Photovoltaic power generation capacity dynamic prediction method and system based on information text feature extraction

Abstract

The invention discloses a photovoltaic power generation capacity dynamic prediction method and system based on information text feature extraction. The method comprises the following steps: S1, preprocessing power generation capacity data and meteorological data recorded in a photovoltaic power generation system; s2, finely adjusting the model T5; s3, performing abstract extraction on the data recorded in the photovoltaic power generation system by using the fine tuning model T5, and converting the data into an embedded vector; s4, using a multi-layer perceptron (MLP) to recommend hyper-parameter suggestions of the prediction model according to the embedded vector; s5, training the prediction model by adopting hyper-parameter suggestions; and S6, using the trained model to predict the future generating capacity according to the generating capacity data and the meteorological data recorded in the power generation system and the future meteorological data. The method can improve the feature extraction accuracy of the generating capacity data and the meteorological data, improve the training efficiency of the model, reduce the consumption of computing resources, improve the generalization ability and robustness of the model, improve the accuracy of generating capacity prediction, and improve the practical application value.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and particularly to a dynamic prediction method, system, storage medium and computing device for photovoltaic power generation based on information text feature extraction. Background Art

[0002] Photovoltaic power generation, as a clean and renewable energy source, has been widely applied and developed in recent years. With the increasing global demand for sustainable energy, photovoltaic power generation has gradually become an important way to address the energy crisis and reduce carbon emissions. However, the photovoltaic power generation is affected by various factors, such as weather, seasonal changes, geographical location, environmental temperature, light intensity, etc. The complexity and uncertainty of these factors make it a key issue to accurately predict the photovoltaic power generation for power system scheduling, energy efficiency management and grid load balancing.

[0003] Currently, the prediction methods for photovoltaic power generation can be mainly divided into two categories: physics-based methods and data-driven methods. Physics-based methods rely on the physical characteristics of the photovoltaic system and the mathematical models of the external environment for prediction. These methods usually require accurate meteorological data and photovoltaic system parameters, and have weak adaptability to environmental changes, resulting in limited prediction accuracy. Data-driven methods, such as machine learning and deep learning methods, automatically learn the complex relationship between the power generation and environmental factors by analyzing historical data, and have become the mainstream of photovoltaic power generation prediction in recent years.

[0004] The application of deep learning methods in photovoltaic power generation prediction mainly includes recurrent neural network (RNN), long short-term memory network (LSTM), Transformer, etc. Among them, the Transformer model shows superior performance in time series modeling with its powerful self-attention mechanism. Compared with traditional RNN and LSTM, Transformer can simultaneously focus on the long-term and short-term dependencies of time series data, improving the accuracy and stability of prediction. However, the standard Transformer still faces some challenges in photovoltaic power generation prediction, such as the problem of hyperparameter selection and the optimization of model generalization ability.

[0005] To address these issues, this study introduces a hyperparameter prediction mechanism that dynamically adjusts the query, key, and value matrices of Transformer through a multi-layer perceptron (MLP) to adapt to the photovoltaic power generation prediction task under different environmental conditions. This method can adaptively optimize the Transformer structure according to data characteristics, improving the model's prediction ability in complex environments. Additionally, to further enhance the model's expressive power, we adopt text embedding as additional context information, enabling the model to make more accurate predictions by combining historical data with external information.

[0006] This study combines the Transformer prediction model with a hyperparameter self-adaptive adjustment strategy to improve the accuracy and robustness of photovoltaic power generation prediction. This method can not only effectively model the complex relationship between photovoltaic power generation and environmental factors but also enhance the model's adaptability under different climate conditions, providing more reliable technical support for smart grid scheduling and new energy management. Summary of the Invention

[0007] The first objective of the present invention is to overcome the shortcomings and deficiencies in the prior art and provide a dynamic prediction method for photovoltaic power generation based on information text feature extraction. By exploring the deeper relationship between meteorological conditions and power generation, this method dynamically adjusts the hyperparameter configuration of the prediction model, effectively solving the problems of low accuracy and high computational resource consumption in existing photovoltaic power generation predictions, and playing a key role in subsequent evaluations of the utilization rate of photovoltaic systems, diagnosis of photovoltaic power generation anomalies, and optimization of the usage methods of photovoltaic systems.

