Temperature acquisition, regulation and control method and system for solar efficient photovoltaic panel

Abstract

The invention discloses a temperature collection regulation and control method and device for a solar efficient photovoltaic panel, computer equipment and a storage medium, and relates to the field of solar photovoltaic power generation, and the method comprises the steps: collecting an environment data set of the solar photovoltaic panel through a sensor, and carrying out the preprocessing of the environment data set, performing feature extraction on the preprocessed environment data set by using principal component analysis (PCA) to obtain an environment feature vector set, constructing a temperature evaluation model by using a long short-term memory (LSTM) network, inputting the environment feature vector set into the temperature evaluation model, outputting a temperature evaluation value, setting a threshold value according to the temperature evaluation value, formulating a temperature regulation and control strategy, and meanwhile, establishing a temperature regulation and control strategy according to the temperature regulation and control strategy. And monitoring the execution effect of the temperature regulation and control strategy, adjusting regulation and control parameters according to the execution effect, collecting a large amount of historical environment data sets, constructing an optimization model by using a machine learning technology, and optimizing a temperature evaluation model and the regulation and control strategy.

Description

Technical Field

[0001] The present invention relates to the field of solar photovoltaic power generation, and particularly to a temperature acquisition and regulation method and system for a high-efficiency solar photovoltaic panel. Background Art

[0002] As a clean and renewable energy source, solar energy has received extensive attention globally. As the core component for solar energy conversion, the efficiency of photovoltaic panels is affected by many factors, and temperature is an important consideration index. In recent years, with the development of Internet of Things technology and sensor technology, the temperature acquisition and regulation technology of solar photovoltaic panels has made remarkable progress. The traditional temperature acquisition method mainly collects data through single-point temperature sensors, while modern technologies tend to use multi-sensor fusion technology to comprehensively evaluate by combining environmental parameters such as temperature, humidity, light intensity, and wind speed. The development of these technologies has made the operation environment monitoring of photovoltaic panels more comprehensive and accurate, which helps to improve the overall efficiency of the photovoltaic system.

[0003] However, there are still some deficiencies in the existing temperature acquisition and regulation technologies. On the one hand, traditional temperature evaluation models often rely on simple statistical methods and lack sufficient consideration of the complexity of environmental data, resulting in inaccurate evaluation results. On the other hand, most existing regulation strategies rely on fixed thresholds and fail to dynamically adjust according to real-time environmental changes, making it difficult to adapt to complex actual application scenarios. In addition, most current systems lack an effective feedback mechanism when performing temperature regulation and cannot adjust regulation parameters in a timely manner according to the actual operation effect, thus affecting the working efficiency of the photovoltaic panel. These problems have limited the optimization potential of the photovoltaic system to a certain extent, especially under extreme weather conditions, the performance of the photovoltaic panel will decline significantly. Summary of the Invention

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

[0005] Therefore, the present invention provides a temperature acquisition and regulation method, device, computer device, and storage medium for a high-efficiency solar photovoltaic panel to solve the problems that traditional temperature evaluation models often rely on simple statistical methods and lack sufficient consideration of the complexity of environmental data, resulting in inaccurate evaluation results. On the other hand, most existing regulation strategies rely on fixed thresholds and fail to dynamically adjust according to real-time environmental changes, making it difficult to adapt to complex actual application scenarios. In addition, most current systems lack an effective feedback mechanism when performing temperature regulation and cannot adjust regulation parameters in a timely manner according to the actual operation effect, thus affecting the working efficiency of the photovoltaic panel. These problems have limited the optimization potential of the photovoltaic system to a certain extent, especially under extreme weather conditions, the performance of the photovoltaic panel will decline significantly.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a temperature acquisition and regulation method for a high-efficiency solar photovoltaic panel, which includes,

[0008] Collecting an environmental data set of the solar photovoltaic panel by using a sensor and preprocessing the environmental data set;

[0009] Using principal component analysis (PCA) to extract features from the preprocessed environmental data set to obtain an environmental feature vector set;

[0010] Using a long short-term memory network (LSTM) to construct a temperature evaluation model, inputting the environmental feature vector set into the temperature evaluation model, and outputting a temperature evaluation value;

[0011] According to the temperature evaluation value, setting a threshold, formulating a temperature regulation strategy, and at the same time, monitoring the execution effect of the temperature regulation strategy and adjusting the regulation parameters according to the execution effect;

[0012] Collecting a large number of historical environmental data sets, using machine learning techniques to construct an optimization model, and optimizing the temperature evaluation model and the regulation strategy.

