Performance monitoring method, device and equipment of photovoltaic power station and storage medium

Abstract

The invention discloses a performance monitoring method, device and equipment of a photovoltaic power station and a storage medium, and relates to the technical field of solar energy industry, and the method comprises the steps: automatically obtaining the electrical data of each electrical device at a certain time interval, and carrying out the collection and unified management of all electrical data, thereby forming a traceable database; according to the photovoltaic power station electrical data management system and method based on the linear regression analysis, direct access of various subsequent analysis software and analysis algorithms through a data interface is facilitated, and subsequent access operations such as query and traceability are also facilitated, so that electrical data of a photovoltaic power station are comprehensively and effectively managed; the performance of each electrical device of the photovoltaic power station can be known through the linear regression model obtained through solving, and finally, the performance of the device can be known to be abnormal by screening out future generating capacity abnormal data through query operation. Advanced monitoring of electrical equipment of a photovoltaic power station is realized.

Description

Technical Field

[0001] The present application relates to the technical field of solar energy industry, and in particular to a performance monitoring method, device, equipment and storage medium for a photovoltaic power station. Background Art

[0002] Photovoltaic power station is a facility that uses solar energy to generate electricity. It converts solar energy into electrical energy through special materials such as crystalline silicon panels and electronic components such as inverters, and is connected to the power grid to transmit electricity to the grid. Photovoltaic power stations are green energy projects encouraged by the state, and are clean, environmentally friendly, and renewable. Photovoltaic power stations are widely used in various occasions, including providing power for areas without electricity, solar-powered daily electronic products (such as solar chargers, solar street lights, etc.), and grid-connected power generation. With the advancement of technology and policy support, photovoltaic power generation will occupy an important position in the future energy structure.

[0003] Performance monitoring of photovoltaic power stations usually involves a series of manual appearance inspections to determine whether the external mechanical performance of electrical equipment is perfect, and manual meter reading and verification to determine whether the internal electronic performance of electrical equipment is normal. Finally, the comprehensive performance of electrical equipment is comprehensively judged. For example, appearance inspection checks the appearance of photovoltaic modules, brackets, cables and other components to confirm that there is no damage, deformation, corrosion, etc. Ensure that the power station site is clean and tidy, and there is no shadow blocking the photovoltaic modules; Component performance testing uses instruments to measure the electrical performance of photovoltaic modules, such as open circuit voltage, short circuit current, maximum power point voltage and current, etc., and uses EL to detect whether there are defects such as hidden cracks and black pieces inside the modules; Inverter performance testing checks the operating status of the inverter, including output voltage, current, frequency, power factor and other parameters. Verify whether the protection functions of the inverter, such as overload protection, short circuit protection, island protection, etc., are working properly; Array output detection monitors the output power of the entire photovoltaic array, compares it with the theoretical value, and evaluates the power generation efficiency of the system; Grid-connected performance testing checks the connection between the photovoltaic power station and the grid to ensure that the voltage, frequency, phase sequence and other parameters of the grid-connected point meet the requirements of the grid. Monitor the power quality parameters of the power station such as grid-connected power factor, harmonic content, etc.

[0004] As can be seen from the above, the above performance monitoring method relies on manual visual judgment and manual meter reading analysis. Although the subsequent electronic performance analysis can be performed with the help of external detection instruments, subjective experience errors are inevitably added. At the same time, the data types and styles obtained by manual meter reading are many, which is not conducive to subsequent data operations such as analysis operations, backup operations, etc. that require unified analysis and management of data. The diverse hand-written data formats require a series of summarization and unified operations in the actual analysis process to adapt to the subsequent analysis software, which is time-consuming and labor-intensive, and the data obtained have subjective experience errors. Summary of the invention

[0005] The main purpose of the present application is to provide a performance monitoring method, device, equipment and storage medium for a photovoltaic power station, so as to solve the problem that the performance analysis of a photovoltaic power station in the prior art has subjective experience errors and a variety of data styles.

[0006] In order to achieve the above objectives, this application provides the following technical solutions: A performance monitoring method for a photovoltaic power station, the photovoltaic power station comprising a plurality of photovoltaic arrays, a DC distribution cabinet electrically connected to each photovoltaic array, an inverter electrically connected to the DC distribution cabinet, an AC distribution cabinet electrically connected to the inverter, and a booster station electrically connected to the AC distribution cabinet, the performance monitoring method comprising: Step S1, obtaining a number of DC electrical data, a number of inverter electrical data, a number of AC electrical data, a number of boost electrical data of the DC distribution cabinet, the inverter, the AC distribution cabinet, and the booster station based on a preset natural time period, and a number of power generation data of the photovoltaic power station based on the preset natural time period; Step S2: manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods; Step S3, defining a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data through the statsmodels library of Python, wherein the multivariate linear regression model has a reserved data import interface; Step S4, connecting the TiDB library and the data import interface through a MySQL client signal to import the power plant data summary table into the multivariate linear regression model; Step S5, solving the multivariate linear regression model by the least square method to obtain a prediction model; Step S6, predicting a number of future power generation data based on a preset future prediction step number by using the prediction model; Step S7, importing all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generating a future power generation summary table; Step S8, searching the future power generation summary table for power generation data that is less than or equal to a preset power generation threshold value through the MySQL client; Step S9: marking the power generation data that is less than or equal to the preset power generation threshold as performance abnormality data.

[0007] As a further improvement of the present application, in step S2, all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods, including: Step S21, building a global environment variable file of the TiDB library through the TiUP component manager; Step S22, generating a TiDB cluster in the global environment variable file through the playground instruction of the TiUP component manager; Step S23, connecting to the TiDB cluster through the MySQL client signal; Step S24, creating a first blank database in the TiDB cluster using the SQL creation statement of the MySQL client, with all electrical data as the row dimension and the number of all preset natural time periods as the column dimension. All electrical data includes all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data. Step S25, importing all electrical data into the first blank database through the SQL import statement of the MySQL client to form the power station data summary table.

[0008] As a further improvement of the present application, step S7, importing all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generating a future power generation summary table, including: Step S71, creating a second blank database in the TiDB cluster through a SQL creation statement of the MySQL client, with the number of all preset natural time periods as the row dimension and the future power generation as a single column dimension; Step S72, importing all future power generation into the second blank database through the SQL import statement of the MySQL client to form the future power generation summary table.

