System status assessment method, device, equipment and medium based on photovoltaic power generation data

Abstract

The present invention proposes a system status assessment method, device, equipment and medium based on photovoltaic power generation data. The method provides data labels for data cleaning, which can be directly used as data input for model training, reducing the data preparation time for modeling; the quality of the cleaned data is effectively improved, laying the foundation for the subsequent establishment of various data models and the improvement of model accuracy; by performing data governance and data analysis on existing stock data, refining data indicators, and realizing effective management and application of incremental data, the group's data assets are managed scientifically; the present invention can perform data governance and mining on existing stock data, gradually build a data management system, and realize effective management and application of incremental data.

Description

Technical Field

[0001] The present invention relates to the field of data governance technology, and in particular to a system status assessment method, device, equipment and medium based on photovoltaic power generation data. Background Art

[0002] In recent years, China's photovoltaic power generation has developed rapidly, with installed capacity growing rapidly. This substantial increase in installed capacity has also brought greater challenges to the operation and maintenance of photovoltaic power generation systems. Modern photovoltaic power plants rely heavily on data generated during actual operation for their O&M. Therefore, high-quality, highly reliable photovoltaic operational data is a prerequisite for carrying out these tasks. However, in actual photovoltaic system operation, a large number of outliers are common. These outliers are caused by factors such as data propagation signal noise, sensor failures, communication and measurement equipment malfunctions, maximum power tracking anomalies, and array shutdowns and power rationing. These large numbers of outliers can severely impact the quality of the raw data and hinder the implementation of O&M functions. Therefore, the ability to accurately identify and cleanse outliers in operational data is crucial for ensuring the safe and economical operation of photovoltaic power plants.

[0003] As enterprises' digital transformation continues to deepen, the demand for data applications continues to expand. However, many companies, despite possessing vast amounts of data, remain stuck in the early stages of data governance. Only by properly managing data and forming data assets can they ultimately enable data-driven businesses and empower products, gradually achieving digital transformation. Therefore, data governance has become a primary and critical issue facing all enterprises.

[0004] Photovoltaic big data specifically includes static information such as installed capacity configuration and the photoelectric conversion efficiency of photovoltaic modules, as well as meteorological measured data such as new energy power generation power data, wind speed, wind direction, irradiance, temperature, and humidity. The above data have significant differences in acquisition methods, physical meanings, measurement units, data types, data levels, sampling frequencies, etc., so data preprocessing and feature parameter construction are essential.

[0005] Because raw data inevitably contains missing data, redundancies, conflicts, errors, omissions, and anomalies, data quality varies. Data cleaning is essential to improve quality before analysis and use. The goal of data cleaning is to smooth noise, fill missing values, and identify outliers in raw data using techniques such as statistics, clustering, and time series analysis to ensure data validity, consistency, and integrity.

[0006] Since the accuracy of model results depends largely on the completeness, accuracy, and low correlation of the input data, the more accurate the data used for model training, the better the model fit and the better the prediction results. In photovoltaic power generation systems, the large amount of historical data collected by sensors at each node contains missing values, outliers, and fault values. Therefore, preprocessing of experimental data is necessary before algorithm model training. Improving data quality is the foundation of power plant status analysis and evaluation, intelligent operation and maintenance, and fault diagnosis. Summary of the Invention

[0007] The present invention provides a system status assessment method, device, equipment and medium based on photovoltaic power generation data, aiming to apply big data to photovoltaic power generation and realize the digitization and intelligence of photovoltaic power stations.

[0008] To this end, the purpose of the present invention is to propose a system status assessment method based on photovoltaic power generation data, comprising:

[0009] Collect photovoltaic power generation data and classify the data, and store the classified photovoltaic power generation data in the database;

[0010] Based on the classification results, the photovoltaic power generation data stored in the database is processed;

[0011] Extract characteristic parameters from the photovoltaic power generation data after data processing and build a feature library;

[0012] By using association rule algorithms, the degree of association between characteristic parameters is quantified, and effective combinations of characteristic parameters are achieved, which are used to realize system and equipment status evaluation and fault diagnosis.

[0013] The data types of photovoltaic power generation data collected include:

[0014] Initial data of photovoltaic equipment, including: original power of equipment components, power of arrival inspection, and installation and commissioning data, which serves as the basis for subsequent data analysis;

[0015] Photovoltaic equipment power generation data, including: string current, voltage, power, and comparative analysis with the basic power generation of the photovoltaic power station;

[0016] Online test equipment data, including component temperature, irradiance, and angle, is used for subsequent analysis of power generation loss mechanisms for different technology products and to assist in decision-making on equipment selection.