[0013] As a preferred solution of the temperature acquisition and regulation method for the high-efficiency solar photovoltaic panel of the present invention, wherein: the step of collecting the environmental data set by using a sensor and preprocessing the environmental data set is specifically:

[0014] Collecting the environmental data set by using a temperature sensor, a humidity sensor, a light intensity sensor, and a wind speed sensor, filling in missing values and removing outliers from the environmental data set, and converting the data into CSV format;

[0015] Setting the collected environmental data set as x, x = (x 1 , x 2 ,..., x 4 );

[0016] Wherein, x 1 represents temperature, x 2 represents humidity, x 3 represents light intensity, and x 4 represents wind speed.

[0017] As a preferred solution of the temperature acquisition and regulation method for the high-efficiency solar photovoltaic panel of the present invention, wherein: the step of using principal component analysis (PCA) to extract features from the preprocessed environmental data set to obtain an environmental feature vector set is specifically:

[0018] Constructing a covariance matrix Σ based on the preprocessed environmental data set, and the expression is:

[0019]

[0020] Among them, x i represents the i-th environmental data set, N represents the number of data points, represents the mean of the environmental data set, and i represents the index variable;

[0021] Perform eigenvalue decomposition on the covariance matrix Σ to obtain the eigenvalues λ and the corresponding eigenvectors v, and the expression is:

[0022] Σv = λv;

[0023] Calculate all eigenvalues, find the maximum eigenvalue, obtain the corresponding eigenvector, and construct the matrix V, which contains the eigenvectors corresponding to all the maximum eigenvalues, and the expression is:

[0024] V = [v max ;

[0025] Among them, λ max represents the maximum eigenvalue, and v max represents the eigenvector corresponding to the maximum eigenvalue.

[0026] As a preferred solution of the temperature acquisition and regulation method for the high-efficiency solar photovoltaic panel described in the present invention, among them: the step of performing feature extraction on the preprocessed environmental data set to obtain an environmental feature vector set is as follows:

[0027] Use principal component analysis PCA to perform feature extraction on the preprocessed environmental data set, and the expression is:

[0028]

[0029] Among them, Z represents the environmental feature vector set, exp represents the exponential function, λ j represents the smallest eigenvalue, j represents the index variable, V represents the matrix composed of the eigenvectors corresponding to the maximum eigenvalues, Γ(α) represents the gamma function for normalization, α represents the parameter of the gamma function, t represents the time vector, e represents the base of the natural logarithm, and dt represents the small increment of the integration variable t.

[0030] As a preferred solution of the temperature acquisition and regulation method for the high-efficiency solar photovoltaic panel described in the present invention, among them: the step of using a long short-term memory network LSTM to construct a temperature evaluation model, inputting the environmental feature vector set into the temperature evaluation model, and outputting a temperature evaluation value is as follows:

[0031] Divide the environmental feature vector set Z into a training set, a validation set, and a test set;

[0032] Select the mean squared error MSE as the loss function to verify the performance of the temperature evaluation model, and the expression is:

[0033]

[0034] Among them, y i represents the actual temperature value, represents the predicted temperature value of the temperature evaluation model, and n represents the number of data points;

[0035] Calculate and compare the MSE values MSE train 、MSE val and MSE test on the training set, validation set, and test set respectively, and set the threshold T 1 . When MSE train -MSE val >T 1 and MSE train -MSE test >T 1 , it indicates that the model has an overfitting phenomenon. When MSE val -MSE test ≤T 1 , it indicates that the model has good performance;

[0036] Select an Adam optimizer, set the initial learning rate, and use the training data set to train the model;

[0037] Use a long short-term memory network (LSTM) to construct a temperature evaluation model. Input the environmental feature vector set Z into the temperature evaluation model, and output the temperature evaluation value T. The expression is:

[0038]

[0039] Among them, s represents the integration variable, W represents the weight of the output layer, b represents the bias of the output layer, and ds represents the small increment of the integration variable s.