[0009] As a further improvement of the present application, in step S3, a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data is defined through the statsmodels library of Python, and the multivariate linear regression model has a reserved data import interface, including: Step S31, defining DC electrical data, inverter electrical data, AC electrical data, and boost electrical data of the same preset natural time period as a set of independent variables; Step S32, defining the power generation data of the same preset natural time period as the dependent variable of the set of independent variables, and defining the dependent variable of the same preset natural time period and all independent variables as a set of linear regression relationships; Step S33, performing standard normalization processing on all linear regression relationships; Step S34, defining all linear regression relationships as the multivariate linear regression model according to formula (1): (1); in, For the A dependent variable with a predetermined natural time period, is the number of all preset natural time periods, is the intercept of all linear regression relationships, is the linear regression coefficient of all DC electrical data, is the linear regression coefficient of all inverter electrical data, is the linear regression coefficient of all AC electrical data, is the linear regression coefficient of all boost electrical data, For the DC electrical data for a preset natural time period, For the Inverter electrical data for a preset natural time period, For the AC electrical data for a preset natural time period, For the Boost electrical data for a preset natural time period, is the random error of all linear regression relationships; Step S35, reserving the data import interface at the beginning of the code of the multivariate linear regression model through the flask framework of Python.

[0010] As a further improvement of the present application, step S5, solving the multivariate linear regression model by the least squares method to obtain a prediction model, includes: Step S51, using the least squares method to solve all linear regression coefficients according to formula (2): (2); in, for The estimated value of ,correspond , , , , is the matrix of all independent variables, For the matrix The transposed matrix of Step S52, substituting all the regression coefficients obtained by solving into all the linear regression relationships to obtain the prediction model.

[0011] As a further improvement of the present application, in step S2, all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods, and then include: Step S10, splitting the power station data summary table into a plurality of data sub-tables based on all preset natural time periods; Step S20, obtaining the chain hash certificate of each data sub-table through the SHA256 algorithm; Step S30, copy all the hash certificates on the chain and save them locally, so as to obtain a local hash certificate based on a data table; Step S40, saving all the hash certificates on the chain to the external blockchain in order from old to new according to all preset natural time periods; Step S50, based on the current local hash certificate, retrieve the on-chain hash certificate that matches the local hash certificate from the external blockchain; Step S60, determining whether the on-chain hash certificate is retrieved successfully, if the on-chain hash certificate is not retrieved successfully, executing step S70; Step S70, determining whether one of the on-chain hash certificate and the local hash certificate has been tampered with; Step S80: Generate a data tampering signal and send it to an external monitoring terminal.

[0012] As a further improvement of the present application, step S7, importing all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generating a future power generation summary table, then includes: Step S100, querying, updating, or deleting data on the power plant data summary table or the future power generation summary table through the SQL query statement, SQL update statement, or SQL delete statement of the MySQL client; Step S200, generating a query record with a query timestamp and query content based on each data query; Step S300, generating an update record with an update timestamp and update content based on each data update; Step S400, generating a deletion record with a deletion timestamp and deletion content based on each data deletion; Step S500, sending all query records, all update records, and all deletion records to an external monitoring terminal.

[0013] In order to achieve the above objectives, this application also provides the following technical solutions: A performance monitoring device for a photovoltaic power station, which is applied to the above-mentioned performance monitoring method, comprises: An electrical data acquisition module, used to acquire a number of DC electrical data, a number of inverter electrical data, a number of AC electrical data, a number of boost electrical data of the DC power distribution cabinet, the inverter, the AC power distribution cabinet, and the booster station based on a preset natural time period, and a number of power generation data of the photovoltaic power station based on the preset natural time period; The electrical data management module is used to manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods; A linear regression definition module is used to define a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data through the statsmodels library of Python, wherein the multivariate linear regression model has a reserved data import interface; An electrical data import module, used to connect to the TiDB library and the data import interface through a MySQL client signal to import the power station data summary table into the multivariate linear regression model; A linear regression solution module, used for solving the multivariate linear regression model by the least square method to obtain a prediction model; A future power generation prediction module, used to predict a number of future power generation data based on a preset future prediction step number through the prediction model; A future power generation data management module, used to import all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generate a future power generation summary table; A future power generation data retrieval module, used to search the future power generation summary table for power generation data that is less than or equal to a preset power generation threshold through the MySQL client; The performance abnormality data marking module is used to mark the power generation data that is less than or equal to a preset power generation threshold as performance abnormality data.

[0014] In order to achieve the above objectives, this application also provides the following technical solutions: An electronic device comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the performance monitoring method of the photovoltaic power station as described above is implemented.

[0015] In order to achieve the above objectives, this application also provides the following technical solutions: A storage medium stores program instructions, and when the program instructions are executed by a processor, the performance monitoring method of a photovoltaic power station as described above can be implemented.

