Photovoltaic prediction method and system capable of explaining MLREP multi-level regression integration

Abstract

The invention discloses a photovoltaic prediction method and system capable of explaining MLREP multi-level regression integration. The method comprises the steps that S1, a multi-source data set related to photovoltaic power generation is collected; s2, forming a preprocessed multi-source data set; s3, forming each hierarchical data set; s4, modeling the spatial-temporal features in each hierarchical data set by using a graph attention mechanism, and generating corresponding spatial-temporal feature weights; s5, constructing a multi-level regression integration framework based on the spatial-temporal feature representation, and generating a sub-prediction result; and S6, integrating sub-prediction results generated by the plurality of regression sub-models by using a weighted fusion method to generate a final photovoltaic power generation capacity prediction result. And S7, performing interpretability analysis on the final photovoltaic generating capacity prediction result in combination with the spatial-temporal characteristic weight and the prediction result of each regression sub-model, and generating an interpretability analysis report. According to the method, sensitivity index calculation can be combined, the source of prediction errors can be evaluated, and optimization suggestions can be given.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic technology, and in particular to a photovoltaic prediction method and system capable of explaining MLREP multi-level regression integration. Background Art

[0002] As the global energy structure transforms to clean and renewable energy, photovoltaic power generation, as an important component of new energy, is expanding its installed capacity and application scope. However, since photovoltaic power generation is affected by many factors such as meteorological environment, equipment status, and historical power generation laws, its power generation has obvious volatility and uncertainty.

[0003] At present, photovoltaic power generation prediction mainly relies on physical models and data-driven models. The physical model method constructs a prediction model based on the electrical characteristics of photovoltaic cells, solar radiation transmission model and meteorological factors. In theory, it can better explain the operation mechanism of the photovoltaic system, but it has high requirements on the accuracy of input variables and is difficult to cope with the complex and changeable actual environment, resulting in large prediction errors. In addition, physical models often require a large amount of parameter calibration, and the data collection and processing costs are high, which makes them difficult to promote and apply.

[0004] In recent years, data-driven machine learning methods have been widely used in photovoltaic power generation forecasting. Prediction models are trained based on historical data, including traditional statistical regression methods and deep learning methods. Although data-driven methods can adapt to different environmental conditions and improve prediction accuracy, there are still many problems with existing technologies. First, a single regression model is difficult to simultaneously capture the long-term trend, short-term fluctuations and instantaneous change characteristics of photovoltaic power generation, resulting in unstable prediction results. Second, existing methods have limitations in spatiotemporal modeling, and it is difficult to fully utilize the complex relationship between meteorological data, equipment status data and power generation data, resulting in limited prediction accuracy. In addition, most traditional data-driven methods lack interpretability, and it is difficult to effectively analyze the contribution of different influencing factors to the prediction results, which limits their application in actual photovoltaic scheduling and management.

[0005] Therefore, there is an urgent need for a new photovoltaic power generation prediction method that can comprehensively consider multi-level characteristics, spatiotemporal correlations, and have high prediction accuracy and interpretability, so as to improve the reliability and practical value of photovoltaic power generation prediction. Summary of the invention

[0006] One object of the present invention is to propose a photovoltaic prediction method and system that can interpret MLREP multi-level regression integration. The present invention can calculate sensitivity indicators, evaluate the source of prediction errors, and provide optimization suggestions.

[0007] A photovoltaic prediction method that can explain MLREP multi-level regression integration according to an embodiment of the present invention includes the following steps: S1. Collect multi-source data sets related to photovoltaic power generation; S2. preprocessing the collected multi-source data set to form a preprocessed multi-source data set; S3. extract hierarchical features from the preprocessed multi-source data set according to the operating characteristics of the photovoltaic power generation system to form hierarchical data sets; S4. Modeling the spatiotemporal features in each hierarchical data set using a graph attention mechanism, extracting the spatiotemporal feature representations of each hierarchical data set, and generating corresponding spatiotemporal feature weights; S5. construct a multi-level regression integration framework based on the spatiotemporal feature representation, wherein the multi-level regression integration framework includes multiple regression sub-models, each of which is trained using the spatiotemporal feature representation of the corresponding hierarchical data set to generate a sub-prediction result; S6. Integrate the sub-prediction results generated by the multiple regression sub-models using a weighted fusion method to generate a final photovoltaic power generation prediction result; S7. Perform an interpretability analysis on the final photovoltaic power generation prediction result in combination with the aforementioned spatiotemporal feature weights and the prediction results of each regression sub-model, and generate an interpretability analysis report.

[0008] Optionally, S1 includes collecting multi-source data sets related to photovoltaic power generation, the multi-source data sets including meteorological data, historical power generation data, equipment status data and environmental impact data, setting a collection time window, and constructing a photovoltaic power generation multi-source data set : ; in, Indicates PV power generation data records, For the time window The number of photovoltaic power generation data collected in is the acquisition timestamp, is the numerical feature vector related to photovoltaic power generation, It is the source device identifier of photovoltaic power generation data. is the category label of photovoltaic power generation data.

[0009] Optionally, S2 includes the following steps: S21. Based on the photovoltaic power generation multi-source dataset Perform data screening, remove samples with missing values ​​exceeding the set threshold, and remove duplicate data to form a screened photovoltaic power generation data set; S22. Standardize the data format of the screened photovoltaic power generation data set and set the normalization interval , the numerical characteristic vector related to photovoltaic power generation Perform minimum-maximum normalization to obtain a standardized photovoltaic power generation data set; S23. Based on the time characteristics of the photovoltaic power generation data, the standardized photovoltaic power generation data set is time-aligned, and the data timestamp is adjusted using a sliding time window method so that the photovoltaic power generation data is aligned according to the time dimension to form a time-aligned photovoltaic power generation data set; S24. Based on the operating status of photovoltaic power generation equipment, environmental influencing factors and meteorological characteristics, the missing values ​​of the photovoltaic power generation data set after time alignment are filled, and some missing feature values ​​are completed to form a complete photovoltaic power generation data set .