[0040] As a preferred solution of the temperature acquisition and regulation method for the high-efficiency solar photovoltaic panel described in the present invention, among them: according to the temperature evaluation value, set a threshold, select a temperature regulation strategy, and simultaneously monitor the execution effect, and adjust the regulation parameters according to the feedback. The specific steps are as follows:

[0041] Set the threshold T 2 . When T≥T 1 , it indicates that the current environmental conditions are not suitable for the efficient operation of the photovoltaic panel, and it is necessary to start the water cooling system for cooling;

[0042] When T<T 2 , it indicates that the current environmental conditions are suitable and no special regulation is required;

[0043] At the same time, continuously monitor the working efficiency and temperature change of the photovoltaic panel, and adjust the regulation parameters according to the actual operation situation.

[0044] As a preferred solution of the temperature acquisition and regulation method for the high-efficiency solar photovoltaic panel of the present invention, wherein: based on a large number of historical environmental data sets, machine learning technology is used to construct an optimization model to optimize the temperature evaluation model and regulation strategy. The specific steps are as follows:

[0045] First, collect a large number of historical environmental data sets and perform preprocessing, and use principal component analysis (PCA) to extract the environmental feature vector set;

[0046] Use K-fold cross-validation to divide the data set into K mutually exclusive subsets, create an LSTM model structure, traverse the K folds, each time using one subset as the validation set and the remaining subsets as the training set. Initialize an LSTM model instance, and use the training set data for training, monitor the performance on the validation set, and save the trained model;

[0047] Define the hyperparameter search space, set the candidate values of the learning rate, batch size, and the number of LSTM units. For each hyperparameter combination, repeat the K-fold cross-validation process, record the average validation set performance under each hyperparameter combination, and select the hyperparameter combination with the lowest validation set MSE as the hyperparameter setting of the final model;

[0048] Use the K trained LSTM models to predict the test set, and take the weighted average of the prediction results of the K models as the final prediction value, calculate the MSE between the final prediction value and the true value, evaluate the overall performance of the model, dynamically adjust the threshold according to the real-time data feedback, continuously monitor the working efficiency and temperature change of the photovoltaic panel, and adjust the regulation parameters according to the actual operation situation to establish a closed-loop control system;

[0049] Finally, deploy the optimized model to the actual environment, continuously monitor and iteratively improve it to ensure the high-efficiency and stable operation of the photovoltaic panel in different environments.

[0050] In a second aspect, the present invention provides a temperature acquisition and regulation system for a high-efficiency solar photovoltaic panel, including

[0051] A data acquisition module, which uses sensors to collect environmental data sets, and performs preprocessing operations such as integrity check, missing value processing, and outlier removal on the collected data to ensure data quality;

[0052] A feature extraction module, which uses principal component analysis (PCA) to extract features from the preprocessed environmental data set to obtain vectors that can characterize environmental features, simplify the data dimension and retain the main information;

[0053] A temperature evaluation module uses a long short-term memory network (LSTM) to construct a temperature evaluation model. It inputs the environmental feature vector set into the model and outputs a temperature evaluation value, which is used to evaluate the temperature state of the photovoltaic panel under the current environmental conditions.

[0054] A temperature regulation module sets thresholds according to the temperature evaluation value, selects appropriate temperature regulation strategies, and monitors the execution effect. It adjusts the regulation parameters based on the feedback to ensure that the photovoltaic panel operates within the optimal temperature range.

[0055] An optimization learning module constructs an optimization model using machine learning techniques based on a large number of historical environmental data sets, continuously optimizes the temperature evaluation model and regulation strategies, and improves the overall performance and adaptability of the system.

[0056] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the temperature acquisition and regulation method of the highly efficient solar photovoltaic panel as described in the first aspect of the present invention.

[0057] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by the processor, it implements any step of the temperature acquisition and regulation method of the highly efficient solar photovoltaic panel as described in the first aspect of the present invention.

[0058] The beneficial effects of the present invention are as follows: By collecting and preprocessing environmental data through multiple sensors, using PCA for feature extraction, and combining with an LSTM network to construct a temperature evaluation model, accurate evaluation and dynamic regulation of the temperature of the solar photovoltaic panel are achieved. By setting thresholds and continuously optimizing the regulation strategy, it is ensured that the photovoltaic panel always operates within the optimal temperature range, thereby improving the energy conversion efficiency, extending the service life of the equipment, and reducing the operating cost. In addition, using historical data and machine learning techniques to further optimize the model enhances the adaptive ability and overall performance of the system, ensuring the efficient and stable operation of the photovoltaic system under different environmental conditions. Description of the Drawings

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 It is a flowchart of the temperature acquisition and regulation method of the highly efficient solar photovoltaic panel in Embodiment 1.