[0016] The present application obtains several DC electrical data, several inverter electrical data, several AC electrical data, several boost electrical data of DC distribution cabinets, inverters, AC distribution cabinets, and booster stations based on preset natural time periods, as well as several power generation data of photovoltaic power stations based on preset natural time periods; all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a summary table of power station data based on several preset natural time periods; all power generation data are defined through the Python statsmodels library as being respectively related to all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data A multivariate linear regression model is built, and a data import interface is reserved for the multivariate linear regression model; the TiDB library and the data import interface are connected through the MySQL client signal to import the power plant data summary table into the multivariate linear regression model; the multivariate linear regression model is solved by the least squares method to obtain a prediction model; a number of future power generation data are predicted based on a preset future prediction step number through the prediction model; all future power generation data and the future time corresponding to all future power generation are imported into the TiDB library through the MySQL client and a future power generation summary table is generated; the power generation data in the future power generation summary table that is less than or equal to the preset power generation threshold is searched through the MySQL client; the power generation data that is less than or equal to the preset power generation threshold is marked as performance abnormality data. The present application automatically obtains the electrical data (such as voltage, current, power, frequency, etc.) of each electrical device at a certain interval and collects and uniformly manages all the electrical data to form a traceable database, which not only facilitates the subsequent various analysis software and analysis algorithms to be directly accessed through the data interface, but also facilitates subsequent query, traceability and other access operations, so that the electrical data of the photovoltaic power station is comprehensively and effectively managed. At the same time, the present application directly connects the linear regression analysis to the database to realize the linear regression analysis of the performance of each electrical device, and then the performance of each electrical device in the photovoltaic power station can be known by solving the linear regression model. The application uses the form of access to the database to perform linear regression analysis, so that the prediction results can also be managed uniformly using the database. Finally, by querying the data of abnormal future power generation, it can be known that the equipment performance is abnormal. At the same time, it also realizes the advanced monitoring of electrical equipment in photovoltaic power stations, and there is no need to wait until the electrical equipment actually fails. Compared with the existing technology, this application avoids subjective experience errors, and the entire process of data collection-data analysis-data management-data screening does not require human participation, and the data style is unified and can be managed uniformly. The obtained database can be directly applied to the data needs of other scenarios, which significantly improves the operation and maintenance efficiency of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1This is a schematic diagram of electrical connections of an embodiment of a method for monitoring performance of a photovoltaic power station of the present application; Figure 2 A schematic diagram of the steps of an embodiment of a method for monitoring the performance of a photovoltaic power station of the present application; Figure 3 This is a functional module diagram of an embodiment of a performance monitoring device for a photovoltaic power station of the present application; Figure 4 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application; Figure 5 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] like Figure 1 As shown, Figure 1 This is a connection diagram of each electrical equipment in this embodiment. This embodiment provides an embodiment of a performance monitoring method for a photovoltaic power station. In this embodiment, the photovoltaic power station includes a plurality of photovoltaic arrays, a DC distribution cabinet electrically connected to each photovoltaic array, an inverter electrically connected to the DC distribution cabinet, an AC distribution cabinet electrically connected to the inverter, and a booster station electrically connected to the AC distribution cabinet.

[0022] Preferably, the performance of the energy storage equipment can also be uniformly monitored and managed.

[0023] Specifically, see Figure 2 , the performance monitoring method comprises the following steps: Step S1, obtaining a number of DC electrical data, a number of inverter electrical data, a number of AC electrical data, a number of boost electrical data of a DC distribution cabinet, an inverter, an AC distribution cabinet, and a booster station based on a preset natural time period, and a number of power generation data of a photovoltaic power station based on a preset natural time period.

[0024] Preferably, due to the random nature of illumination, the preset natural time period can be set to 1 hour or half an hour.

[0025] Step S2: manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods.

[0026] Preferably, TiDB (Ti Distributed Database) is an open source distributed relational database. TiDB is a hybrid transactional and analytical processing (HTAP) distributed database that can support both online transaction processing (OLTP) and online analytical processing (OLAP). It has important features such as horizontal expansion or contraction, financial-grade high availability, real-time HTAP, cloud native, and is compatible with the MySQL 5.7 protocol and ecosystem; TiDB is suitable for various scenarios with high availability and strong consistency requirements, especially in environments with large data scale and high concurrency requirements. It combines the best features of traditional RDBMS and NoSQL, and TiDB is compatible with MySQL and supports unlimited horizontal expansion, which is conducive to the continuous expansion of additional electrical data in the later stage of this embodiment, and has strong consistency and high availability.

[0027] Step S3, using Python's statsmodels library to define a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data. The multivariate linear regression model has a data import interface reserved.

[0028] Preferably, the definition of the multivariate linear regression model and the reservation of the data import interface can be implemented through the following code framework: import statsmodels.api as sm import numpy as np from flask import Flask, jsonify app = Flask(__name__) # Electrical Data data={} @app.route(' / users / <string:user_id> ', methods=['GET']) def get_user(user_id): if user_id in data: return jsonify(data[user_id]) else: return 'User not found', 404 if__name__=='__main__': app.run(debug=True) #X is the matrix of independent variables, y is the dependent variable X=np.array([[*,*,*],[*,*,*],[*,*,*]]) y = np.array([*,*,*]) # Create model and fit model = sm.OLS(y, X).fit() # Output model results print(model.summary()) It is worth noting that the data of independent variables and dependent variables are automatically filled in by the MySQL client and do not need to be manually entered.

[0029] It is worth noting that the above code is an excerpt of the complete code. The above code is not a complete version and cannot be run directly.

[0030] Step S4, connect the TiDB library and the data import interface through the MySQL client signal to import the power plant data summary table into the multivariate linear regression model.

[0031] Preferably, the multiple linear regression model may adopt LASSO regression.

[0032] Step S5, solving the multivariate linear regression model by the least square method to obtain a prediction model.

[0033] Step S6, predicting a number of future power generation data based on a preset future prediction step number through the prediction model.

[0034] Step S7, import all future power generation data and the future time corresponding to all future power generation into the TiDB database through the MySQL client and generate a future power generation summary table; Step S8, searching the future power generation summary table for power generation data that is less than or equal to a preset power generation threshold value through the MySQL client.

[0035] Preferably, the MySQL database implements conditional data screening by using the WHERE clause in the SQL statement, so as to accurately query the required data. MySQL supports multiple screening functions, including logical operator screening, fuzzy query, NULL value screening and range screening.

[0036] Preferably, the specific method of MySQL data screening is as follows: ‌Logical operator filtering‌: MySQL supports logical operators such as AND, OR, and NOT, and can combine multiple conditions for complex queries.

[0037] ‌Fuzzy Query‌: Use LIKE and REGEXP operators for fuzzy matching. LIKE is used for fuzzy matching, while REGEXP is used for regular expression matching.

[0038] ‌NULL value filtering‌: Use IS NULL and IS NOT NULL operators to filter for NULL values.

[0039] ‌Range Filter‌: Use BETWEEN and IN operators to perform range filtering on field values.

[0040] Step S9: marking the power generation data that is less than or equal to the preset power generation threshold as performance abnormality data.

[0041] Preferably, since the prediction result has the characteristic of randomness of illumination, the preset power generation threshold can be set to a proportional value, for example 80%, that is, if the power generation predicted at a certain moment is less than 80% of the normal value, the performance is judged to be abnormal.

[0042] Further, in step S2, all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods, including: Step S21: Build the global environment variable file of the TiDB library through the TiUP component manager.