[0017] Among them, photovoltaic power generation data is stored in the database, including:

[0018] When photovoltaic power generation data is stored in the database, data tag calculation logic is designed to filter and analyze data by operating different tags to improve system access efficiency;

[0019] Carry out data standardization and normalization, conduct correlation analysis based on the processed data, and manage data versions, dividing them into original data, time series data, governed data, and result data.

[0020] Among them, according to the classification results, the photovoltaic power generation data stored in the database is processed, including:

[0021] Abnormal data processing: locate the data points in the photovoltaic array operation data in the photovoltaic power generation data that do not conform to the photovoltaic array mechanism and actual operation rules, and identify and delete abnormal data points from the data set or sample data;

[0022] Vacancy value processing: for multidimensional data composed of multiple indicators affecting photovoltaic power generation, missing data are filled according to the nearest neighbor algorithm;

[0023] All collected data are standardized after being stored in the database to facilitate query and retrieval.

[0024] Among them, abnormal data processing includes:

[0025] In the actual distributed photovoltaic power station historical detection data, if there are a small number of values ​​that exceed the value range, choose to directly delete the abnormal values;

[0026] If there are negative values ​​in the power monitoring value, the abnormal value is regarded as a missing value and processed using the nearest neighbor algorithm;

[0027] If invalid values ​​appear in the temperature detection value, the average value of the two sampling records before and after is taken for correction;

[0028] If the component temperature monitoring values ​​are too high or too low, record them and conduct actual problem investigation.

[0029] Among them, feature parameters are extracted from the photovoltaic power generation data after data processing to build a feature library, including:

[0030] Select the most critical features from all features, use the corresponding feature extraction method according to the problem requirements and data type, extract key feature information from photovoltaic power generation data, and combine different features together;

[0031] For high-dimensional features, dimensionality reduction is performed to reduce computational complexity;

[0032] Identify and label the equipment, consider the influencing factors of environmental parameters and equipment-related data, establish a standard database and feature library for comprehensive analysis, and realize management analysis of the equipment.

[0033] Among them, the association rule algorithm is used to quantify the degree of association between characteristic parameters and realize the effective combination between characteristic parameters, which is used in the steps of realizing the status evaluation and fault diagnosis of systems and equipment.

[0034] Photovoltaic power generation data are divided into full life cycle data: construction and acceptance, monitoring and control, operation and maintenance and management, asset evaluation and transaction, real-time operation data, meteorological and environmental data, resource index data and energy efficiency index data; each data category can be divided into data subcategories, and data indicators are constructed according to these data categories and data subcategories.

[0035] Another object of the present invention is to provide a system status assessment device based on photovoltaic power generation data, comprising:

[0036] The data acquisition module is used to collect photovoltaic power generation data and classify the data, and store the photovoltaic power generation data after data classification in the database;

[0037] A data processing module is used to process the photovoltaic power generation data stored in the database according to the classification results;

[0038] The feature extraction module is used to extract feature parameters from the photovoltaic power generation data after data processing and build a feature library;

[0039] The status evaluation module is used to utilize the association rule algorithm to quantify the degree of association between characteristic parameters and realize the effective combination between characteristic parameters, so as to realize the status evaluation and fault diagnosis of the system and equipment.

[0040] The present invention also aims to provide a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method of any one of the aforementioned technical solutions is implemented.

[0041] Another object of the present invention is to provide a non-temporary computer-readable storage medium having a computer program stored thereon, which implements the method of the aforementioned technical solution when the computer program is executed by a processor.

[0042] Different from the existing technology, the system status assessment method based on photovoltaic power generation data provided by the present invention provides data label setting and data cleaning, which can be directly used as data input for model training, reducing the data preparation time for modeling; the quality of the cleaned data is effectively improved, laying the foundation for the subsequent establishment of various data models and the improvement of model accuracy; by performing data governance and data analysis on existing stock data, refining data indicators, and realizing effective management and application of incremental data, scientifically managing the group's data assets; through the present invention, data governance and mining of existing stock data can be carried out, and a data management system can be gradually established to realize effective management and application of incremental data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0044] Figure 1 It is a flow chart of a system status assessment method based on photovoltaic power generation data provided by the present invention.

[0045] Figure 2 This is a schematic diagram of the overall framework design of data acquisition and storage in a system status assessment method based on photovoltaic power generation data provided by the present invention.

[0046] Figure 3 This is a schematic diagram of the evaluation index model structure in a system status evaluation method based on photovoltaic power generation data provided by the present invention.