[0061] Figure 2It is a flowchart of the temperature acquisition and regulation system for the high-efficiency solar photovoltaic panel in Embodiment 1. Detailed implementation manners

[0062] To make the above objects, features and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings of the specification.

[0063] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0064] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that can be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0065] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a temperature acquisition and regulation method for a high-efficiency solar photovoltaic panel, including the following steps:

[0066] S1 Use sensors to collect environmental data sets and preprocess the environmental data sets;

[0067] Use temperature sensors, humidity sensors, light intensity sensors, and wind speed sensors to collect environmental data sets, fill in missing values and remove outliers from the environmental data sets, and convert the data into CSV format;

[0068] Set the collected environmental data set as x, x = (x 1 , x 2 ,..., x 4 );

[0069] Among them, x 1 represents temperature, x 2 represents humidity, x 3 represents light intensity, x 4 represents wind speed;

[0070] Collecting comprehensive environmental data through multi-type sensors and preprocessing it ensure the data quality and accuracy for subsequent analysis, laying a foundation for accurate temperature assessment.

[0071] S2 Use principal component analysis (PCA) to extract features from the preprocessed environmental data set to obtain an environmental feature vector set;

[0072] Construct a covariance matrix Σ based on the preprocessed environmental data set, and the expression is:

[0073]

[0074] where x i represents the i-th environmental data set, N represents the number of data points, represents the mean of the environmental data set, and i represents the index variable;

[0075] Perform eigenvalue decomposition on the covariance matrix Σ to obtain eigenvalues λ and corresponding eigenvectors v, and the expression is:

[0076] Σv = λv;

[0077] Calculate all eigenvalues, find the maximum eigenvalue, obtain the corresponding eigenvector, and construct a matrix V that contains all eigenvectors corresponding to the maximum eigenvalues, and the expression is:

[0078] V = [v max ;

[0079] where λ max represents the maximum eigenvalue, and v max represents the eigenvector corresponding to the maximum eigenvalue;

[0080] Use PCA to perform dimensionality reduction on the environmental data, extract key eigenvectors, reduce the computational complexity, improve the response speed of the model, and make the system more efficient.

[0081] S3 Extract features from the preprocessed environmental data set to obtain an environmental feature vector set;

[0082] Use principal component analysis PCA to extract features from the preprocessed environmental data set, and the expression is:

[0083]

[0084] where Z represents the environmental feature vector set, exp represents the exponential function, λ j represents the smallest eigenvalue, j represents the index variable, V represents the matrix composed of eigenvectors corresponding to the largest eigenvalues, Γ(α) represents the gamma function used for normalization, α represents the parameter of the gamma function, t represents the time vector, e represents the base of the natural logarithm, and dt represents the small increment of the integration variable t.

[0085] S4 Use a long short-term memory network LSTM to construct a temperature evaluation model, input the environmental feature vector set into the temperature evaluation model, and output the temperature evaluation value;

[0086] Divide the environmental feature vector set Z into a training set, a validation set, and a test set;

[0087] Select the mean squared error MSE as the loss function to verify the performance of the temperature evaluation model. The expression is:

[0088]

[0089] Among them, y i represents the actual temperature value, represents the predicted temperature value of the temperature evaluation model, and n represents the number of data points;

[0090] Calculate and compare the MSE values MSE train 、MSE val and MSE test on the training set, the validation set, and the test set respectively. Set a threshold T 1 When MSE train -MSE val >T 1 and MSE train -MSE test >T 1 it indicates that the model has an overfitting phenomenon. When MSE val -MSE test ≤T 1 it indicates that the model has good performance;

[0091] Select an Adam optimizer, set the initial learning rate, and use the training data set to train the model;

[0092] Use a long short-term memory network LSTM to construct a temperature evaluation model. Input the environmental feature vector set Z into the temperature evaluation model, and output the temperature evaluation value T. The expression is:

[0093]

[0094] Among them, s represents the integration variable, W represents the weight of the output layer, b represents the bias of the output layer, and ds represents the small increment of the integration variable s;

[0095] Using an LSTM network to construct a temperature evaluation model can effectively capture the time series characteristics of environmental data, provide real-time and accurate temperature evaluation, and support more precise temperature management strategies.