[0043] Step S22: Generate a TiDB cluster in the global environment variable file through the playground instruction of the TiUP component manager.

[0044] Preferably, the most basic TiDB test cluster usually consists of 2 TiDB instances, 3 TiKV instances, 3 PD instances, and an optional TiFlash instance. Through TiUP Playground, you can quickly build a basic test cluster.

[0045] Preferably, the above TiDB instance, TiKV instance, PD instance, and TiFlash instance can be implemented through the following commands: [root@worker2 tidb]# tiup playground v7.5.0 --db 2 --pd 3 --kv 3.

[0046] It is worth noting that TiUP requires the absolute path of the Shell profile file to be set. Before executing the source command ([root@worker2 tidb]# source / root / .bash_profile), you need to modify ${your_shell_profile} to the actual location of the Shell profile data file.

[0047] Step S23: Connect to the TiDB cluster through the MySQL client signal.

[0048] Preferably, you can use the following command to connect the MySQL client to the TiDB cluster: [root@worker2 tidb]# mysql --host 127.0.0.1 --port 4000 -u root.

[0049] It is worth noting that the host address needs to be queried and replaced by yourself.

[0050] Step S24, create a first blank database in the TiDB cluster through the SQL creation statement of the MySQL client, with all electrical data as the row dimension and the number of all preset natural time periods as the column dimension. All electrical data includes all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data.

[0051] Preferably, the SQL creation statement is: mysql>CREATE DATABASE IF NOT EXISTS 'tidb'.

[0052] It can be seen that the dimension of the first blank database is 5×n, the first column from the left is each preset natural time period, and the second to fifth columns from the left are the above-mentioned four electrical data.

[0053] Step S25, importing all electrical data into the first blank database through the SQL import statement of the MySQL client to form a power station data summary table.

[0054] Preferably, the SQL import statement is: mysql>INSERT INTO tidb VALUES(1,2,3,4); The statement here means to add 1,2,3,4 in the data (1,2,3,4) to the first blank database in the order of the four headers of Table 1.

[0055] Further, in step S7, all future power generation data and all future times corresponding to future power generation are imported into the TiDB library through the MySQL client and a future power generation summary table is generated, including: Step S71, create a second blank database in the TiDB cluster through the SQL creation statement of the MySQL client, with the number of all preset natural time periods as the row dimension and the future power generation as a single column dimension.

[0056] Step S72, importing all future power generation into the second blank database through the SQL import statement of the MySQL client to form a future power generation summary table.

[0057] Preferably, the principle of step S7 and its sub-steps is the same as the principle of step S2 and its sub-steps.

[0058] Further, in step S3, a multivariate linear regression model is defined for all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data through the statsmodels library of Python. The multivariate linear regression model has a reserved data import interface, including: Step S31, defining the DC electrical data, inverter electrical data, AC electrical data, and boost electrical data of the same preset natural time period as a group of independent variables.

[0059] Step S32, defining the power generation data of the same preset natural time period as a dependent variable of a set of independent variables, and defining the dependent variable and all independent variables of the same preset natural time period as a set of linear regression relationships.

[0060] Step S33, performing standard normalization processing on all linear regression relationships.

[0061] Preferably, this embodiment prefers the zero-mean normalization (Z-score normalization) normalization method, which gives the mean and standard deviation of the original data to standardize the data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1.

[0062] Step S34, all linear regression relationships are defined as a multivariate linear regression model according to formula (1): (1).

[0063] in, For the A dependent variable with a predetermined natural time period, is the number of all preset natural time periods, is the intercept of all linear regression relationships, is the linear regression coefficient of all DC electrical data, is the linear regression coefficient of all inverter electrical data, is the linear regression coefficient of all AC electrical data, is the linear regression coefficient of all boost electrical data, For the DC electrical data for a preset natural time period, For the Inverter electrical data for a preset natural time period, For the AC electrical data for a preset natural time period, For the Boost electrical data for a preset natural time period, is the random error of all linear regression relationships.

[0064] Step S35, a data import interface is reserved at the beginning of the code of the multivariate linear regression model through the flask framework of Python.

[0065] Preferably, Python comes with the DB-API database programming interface specification, which defines a set of database programming interface standards so that developers can use a unified method to connect and operate different types of databases. The latest version is PEP249, which defines a series of interfaces and behaviors so that Python programs can easily interact with databases.

[0066] Preferably, commonly used database adapters such as MySQL-python, psycopg2 (for PostgreSQL), cx_Oracle (for Oracle database), etc.; in addition to using native database adapters to connect to the database, many developers also like to use ORM (object-relational mapping) frameworks, such as SQLAlchemy, DjangoORM, etc. The ORM framework provides a more object-oriented approach to database operations, so that developers do not need to write SQL statements, but use classes and objects to represent and operate data in the database.

[0067] Further, step S5, solving the multivariate linear regression model by the least square method to obtain a prediction model, including: Step S51, using the least squares method to solve all linear regression coefficients according to formula (2): (2).

[0068] in, for The estimated value of ,correspond , , , , is the matrix of all independent variables, For the matrix The transposed matrix of .

[0069] Preferably, .

[0070] Step S52: Substitute all the regression coefficients obtained by solving into all the linear regression relationships to obtain a prediction model.

[0071] Preferably, the square of the residual To test the significance of the prediction model, if , it means that the prediction model is more significant; if , it means that the significance of the prediction model is general; if , it means that the significance of the prediction model is poor, and the significance of the prediction model is linearly positively correlated with the square of the residual.

[0072] Further, in step S2, all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods, and then include: Step S10: split the power plant data summary table into a plurality of data sub-tables based on all preset natural time periods.

[0073] Step S20, obtain the chain hash certificate of each data sub-table through the SHA256 algorithm.

[0074] Preferably, the SHA256 algorithm is a subdivided algorithm under SHA-2. The name SHA-2 comes from the abbreviation of Secure Hash Algorithm 2, which is a cryptographic hash function algorithm standard. SHA-2 can be further divided into six different algorithm standards: SHA224, SHA256, SHA384, SHA512, SHA512 / 224, SHA512 / 256. These variants have the same basic structure except for some minor differences such as the length of the generated summary and the number of loop runs. SHA-256 is a hash function, also known as a hash algorithm, which is a method of creating a small digital "fingerprint" from any kind of data. The hash function compresses a message or data into a summary, making the data smaller and fixing the format of the data. The function shuffles and mixes the data to recreate a fingerprint called a hash value (or hash value). The hash value is usually represented by a short string of random letters and numbers. For messages of any length, SHA256 will generate a 256-bit hash value, called a message digest. This message digest is equivalent to an array of 32 bytes in length, usually represented by a 64-byte hexadecimal string.