[0047] Figure 4 This is a schematic diagram of the evaluation index system architecture in a system status evaluation method based on photovoltaic power generation data provided by the present invention.

[0048] Figure 5 It is a structural schematic diagram of a system status assessment device based on photovoltaic power generation data provided by the present invention.

[0049] Figure 6 It is a structural schematic diagram of a non-transitory computer-readable storage medium storing computer instructions provided by the present invention. DETAILED DESCRIPTION

[0050] Specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although specific embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0051] Figure 1 This is a flow chart of a method for evaluating system status based on photovoltaic power generation data provided by an embodiment of the present invention. It includes:

[0052] S110: Collecting photovoltaic power generation data and classifying the data, and storing the classified photovoltaic power generation data in a database.

[0053] Data is collected, including historical operating conditions of various PV power plant components, status information, outages and expected operating conditions, and forecasted signals, geographic information, weather, on-site environment, and images during system operation. This data is categorized as ledger data, real-time operating data, and environmental data. Based on these data types, a unified and standardized basic data standard library is constructed, encompassing datasets, data classes, data subclasses, and data tables. A data model is designed, providing a unified set of data standards, including standardized definitions of dimensions and indicators, data model design, data development, and data service specifications.

[0054] Specifically, the data types of photovoltaic power generation data collected include:

[0055] Initial data of photovoltaic equipment, including: original power of equipment components, power of arrival inspection, and installation and commissioning data, which serves as the basis for subsequent data analysis;

[0056] Photovoltaic equipment power generation data, including: string current, voltage, power, and comparative analysis with the basic power generation of the photovoltaic power station;

[0057] Online test equipment data, including component temperature, irradiance, and angle, is used for subsequent analysis of power generation loss mechanisms for different technology products and to assist in decision-making on equipment selection.

[0058] Photovoltaic power generation data is stored in the database, including:

[0059] When photovoltaic power generation data is stored in the database, data tag calculation logic is designed to filter and analyze data by operating different tags to improve system access efficiency;

[0060] Carry out data standardization and normalization, carry out correlation analysis based on the processed data, and manage the data version, dividing it into original data, time series data, data after governance, and result data. The overall framework design of data management is as follows: Figure 2 shown.

[0061] S120: Processing the photovoltaic power generation data stored in the database according to the classification result.

[0062] Outlier analysis is used to check whether there are any unreasonable data caused by input errors or equipment failures. The existence of these missing values ​​and outliers will have a serious impact on the model output.

[0063] The deficiencies of the original data of solar photovoltaic power and weather information obtained are analyzed, the locations of missing values ​​and outliers in the data are determined, the missing values ​​and outliers are filled and replaced based on the proximity algorithm, and the data are preprocessed using normalization to establish various photovoltaic power generation data sets.

[0064] The steps of data processing include:

[0065] Abnormal data processing: locate the data points in the photovoltaic array operation data in the photovoltaic power generation data that do not conform to the photovoltaic array mechanism and actual operation rules, and identify and delete abnormal data points from the data set or sample data;

[0066] Vacancy value processing: for multidimensional data composed of multiple indicators affecting photovoltaic power generation, missing data are filled according to the nearest neighbor algorithm;

[0067] All collected data are standardized after being stored in the database to facilitate query and retrieval.

[0068] Among them, abnormal data processing includes:

[0069] In the actual historical detection data of distributed photovoltaic power stations, if a small number of values ​​appear outside the value range, the outliers are directly deleted. For example, the PR monitoring value is usually 0 in the two time periods of 0-5 o'clock and 19-23 o'clock. However, a small number of values ​​outside the value range appear in the actual data, so the outliers are directly deleted.

[0070] If there are negative values ​​in the power monitoring value, the abnormal value is regarded as a missing value and processed using the nearest neighbor algorithm;

[0071] If invalid values ​​appear in the temperature detection value, the average value of the two sampling records before and after is taken for correction;

[0072] If the component temperature monitoring values ​​are too high or too low, record them and conduct actual problem investigation.

[0073] S130: Extracting characteristic parameters from the processed photovoltaic power generation data and constructing a characteristic library.

[0074] Specifically, the most critical features are selected from all features. According to the problem requirements and data types, corresponding feature extraction methods are used to extract key feature information from photovoltaic power generation data and combine different features together.

[0075] For high-dimensional features, dimensionality reduction is performed to reduce computational complexity;

[0076] Identify and label the equipment, consider the influencing factors of environmental parameters and equipment-related data, establish a standard database and feature library for comprehensive analysis, and realize management analysis of the equipment.