[0096] S5 According to the temperature evaluation value, set a threshold, select a temperature control strategy, and at the same time monitor the execution effect, and adjust the control parameters according to the feedback;

[0097] Set a threshold T 2 , 20°C ≤ T ≤ 40°C. When T ≥ T 1When it is, it indicates that the current environmental conditions are not suitable for the efficient operation of the photovoltaic panel, and it is necessary to start the water cooling system for cooling;

[0098] When T < T 2 , it indicates that the current environmental conditions are suitable and no special regulation is required;

[0099] At the same time, continuously monitor the working efficiency and temperature change of the photovoltaic panel, and adjust the regulation parameters according to the actual operation situation;

[0100] Setting the threshold according to the temperature evaluation value and implementing the regulation strategy, while monitoring the execution effect and adjusting the parameters, ensure that the photovoltaic panel works in the optimal temperature range, extend the service life of the equipment, and improve the energy conversion efficiency.

[0101] S6 constructs an optimization model based on a large number of historical environmental data sets using machine learning techniques to optimize the temperature evaluation model and regulation strategy;

[0102] First, collect a large number of historical environmental data sets and preprocess them, and use principal component analysis PCA to extract the environmental feature vector set;

[0103] Use K-fold cross-validation to divide the data set into K mutually exclusive subsets, create the LSTM model structure, traverse the K folds, use one subset as the validation set each time, and the remaining subsets as the training set. Initialize an LSTM model instance, train it using the training set data, monitor the performance on the validation set, and save the trained model;

[0104] Define the hyperparameter search space, set the candidate values of the learning rate, batch size, and the number of LSTM units. For each hyperparameter combination, repeat the K-fold cross-validation process, record the average validation set performance under each hyperparameter combination, and select the hyperparameter combination with the lowest validation set MSE as the hyperparameter setting of the final model;

[0105] Use the K trained LSTM models to predict the test set, take the weighted average of the prediction results of the K models as the final prediction value, calculate the MSE between the final prediction value and the true value, evaluate the overall performance of the model, dynamically adjust the threshold according to the real-time data feedback, continuously monitor the working efficiency and temperature change of the photovoltaic panel, and adjust the regulation parameters according to the actual operation situation to establish a closed-loop control system;

[0106] Finally, deploy the optimized model to the actual environment, continuously monitor and iteratively improve it to ensure the efficient and stable operation of the photovoltaic panel in different environments;

[0107] Optimizing the temperature evaluation model and regulation strategy using historical data and machine learning techniques enhances the adaptive ability of the system, enabling it to better cope with the changes in different environmental conditions and continuously improve the overall performance.

[0108] This embodiment also provides a temperature acquisition and regulation system for a highly efficient solar photovoltaic panel, including:

[0109] A data acquisition module, which uses sensors to collect an environmental data set, and performs preprocessing operations such as integrity check, missing value processing, and outlier removal on the collected data to ensure data quality;

[0110] A feature extraction module, which uses principal component analysis (PCA) to extract features from the preprocessed environmental data set, obtains a vector that can characterize environmental features, simplifies the data dimension and retains the main information;

[0111] A temperature evaluation module, which uses a long short-term memory network (LSTM) to build a temperature evaluation model, inputs the environmental feature vector set into the model, and outputs a temperature evaluation value for evaluating the temperature state of the photovoltaic panel under the current environmental conditions;

[0112] A temperature regulation module, which sets a threshold according to the temperature evaluation value, selects an appropriate temperature regulation strategy, and adjusts the regulation parameters according to the feedback by monitoring the execution effect to ensure that the photovoltaic panel operates within the optimal temperature range;

[0113] An optimization learning module, which constructs an optimization model based on a large number of historical environmental data sets using machine learning techniques, continuously optimizes the temperature evaluation model and regulation strategy, and improves the overall performance and adaptability of the system.

[0114] This embodiment also provides a computer device, which is applicable to the case of the temperature acquisition and regulation method for a highly efficient solar photovoltaic panel, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the temperature acquisition and regulation method for a highly efficient solar photovoltaic panel as proposed in the above embodiment.

[0115] This computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (near field communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0116] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the temperature acquisition and regulation method for an efficient solar photovoltaic panel as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (abbreviated as SRAM), electrically erasable programmable read-only memory (abbreviated as EEPROM), erasable programmable read-only memory (abbreviated as EPROM), programmable read-only memory (abbreviated as PROM), read-only memory (abbreviated as ROM), magnetic memory, flash memory, a magnetic disk or an optical disc.