[0010] Optionally, S3 includes the following steps: S31. Based on the operation characteristics of the photovoltaic power generation system, the complete photovoltaic power generation data set Perform feature extraction. Feature extraction divides the features into long-term trend features, short-term fluctuation features and instantaneous change features according to the time distribution and physical meaning of the data, forming a stratified feature data set for photovoltaic power generation. The photovoltaic power generation hierarchical characteristic data set includes a long-term trend characteristic data set , short-term volatility characteristics dataset and instantaneous change feature datasets The long-term trend characteristic data set contains the power generation change trend information within a long time scale, the short-term fluctuation characteristic data set contains the power generation fluctuation characteristics within a day and a short period, and the instantaneous change characteristic data set contains the immediate impact of environmental conditions and equipment status changes on power generation; S32. Long-term trend feature dataset Perform feature calculations and use historical time series data to extract the long-term trend feature vectors of photovoltaic power generation systems ; S33. Short-term volatility characteristics dataset Perform feature calculations, analyze the photovoltaic power generation fluctuation pattern in a short period of time, and extract short-term fluctuation feature vectors ; S34. For instantaneous change feature data set Perform feature calculations, analyze the instantaneous impact of environmental variables and equipment status on photovoltaic power generation, and extract instantaneous change feature vectors ; S35. According to the importance of feature data at different levels, the long-term trend feature vector , short-term volatility characteristic vector and the instantaneous change eigenvector Fusion to form a complete photovoltaic power generation characteristic data set : .

[0011] Optionally, S4 includes the following steps: S41. Photovoltaic power generation layered feature dataset , constructing a multi-view spatiotemporal feature modeling diagram for photovoltaic power generation , including long-term trend views , Short-term volatility view and transient change views In each view, is a node set, each node represents the corresponding feature vector ,in , is the edge set, is the adjacency matrix; S42. For each view According to the spatiotemporal correlation of photovoltaic power generation data, the adjacency matrix is ​​calculated using the time-attenuated similarity function : ; in, Representation View Midpoint The characteristic vector of Representation View Midpoint The characteristic vector of For View The scale parameter, Representation Node With Node The difference in data collection time, For View The time decay factor of S43. For each view , a multi-head graph attention mechanism is used to model the spatiotemporal correlation between nodes, and the number of multi-heads is set , for each attention head , , calculate the attention weight : ; in, For View Middle The feature transformation matrix of the attention head is is the corresponding attention coefficient vector, represents the feature concatenation operation, For Node In view The set of neighbors in ; S44. For each view Each node in , fusion of multi-head attention results to generate updated spatiotemporal feature representation , the updated spatiotemporal feature representation Reflects the spatiotemporal dynamic characteristics of photovoltaic power generation in the corresponding view: ; in, is a nonlinear activation function; S45. Collect current weather feedback data , and the calculation view is represented based on the updated features of all nodes in each view The average eigenvector of : ; in, Representation View The number of nodes in the S46. Based on the average eigenvector With weather feedback data , using the mapping function Calculate the adaptive fusion weights of each view : ; S47. Generate the final photovoltaic power generation spatiotemporal feature representation set based on the updated feature representation and adaptive fusion weight of each view : ; in, Representation View Updated feature representation of all nodes in ; S48. Based on the final photovoltaic power generation spatiotemporal characteristics, the set , calculate the photovoltaic power generation characteristic weight vector : ; in, is the feature fusion parameter matrix.

[0012] Optionally, S5 includes the following steps: S51. Representing the set based on the spatiotemporal characteristics of photovoltaic power generation Build a multi-level regression integration framework and define a set of regression sub-models ,in, , and They are long-term trend regression sub-model, short-term fluctuation regression sub-model and instantaneous change regression sub-model. Each regression sub-model corresponds to a long-term trend feature data set. , short-term volatility characteristics dataset and instantaneous change feature datasets ; S52. Use supervised learning methods to ensemble regression sub-models Perform training and set the target variable as the photovoltaic power generation at the future moment , for each regression submodel , optimize its parameters , so that it minimizes the prediction error, the loss function is defined as: ; in, For the regression submodel The number of training data samples, For sample In view The spatiotemporal features in is the corresponding real value of photovoltaic power generation, is the trainable parameter of the regression sub-model; S53. Calculate the regression sub-model set based on the historical data of photovoltaic power generation and the model training error The prediction confidence weights of each regression sub-model : ; in, Reflection regression submodel Prediction accuracy on historical training data; S54. Use weighted regression fusion strategy to combine the prediction results of each regression sub-model to generate multi-level regression integrated prediction results : ; in, Indicates the moment The forecast value of future photovoltaic power generation, For the moment In view The spatiotemporal features in is the adaptive fusion weight of the regression sub-model.

[0013] Optionally, the S6 comprises the following steps: S61.According to the multi-level regression integration framework, obtain the sub-prediction results of the regression sub-model set and define the sub-prediction result set : ; in, The long-term trend regression submodel The generated sub-prediction results, Regression submodel for short-term volatility The generated sub-prediction results, The regression submodel for instantaneous changes Generated sub-prediction results; S62. Based on spatiotemporal feature weight vector and regression sub-model prediction confidence weights Calculate the final fusion weights ; S63. Use weighted fusion method to integrate all sub-forecast results and generate the final photovoltaic power generation forecast result : .