[0008] The second objective of the present invention is to provide a dynamic prediction system for photovoltaic power generation based on information text feature extraction.

[0009] The third objective of the present invention is to provide a storage medium.

[0010] The fourth objective of the present invention is to provide a computing device.

[0011] The first objective of the present invention is achieved through the following technical solutions: A dynamic prediction method for photovoltaic power generation based on information text feature extraction includes the following steps: S1, Preprocess the power generation data and meteorological data recorded in the photovoltaic power generation system; S2, Fine-tune the model T5 and train the model T5 using the existing power generation data and meteorological data; S3, Use the fine-tuned model T5 in S2 to extract summaries from the power generation data and meteorological data in S1 and convert them into embedding vectors; S4, Use a multi-layer perceptron MLP to recommend hyperparameter suggestions for the prediction model Transformer based on the embedding vectors in S3; S5. The prediction model Transformer is trained using the hyperparameter suggestions in S4. S6. Use the trained prediction model Transformer in S5 to predict future power generation based on existing power generation data, meteorological data, and future meteorological data.

[0012] Furthermore, in S1, the specific situation of preprocessing the power generation data and meteorological data recorded in the photovoltaic power generation system is as follows: a. Collect the power generation data and meteorological data recorded in the photovoltaic power generation system. b. Identify the missing values and outliers recorded in a. c. Mark and process the missing values and outliers identified in b. The processing method is to replace the missing values and outliers with the average of the values before and after them. d. Standardize the timestamps recorded in c, and uniformly convert the time to Unix timestamps. The conversion formula is: ; where UTC is the local time zone. e. Normalize the data in d, compress the data to a unified range, that is, within 0 to 1. The normalization calculation formula is: ; where is the data value to be normalized, is the maximum value in the column where the data value is located, is the data value and is the minimum value in the column where it is located.

[0013] Furthermore, in S2, the model T5 (Text-To-Text Transfer Transformer) is a general text processing model based on the Transformer architecture. By unifying various NLP tasks into the form of "text-to-text", it uses transfer learning to achieve multi-task processing in pre-training and fine-tuning.

[0014] Furthermore, in S2, when fine-tuning the model T5, the specific situation of training the model T5 using the existing power generation data and meteorological data is as follows: a. Collect the power generation data and meteorological data related to photovoltaic power generation. b. Fine-tune the model T5 using the data in a, and train the model T5 to extract a high-precision summary according to the text format of power generation data and meteorological data.

[0015] Furthermore, in S3, the specific situation of using the fine-tuned model T5 to extract a summary from the text format of the power generation data and meteorological data in step 1) and convert it into an embedding vector is as follows: a. Use the fine-tuned model T5 to extract a summary from the power generation data and meteorological data in S1; b. Split the summary extracted in a into sub-word units, that is , where represents the th sub-word unit in the text; c. Use the tokenizer of the fine-tuned model T5 to convert the sub-word units in b into corresponding input IDs, and the form of Input IDs is: , where is the start token, is the separator token; d. The encoder of the fine-tuned model T5 generates an embedding vector for each input ID in the Input IDs in c, and obtains an embedding vector set , where is the embedding vector of the th sub-word unit, is the hidden layer dimension; e. Perform average pooling on the embedding vectors of all sub-word units to obtain the embedding vector of the entire text. The calculation formula for average pooling is: ; where is the number of sub-word units; f. Combine the embedding vector v avg of the entire text obtained in e with other meteorological features x to obtain an input vector , where k is the dimension of the meteorological feature.

[0016] Furthermore, in S4, the prediction model Transformer is an architecture based on the self-attention mechanism and the feed-forward neural network, which performs sequence-to-sequence mapping through the encoder-decoder structure and uses the multi-head attention mechanism to capture global dependencies; the multi-layer perceptron MLP is a feed-forward neural network composed of multiple fully connected layers and non-linear activation functions.