[0075] Step S30, copy all the on-chain hash certificates and save them locally, forming a local hash certificate based on a data partition table.

[0076] Preferably, the power plant data is of vital importance, and the on-chain hash certificate and the local hash certificate can ensure the authenticity of the data.

[0077] Step S40, save all the on-chain hash certificates in order from old to new according to all preset natural time periods to the external blockchain.

[0078] Preferably, the above-mentioned one hour or half an hour can be used as a storage node, and the chain span of the on-chain hash certificate can be realized with the chain span of natural time.

[0079] Step S50, based on the current local hash certificate, retrieve the on-chain hash certificate that matches the local hash certificate from the external blockchain.

[0080] Step S60, determine whether the on-chain hash certificate is retrieved successfully. If the on-chain hash certificate is not retrieved successfully, execute step S70.

[0081] Step S70, determining whether one of the on-chain hash certificate and the local hash certificate has been tampered with.

[0082] Step S80: Generate a data tampering signal and send it to an external monitoring terminal.

[0083] Preferably, the hash voucher is to save the hash value of the file content on the chain. The hash value of the file content is usually called the digital fingerprint of the file, which can be obtained by hashing the file content. Because the length of the hash value is relatively limited, for example, the SHA256 hash value of data with tens of thousands of words is only 256 bits of characters, and the storage of such a length of content on the chain is stress-free for the blockchain. The hash voucher can be used to verify whether the file content has been tampered with. For example, the hash value of an original text is stored on the blockchain. When the file is obtained again, the content is hashed. If it is consistent with the content stored on the chain, the content is considered to be credible and has not been tampered with. If the hash value is different, it is considered that the content has been tampered with and is no longer credible. To prevent the data from being maliciously implanted with viruses, the power station can put the digital fingerprint of the electrical data it has obtained into the blockchain. Users can verify whether the digital fingerprint has changed in the software downloaded from different channels. If there is a change, it is considered that the software may be implanted with a virus or a Trojan horse and is no longer safe.

[0084] Further, in step S7, all future power generation data and all future times corresponding to future power generation are imported into the TiDB database through the MySQL client and a future power generation summary table is generated, and then, the following steps are included: Step S100, query, update, and delete data on a power plant data summary table or a future power generation summary table through SQL query statements, SQL update statements, and SQL delete statements of a MySQL client.

[0085] Step S200: Generate a query record with a query timestamp and query content based on each data query.

[0086] Step S300: Generate an update record with an update timestamp and update content based on each data update.

[0087] Step S400: Generate a deletion record with a deletion timestamp and deletion content based on each data deletion.

[0088] Step S500, sending all query records, all update records, and all deletion records to an external monitoring terminal.

[0089] Preferably, the SQL query statement is: mysql>SELECT * FROM tidb.

[0090] mysql>SELECT * FROM tidb WHERE id<10; the statement here means to query the data with a sequence number less than 10.

[0091] The SQL update statement is: mysql>UPDATE tidb SET (3)='35kV' WHERE id=3; The statement here means to replace the data with serial number 3 in the third column with "35kV".

[0092] The SQL delete statement is: mysql>DELETE FROM tidb WHERE id=2; the statement here means to delete the entire row of data with sequence number 2.

[0093] It should be noted that the above statements are only examples and are not used to limit the fixed format of the statements. Other SQL call statements can also directly call the database of this embodiment.

[0094] This embodiment obtains several DC electrical data, several inverter electrical data, several AC electrical data, several boost electrical data of DC distribution cabinets, inverters, AC distribution cabinets, and booster stations based on preset natural time periods, as well as several power generation data of photovoltaic power stations based on preset natural time periods; all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods; all power generation data are defined through the Python statsmodels library as being respectively related to all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data A multivariate linear regression model based on the data is prepared, and a data import interface is reserved for the multivariate linear regression model; the TiDB library and the data import interface are connected through the MySQL client signal to import the power plant data summary table into the multivariate linear regression model; the multivariate linear regression model is solved by the least squares method to obtain a prediction model; a number of future power generation data are predicted based on the preset future prediction steps through the prediction model; all future power generation data and the future time corresponding to all future power generation are imported into the TiDB library through the MySQL client and a future power generation summary table is generated; the power generation data in the future power generation summary table that is less than or equal to the preset power generation threshold is searched through the MySQL client; the power generation data that is less than or equal to the preset power generation threshold is marked as performance abnormality data. This embodiment automatically obtains the electrical data (such as voltage, current, power, frequency, etc.) of each electrical device at a certain interval and collects and uniformly manages all the electrical data to form a traceable database, which not only facilitates the subsequent various analysis software and analysis algorithms to be directly accessed through the data interface, but also facilitates subsequent query, traceability and other access operations, so that the electrical data of the photovoltaic power station is comprehensively and effectively managed. At the same time, this embodiment directly connects the linear regression analysis to the database to realize the linear regression analysis of the performance of each electrical device, and then the performance of each electrical device in the photovoltaic power station can be obtained by solving the linear regression model. The embodiment uses the form of access to the database to perform linear regression analysis, so that the prediction results can also be managed uniformly using the database. Finally, by querying the data of abnormal future power generation, it can be known that the equipment performance is abnormal. At the same time, it also realizes the advanced monitoring of electrical equipment in the photovoltaic power station, and there is no need to wait until the electrical equipment actually fails. Compared with the prior art, this embodiment avoids subjective experience errors, and the entire process of data collection-data analysis-data management-data screening does not require human participation, and the data style is unified and can be managed uniformly. The obtained database can be directly applied to the data needs of other scenarios, which significantly improves the operation and maintenance efficiency of photovoltaic power stations.

[0095] like Figure 3As shown, this embodiment provides an embodiment of a performance monitoring device for a photovoltaic power station. In this embodiment, the performance monitoring device is applied to the performance monitoring method in the above embodiment.

