prediction error is large, a negative penalty is given; After each step of training, the adaptive photovoltaic tracking control model is fine-tuned according to the result of the reward function, and the training process is repeated until the prediction error of the adaptive photovoltaic tracking control model reaches the preset target.

8. The adaptive photovoltaic tracking control method according to claim 1, characterized in that: The process of designing a multi-objective optimization strategy includes the following steps: Use sensors to monitor the angle error between the photovoltaic panel and the sun in real time and collect light intensity environmental data; Apply Kalman filtering or particle filtering algorithms to estimate and correct errors in real time; if the system detects that the error exceeds the threshold, the drive motor is fine-tuned to keep the photovoltaic panel at the optimal angle at all times; The particle filter algorithm includes: Nonlinear state prediction formula: In the formula, Indicates Particles at time The state vector contains the angle and angular velocity information of the photovoltaic panel; It is the basic state transfer function, which describes the dynamic characteristics and represents the motion law of photovoltaic panels without interference; Represents a high-order nonlinear function, used to describe secondary dynamic characteristics, wind disturbances, mechanical vibrations; It represents the weight coefficient of the nonlinear term, which is used to adjust the influence of each nonlinear term on the state prediction and is determined by experiments or optimization algorithms; It is the number of nonlinear terms, indicating the kind of secondary dynamic characteristics that need to be considered in the system; Higher-order observation likelihood function: In the formula, Indicates time The observation vector contains information such as the angle error and light intensity measured by the sensor; Indicates l An observation model that describes the mapping relationship from the state vector to the observation vector; represents a Gaussian distribution with a mean of , the covariance matrix is , indicating that in the state Next, observe probability; Indicates l Gaussian distribution weights satisfy , represents the importance of each observation model in the overall observation likelihood function; L represents the number of Gaussian distributions, indicating the types of observation models that need to be considered; Adaptive resampling formula: In the formula, Indicates the number of effective particles, which is used to measure the degree of particle degradation. If the number of effective particles is too small, it means that the weights of most particles are concentrated on a few particles, resulting in particle degradation. represents the normalized particle weight, which indicates the matching degree of each particle with the observed data; Represents the resampling threshold, usually set to N / 2; if the number of valid particles is lower than this threshold, resampling is performed; The optimization formula for error correction is: In the formula, Indicates time Angle error correction amount, used to adjust the angle of the photovoltaic panel; represents the desired photovoltaic panel angle, calculated by the sun position model; Indicates Particles at time An estimated value of the angle represents the regularization coefficient, which is used to balance the error correction amount and the smoothness of the control signal; represents the regularization term, which is used to prevent the correction amount from being too large; High-level generation formula for motor control signals: In the formula, Indicates time The motor control signal is used to drive the motor to adjust the angle of the photovoltaic panel; Represents the proportional gain coefficient, which is used to adjust the response speed of the system; Represents the differential gain coefficient, which is used to adjust the damping characteristics of the system; Represents the integral gain coefficient, which is used to eliminate steady-state errors; Represents the sliding mode gain coefficient, which is used to enhance the robustness of the system; represents the sign function, used for sliding mode control; The integral term representing the error correction amount is used to eliminate the steady-state error; Multi-objective optimization objective function: In the formula, represents the multi-objective optimization objective function, which is used to comprehensively consider the angle error, energy consumption and system stability; , , represents the weight coefficient, corresponding to angle error, energy consumption and system stability respectively; represents the optimization time range, indicating the number of time steps to be considered; represents the stability term, which is used to smooth the control signal; According to real-time environmental data, the tracking strategy is dynamically adjusted through fuzzy control or genetic algorithm, and the use environment of different tracking strategies is set, including the use of fast tracking mode in cloudy weather and stable tracking mode in sunny weather.

9. The adaptive photovoltaic tracking control method according to claim 8, characterized in that: The process of setting up the environment for using different tracking strategies includes the following steps: Using fuzzy logic controllers, the tracking strategy is dynamically adjusted according to real-time environmental data; by fuzzifying weather condition variables, the output tracking strategy is determined using preset fuzzy rules; The parameters of the fuzzy controller are optimized by genetic algorithm, and the performance of the fuzzy controller is continuously optimized through iterative selection, crossover and mutation operations, so that it adopts fast tracking mode in cloudy weather and stable tracking mode in sunny weather. The control strategy is further optimized by real-time monitoring of the tracking effect, and the tracking strategy is dynamically adjusted according to changes in environmental data. When the weather and environmental conditions change, the system automatically switches the tracking mode.

10. An adaptive photovoltaic tracking control system, applied to the adaptive photovoltaic tracking control method according to any one of claims 1 to 9, characterized in that: The adaptive photovoltaic tracking control system comprises: Multi-source data acquisition module, used to collect and integrate multi-source data, detect the operating environment of the photovoltaic system in real time, and process the collected environmental data in real time; Photovoltaic tracking control module, used to build an adaptive photovoltaic tracking control model, train the adaptive photovoltaic tracking control model, and dynamically adjust the tracking strategy of photovoltaic panels according to historical data and real-time environmental changes; The tracking mode switching module is used to introduce a dynamic error compensation mechanism to correct the error of the tracking system in real time, and to design a multi-objective optimization strategy to automatically switch the tracking mode according to different environmental conditions.

Images