[0017] Further, in S4, the specific situation of using a multi-layer perceptron (MLP) to generate hyperparameter suggestions for the prediction model Transformer based on the embedding vectors in S3 is as follows: a. The MLP generates dynamically adjusted parameters through forward propagation based on the embedding vectors in S3 That is , and the calculation formula for the dynamically adjusted parameters is: ; Among them, and are the weights and biases of the first layer, and are the weights and biases of the second layer, ReLU is the activation function, and Tanh restricts the output to the range of [−1, 1]; b. Use the dynamically adjusted parameters in a to adjust the query weight matrix W Query , key weight matrix W Key and value weight matrix W Value in the prediction model Transformer. The calculation formula for the dynamic adjustment of the weight matrix is: ; c. Use the dynamic weight matrix in b to calculate the query matrix Query , key matrix Key and value matrix Value . The matrix calculation formula is: ; Among them, X is the input feature matrix.

[0018] Further, in S5, the specific situation of the prediction model Transformer using the hyperparameter suggestions in S4 for model training is as follows: a. Transformer calculates the attention scores using the dot product of the dynamic query matrix Query and the dynamic key matrix Key . The calculation formula for the attention scores is: ; Among them, T represents the matrix transpose operation, and then the attention scores are normalized through the softmax function. The normalization formula is: ; b. Use the attention weights to perform weighted summation on the dynamic value matrix Value to obtain the final output. The calculation formula is .

[0019] Further, in S6, the trained model in S5 is used to predict the future power generation according to the data collected in S1 and the future meteorological data.

[0020] The second object of the present invention is achieved by the following technical solutions: A photovoltaic power generation dynamic prediction system based on information text feature extraction, which is used to implement the above-mentioned photovoltaic power generation dynamic prediction method based on text information feature extraction, and includes: A data processing module, which is used to process the data values and data formats recorded in the photovoltaic power generation system; A model fine-tuning module, which is used to fine-tune the model T5 and train the model T5 using the existing power generation data and meteorological data; A summary extraction and embedding vector conversion module, which is used to fine-tune the model T5 to extract the summary of power generation data and meteorological data and perform embedding vector conversion; A prediction model parameter recommendation module, which is used to recommend hyperparameter suggestions for the training of the prediction model by the multi-layer perceptron MLP; A prediction model training module, which is used to train the prediction model Transformer using the hyperparameter suggestions; The third object of the present invention is achieved by the following technical solutions: A storage medium stores a program, and when the program is executed by a processor, the above-mentioned photovoltaic power generation dynamic prediction method based on text information feature extraction is implemented.

[0021] The fourth object of the present invention is achieved by the following technical solutions: A computing device includes a device and a memory for storing a program executable by a processor. When the processor executes the program stored in the memory, the above-mentioned photovoltaic power generation dynamic prediction method based on text information feature extraction is implemented.

[0022] Compared with the prior art, the present invention has the following advantages and beneficial effects: 1. The present invention first considers from the perspective of extracting information feature summaries, and uses the model T5 to perform high-precision summary extraction on power generation data and meteorological data, which can capture the complex correlation between weather conditions and power generation, and improves the feature capture ability.

[0023] 2. The present invention first adopts the method of dynamically adjusting model parameters based on variable time-series data, automatically selects appropriate model training parameters according to power generation data and meteorological data in different time ranges, reduces ineffective searches, and improves the hyperparameter tuning efficiency.

[0024] 3. The present invention first fuses text summaries and numerical features, realizes the deep fusion of multi-modal data, improves the utilization value of data, enhances the ability to establish complex non-linear relationship models, and thus improves the prediction accuracy.

[0025] 4. For the first time, the present invention combines the fine-tuned model T5, enabling the model with generalization ability to be better at solving the problem of photovoltaic power generation prediction, and enhancing the adaptability of the prediction model.

