Generating capacity prediction method based on photovoltaic power generation efficiency

Abstract

The invention relates to the technical field of photovoltaic power generation, and discloses a photovoltaic power generation efficiency-based power generation capacity prediction method, which comprises the following steps of S1, data collection and preprocessing; s2, establishing a prediction model; and S3, predicting the generating capacity according to the prediction model. Compared with the prior art, the method has the advantages that an accurate, reliable and practical prediction model can be established through reasonable data collection, preprocessing, construction of a prediction model based on a physical model and a time sequence model and through the steps of training, evaluation, verification and the like; the method can help people to better understand the performance and potential of a photovoltaic power generation system, and provides a scientific basis for the planning, design, operation and maintenance of photovoltaic power generation.

Description

Technical Field

[0001] The invention relates to the technical field of photovoltaic power generation, and in particular to a method for predicting power generation based on photovoltaic power generation efficiency. Background Art

[0002] Photovoltaic power generation has obvious intermittent, random and volatile characteristics. Large-scale photovoltaic power generation connected to the power system will bring huge impact and challenges to the power grid. Through the prediction of photovoltaic power generation, the operation mode and response measures of the power system can be reasonably arranged to improve the stability and safety of the power system. Photovoltaic power generation prediction can help power companies to reasonably arrange scheduling plans and ensure the balance between power generation and consumption. Through accurate power generation prediction, the dispatching department can adjust the power generation plan in advance, reduce the pressure on the power grid caused by the volatility of photovoltaic power generation, and ensure the balance of supply and demand in the power system.

[0003] Current power generation estimates are based on the theoretical power generation efficiency of system design, which still has a large error compared with the actual power generation efficiency. The power generation efficiency calculation is not accurate enough, which seriously affects the prediction of power generation. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the above technical defects and provide a method for predicting power generation based on photovoltaic power generation efficiency.

[0005] In order to solve the above problems, the technical solution of the present invention is: a method for predicting power generation based on photovoltaic power generation efficiency, comprising the following steps:

[0006] S1, data collection and preprocessing;

[0007] S2, establish a prediction model;

[0008] S3. Predict the power generation according to the prediction model.

[0009] Furthermore, the data collected in step S1 include: collecting historical power generation data of the photovoltaic power station, including daily, monthly or annual power generation records; collecting meteorological data related to power generation, including solar irradiance, temperature, humidity, wind speed and wind direction; collecting system parameters of the photovoltaic power station, including photovoltaic panel type, quantity, installation angle, size, photoelectric conversion efficiency, and attenuation coefficient.

[0010] Furthermore, the collected data is preprocessed, including: processing missing values, filling them with the mean, median or interpolation algorithm; detecting and processing outliers, identifying them using statistical methods, box plots or local anomaly factor detection methods, and deleting or replacing outliers with normal values; normalizing or standardizing the data to improve the training efficiency and prediction accuracy of the model.

[0011] Furthermore, the filter method or the wrapping method is used to select features that are highly correlated with photovoltaic power generation efficiency from the collected data; the original features are converted through a binarization method to make them more suitable for the prediction task; new features are generated through a feature crossing method to supplement the original features and improve the prediction performance.

[0012] Furthermore, the prediction model established in step S2 includes a physical model and a time series model;

[0013] Physical model: Based on the physical characteristics of the photovoltaic array, mathematical equations are used to establish a photovoltaic array model;

[0014] Time series model: Based on the time series data of photovoltaic power generation, a prediction model of time convolutional neural network is established.

[0015] Furthermore, the time model is used to analyze and process the data, extract meaningful statistical information, and combine it with the physical model to predict power generation.

[0016] Furthermore, the collected data is divided into a training set and a validation set using a cross-validation method, the prediction model is trained using the training set, and the performance of the prediction model is evaluated on the validation set;

[0017] Improve model performance by adjusting model parameters and using the stochastic gradient descent optimization algorithm to minimize prediction errors.

[0018] Furthermore, the trained prediction model is applied to actual photovoltaic power stations to predict power generation.

[0019] Furthermore, the prediction model is continuously optimized and improved according to the actual application results to improve the prediction accuracy and robustness; new data is continuously collected and the model is updated to adapt to changes in the operating conditions of the photovoltaic power station.

[0020] The advantages of the present invention compared with the existing technology are: through reasonable data collection and preprocessing, the construction of a prediction model based on a physical model and a timing model, and through training, evaluation and verification steps, an accurate, reliable and practical prediction model can be established, which can help us better understand the performance and potential of photovoltaic power generation systems, and provide a scientific basis for the planning, design and operation and maintenance of photovoltaic power generation. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention are clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] A method for predicting power generation based on photovoltaic power generation efficiency, comprising:

[0023] S1. Data collection and preprocessing.