[0014] Optionally, the S7 includes the following steps: S71. Based on the final photovoltaic power generation prediction results , combined with the spatiotemporal feature weight vector and regression sub-model prediction confidence weights , construct the photovoltaic prediction interpretability analysis framework and analyze the influence of each characteristic variable on the prediction results; S72. Extract long-term trend characteristics, short-term fluctuation characteristics and instantaneous change characteristics based on the photovoltaic power generation layered feature data set, calculate the contribution of each feature variable in the final prediction result, define the feature importance scoring rule, and assign weights based on the feature contribution, where: Long-term trend characteristics: The characteristic contribution is positively correlated with the fitting degree of the historical trend. Variables with higher characteristic contribution include historical average power generation, power generation standard deviation, and long-term trend fitting parameters; Short-term fluctuation characteristics: The characteristic contribution is positively correlated with the matching degree of short-term fluctuation amplitude and periodic changes. Variables with higher characteristic contribution include power change rate, main frequency component, and autocorrelation function results; Instantaneous change characteristics: The characteristic contribution is positively correlated with the instantaneous impact of environmental variables. Variables with higher characteristic contributions include current irradiance, component temperature, and conversion efficiency. S73. Track the generation path of the prediction results based on the regression sub-model set, analyze the weight of each regression sub-model in the prediction process, and define the decision path tracking rules: When the confidence weight of the long-term trend regression submodel When the maximum, the long-term trend regression submodel The contribution is the highest, indicating that the current forecast mainly relies on long-term trend information; When the confidence weight of the short-term volatility regression submodel When the maximum value is reached, the short-term volatility regression submodel The contribution is the highest, indicating that the current forecast is significantly affected by short-term fluctuations; When the confidence weight of the regression sub-model changes instantaneously Maximum, instantaneous change regression submodel The contribution is the highest, indicating that environmental variables have a great influence on the current prediction; S74. Calculate the sensitivity index of photovoltaic prediction, analyze the response of prediction results to changes in input variables, and define sensitivity calculation rules: like , the forecast results are highly sensitive to irradiance changes, and special attention should be paid to meteorological fluctuations, among which, It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the irradiance, that is, the rate of change of the photovoltaic power generation prediction value when the irradiance changes. is the irradiance sensitivity threshold; like , the prediction results are sensitive to component temperature changes, and the temperature compensation strategy needs to be evaluated, where It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the surface temperature of the photovoltaic module, that is, the rate of change of the photovoltaic power generation prediction value when the module temperature changes. is the component temperature sensitivity threshold; like , the prediction results have a greater impact on the photovoltaic conversion efficiency, and attention should be paid to the aging and maintenance of components. It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the conversion efficiency of the photovoltaic module, that is, the rate of change of the photovoltaic power generation prediction value when the conversion efficiency of the photovoltaic module changes. is the sensitivity threshold of photovoltaic conversion efficiency; S75. Generate an interpretability analysis report based on the feature importance assessment, decision path tracing and sensitivity index calculation results. The report content includes: Final photovoltaic power generation forecast results and forecast confidence intervals; Ranking of the contribution of each characteristic variable to the prediction results; The regression sub-models and weight distribution that the prediction results depend on; Sensitivity analysis of forecast results to changes in key input variables; S76. Dynamically adjust the weight of the regression sub-model based on the interpretability analysis report and feature weights .

[0015] A photovoltaic prediction system capable of interpreting MLREP multi-level regression integration includes a computer program. When the computer program is executed by a processor, the steps of a photovoltaic prediction method capable of interpreting MLREP multi-level regression integration are implemented.

[0016] The beneficial effects of the present invention are: (1) Based on the operating characteristics of the photovoltaic power generation system, the present invention divides the input data into three levels: long-term trend, short-term fluctuation and instantaneous change, and extracts the corresponding feature vectors respectively to more accurately describe the temporal dynamic characteristics of photovoltaic power generation. Through hierarchical feature division, the long-term trend characteristics can reflect the overall power generation trend, the short-term fluctuation characteristics can capture periodic changes, and the instantaneous change characteristics can cope with the fluctuations of the environment and equipment status in a short time.

[0017] (2) The present invention constructs a multi-view spatiotemporal feature modeling graph, takes the long-term trend, short-term fluctuation and instantaneous change of photovoltaic power generation as different views, and uses the graph attention mechanism to learn the spatiotemporal features under each view. Specifically, in different time windows, the multi-head graph attention is used to calculate the association weight of each data node to fully capture the spatiotemporal correlation of photovoltaic power generation data, and dynamically adjusts the adjacency matrix weights through the time-attenuated similarity function to enhance the model's adaptability to time dynamics.

[0018] (3) The present invention introduces an explainable analysis method in the photovoltaic prediction process to make the prediction results transparent. Specifically, the feature importance evaluation method is used to analyze the contribution of different features to the final prediction results. The decision path tracing technology is used to reveal the main influencing factors used by different regression sub-models in the prediction process. In addition, the sensitivity index calculation is combined to evaluate the source of the prediction error and provide optimization suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a flow chart of a photovoltaic prediction method and system that can explain MLREP multi-level regression integration proposed by the present invention. DETAILED DESCRIPTION

[0020] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0021] refer to Figure 1 , a photovoltaic prediction method that can explain MLREP multi-level regression integration, including the following steps: S1. Collect multi-source data sets related to photovoltaic power generation; S2. preprocessing the collected multi-source data set to form a preprocessed multi-source data set; S3. extract hierarchical features from the preprocessed multi-source data set according to the operating characteristics of the photovoltaic power generation system to form hierarchical data sets; S4. Use the graph attention mechanism to model the spatiotemporal features in each hierarchical dataset, extract the spatiotemporal feature representation of each hierarchical dataset, and generate the corresponding spatiotemporal feature weights; S5. Construct a multi-level regression integration framework based on spatiotemporal feature representation, which includes multiple regression sub-models. Each regression sub-model is trained using the spatiotemporal feature representation of the corresponding hierarchical data set to generate sub-prediction results. S6. Integrate the sub-prediction results generated by multiple regression sub-models using a weighted fusion method to generate the final photovoltaic power generation prediction result; S7. Perform interpretability analysis on the final photovoltaic power generation prediction results in combination with the aforementioned spatiotemporal feature weights and the prediction results of each regression sub-model, and generate an interpretability analysis report.