[0026] 5. The present invention has a wide range of application space in the improvement of the photovoltaic power generation prediction method, and has broad prospects in improving the prediction accuracy of photovoltaic power generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic logical flow diagram of the method of the present invention; Figure 2 is an architecture diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The present invention will be further described below in conjunction with specific embodiments.

[0029] As Figure 1 shown, this embodiment discloses a dynamic prediction method for photovoltaic power generation based on information text feature extraction. First, the power generation data and meteorological data recorded in the photovoltaic power generation system are collected and preprocessed. Then, the existing dataset is used to fine-tune the model T5. After that, the model T5 extracts the summary of the preprocessed data and converts the summary into an embedding vector. Then, the multi-layer perceptron MLP recommends dynamic hyperparameter suggestions for the prediction model according to the embedding vector. After that, the prediction model uses the hyperparameter suggestions for training and predicting future power generation, and it includes the following steps: S1. The specific situation of preprocessing the power generation data and meteorological data recorded in the photovoltaic power generation system is as follows: a. Collect the power generation data and meteorological data recorded in the photovoltaic power generation system; b. Identify the missing values and outliers recorded in a; c. Mark and process the missing values and outliers identified in b, and the processing method is to replace the missing values and outliers with the average values of the previous and subsequent values of the missing values and outliers; d. Standardize the timestamps recorded in c, and uniformly convert the time to Unix timestamp. The conversion formula is: ; where UTC is the local time zone; e. Normalize the data in d, and compress the data to a unified range, that is, within 0 to 1. The normalization calculation formula is: ; where is the data value to be normalized, is the maximum value in the column where the data value is located, is the data value the minimum value in its column; f. Convert the power generation data and meteorological data after the missing value and outlier processing in step c, the timestamp normalization in step d, and the numerical normalization in step e into the text format of natural language.

[0030] Using the above steps, taking the power generation data and meteorological data of the photovoltaic power station D as an example, after marking and smoothing the missing values and outliers, unifying the timestamp format, and finally normalizing, the standardized data obtained D standard as shown, finally convert the standardized data D standard into the text format T .

[0031] S2. Fine-tune the model T5. Use the existing power generation data and meteorological data to train the model T5 to obtain the fine-tuned model T5 for photovoltaic power generation prediction requirements. The model T5 (Text-To-Text Transfer Transformer) is a general text processing model based on the Transformer architecture. By uniformly converting various NLP tasks into the form of "text-to-text", multi-task processing is achieved in pre-training and fine-tuning using transfer learning.

[0032] The specific situation of fine-tuning the model T5 and using the existing power generation data and meteorological data to train the model T5 is as follows: a. Collect the power generation data and meteorological data related to photovoltaic power generation; b. Use the data in a to fine-tune the model T5 and train the model T5 to extract high-precision summaries according to the text format of the power generation data and meteorological data.

[0033] Using the above steps, obtain the fine-tuned model T5 for the photovoltaic power generation prediction scenario.

[0034] S3. The specific situation of using the fine-tuned model T5 to extract summaries from the text format of the power generation data and meteorological data in S1 and convert them into embedding vectors is as follows: a. Use the fine-tuned model T5 to extract summaries from the power generation data and meteorological data in S1; b. Segment the summaries extracted in a into sub-word units, that is , where represents the text in the th sub-word unit; c. Use the tokenizer of the fine-tuned model T5 to convert the subword units in b into corresponding input IDs. The form of the Input IDs is: , where is the start token, is the separator token; d. The encoder of the fine-tuned model T5 generates the embedding vectors of each input ID in the Input IDs in c, obtaining the embedding vector set , where is the embedding vector of the -th subword unit, is the hidden layer dimension; e. Perform average pooling on the embedding vectors of all subword units to obtain the embedding vector of the entire text. The calculation formula for average pooling is: ; where is the number of subword units; f. Combine the embedding vector v avg of the entire text obtained in e with other meteorological features x to obtain the input vector , where k is the dimension of the meteorological feature.