[0096] Specifically, the performance monitoring device includes an electrical data acquisition module 1, an electrical data management module 2, a linear regression definition module 3, an electrical data import module 4, a linear regression solution module 5, a future power generation prediction module 6, a future power generation data management module 7, a future power generation data retrieval module 8, and a performance abnormality data marking module 9, which are electrically connected in sequence.

[0097] Among them, the electrical data acquisition module 1 is used to obtain a number of DC electrical data, a number of inverter electrical data, a number of AC electrical data, a number of boost electrical data of the DC distribution cabinet, the inverter, the AC distribution cabinet, and the booster station based on a preset natural time period, as well as a number of power generation data of the photovoltaic power station based on a preset natural time period; the electrical data management module 2 is used to manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods; the linear regression definition module 3 is used to define a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data through the statsmodels library of Python, and the multivariate linear regression model reserves data The electrical data import interface is used; the electrical data import module 4 is used to connect the TiDB library and the data import interface through the MySQL client signal to import the power station data summary table into the multivariate linear regression model; the linear regression solution module 5 is used to solve the multivariate linear regression model through the least squares method to obtain the prediction model; the future power generation prediction module 6 is used to predict a number of future power generation data based on the preset future prediction steps through the prediction model; the future power generation data management module 7 is used to import all future power generation data and the future time corresponding to all future power generation into the TiDB library through the MySQL client and generate a future power generation summary table; the future power generation data retrieval module 8 is used to search for power generation data in the future power generation summary table that is less than or equal to the preset power generation threshold through the MySQL client; the performance abnormality data marking module 9 is used to mark the power generation data that is less than or equal to the preset power generation threshold as performance abnormality data.

[0098] Furthermore, the electrical data management module 2 specifically includes a first electrical data management sub-module, a second electrical data management sub-module, a third electrical data management sub-module, a fourth electrical data management sub-module, and a fifth electrical data management sub-module, which are electrically connected in sequence; the first electrical data management sub-module is electrically connected to the electrical data acquisition module 1, and the fifth electrical data management sub-module is electrically connected to the linear regression definition module 3.

[0099] Among them, the first electrical data management submodule is used to build the global environment variable file of the TiDB library through the TiUP component manager; the second electrical data management submodule is used to generate a TiDB cluster in the global environment variable file through the playground instruction of the TiUP component manager; the third electrical data management submodule is used to connect the TiDB cluster through the MySQL client signal; the fourth electrical data management submodule is used to create a first blank database in the TiDB cluster through the SQL creation statement of the MySQL client, with all electrical data as the row dimension and the number of all preset natural time periods as the column dimension. All electrical data includes all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data; the fifth electrical data management submodule is used to import all electrical data into the first blank database through the SQL import statement of the MySQL client to form a power plant data summary table.

[0100] Furthermore, the future power generation data management module 7 specifically includes a first future power generation data management submodule and a second future power generation data management submodule which are electrically connected in sequence; the first future power generation data management submodule is electrically connected to the future power generation prediction module 6, and the second future power generation data management submodule is electrically connected to the future power generation data retrieval module 8.

[0101] Among them, the first future power generation data management submodule is used to create a second blank database in the TiDB cluster through the SQL creation statement of the MySQL client, with the number of all preset natural time periods as the row dimension and the future power generation as the single column dimension; the second future power generation data management submodule is used to import all future power generation into the second blank database through the SQL import statement of the MySQL client to form a future power generation summary table.

[0102] Furthermore, the linear regression definition module 3 specifically includes a first linear regression definition submodule, a second linear regression definition submodule, a third linear regression definition submodule, a fourth linear regression definition submodule, and a fifth linear regression definition submodule, which are electrically connected in sequence; the first linear regression definition submodule is electrically connected to the electrical data management module 2, and the fifth linear regression definition submodule is electrically connected to the electrical data import module 4.

[0103] Among them, the first linear regression definition submodule is used to define DC electrical data, inverter electrical data, AC electrical data, and boost electrical data of the same preset natural time period as a set of independent variables.

[0104] The second linear regression definition submodule is used to define the power generation data of the same preset natural time period as a dependent variable of a set of independent variables, and define the dependent variable and all independent variables of the same preset natural time period as a set of linear regression relationships.

[0105] The third linear regression definition submodule is used to perform standard normalization on all linear regression relationships.

[0106] The fourth linear regression definition submodule is used to define all linear regression relationships as a multivariate linear regression model according to formula (1): (1).

[0107] in, For the A dependent variable with a predetermined natural time period, is the number of all preset natural time periods, is the intercept of all linear regression relationships, is the linear regression coefficient of all DC electrical data, is the linear regression coefficient of all inverter electrical data, is the linear regression coefficient of all AC electrical data, is the linear regression coefficient of all boost electrical data, For the DC electrical data for a preset natural time period, For the Inverter electrical data for a preset natural time period, For the AC electrical data for a preset natural time period, For the Boost electrical data for a preset natural time period, is the random error of all linear regression relationships.

[0108] The fifth linear regression definition submodule is used to reserve a data import interface at the beginning of the code of the multivariate linear regression model through the Python flask framework.

[0109] Furthermore, the linear regression solution module 5 specifically includes a first linear regression solution module and a second linear regression solution module which are electrically connected in sequence; the first linear regression solution module is electrically connected to the electrical data import module 4, and the second linear regression solution module is electrically connected to the future power generation prediction module 6.

[0110] The first linear regression solution module is used to solve all linear regression coefficients according to formula (2) by the least square method: (2).

[0111] in, for The estimated value of ,correspond , , , , is the matrix of all independent variables, For the matrix The transposed matrix of .

[0112] The second linear regression solution module is used to substitute all the regression coefficients obtained by solution into all the linear regression relationships to obtain a prediction model.

[0113] Furthermore, the performance monitoring device also includes a power plant data summary table splitting module, an up-chain hash credential acquisition module, a local hash credential acquisition module, an up-chain hash credential storage module, a hash credential matching module, a hash credential judgment module, a hash credential tampering judgment module, and a tampering signal generation and sending module, which are electrically connected in sequence; the power plant data summary table splitting module is electrically connected to the electrical data management module 2, or is electrically connected to the fifth electrical data management sub-module of the electrical data management module 2.