[0022] In this embodiment, S1 includes collecting multi-source data sets related to photovoltaic power generation, which include meteorological data, historical power generation data, equipment status data and environmental impact data, setting the collection time window, and constructing a photovoltaic power generation multi-source data set. : ; in, Indicates PV power generation data records, For the time window The number of photovoltaic power generation data collected in is the acquisition timestamp, is the numerical feature vector related to photovoltaic power generation, It is the source device identifier of photovoltaic power generation data. is the category label of photovoltaic power generation data.

[0023] In this implementation, S2 includes the following steps: S21. Based on the photovoltaic power generation multi-source dataset Perform data screening, remove samples with missing values ​​exceeding the set threshold, and remove duplicate data to form a screened photovoltaic power generation data set; S22. Standardize the data format of the screened photovoltaic power generation data set and set the normalization interval , the numerical characteristic vector related to photovoltaic power generation Perform minimum-maximum normalization to obtain a standardized photovoltaic power generation data set; S23. Based on the time characteristics of the photovoltaic power generation data, the standardized photovoltaic power generation data set is time-aligned, and the data timestamp is adjusted using a sliding time window method so that the photovoltaic power generation data is aligned according to the time dimension to form a time-aligned photovoltaic power generation data set; S24. Based on the operating status of photovoltaic power generation equipment, environmental influencing factors and meteorological characteristics, the missing values ​​of the photovoltaic power generation data set after time alignment are filled, and some missing feature values ​​are completed to form a complete photovoltaic power generation data set .

[0024] In this implementation, S3 includes the following steps: S31. Based on the operation characteristics of the photovoltaic power generation system, the complete photovoltaic power generation data set Perform feature extraction. Feature extraction divides the features into long-term trend features, short-term fluctuation features and instantaneous change features according to the time distribution and physical meaning of the data, forming a stratified feature data set for photovoltaic power generation. , the photovoltaic power generation layered characteristic data set includes the long-term trend characteristic data set , short-term volatility characteristics dataset and instantaneous change feature datasets ,The long-term trend feature dataset contains the power generation change trend information in a long time scale, the short-term fluctuation feature dataset contains the power generation fluctuation characteristics within a day and a short period, and the instantaneous change feature dataset contains the immediate impact of environmental conditions and equipment status changes on power generation; S32. Long-term trend feature dataset Perform feature calculations and use historical time series data to extract the long-term trend feature vectors of photovoltaic power generation systems ; S33. Short-term volatility characteristics dataset Perform feature calculations, analyze the photovoltaic power generation fluctuation pattern in a short period of time, and extract short-term fluctuation feature vectors ; S34. For instantaneous change feature data set Perform feature calculations, analyze the instantaneous impact of environmental variables and equipment status on photovoltaic power generation, and extract instantaneous change feature vectors ; S35. According to the importance of feature data at different levels, the long-term trend feature vector , short-term volatility characteristic vector and the instantaneous change eigenvector Fusion to form a complete photovoltaic power generation characteristic data set : .

[0025] In this implementation, S4 includes the following steps: S41. Photovoltaic power generation layered feature dataset , constructing a multi-view spatiotemporal feature modeling diagram for photovoltaic power generation , including long-term trend views , Short-term volatility view and transient change views In each view, is a node set, each node represents the corresponding feature vector ,in , is the edge set, is the adjacency matrix; S42. For each view According to the spatiotemporal correlation of photovoltaic power generation data, the adjacency matrix is ​​calculated using the time-attenuated similarity function : ; in, Representation View Midpoint The characteristic vector of Representation View Midpoint The characteristic vector of For View The scale parameter, Representation Node With Node The difference in data collection time, For View The time decay factor of S43. For each view , a multi-head graph attention mechanism is used to model the spatiotemporal correlation between nodes, and the number of multi-heads is set , for each attention head , , calculate the attention weight : ; in, For View Middle The feature transformation matrix of the attention head is is the corresponding attention coefficient vector, represents the feature concatenation operation, For Node In view The set of neighbors in ; S44. For each view Each node in , fusion of multi-head attention results to generate updated spatiotemporal feature representation , the updated spatiotemporal feature representation Reflects the spatiotemporal dynamic characteristics of photovoltaic power generation in the corresponding view: ; in, is a nonlinear activation function; S45. Collect current weather feedback data , and the calculation view is represented based on the updated features of all nodes in each view The average eigenvector of : ; in, Representation View The number of nodes in the S46. Based on the average eigenvector With weather feedback data , using the mapping function Calculate the adaptive fusion weights of each view : ; S47. Generate the final photovoltaic power generation spatiotemporal feature representation set based on the updated feature representation and adaptive fusion weight of each view : ; in, Representation View Updated feature representation of all nodes in ; S48. Based on the final photovoltaic power generation spatiotemporal characteristics, the set , calculate the photovoltaic power generation characteristic weight vector : ; in, is the feature fusion parameter matrix.

[0026] In this implementation, S5 includes the following steps: S51. Representing the set based on the spatiotemporal characteristics of photovoltaic power generation Build a multi-level regression integration framework and define a set of regression sub-models ,in, , and They are long-term trend regression sub-model, short-term fluctuation regression sub-model and instantaneous change regression sub-model. Each regression sub-model corresponds to a long-term trend feature data set. , short-term volatility characteristics dataset and instantaneous change feature datasets ; S52. Use supervised learning methods to ensemble regression sub-models Perform training and set the target variable as the photovoltaic power generation at the future moment , for each regression submodel , optimize its parameters , so that it minimizes the prediction error, the loss function is defined as: ; in, For the regression submodel The number of training data samples, For sample In view The spatiotemporal features in is the corresponding real value of photovoltaic power generation, is the trainable parameter of the regression sub-model; S53. Calculate the regression sub-model set based on the historical data of photovoltaic power generation and the model training error The prediction confidence weights of each regression sub-model : ; in, Reflection regression submodel Prediction accuracy on historical training data; S54. Use weighted regression fusion strategy to combine the prediction results of each regression sub-model to generate multi-level regression integrated prediction results : ; in, Indicates the moment The forecast value of future photovoltaic power generation, For the moment In view The spatiotemporal features in is the adaptive fusion weight of the regression sub-model.