[0035] Using the above steps, taking the text format T as an example, the fine-tuned model T5 extracts the summary from the text format T to obtain the summary T summary . Then, the summary T summary is segmented to obtain the segmented unit subword result as T summary = { t 1 , t 2 , …, t n}, and then use the tokenizer of the fine-tuned model T5 to convert the subword units into corresponding input IDs, obtaining Input IDs = { id 1 , id 2 , …, id n}. Then, convert the input IDs into embedding vectors through the encoder of the fine-tuned model T5, obtaining H = { h 1 , h 2 , …, hn}, then perform pooling on all the obtained embedding vectors, and finally merge them with the meteorological features to obtain the input vector .

[0036] S4. Use a multi-layer perceptron (MLP) to generate hyperparameter suggestions for the prediction model Transformer based on the embedding vectors in S3. The prediction model Transformer is an architecture based on the self-attention mechanism and the feed-forward neural network, which performs sequence-to-sequence mapping through an encoder-decoder structure and uses the multi-head attention mechanism to capture global dependencies. The multi-layer perceptron (MLP) is a feed-forward neural network composed of multiple fully connected layers and non-linear activation functions.

[0037] The specific situation of the multi-layer perceptron (MLP) generating hyperparameter suggestions for the prediction model Transformer based on the embedding vectors in S3 is as follows: a. The multi-layer perceptron (MLP) generates dynamically adjusted parameters through forward propagation based on the embedding vectors in S3 That is , and the calculation formula for the dynamically adjusted parameters is: ; Among them, and are the weights and biases of the first layer, and are the weights and biases of the second layer, ReLU is the activation function, and Tanh limits the output to the range of [−1, 1]; b. Use the dynamically adjusted parameters in a to adjust the query weight matrix W Query , key weight matrix W Key and value weight matrix W Value in the prediction model Transformer. The calculation formula for the dynamic adjustment of the weight matrix is: ; c. Use the dynamic weight matrix in b to calculate the query matrix Query , key matrix Key and value matrix Value . The matrix calculation formula is: ; Among them, X is the input feature matrix.

[0038] By adopting the above steps, the multi-layer perceptron (MLP) generates dynamically adjusted parameters v avg based on the embedding vectors , and then the prediction model dynamically adjusts the parameters Dynamically adjust the query weight matrix W Query , the key weight matrix W Key and the value weight matrix W Value , and further calculate the query matrix Query , the key matrix Key and the value matrix Value .

[0039] 5) The specific situation of the prediction model Transformer using the hyperparameter suggestions in S4 for model training is as follows: a. Transformer uses the dynamic query matrix in S4 Query and the dynamic key matrix Key to calculate the attention score through the dot product. The calculation formula of the attention score is: ; where, T represents the matrix transpose operation, and then the attention score is normalized through the softmax function. The normalization formula is: ; b. Use the attention weights to perform weighted summation on the dynamic value matrix Value to obtain the final output. The calculation formula is .

[0040] Using the above steps, the prediction model Transformer calculates the dynamic attention score Attention Score according to the dynamic query matrix Query and the dynamic key matrix Key in S4, then normalizes it through softmax, and then performs weighted summation on the attention weights and the dynamic value matrix Value in S4 to obtain the final input Output.

[0041] S6. Use the model trained in S5 to predict the future power generation according to the data collected in S1 and the future meteorological data.

[0042] Using the above steps, predict the future power generation according to the existing power generation data, meteorological data and future meteorological data to obtain the future power generation prediction result.

[0043] Embodiment 2 This embodiment discloses a photovoltaic power generation dynamic prediction system based on the extraction of information features in this article, which is used to implement the photovoltaic power generation dynamic prediction method based on the extraction of information features in Embodiment 1, asFigure 2 As shown in the figure, the system includes the following functional modules: A data processing module for processing the recorded data values and data formats in the photovoltaic power generation system; A model fine-tuning module for fine-tuning the model T5 and training the model T5 using the existing power generation data and meteorological data; A summary extraction and embedding vector conversion module for fine-tuning the model T5 to extract summaries of power generation data and meteorological data and perform embedding vector conversion; A prediction model parameter recommendation module for recommending hyperparameter suggestions for the training of the prediction model by the multi-layer perceptron MLP; A prediction model training module for training the prediction model Transformer using the hyperparameter suggestions; Embodiment 3 This embodiment discloses a storage medium storing a program, which when executed by a processor, implements the dynamic prediction method for photovoltaic power generation based on the information feature extraction described in Embodiment 1.