[0117] In summary, the present invention collects and preprocesses environmental data through multiple sensors, extracts features using PCA, constructs a temperature evaluation model in combination with an LSTM network, realizes the accurate evaluation and dynamic regulation of the temperature of a solar photovoltaic panel, and ensures that the photovoltaic panel always operates within the optimal temperature range by setting thresholds and continuously optimizing the regulation strategy, thereby improving the energy conversion efficiency, extending the service life of the device, and reducing the operating cost. In addition, the model is further optimized using historical data and machine learning techniques, enhancing the adaptive ability and overall performance of the system and ensuring the efficient and stable operation of the photovoltaic system under different environmental conditions.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A temperature collection and control method for a solar high-efficiency photovoltaic panel, characterized in that: including collecting an environmental data set of a solar photovoltaic panel by using sensors and preprocessing the environmental data set extracting features from the preprocessed environmental data set by using principal component analysis (PCA) to obtain an environmental feature vector set constructing a temperature evaluation model by using a long short-term memory (LSTM) network, inputting the environmental feature vector set into the temperature evaluation model, and outputting a temperature evaluation value setting a threshold according to the temperature evaluation value, formulating a temperature regulation strategy, and at the same time, monitoring the execution effect of the temperature regulation strategy and adjusting the regulation parameters according to the execution effect collecting a large amount of historical environmental data sets, and constructing an optimization model by using machine learning techniques to optimize the temperature evaluation model and the regulation strategy 2. The temperature collection and control method of a solar high-efficiency photovoltaic panel according to claim 1, characterized in that: The step of collecting the environmental data set by using sensors and preprocessing the environmental data set is specifically as follows collecting an environmental data set by using a temperature sensor, a humidity sensor, a light intensity sensor, and a wind speed sensor, filling missing values and removing outliers from the environmental data set, and converting the data into a CSV format setting the collected environmental data set as x, where x = (x1, x2,..., x4) wherein, x1 represents temperature, x2 represents humidity, x3 represents light intensity, and x4 represents wind speed 3. The temperature collection and control method of the solar high-efficiency photovoltaic panel according to claim 2, characterized in that: The step of extracting features from the preprocessed environmental data set by using principal component analysis (PCA) to obtain an environmental feature vector set is specifically as follows constructing a covariance matrix Σ based on the preprocessed environmental data set, and the expression is Among them, x i represents the i-th environmental data set, N represents the number of data points, represents the mean of the environmental data set, and i represents the index variable; performing eigen decomposition on the covariance matrix Σ to obtain eigenvalues λ and corresponding eigenvectors v, and the expression is Σv = λv calculating all eigenvalues, finding the maximum eigenvalue, obtaining the corresponding eigenvector, and constructing a matrix V containing all eigenvectors corresponding to the maximum eigenvalues, and the expression is V=[v max ]; where λ max represents the maximum eigenvalue, v max Represents the eigenvector corresponding to the largest eigenvalue.

4. The temperature collection and control method of the solar high-efficiency photovoltaic panel according to claim 3, characterized in that: The step of extracting features from the preprocessed environmental data set to obtain an environmental feature vector set is specifically as follows extracting features from the preprocessed environmental data set by using principal component analysis (PCA), and the expression is Among them, Z represents the environmental feature vector set, exp represents the exponential function, and λ j represents the smallest eigenvalue, j represents the index variable, V represents the matrix consisting of the eigenvectors corresponding to the largest eigenvalue, Γ(α) represents the gamma function used for normalization, α represents the parameter of the gamma function, t represents the time vector, e represents the base of the natural logarithm, and dt represents the small increment of the integral variable t.