[0027] In this implementation, S6 includes the following steps: S61.According to the multi-level regression integration framework, obtain the sub-prediction results of the regression sub-model set and define the sub-prediction result set : ; in, The long-term trend regression submodel The generated sub-prediction results, The short-term volatility regression submodel The generated sub-prediction results, The regression submodel for instantaneous changes Generated sub-prediction results; S62. Based on spatiotemporal feature weight vector and regression sub-model prediction confidence weights Calculate the final fusion weights ; S63. Use weighted fusion method to integrate all sub-forecast results and generate the final photovoltaic power generation forecast result : .

[0028] In this implementation, S7 includes the following steps: S71. Based on the final photovoltaic power generation prediction results , combined with the spatiotemporal feature weight vector and regression sub-model prediction confidence weights , construct the photovoltaic prediction interpretability analysis framework and analyze the influence of each characteristic variable on the prediction results; S72. Extract long-term trend characteristics, short-term fluctuation characteristics and instantaneous change characteristics based on the photovoltaic power generation layered feature data set, calculate the contribution of each feature variable in the final prediction result, define the feature importance scoring rule, and assign weights based on the feature contribution, where: Long-term trend characteristics: The characteristic contribution is positively correlated with the fitting degree of the historical trend. Variables with higher characteristic contribution include historical average power generation, power generation standard deviation, and long-term trend fitting parameters; Short-term fluctuation characteristics: The characteristic contribution is positively correlated with the matching degree of short-term fluctuation amplitude and periodic changes. Variables with higher characteristic contribution include power change rate, main frequency component, and autocorrelation function results; Instantaneous change characteristics: The characteristic contribution is positively correlated with the instantaneous impact of environmental variables. Variables with higher characteristic contributions include current irradiance, component temperature, and conversion efficiency. S73. Track the generation path of the prediction results based on the regression sub-model set, analyze the weight of each regression sub-model in the prediction process, and define the decision path tracking rules: When the confidence weight of the long-term trend regression submodel When the maximum, the long-term trend regression submodel The contribution is the highest, indicating that the current forecast mainly relies on long-term trend information; When the confidence weight of the short-term volatility regression submodel When the maximum value is reached, the short-term volatility regression submodel The contribution is the highest, indicating that the current forecast is significantly affected by short-term fluctuations; When the confidence weight of the regression sub-model changes instantaneously Maximum, instantaneous change regression submodel The contribution is the highest, indicating that environmental variables have a great influence on the current prediction; S74. Calculate the sensitivity index of photovoltaic prediction, analyze the response of prediction results to changes in input variables, and define sensitivity calculation rules: like , the forecast results are highly sensitive to irradiance changes, and special attention should be paid to meteorological fluctuations, among which, It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the irradiance, that is, the rate of change of the photovoltaic power generation prediction value when the irradiance changes. is the irradiance sensitivity threshold; like , the prediction results are sensitive to component temperature changes, and the temperature compensation strategy needs to be evaluated, where It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the surface temperature of the photovoltaic module, that is, the rate of change of the photovoltaic power generation prediction value when the module temperature changes. is the component temperature sensitivity threshold; like , the prediction results have a greater impact on the photovoltaic conversion efficiency, and attention should be paid to the aging and maintenance of components. It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the conversion efficiency of the photovoltaic module, that is, the rate of change of the photovoltaic power generation prediction value when the conversion efficiency of the photovoltaic module changes. is the sensitivity threshold of photovoltaic conversion efficiency; S75. Generate an interpretability analysis report based on the feature importance assessment, decision path tracing and sensitivity index calculation results. The report content includes: Final photovoltaic power generation forecast results and forecast confidence intervals; Ranking of the contribution of each characteristic variable to the prediction results; The regression sub-models and weight distribution that the prediction results depend on; Sensitivity analysis of forecast results to changes in key input variables; S76. Dynamically adjust the weight of the regression sub-model based on the interpretability analysis report and feature weights .

[0029] A photovoltaic prediction system capable of interpreting MLREP multi-level regression integration includes a computer program. When the computer program is executed by a processor, the steps of a photovoltaic prediction method capable of interpreting MLREP multi-level regression integration are implemented.

[0030] Example 1: On August 12, 2023, the operator discovered during the dispatch process that the local weather forecast showed that the area would experience short-term heavy rainfall between 14:00 and 16:00 in the afternoon of the same day, accompanied by a rapid increase in cloud coverage. However, the traditional photovoltaic prediction system of the power station did not accurately reflect the risk of a decrease in photovoltaic power generation due to this weather change in the forecast report generated at 12:00, and still predicted that the photovoltaic power generation at 14:00 would be around 320kW. Based on experience, the operator judged that this forecast was too optimistic and had great uncertainty.

[0031] In order to further verify the accuracy of the prediction, the operator decided to introduce the method of the present invention, namely the explainable MLREP multi-level regression integrated photovoltaic prediction method, and test its prediction effect in practical applications. They immediately called this method and input the meteorological data, historical power generation data, equipment status data and environmental impact data from 06:00 to 12:00 that morning for calculation. A hierarchical feature extraction strategy was used to calculate the impact of long-term trends, short-term fluctuations and instantaneous changes respectively, and the graph attention mechanism was used to model the spatiotemporal characteristics of the photovoltaic power generation system, and finally the photovoltaic power generation forecast value at 14:00 was generated.

[0032] At 12:15, this method produced a new forecast result: the photovoltaic power generation at 14:00 was expected to be about 245.3kW, nearly 23.3% lower than the 320kW predicted by the traditional method. This gap alerted the operators, who immediately decided to use the new forecast results to optimize grid dispatch and notified the dispatch center to adjust the operation plan of the standby thermal power units to prevent grid load imbalance caused by the sudden drop in photovoltaic power generation.