[0044] The storage medium in this embodiment may be a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), a USB flash drive, a mobile hard disk, or other media.

[0045] Embodiment 4 This embodiment discloses a computing device including a processor and a memory for storing the executable program of the processor. When the processor executes the program stored in the memory, it implements the dynamic prediction method for photovoltaic power generation based on the information feature extraction described in Embodiment 1.

[0046] The computing device described in this embodiment may be a desktop computer, a laptop computer, a smart phone, a PDA handheld terminal, a tablet computer, a programmable logic controller (PLC), or other terminal devices with processor functions.

[0047] In summary, this study proposes a brand-new method and system for predicting photovoltaic power generation. For the first time, the fine-tuning model T5 is introduced to extract features from power generation data and meteorological data and automatically generate summary texts to improve the accuracy of feature extraction. Based on the generated summary texts, this method can intelligently recommend the hyperparameter configuration of the prediction model, thereby reducing unnecessary consumption of computing resources, improving the training efficiency of the model, enhancing its generalization ability and robustness, providing guidance for the prediction idea of photovoltaic power generation, improving the practical use value, and having the value of promotion and being worthy of promotion.

[0048] The above-described embodiments are only the preferred embodiments of the present invention, and do not limit the scope of implementation of the present invention. Therefore, any changes made according to the shape and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for dynamic prediction of photovoltaic power generation based on information text feature extraction, characterized in that: The following steps are involved: S1, preprocessing the power generation data and meteorological data recorded in the photovoltaic power generation system; S2, fine-tuning model T5, using existing power generation data and meteorological data to train model T5; S3, uses the model T5 fine-tuned in S2 to extract the summary of the power generation data and meteorological data in S1 and convert them into embedding vectors; S4, uses a multi-layer perceptron MLP to recommend hyperparameters for the prediction model Transformer based on the embedding vector in S3; S5, the prediction model Transformer uses the hyperparameter recommendations in S4 for model training; S6, using the prediction model Transformer trained in S5 to predict future power generation based on existing power generation data and meteorological data as well as future meteorological data.

2. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized in that: In S1, the specific conditions of the power generation data and meteorological data recorded in the photovoltaic power generation system are as follows: a. Collect power generation data and meteorological data recorded in the photovoltaic power generation system; b. Identify missing values ​​and outliers recorded in a; c. Mark and process the missing values ​​and outliers identified in b. The processing method is to replace the missing values ​​and outliers with the average of the values ​​before and after the missing values ​​and outliers; d. Standardize the timestamps recorded in c and convert the times to Unix timestamps. The conversion formula is: ； Among them, UTC is the local time zone; e. Normalize the data in d and compress the data to a uniform range, that is, between 0 and 1. The normalization calculation formula is: ； in, is the data value that needs to be normalized. Is the data value The maximum value in the column. Is the data value The minimum value in its column; f. Convert the power generation data and meteorological data after the missing value and outlier processing in step c, the timestamp standardization in step d, and the numerical normalization in step e into a natural language text format.

3. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized in that: In S2, the model T5, namely Text-To-Text Transfer Transformer, is a general text processing model based on the Transformer architecture. It converts various NLP tasks into "text-to-text" form and uses transfer learning to achieve multi-task processing in pre-training and fine-tuning.

4. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized in that: In S1, fine-tune model T5. The specific situation of using existing power generation data and meteorological data to train model T5 is as follows: a. Collect power generation data and meteorological data related to photovoltaic power generation; b. Fine-tune model T5 using the data in a. Train model T5 to extract high-precision summaries based on the text format of power generation data and meteorological data.