[0114] Among them, the power plant data summary table splitting module is used to split the power plant data summary table into several data sub-tables based on all preset natural time periods; the on-chain hash certificate acquisition module is used to obtain the on-chain hash certificate of each data sub-table through the SHA256 algorithm; the local hash certificate acquisition module is used to copy all on-chain hash certificates and save them locally, forming a local hash certificate based on a data sub-table; the on-chain hash certificate preservation module is used to save all on-chain hash certificates in sequence from old to new according to all preset natural time periods to the external blockchain; the hash certificate matching module is used to retrieve the on-chain hash certificate that matches the local hash certificate in the external blockchain based on the current local hash certificate; the hash certificate judgment module is used to judge whether the on-chain hash certificate is successfully retrieved; the hash certificate tampering judgment module is used to determine that one of the on-chain hash certificate and the local hash certificate has been tampered with if the on-chain hash certificate is not successfully retrieved; the tampering signal generation and sending module is used to generate a data tampering signal and send it to an external monitoring terminal.

[0115] Furthermore, the performance monitoring device also includes a database maintenance module, a database query record generating module, a database update record generating module, a database deletion record generating module, a database maintenance record sending module, and a database maintenance record sending module, which are electrically connected in sequence; the database maintenance module is electrically connected to the future power generation data management module 7, or is electrically connected to the second future power generation data management sub-module of the future power generation data management module 7.

[0116] Among them, the database maintenance module is used to query, update and delete data on the power plant data summary table or the future power generation summary table through the SQL query statement, SQL update statement and SQL delete statement of the MySQL client; the database query record generation module is used to generate a query record with a query timestamp and query content based on each data query; the database update record generation module is used to generate an update record with an update timestamp and update content based on each data update; the database deletion record generation module is used to generate a deletion record with a deletion timestamp and deletion content based on each data deletion; the database maintenance record sending module is used to send all query records, all update records and all deletion records to the external monitoring terminal.

[0117] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The optimization, expansion, limitation, example, and principle description of this embodiment can be referred to the above embodiment, and this embodiment will not be repeated.

[0118] This embodiment obtains several DC electrical data, several inverter electrical data, several AC electrical data, several boost electrical data of DC distribution cabinets, inverters, AC distribution cabinets, and booster stations based on preset natural time periods, as well as several power generation data of photovoltaic power stations based on preset natural time periods; all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods; all power generation data are defined through the Python statsmodels library as being respectively related to all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data A multivariate linear regression model based on the data is prepared, and a data import interface is reserved for the multivariate linear regression model; the TiDB library and the data import interface are connected through the MySQL client signal to import the power plant data summary table into the multivariate linear regression model; the multivariate linear regression model is solved by the least squares method to obtain a prediction model; a number of future power generation data are predicted based on the preset future prediction steps through the prediction model; all future power generation data and the future time corresponding to all future power generation are imported into the TiDB library through the MySQL client and a future power generation summary table is generated; the power generation data in the future power generation summary table that is less than or equal to the preset power generation threshold is searched through the MySQL client; the power generation data that is less than or equal to the preset power generation threshold is marked as performance abnormality data. This embodiment automatically obtains the electrical data (such as voltage, current, power, frequency, etc.) of each electrical device at a certain interval and collects and uniformly manages all the electrical data to form a traceable database, which not only facilitates the subsequent various analysis software and analysis algorithms to be directly accessed through the data interface, but also facilitates subsequent query, traceability and other access operations, so that the electrical data of the photovoltaic power station is comprehensively and effectively managed. At the same time, this embodiment directly connects the linear regression analysis to the database to realize the linear regression analysis of the performance of each electrical device, and then the performance of each electrical device in the photovoltaic power station can be obtained by solving the linear regression model. The embodiment uses the form of access to the database to perform linear regression analysis, so that the prediction results can also be managed uniformly using the database. Finally, by querying the data of abnormal future power generation, it can be known that the equipment performance is abnormal. At the same time, it also realizes the advanced monitoring of electrical equipment in the photovoltaic power station, and there is no need to wait until the electrical equipment actually fails. Compared with the prior art, this embodiment avoids subjective experience errors, and the entire process of data collection-data analysis-data management-data screening does not require human participation, and the data style is unified and can be managed uniformly. The obtained database can be directly applied to the data needs of other scenarios, which significantly improves the operation and maintenance efficiency of photovoltaic power stations.

[0119] like Figure 4As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0120] The memory 102 stores program instructions for implementing the performance monitoring method of a photovoltaic power station according to any of the above embodiments.

[0121] The processor 101 is used to execute program instructions stored in the memory 102 to monitor the performance of the photovoltaic power station.

[0122] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having data processing capabilities. The processor 101 may also be a general-purpose processor, a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0123] Further, Figure 5 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0125] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0126] The specific implementation methods of the present application are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the present application is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A performance monitoring method for a photovoltaic power station, wherein the photovoltaic power station comprises a plurality of photovoltaic arrays, a DC distribution cabinet electrically connected to each photovoltaic array, an inverter electrically connected to the DC distribution cabinet, an AC distribution cabinet electrically connected to the inverter, and a booster station electrically connected to the AC distribution cabinet, wherein: The performance monitoring method comprises: Step S1, obtaining a number of DC electrical data, a number of inverter electrical data, a number of AC electrical data, a number of boost electrical data of the DC distribution cabinet, the inverter, the AC distribution cabinet, and the booster station based on a preset natural time period, and a number of power generation data of the photovoltaic power station based on the preset natural time period; Step S2: manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods; Step S3, defining a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data through the statsmodels library of Python, wherein the multivariate linear regression model has a reserved data import interface; Step S4, connecting the TiDB library and the data import interface through a MySQL client signal to import the power plant data summary table into the multivariate linear regression model; Step S5, solving the multivariate linear regression model by the least square method to obtain a prediction model; Step S6, predicting a number of future power generation data based on a preset future prediction step number by using the prediction model; Step S7, importing all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generating a future power generation summary table; Step S8, searching the future power generation summary table for power generation data that is less than or equal to a preset power generation threshold value through the MySQL client; Step S9: marking the power generation data that is less than or equal to the preset power generation threshold as performance abnormality data.