[0033] At 14:00, actual monitoring data showed that the actual power generation of the photovoltaic power station was 241.6kW. The prediction error of the method of the present invention was only 1.5%, while the error of the traditional method was as high as 32.8%. The operator found that the method of the present invention can more accurately capture the short-term power fluctuations caused by weather changes, avoiding the misjudgment caused by the traditional method due to the lack of short-term meteorological change characteristics.

[0034] During the same time period, the dispatch center received feedback from another photovoltaic power station, which experienced a sudden sandstorm on July 22. The forecast report generated by the traditional forecasting system of the site at 07:00 showed that the photovoltaic power generation at 11:00 on the same day was about 410kW, but the site monitoring equipment found that the air quality index (AQI) rose sharply after 08:30, soaring from 55 (good) to 185 (moderate pollution), and visibility dropped to 1.2 kilometers.

[0035] The site's operations team decided to use the method of the present invention to make a revised forecast. At 08:45, the operations team input the meteorological data between 04:00 and 08:30 of the day into the method of the present invention, including wind speed, air particle concentration, cloud thickness and temperature data. The method quickly calculated the impact of environmental changes on photovoltaic power generation, especially the impact of AQI changes on the amount of light received by the photovoltaic power station, and combined with historical data under similar meteorological conditions in the past, it obtained a revised forecast value of 358.7kW for 11:00.

[0036] When the real power generation data at 11:00 was recorded, it was found that the actual power generation was 352.9kW. The prediction error of the method of the present invention was only 1.6%, while the prediction error of the traditional method reached 14.5%. The managers of the dispatching center realized that the traditional method had limited prediction ability when facing sudden environmental changes. The method of the present invention can more accurately predict the changing trend of photovoltaic power generation through hierarchical feature extraction and spatiotemporal modeling, providing a more reliable tool for future intelligent management of photovoltaic power stations.

[0037] In another case, on May 15, 2023, during routine maintenance, a photovoltaic park operation team discovered that a group of inverters (device ID: INV-20230515-008) had output fluctuations and unstable power since 10:30, and the feedback data from the photovoltaic module cleanliness detection sensor (device ID: SENSOR-CLN-101) showed that the cleanliness factor of the photovoltaic module had dropped to 0.72, which was lower than the normal operating threshold (0.85).

[0038] In order to determine the impact of this factor on photovoltaic power generation, the operator used the method of the present invention to recalculate the photovoltaic power generation forecast value at 13:00 on the same day at 10:45. The forecast result of the traditional method was 510.2kW, while the method of the present invention combined with the impact of the cleanliness of the photovoltaic modules gave a new forecast value of 468.9kW, and clearly pointed out in the forecast report: A 15.3% reduction in cleanliness will have an impact of about 7.2% on power generation efficiency; short-term meteorological effects (cloud changes) will have an impact of about 2.3%; equipment status (inverter fluctuations) will have an impact of about 1.6%; According to the prediction data provided by the method of the present invention, the operation team decided to arrange the cleaning work in advance and dispatched maintenance personnel to clean the group of photovoltaic modules at 11:30. The monitoring data at 13:00 showed that after the cleaning was completed, the actual power generation of the group of photovoltaic modules recovered to 497.1 kW, and the error decreased from 10.5% of the traditional method to 1.3%, verifying the effectiveness of the method of the present invention.

[0039] Table 1 Data comparison between the method of the present invention and the traditional method

[0040] It can be seen from the above cases that the method of the present invention has stronger short-term fluctuation prediction ability and environmental adaptability than traditional methods. Especially when dealing with sudden weather events, air pollution and equipment status fluctuations, the prediction error is significantly reduced and the prediction reliability is significantly improved, providing more accurate decision-making support for the intelligent management of photovoltaic power stations.

[0041] Experimental data show that the prediction error of the method of the present invention is reduced by 60.2%-95.4% compared with the traditional method when sudden weather and equipment failure have a strong impact, providing a more reliable basis for the optimization of photovoltaic power generation scheduling and having broad engineering application value.

[0042] According to the operating characteristics of the photovoltaic power generation system, the present invention divides the input data into three levels: long-term trend, short-term fluctuation and instantaneous change, and extracts the corresponding feature vectors respectively to more accurately describe the temporal dynamic characteristics of photovoltaic power generation. Through hierarchical feature division, the long-term trend characteristics can reflect the overall power generation trend, the short-term fluctuation characteristics can capture periodic changes, and the instantaneous change characteristics can cope with fluctuations in the environment and equipment status in a short period of time.

[0043] The present invention constructs a multi-view spatiotemporal feature modeling graph, takes the long-term trend, short-term fluctuation and instantaneous change of photovoltaic power generation as different views, and uses the graph attention mechanism to learn the spatiotemporal features under each view. Specifically, in different time windows, the multi-head graph attention is used to calculate the association weight of each data node to fully capture the spatiotemporal correlation of photovoltaic power generation data, and dynamically adjusts the adjacency matrix weights through the time-attenuated similarity function to enhance the model's adaptability to time dynamics.

[0044] The present invention introduces an explainable analysis method in the photovoltaic prediction process to make the prediction results transparent. Specifically, the feature importance evaluation method is used to analyze the contribution of different features to the final prediction results. The decision path tracing technology is used to reveal the main influencing factors used by different regression sub-models in the prediction process. In addition, the sensitivity index calculation is combined to evaluate the source of the prediction error and provide optimization suggestions.