[0024] The data collected includes:

[0025] Collect historical power generation data of PV power plants, including daily, monthly or annual power generation records;

[0026] Collect meteorological data relevant to power generation, including solar irradiance, temperature, humidity, wind speed and direction;

[0027] Collect the system parameters of the photovoltaic power station, including the type, quantity, installation angle, size, photoelectric conversion efficiency, and attenuation coefficient of photovoltaic panels.

[0028] Preprocessing of collected data, including:

[0029] Handle missing values ​​and fill them using mean, median or interpolation algorithms;

[0030] Detect and process outliers, identify them using statistical methods, box plots, or local outlier factor detection methods, and remove or replace outliers with normal values;

[0031] Normalize or standardize the data to improve the training efficiency and prediction accuracy of the model.

[0032] Select features that are highly correlated with PV power generation efficiency from the collected data using a filter method or a wrapping method;

[0033] The original features are converted into binarization to make them more suitable for prediction tasks;

[0034] New features are generated through feature crossing method to supplement the original features and improve the prediction performance.

[0035] S2. Establish a prediction model.

[0036] The established prediction models include physical models and time series models;

[0037] Physical model: Based on the physical characteristics of the photovoltaic array, mathematical equations are used to establish a photovoltaic array model;

[0038] Time series model: Based on the time series data of photovoltaic power generation, a prediction model of time convolutional neural network is established.

[0039] The time model is used to analyze and process the data, extract meaningful statistical information, and combine it with the physical model to predict power generation.

[0040] The collected data is divided into a training set and a validation set using the cross-validation method. The prediction model is trained using the training set, and the performance of the prediction model is evaluated on the validation set. The prediction error is minimized and the model performance is improved by adjusting the model parameters and using the stochastic gradient descent optimization algorithm.

[0041] S3. Predict the power generation according to the prediction model.

[0042] The trained prediction model is applied to the actual photovoltaic power station to predict the power generation.

[0043] The prediction model is continuously optimized and improved based on the actual application results to improve the prediction accuracy and robustness; new data is continuously collected and the model is updated to adapt to changes in the operating conditions of the photovoltaic power station.

[0044] Through reasonable data collection and preprocessing, the construction of prediction models based on physical models and time series models, and through training, evaluation and verification steps, an accurate, reliable and practical prediction model can be established, which can help us better understand the performance and potential of photovoltaic power generation systems, and provide a scientific basis for the planning, design and operation and maintenance of photovoltaic power generation.

[0045] The undisclosed parts in the present invention are all prior art, and their specific structures and working principles are not described in detail.

[0046] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0047] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0048] The present invention and its implementation methods are described above, and such description is not restrictive, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design structures and embodiments similar to the technical solution without creativity, which should all fall within the protection scope of the present invention.

Claims

1. A method for predicting power generation based on photovoltaic power generation efficiency, characterized in that: The steps include: S1, data collection and preprocessing; S2, establish a prediction model; S3. Predict the power generation according to the prediction model.

2. A method for predicting power generation based on photovoltaic power generation efficiency according to claim 1, characterized in that: The data collected in step S1 include: Collect historical power generation data of PV power plants, including daily, monthly or annual power generation records; Collect meteorological data relevant to power generation, including solar irradiance, temperature, humidity, wind speed and direction; Collect the system parameters of the photovoltaic power station, including the type, quantity, installation angle, size, photoelectric conversion efficiency, and attenuation coefficient of photovoltaic panels.

3. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 2, characterized in that: Preprocessing of collected data, including: Handle missing values ​​and fill them using mean, median or interpolation algorithms; Detect and process outliers, identify them using statistical methods, box plots, or local outlier factor detection methods, and remove or replace outliers with normal values; Normalize or standardize the data to improve the training efficiency and prediction accuracy of the model.

4. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 3, characterized in that: Select features that are highly correlated with PV power generation efficiency from the collected data using a filter method or a wrapping method; The original features are converted into binarization to make them more suitable for prediction tasks; New features are generated through feature crossing method to supplement the original features and improve the prediction performance.

5. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 4, characterized in that: The prediction model established in step S2 includes a physical model and a time series model; Physical model: Based on the physical characteristics of the photovoltaic array, mathematical equations are used to establish a photovoltaic array model; Time series model: Based on the time series data of photovoltaic power generation, a prediction model of time convolutional neural network is established.

6. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 5, characterized in that: The time model is used to analyze and process the data, extract meaningful statistical information, and combine it with the physical model to predict power generation.

7. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 6, characterized in that: The collected data is divided into a training set and a validation set using a cross-validation method, the prediction model is trained using the training set, and the performance of the prediction model is evaluated on the validation set; Improve model performance by adjusting model parameters and using the stochastic gradient descent optimization algorithm to minimize prediction errors.

8. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 7, characterized in that: The trained prediction model is applied to the actual photovoltaic power station to predict the power generation.

9. The method for predicting power generation based on photovoltaic power generation efficiency according to claim 8, characterized in that: The prediction model is continuously optimized and improved based on the actual application results to improve the prediction accuracy and robustness; new data is continuously collected and the model is updated to adapt to changes in the operating conditions of the photovoltaic power station.