[0077] S140: Quantify the degree of association between characteristic parameters using an association rule algorithm to achieve effective combination of characteristic parameters for status evaluation and fault diagnosis of systems and equipment.

[0078] Photovoltaic power generation data is divided into data classes and data subclasses. Feature extraction and feature selection are performed from different dimensions at the system level and device level in combination with typical scenarios. Data indicators are established. Model analysis is carried out based on different intelligent algorithms. Sample training and model correction are performed to build a status evaluation indicator system. The evaluation indicator model process is as follows: Figure 3 shown.

[0079] Photovoltaic power generation data is divided into full life cycle data: construction and acceptance, monitoring and control, operation and maintenance and management, asset evaluation and transaction, real-time operation data, meteorological and environmental data, resource index data and energy efficiency index data; each data category can be divided into data subcategories, and data indicators are constructed according to these data categories and data subcategories. The evaluation index system is as follows: Figure 4 shown.

[0080] like Figure 4 In the data, the data is divided into four categories, namely real-time data, energy consumption indicators, energy efficiency indicators and historical data; among them,

[0081] The data subcategories to which real-time data belongs include:

[0082] Meteorological data: irradiance, temperature, wind speed;

[0083] Component performance: DC power, PV panel temperature, DC side voltage;

[0084] Inverter performance: power generation, inverter conversion efficiency, inverter temperature, grid-connected voltage, grid-connected frequency;

[0085] Collector line: line load, line insulation impedance;

[0086] The data subcategories of energy consumption indicators include:

[0087] Total loss hours; inverter loss equivalent hours; power station inverter loss; photovoltaic array loss; integrated circuit and box transformer loss;

[0088] The data subcategories to which energy efficiency indicators belong include:

[0089] Comprehensive efficiency of photovoltaic power station; degree of component degradation; photovoltaic array efficiency; inverter conversion efficiency; utilization hours;

[0090] The data subcategories to which historical data belongs include:

[0091] Solar energy resource indicators: total radiation, total radiation on inclined surfaces, sunshine hours, average wind speed, average temperature, and relative humidity;

[0092] Equipment operating time; equipment downtime; equipment service life; inverter failure rate; historical maintenance information.

[0093] like Figure 5 As shown, the present invention further provides a system status assessment device 300 based on photovoltaic power generation data, comprising:

[0094] The data collection module 310 is used to collect photovoltaic power generation data and classify the data, and store the classified photovoltaic power generation data in a database;

[0095] The data processing module 320 is used to process the photovoltaic power generation data stored in the database according to the classification results;

[0096] The feature extraction module 330 is used to extract feature parameters from the photovoltaic power generation data after data processing and build a feature library;

[0097] The status evaluation module 340 is used to quantify the degree of association between characteristic parameters using an association rule algorithm, thereby achieving effective combination of characteristic parameters and realizing status evaluation and fault diagnosis of systems and equipment.

[0098] The implementation process of the above-mentioned device is similar to or even the same as the implementation process of the system status assessment method based on photovoltaic power generation data in the aforementioned embodiment, and will not be repeated here.

[0099] In order to implement the embodiment, the present invention also proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute each step in the system status assessment method based on photovoltaic power generation data of the aforementioned technical solution.

[0100] like Figure 6 As shown, the non-transitory computer-readable storage medium includes a memory 810 of instructions and an interface 830. The instructions can be executed by a processor 820 based on the system status assessment based on photovoltaic power generation data to complete the method. Alternatively, the storage medium can be a non-transitory computer-readable storage medium, for example, a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0101] To implement the embodiment, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the system status assessment based on photovoltaic power generation data according to the embodiment of the present invention is implemented.