[0045] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A photovoltaic prediction method that can interpret MLREP multi-level regression integration, characterized in that: The steps include: S1. Collect multi-source data sets related to photovoltaic power generation; S2. preprocessing the collected multi-source data set to form a preprocessed multi-source data set; S3. extract hierarchical features from the preprocessed multi-source data set according to the operating characteristics of the photovoltaic power generation system to form hierarchical data sets; S4. Modeling the spatiotemporal features in each hierarchical data set using a graph attention mechanism, extracting the spatiotemporal feature representations of each hierarchical data set, and generating corresponding spatiotemporal feature weights; S5. construct a multi-level regression integration framework based on the spatiotemporal feature representation, wherein the multi-level regression integration framework includes multiple regression sub-models, each of which is trained using the spatiotemporal feature representation of the corresponding hierarchical data set to generate a sub-prediction result; S6. Integrate the sub-prediction results generated by the multiple regression sub-models using a weighted fusion method to generate a final photovoltaic power generation prediction result; S7. Perform an interpretability analysis on the final photovoltaic power generation prediction result in combination with the aforementioned spatiotemporal feature weights and the prediction results of each regression sub-model, and generate an interpretability analysis report.

2. A photovoltaic prediction method based on interpretable MLREP multi-level regression integration according to claim 1, characterized in that: S1 includes collecting multi-source data sets related to photovoltaic power generation, the multi-source data sets include meteorological data, historical power generation data, equipment status data and environmental impact data, setting a collection time window, and constructing a photovoltaic power generation multi-source data set : ； in, Indicates Photovoltaic power generation data records, For the time window The number of photovoltaic power generation data collected in is the acquisition timestamp, is the numerical feature vector related to photovoltaic power generation, It is the source device identifier of photovoltaic power generation data. is the category label of photovoltaic power generation data.

3. A photovoltaic prediction method based on interpretable MLREP multi-level regression integration according to claim 1, characterized in that: The S2 comprises the following steps: S21. Based on the photovoltaic power generation multi-source dataset Perform data screening, remove samples with missing values ​​exceeding the set threshold, and remove duplicate data to form a screened photovoltaic power generation data set; S22. Standardize the data format of the screened photovoltaic power generation data set and set the normalization interval , the numerical characteristic vector related to photovoltaic power generation Perform minimum-maximum normalization to obtain a standardized photovoltaic power generation data set; S23. Based on the time characteristics of the photovoltaic power generation data, the standardized photovoltaic power generation data set is time-aligned, and the data timestamp is adjusted using a sliding time window method so that the photovoltaic power generation data is aligned according to the time dimension to form a time-aligned photovoltaic power generation data set; S24. Based on the operating status of photovoltaic power generation equipment, environmental influencing factors and meteorological characteristics, the missing values ​​of the photovoltaic power generation data set after time alignment are filled, and some missing feature values ​​are completed to form a complete photovoltaic power generation data set .

4. A photovoltaic prediction method based on interpretable MLREP multi-level regression integration according to claim 1, characterized in that: The S3 comprises the following steps: S31. Based on the operation characteristics of the photovoltaic power generation system, the complete photovoltaic power generation data set Perform feature extraction. Feature extraction divides the features into long-term trend features, short-term fluctuation features and instantaneous change features according to the time distribution and physical meaning of the data, forming a stratified feature data set for photovoltaic power generation. The photovoltaic power generation hierarchical characteristic data set includes a long-term trend characteristic data set , short-term volatility characteristics dataset and instantaneous change feature datasets The long-term trend characteristic data set contains the power generation change trend information within a long time scale, the short-term fluctuation characteristic data set contains the power generation fluctuation characteristics within a day and a short period, and the instantaneous change characteristic data set contains the immediate impact of environmental conditions and equipment status changes on power generation; S32. Long-term trend feature dataset Perform feature calculations and use historical time series data to extract the long-term trend feature vectors of photovoltaic power generation systems ; S33. Short-term volatility characteristics dataset Perform feature calculations, analyze the photovoltaic power generation fluctuation pattern in a short period of time, and extract short-term fluctuation feature vectors ; S34. For instantaneous change feature data set Perform feature calculations, analyze the instantaneous impact of environmental variables and equipment status on photovoltaic power generation, and extract instantaneous change feature vectors ; S35. According to the importance of feature data at different levels, the long-term trend feature vector , short-term volatility characteristic vector and the instantaneous change eigenvector Fusion to form a complete photovoltaic power generation characteristic data set : 。 5. The photovoltaic prediction method of the interpretable MLREP multi-level regression integration according to claim 1 is characterized in that: The S4 comprises the following steps: S41. Photovoltaic power generation layered feature dataset , constructing a multi-view spatiotemporal feature modeling diagram for photovoltaic power generation , including long-term trend views , Short-term volatility view and transient change views In each view, is a node set, each node represents the corresponding feature vector ,in , is the edge set, is the adjacency matrix; S42. For each view According to the spatiotemporal correlation of photovoltaic power generation data, the adjacency matrix is ​​calculated using the time-attenuated similarity function : ； in, Representation View Midpoint The characteristic vector of Representation View Midpoint The characteristic vector of For View The scale parameter, Representation Node With Node The difference in data collection time, For View The time decay factor of S43. For each view , a multi-head graph attention mechanism is used to model the spatiotemporal correlation between nodes, and the number of multi-heads is set , for each attention head , , calculate the attention weight : ； in, For View Middle The feature transformation matrix of the attention head is is the corresponding attention coefficient vector, represents the feature concatenation operation, For Node In view The set of neighbors in ; S44. For each view Each node in , fusion of multi-head attention results to generate updated spatiotemporal feature representation , the updated spatiotemporal feature representation Reflects the spatiotemporal dynamic characteristics of photovoltaic power generation in the corresponding view: ； in, is a nonlinear activation function; S45. Collect current weather feedback data , and the calculation view is represented based on the updated features of all nodes in each view The average eigenvector of : ； in, Representation View The number of nodes in the S46. Based on the average eigenvector With weather feedback data , using the mapping function Calculate the adaptive fusion weights of each view : ； S47. Generate the final photovoltaic power generation spatiotemporal feature representation set based on the updated feature representation and adaptive fusion weight of each view : ； in, Representation View Updated feature representation of all nodes in ; S48. Based on the final photovoltaic power generation spatiotemporal characteristics, the set , calculate the photovoltaic power generation characteristic weight vector : ； in, is the feature fusion parameter matrix.