5. The temperature collection and control method of a solar high-efficiency photovoltaic panel according to claim 4, characterized in that: The step of constructing a temperature evaluation model by using a long short-term memory (LSTM) network, inputting the environmental feature vector set into the temperature evaluation model, and outputting a temperature evaluation value is specifically as follows dividing the environmental feature vector set Z into a training set, a validation set, and a test set selecting the mean squared error (MSE) as a loss function to verify the performance of the temperature evaluation model, and the expression is Among them, y i Indicates the actual temperature value. represents the predicted temperature value of the temperature assessment model, and n represents the number of data points; Calculate and compare the MSE values ​​on the training set, validation set, and test set respectively train , MSE val and MSE test , set the threshold T1, when MSE train -MSE val >T1 and MSE train -MSE test >T1, indicating that the model is overfitting. val -MSE test When ≤T1, it means that the model has good performance; selecting an Adam optimizer, setting an initial learning rate, and training the model by using the training data set constructing a temperature evaluation model by using a long short-term memory (LSTM) network, inputting the environmental feature vector set Z into the temperature evaluation model, and outputting a temperature evaluation value T, and the expression is wherein, s represents an integration variable, W represents the weight of the output layer, b represents the bias of the output layer, and ds represents a small increment of the integration variable s 6. The temperature collection and control method of a solar high-efficiency photovoltaic panel according to claim 5, characterized in that: The step of setting a threshold according to the temperature evaluation value, selecting a temperature regulation strategy, monitoring the execution effect at the same time, and adjusting the regulation parameters according to the feedback is specifically as follows setting a threshold T2, when T ≥ T1, it indicates that the current environmental conditions are not suitable for the efficient operation of the photovoltaic panel, and it is necessary to start a water cooling system for cooling when T < T2, it indicates that the current environmental conditions are suitable and no special regulation is required At the same time, the working efficiency and temperature changes of the photovoltaic panels are continuously monitored, and the control parameters are adjusted according to the actual operating conditions.

7. The temperature collection and control method of a solar high-efficiency photovoltaic panel according to claim 6, characterized in that: Based on a large number of historical environmental data sets, the optimization model is constructed using machine learning technology to optimize the temperature assessment model and control strategy. The specific steps are as follows: Firstly, a large number of historical environmental data sets are collected and preprocessed, and the environmental feature vector set is extracted using principal component analysis (PCA). Use K-fold cross validation to divide the dataset into K mutually exclusive subsets, create the LSTM model structure, traverse the K folds, use one subset as the validation set each time, and the remaining subsets as the training set. Initialize an LSTM model instance and train it using the training set data, monitor the performance on the validation set, and save the trained model; Define the hyperparameter search space, set candidate values ​​for learning rate, batch size, and number of LSTM units, repeat the K-fold cross-validation process for each hyperparameter combination, record the average validation set performance under each hyperparameter combination, and select the hyperparameter combination with the lowest validation set MSE as the hyperparameter setting for the final model; Use K trained LSTM models to predict the test set, and take the weighted average of the prediction results of the K models as the final prediction value. Calculate the MSE between the final prediction value and the true value to evaluate the overall performance of the model. According to real-time data feedback, dynamically adjust the threshold, continuously monitor the working efficiency and temperature changes of the photovoltaic panels, and adjust the control parameters according to the actual operation conditions to establish a closed-loop control system. Finally, the optimized model will be deployed in the actual environment, continuously monitored and iteratively improved to ensure that the photovoltaic panels can operate efficiently and stably in different environments.

8. A temperature collection and control system for a solar high-efficiency photovoltaic panel, based on the temperature collection and control method for a solar high-efficiency photovoltaic panel according to any one of claims 1 to 7, characterized in that: include, The data acquisition module uses sensors to collect environmental data sets and performs preprocessing operations such as integrity check, missing value processing, and outlier removal on the collected data to ensure data quality; The feature extraction module uses principal component analysis (PCA) to extract features from the preprocessed environmental data set to obtain vectors that can characterize environmental features, simplify data dimensions, and retain the main information. The temperature assessment module uses the long short-term memory network LSTM to build a temperature assessment model, inputs the environmental feature vector set into the model, and outputs the temperature assessment value, which is used to assess the temperature status of the photovoltaic panel under the current environmental conditions; The temperature control module sets the threshold according to the temperature evaluation value, selects the appropriate temperature control strategy, and adjusts the control parameters according to the feedback by monitoring the execution effect to ensure that the photovoltaic panel operates within the optimal temperature range; The optimization learning module uses machine learning technology to build an optimization model based on a large amount of historical environmental data sets, continuously optimizes the temperature assessment model and control strategy, and improves the overall performance and adaptability of the system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the temperature collection and control method of the solar high-efficiency photovoltaic panel according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the temperature collection and control method of a solar high-efficiency photovoltaic panel according to any one of claims 1 to 7 are implemented.

Images