2. The performance monitoring method according to claim 1, characterized in that: Step S2: All DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data are managed through the TiDB library to obtain a power station data summary table based on several preset natural time periods, including: Step S21, building a global environment variable file of the TiDB library through the TiUP component manager; Step S22, generating a TiDB cluster in the global environment variable file through the playground instruction of the TiUP component manager; Step S23, connecting to the TiDB cluster through the MySQL client signal; Step S24, creating a first blank database in the TiDB cluster using the SQL creation statement of the MySQL client, with all electrical data as the row dimension and the number of all preset natural time periods as the column dimension. All electrical data includes all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data. Step S25, importing all electrical data into the first blank database through the SQL import statement of the MySQL client to form the power station data summary table.

3. The performance monitoring method according to claim 2, characterized in that: Step S7, importing all future power generation data and all future times corresponding to future power generation into the TiDB database through the MySQL client and generating a future power generation summary table, including: Step S71, creating a second blank database in the TiDB cluster through a SQL creation statement of the MySQL client, with the number of all preset natural time periods as the row dimension and the future power generation as a single column dimension; Step S72, importing all future power generation into the second blank database through the SQL import statement of the MySQL client to form the future power generation summary table.

4. The performance monitoring method according to claim 1, characterized in that: Step S3, using Python's statsmodels library to define a multiple linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data, wherein the multiple linear regression model has a reserved data import interface, including: Step S31, defining DC electrical data, inverter electrical data, AC electrical data, and boost electrical data of the same preset natural time period as a set of independent variables; Step S32, defining the power generation data of the same preset natural time period as the dependent variable of the set of independent variables, and defining the dependent variable of the same preset natural time period and all independent variables as a set of linear regression relationships; Step S33, performing standard normalization processing on all linear regression relationships; Step S34, defining all linear regression relationships as the multivariate linear regression model according to formula (1): （1）； in, For the A dependent variable with a predetermined natural time period, is the number of all preset natural time periods, is the intercept of all linear regression relationships, is the linear regression coefficient of all DC electrical data, is the linear regression coefficient of all inverter electrical data, is the linear regression coefficient of all AC electrical data, is the linear regression coefficient of all boost electrical data, For the DC electrical data for a preset natural time period, For the Inverter electrical data for a preset natural time period, For the AC electrical data for a preset natural time period, For the Boost electrical data for a preset natural time period, is the random error of all linear regression relationships; Step S35, reserving the data import interface at the beginning of the code of the multivariate linear regression model through the flask framework of Python.

5. The performance monitoring method according to claim 4, characterized in that: Step S5, solving the multivariate linear regression model by the least square method to obtain a prediction model, including: Step S51, using the least squares method to solve all linear regression coefficients according to formula (2): （2）； in, for The estimated value of ,correspond , , , , is the matrix of all independent variables, For the matrix The transposed matrix of Step S52, substituting all the regression coefficients obtained by solving into all the linear regression relationships to obtain the prediction model.

6. The performance monitoring method according to claim 1, characterized in that: Step S2: manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods, and then include: Step S10, splitting the power station data summary table into a plurality of data sub-tables based on all preset natural time periods; Step S20, obtaining the chain hash certificate of each data sub-table through the SHA256 algorithm; Step S30, copy all the hash certificates on the chain and save them locally, so as to obtain a local hash certificate based on a data table; Step S40, saving all the hash certificates on the chain to the external blockchain in order from old to new according to all preset natural time periods; Step S50, based on the current local hash certificate, retrieve the on-chain hash certificate that matches the local hash certificate from the external blockchain; Step S60, determining whether the on-chain hash certificate is retrieved successfully, if the on-chain hash certificate is not retrieved successfully, executing step S70; Step S70, determining whether one of the on-chain hash certificate and the local hash certificate has been tampered with; Step S80: Generate a data tampering signal and send it to an external monitoring terminal.

7. The performance monitoring method according to claim 1, characterized in that: Step S7, importing all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generating a future power generation summary table, and then including: Step S100, querying, updating, or deleting data on the power plant data summary table or the future power generation summary table through the SQL query statement, SQL update statement, or SQL delete statement of the MySQL client; Step S200, generating a query record with a query timestamp and query content based on each data query; Step S300, generating an update record with an update timestamp and update content based on each data update; Step S400, generating a deletion record with a deletion timestamp and deletion content based on each data deletion; Step S500, all query records, all update records, and all deletion records are sent to an external monitoring terminal.

8. A performance monitoring device for a photovoltaic power station, applied to the performance monitoring method according to any one of claims 1 to 7, characterized in that: The performance monitoring device comprises: An electrical data acquisition module, used to acquire a number of DC electrical data, a number of inverter electrical data, a number of AC electrical data, a number of boost electrical data of the DC power distribution cabinet, the inverter, the AC power distribution cabinet, and the booster station based on a preset natural time period, and a number of power generation data of the photovoltaic power station based on the preset natural time period; The electrical data management module is used to manage all DC electrical data, all inverter electrical data, all AC electrical data, all boost electrical data, and all power generation data through the TiDB library to obtain a power station data summary table based on several preset natural time periods; A linear regression definition module is used to define a multivariate linear regression model of all power generation data and all DC electrical data, all inverter electrical data, all AC electrical data, and all boost electrical data through the statsmodels library of Python, wherein the multivariate linear regression model has a reserved data import interface; An electrical data import module, used to connect to the TiDB library and the data import interface through a MySQL client signal to import the power station data summary table into the multivariate linear regression model; A linear regression solution module, used for solving the multivariate linear regression model by the least square method to obtain a prediction model; A future power generation prediction module, used to predict a number of future power generation data based on a preset future prediction step number through the prediction model; A future power generation data management module, used to import all future power generation data and all future times corresponding to future power generation into the TiDB library through the MySQL client and generate a future power generation summary table; A future power generation data retrieval module, used to search the future power generation summary table for power generation data that is less than or equal to a preset power generation threshold through the MySQL client; The performance abnormality data marking module is used to mark the power generation data that is less than or equal to a preset power generation threshold as performance abnormality data.

9. An electronic device, characterized in that: It comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the performance monitoring method as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the performance monitoring method according to any one of claims 1 to 7 can be implemented.

Images