6. A photovoltaic prediction method based on interpretable MLREP multi-level regression integration according to claim 1, characterized in that: The S5 comprises the following steps: S51. Representing the set based on the spatiotemporal characteristics of photovoltaic power generation Build a multi-level regression integration framework and define a set of regression sub-models ,in, , and They are long-term trend regression sub-model, short-term fluctuation regression sub-model and instantaneous change regression sub-model. Each regression sub-model corresponds to a long-term trend feature data set. , short-term volatility characteristics dataset and instantaneous change feature datasets ; S52. Use supervised learning methods to ensemble regression sub-models Perform training and set the target variable as the photovoltaic power generation at the future moment , for each regression submodel , optimize its parameters , so that it minimizes the prediction error, the loss function is defined as: ； in, For the regression submodel The number of training data samples, For sample In view The spatiotemporal features in is the corresponding real value of photovoltaic power generation, is the trainable parameter of the regression sub-model; S53. Calculate the regression sub-model set based on the historical data of photovoltaic power generation and the model training error The prediction confidence weights of each regression sub-model : ； in, Reflection regression submodel Prediction accuracy on historical training data; S54. Use weighted regression fusion strategy to combine the prediction results of each regression sub-model to generate multi-level regression integrated prediction results : ； in, Indicates the moment The forecast value of future photovoltaic power generation, For the moment In view The spatiotemporal features in is the adaptive fusion weight of the regression sub-model.

7. A photovoltaic prediction method based on interpretable MLREP multi-level regression integration according to claim 6, characterized in that: The S6 comprises the following steps: S61.According to the multi-level regression integration framework, obtain the sub-prediction results of the regression sub-model set and define the sub-prediction result set : ； in, The long-term trend regression submodel The generated sub-prediction results, The short-term volatility regression submodel The generated sub-prediction results, The regression submodel for instantaneous changes Generated sub-prediction results; S62. Based on spatiotemporal feature weight vector and regression sub-model prediction confidence weights Calculate the final fusion weights ; S63. Use weighted fusion method to integrate all sub-forecast results and generate the final photovoltaic power generation forecast result : 。 8. The photovoltaic prediction method of the interpretable MLREP multi-level regression integration according to claim 1 is characterized in that: The S7 comprises the following steps: S71. Based on the final photovoltaic power generation prediction results , combined with the spatiotemporal feature weight vector and regression sub-model prediction confidence weights , construct the photovoltaic prediction interpretability analysis framework and analyze the influence of each characteristic variable on the prediction results; S72. Extract long-term trend characteristics, short-term fluctuation characteristics and instantaneous change characteristics based on the photovoltaic power generation layered feature data set, calculate the contribution of each feature variable in the final prediction result, define the feature importance scoring rule, and assign weights based on the feature contribution, where: Long-term trend characteristics: The characteristic contribution is positively correlated with the fitting degree of the historical trend. Variables with higher characteristic contribution include historical average power generation, power generation standard deviation, and long-term trend fitting parameters; Short-term fluctuation characteristics: The characteristic contribution is positively correlated with the matching degree of short-term fluctuation amplitude and periodic changes. Variables with higher characteristic contribution include power change rate, main frequency component, and autocorrelation function results; Instantaneous change characteristics: The characteristic contribution is positively correlated with the instantaneous impact of environmental variables. Variables with higher characteristic contributions include current irradiance, component temperature, and conversion efficiency. S73. Track the generation path of the prediction results based on the regression sub-model set, analyze the weight of each regression sub-model in the prediction process, and define the decision path tracking rules: When the confidence weight of the long-term trend regression submodel When the maximum, the long-term trend regression submodel The contribution is the highest, indicating that the current forecast mainly relies on long-term trend information; When the confidence weight of the short-term volatility regression submodel When the maximum value is reached, the short-term volatility regression submodel The contribution is the highest, indicating that the current forecast is significantly affected by short-term fluctuations; When the confidence weight of the regression sub-model changes instantaneously Maximum, instantaneous change regression submodel The contribution is the highest, indicating that environmental variables have a great influence on the current prediction; S74. Calculate the sensitivity index of photovoltaic prediction, analyze the response of prediction results to changes in input variables, and define sensitivity calculation rules: like , the forecast results are highly sensitive to irradiance changes, and special attention should be paid to meteorological fluctuations, among which, It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the irradiance, that is, the rate of change of the photovoltaic power generation prediction value when the irradiance changes. is the irradiance sensitivity threshold; like , the prediction results are sensitive to component temperature changes, and the temperature compensation strategy needs to be evaluated, where It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the surface temperature of the photovoltaic module, that is, the rate of change of the photovoltaic power generation prediction value when the module temperature changes. is the component temperature sensitivity threshold; like , the prediction results have a greater impact on the photovoltaic conversion efficiency, and attention should be paid to the aging and maintenance of components. It represents the partial derivative of the final photovoltaic power generation prediction result with respect to the conversion efficiency of the photovoltaic module, that is, the rate of change of the photovoltaic power generation prediction value when the conversion efficiency of the photovoltaic module changes. is the sensitivity threshold of photovoltaic conversion efficiency; S75. Generate an interpretability analysis report based on the feature importance evaluation, decision path tracing and sensitivity index calculation results. The report content includes: Final photovoltaic power generation forecast results and forecast confidence intervals; Ranking of the contribution of each characteristic variable to the prediction results; The regression sub-models and weight distribution that the prediction results depend on; Sensitivity analysis of forecast results to changes in key input variables; S76. Dynamically adjust the weight of the regression sub-model based on the interpretability analysis report and feature weights .

9. A photovoltaic prediction system capable of interpreting MLREP multi-level regression integration, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of a photovoltaic prediction method capable of interpreting MLREP multi-level regression integration as described in any one of claims 1 to 8 are implemented.

Images