5. The method for dynamic prediction of photovoltaic power generation based on information text feature extraction according to claim 1 is characterized in that: The specific situation of using the fine-tuned model T5 to extract the summary of the text format of the power generation data and meteorological data in S1 and convert them into embedding vectors is as follows: a. Use the fine-tuned model T5 to extract summary of power generation data and meteorological data in S1; b. Extract the summary from a is divided into subword units, i.e. ,in Representative text The subword units; c. Use the word segmenter of the fine-tuned model T5 to convert the subword units in b into corresponding input IDs. The form of Input IDs is: ,in is the start tag, is the delimiter marker; d. The encoder of fine-tuned model T5 generates an embedding vector for each input ID in Input IDs in c, and obtains the embedding vector set ,in It is The embedding vector of subword units, is the hidden layer dimension; e. Perform average pooling on the embedding vectors of all subword units to obtain the embedding vector of the entire text. The calculation formula for average pooling is: ； in is the number of subword units; f. Embed the entire text obtained in e v avg With other meteorological features x Combine to get the input vector ,in k It is the dimension of meteorological characteristics.

6. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized by: In S4, the prediction model Transformer is an architecture based on a self-attention mechanism and a feedforward neural network, which performs sequence-to-sequence mapping through an encoder-decoder structure and uses a multi-head attention mechanism to capture global dependencies; the multi-layer perceptron MLP is a feedforward neural network composed of multiple fully connected layers and nonlinear activation functions.

7. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized by: In S4, the specific situation of using the multi-layer perceptron MLP to generate the hyperparameter recommendations of the prediction model Transformer according to the embedding vector in S3 is as follows: a. The multi-layer perceptron MLP generates dynamic adjustment parameters through forward propagation based on the embedding vector in S3 Right now , the calculation formula of dynamic adjustment parameters is: ； in, and are the weights and biases of the first layer, and are the weights and biases of the second layer, ReLU is the activation function, and Tanh limits the output to [−1, 1]; b. Use the dynamic adjustment parameters in a to adjust the query weight matrix in the prediction model Transformer W Query , key weight matrix W Key Sum weight matrix W Value , the calculation formula for dynamic adjustment of the weight matrix is: ； c. Calculate the query matrix using the dynamic weight matrix in b. Query , key matrix Key Sum Matrix Value , the matrix calculation formula is: ； in, X is the input feature matrix.

8. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized by: In S5, the prediction model Transformer uses the hyperparameter recommendations in S4 for model training as follows: a. Transformer uses the dynamic query matrix in S4 Query and the dynamic key matrix Key The dot product calculation of is used to obtain the attention score. The calculation formula of the attention score is: ； Among them, T represents the matrix transpose operation, and then the attention score is normalized by the softmax function. The normalization formula is: ； b. Use attention weights to adjust the dynamic value matrix Value Perform weighted summation to get the final output. The calculation formula is: 。 9. The photovoltaic power generation dynamic prediction method based on information text feature extraction according to claim 1 is characterized by: In S6, the model trained in S5 is used to predict future power generation based on the data collected in S1 and future meteorological data.

10. A photovoltaic power generation dynamic prediction system based on information text feature extraction, characterized in that: A method for dynamically predicting photovoltaic power generation based on information text feature extraction according to any one of claims 1 to 9, comprising: A data processing module, used for processing data values ​​and data formats recorded in the photovoltaic power generation system; Model fine-tuning module, used to fine-tune model T5, using existing power generation data and meteorological data to train model T5; Summary extraction and embedding vector conversion module, used to fine-tune model T5 to extract power generation data and meteorological data summary and embedding vector conversion; Prediction model parameter recommendation module, which is used to recommend hyperparameters for training the multi-layer perceptron MLP recommendation prediction model; The prediction model training module is used to train the prediction model Transformer using hyperparameter recommendations.

11. A storage medium storing a program, characterized in that: When the program is executed by a processor, the method for dynamic prediction of photovoltaic power generation based on information text feature extraction according to any one of claims 1 to 9 is implemented.

12. A computing device comprising a processor and a memory for a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the method for dynamic prediction of photovoltaic power generation based on information text feature extraction according to any one of claims 1 to 9 is implemented.

Images