[0102] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0103] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0104] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0105] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0106] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0107] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0108] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0109] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limiting the present invention. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A system status assessment method based on photovoltaic power generation data, characterized in that: include: Collect photovoltaic power generation data and classify the data, and store the classified photovoltaic power generation data in the database; performing data processing on the photovoltaic power generation data stored in the database according to the classification result; Select the most critical features from all features. Based on the problem requirements and data type, use the corresponding feature extraction method to extract key feature information from photovoltaic power generation data and combine different features together. For high-dimensional features, perform dimensionality reduction operations to reduce computational complexity. Identify and label the equipment and consider the influencing factors of environmental parameters and equipment-related data to build a standard database and feature library for comprehensive analysis to achieve management analysis of the equipment. Utilize association rule algorithms to quantify the degree of association between characteristic parameters and achieve effective combinations between characteristic parameters for status evaluation and fault diagnosis of systems and equipment. According to the classification result, the photovoltaic power generation data stored in the database is processed, including: Abnormal data processing: locate the data points in the photovoltaic array operation data in the photovoltaic power generation data that do not conform to the photovoltaic array mechanism and actual operation rules, identify and delete abnormal data points from the data set or sample data; among them, in the actual distributed photovoltaic power station historical detection data, for a small number of values ​​that exceed the value range, choose to directly delete the abnormal values; if there are negative values ​​in the power monitoring value, the abnormal values ​​are regarded as missing values ​​and processed using the nearest neighbor algorithm; if invalid values ​​appear in the temperature detection value, the average of the two is taken according to the previous and next sampling records for correction; if the component temperature monitoring value is too high or too low, record it and conduct actual problem investigation Vacancy value processing: for multidimensional data composed of multiple indicators affecting photovoltaic power generation, missing data are filled according to the nearest neighbor algorithm; All collected data are standardized after being stored in the database to facilitate query and retrieval.

2. The system status assessment method based on photovoltaic power generation data according to claim 1, characterized in that: The types of data collected for photovoltaic power generation include: Initial data of photovoltaic equipment, including: original power of equipment components, power of arrival inspection, and installation and commissioning data, which serves as the basis for subsequent data analysis; Photovoltaic equipment power generation data, including: string current, voltage, power, and comparative analysis with the basic power generation of the photovoltaic power station; Online test equipment data, including component temperature, irradiance, and angle, is used for subsequent analysis of power generation loss mechanisms for different technology products and to assist in decision-making on equipment selection.

3. The system status assessment method based on photovoltaic power generation data according to claim 2, characterized in that: The photovoltaic power generation data is stored in the database, including: When the photovoltaic power generation data is stored in the database, the data tag calculation logic is designed to perform data screening and analysis by operating different tags to improve the system access efficiency; Carry out data standardization and normalization, conduct correlation analysis based on the processed data, and manage data versions, dividing them into original data, time series data, governed data, and result data.

4. The system status assessment method based on photovoltaic power generation data according to claim 1, characterized in that: The association rule algorithm is used to quantify the degree of association between characteristic parameters and realize the effective combination between characteristic parameters, which is used to realize the state evaluation and fault diagnosis of the system and equipment. The photovoltaic power generation data categories are divided into full life cycle data: construction and acceptance, monitoring and control, operation and maintenance and management, and asset evaluation and transaction, real-time operation data, meteorological environment data, resource index data and energy efficiency index data; each data category can be divided into data subcategories, and data indicators are constructed according to such data categories and data subcategories.

5. A system status assessment device based on photovoltaic power generation data, characterized in that: include: The data acquisition module is used to collect photovoltaic power generation data and classify the data, and store the photovoltaic power generation data after data classification in the database; A data processing module, configured to process the photovoltaic power generation data stored in the database according to the classification result; The feature extraction module selects the most critical features from all features. Based on the problem requirements and data type, it uses the corresponding feature extraction method to extract key feature information from photovoltaic power generation data and combine different features. It performs dimensionality reduction operations on high-dimensional features to reduce computational complexity. It identifies and labels devices and considers the influencing factors of environmental parameters and device-related data to build a standard database and feature library for comprehensive analysis to achieve management and analysis of devices. The status evaluation module is used to quantify the degree of association between characteristic parameters using association rule algorithms, achieve effective combination of characteristic parameters, and realize status evaluation and fault diagnosis of systems and equipment; According to the classification result, the photovoltaic power generation data stored in the database is processed, including: Abnormal data processing: locate the data points in the photovoltaic array operation data in the photovoltaic power generation data that do not conform to the photovoltaic array mechanism and actual operation rules, identify and delete abnormal data points from the data set or sample data; among them, in the actual distributed photovoltaic power station historical detection data, for a small number of values ​​that exceed the value range, choose to directly delete the abnormal values; if there are negative values ​​in the power monitoring value, the abnormal values ​​are regarded as missing values ​​and processed using the nearest neighbor algorithm; if invalid values ​​appear in the temperature detection value, the average of the two is taken according to the previous and next sampling records for correction; if the component temperature monitoring value is too high or too low, record it and conduct actual problem investigation Vacancy value processing: for multidimensional data composed of multiple indicators affecting photovoltaic power generation, missing data are filled according to the nearest neighbor algorithm; All collected data are standardized after being stored in the database to facilitate query and retrieval.

6. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images