Power supply output curve data quality restoration method, system, medium and equipment

Abstract

The invention provides a power supply output curve data quality restoration method and system, a medium and equipment. The method comprises the following steps: acquiring power supply output curve data of a target photovoltaic power station; determining to-be-repaired data with problems in the power supply output curve data; if the to-be-repaired data is multi-day data, repairing the to-be-repaired data by adopting a proportional repair method; and if the to-be-repaired data is single-day data, repairing the to-be-repaired data by adopting a linear interpolation method. According to the method, the single-day data or the multi-day data or the combination of the single-day data and the multi-day data is selected for restoration according to the data missing condition, and the accuracy of power output curve data restoration of the target photovoltaic power station is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a method, system, medium and equipment for repairing power output curve data quality. Background Art

[0002] Photovoltaic and thermal power plant power generation are important energy generation bases. The output of photovoltaic power generation will fluctuate and be intermittent as the intensity of solar radiation and temperature change. The output of power plant power generation will fluctuate and be intermittent as the capacity and parameters of the units change.

[0003] Power generation output data is often minute-level data with a large data volume. When quickly identifying abnormal data in a massive amount of data and then repairing it based on historical data fluctuations, the accuracy of data repair is often greatly reduced due to complex algorithms and large data volumes.

[0004] Therefore, in the prior art, there is a problem that the results of the repair method of the power output curve data are not accurate enough. Summary of the invention

[0005] In order to overcome the above-mentioned deficiencies of the prior art, in a first aspect, the present invention proposes a method for repairing the quality of power output curve data, comprising:

[0006] Collect power output curve data of the target photovoltaic power station;

[0007] Determining problematic data to be repaired in the power output curve data;

[0008] If the data to be repaired is data for multiple days, the data to be repaired is repaired using a proportional repair method;

[0009] If the data to be repaired is single-day data, a linear interpolation method is used to repair the data to be repaired.

[0010] Preferably, if the data to be repaired is multi-day data, a proportional repair method is used to repair the data to be repaired, including:

[0011] Based on the data to be repaired being multi-day data, determining a data missing value interval of the data to be repaired, the number of days between the data missing value intervals, and a previous period value of the missing data in the data to be repaired;

[0012] Based on the data missing value interval, the interval days, and the previous period value of the missing data, the missing data in the data missing value interval is calculated using a proportional repair method;

[0013] Based on the calculation result, the missing data in the data missing value interval is repaired.

[0014] Preferably, the missing data in the missing data interval is calculated using a proportional repair method based on the missing data interval, the interval days, and the previous period value of the missing data, satisfying the following calculation formula:

[0015]

[0016] In the above formula, x t is the missing data in multiple days’ data, x t-1 is the previous period data value of the missing data, x t-1+n is the data value of the next period after the missing data, n is the number of days, and t is the number of days; i is the proportion of missing data in multiple days of data, and its value is an integer from 1 to n.

[0017] Preferably, if the data to be repaired is single-day data, the data to be repaired is repaired using a linear interpolation method, including:

[0018] Based on the fact that the data to be repaired is single-day data, taking the average of the data before and after the missing data in the data to be repaired, and using the average as the missing data to interpolate the position where the missing data is located;

[0019] The average of the preceding and following data of the missing data in the data to be repaired satisfies the following calculation formula:

[0020]

[0021] Among them, x t’ is the mean of the data before and after the missing data, x t-1’ is the previous period value of the missing data, x t+1 is the value of the next period for missing data.

[0022] Preferably, after collecting the power output curve data of the target photovoltaic power station, the method further comprises:

[0023] Based on the power output curve data, the power output curve data is cleaned.

[0024] Preferably, the power output curve data of the target photovoltaic power station is derived from the original meter code of the target photovoltaic power station.

[0025] In a second aspect, the present invention also provides a power output curve data quality repair system, comprising:

[0026] A collection module, used to collect power output curve data of the target photovoltaic power station;

[0027] A module for determining data to be repaired, used for determining data to be repaired that has problems in the power output curve data;

[0028] A proportion repair method repair module, used to repair the data to be repaired by using a proportion repair method if the data to be repaired is multi-day data;

[0029] The linear interpolation repair module is used to repair the data to be repaired by using the linear interpolation method if the data to be repaired is single-day data.

[0030] Preferably, the proportion repair method repair module includes:

[0031] A data determination submodule, for determining, based on the data to be repaired being multi-day data, a data missing value interval of the data to be repaired, the number of days between the data missing value intervals, and a previous period value of missing data in the data to be repaired;

[0032] A data calculation submodule, for calculating the missing data in the data missing value interval by using a proportional repair method based on the data missing value interval, the interval days, and the previous period value of the missing data;

[0033] The data repair submodule is used to repair the missing data in the data missing value interval based on the calculation result.

[0034] Preferably, the missing data in the missing data interval is calculated using a proportional repair method based on the missing data interval, the interval days, and the previous period value of the missing data, satisfying the following calculation formula:

[0035]

[0036] In the above formula, x t is the missing data in multiple days’ data, x t-1 is the previous period data value of the missing data, x t-1+n is the data value of the next period after the missing data, n is the number of days, and t is the number of days; i is the proportion of missing data in multiple days of data, and its value is an integer from 1 to n.

[0037] Preferably, the linear interpolation repair module comprises:

[0038] A data interpolation submodule is used for taking the average of the data before and after the missing data in the data to be repaired based on the fact that the data to be repaired is a single day's data, and using the average as the missing data to interpolate the position where the missing data is located;

[0039] The average of the preceding and following data of the missing data in the data to be repaired satisfies the following calculation formula:

[0040]

[0041] Among them, xt’ is the mean of the data before and after the missing data, x t-1’ is the previous period value of the missing data, x t+1 is the value of the next period for missing data.

[0042] Preferably, the system further comprises:

[0043] A cleaning module is used to clean the power output curve data based on the power output curve data.

[0044] Preferably, the power output curve data of the target photovoltaic power station is derived from the original meter code of the target photovoltaic power station.

[0045] In a third aspect, the present invention also provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0046] The memory is used to store one or more programs;

[0047] When the one or more programs are executed by the at least one processor, the power output curve data quality repair method is implemented.

[0048] In a fourth aspect, the present invention application further provides a readable storage medium having an execution program stored thereon, and when the execution program is executed, a power output curve data quality repair method as described above is implemented.

[0049] Compared with the closest prior art, the present invention has the following beneficial effects:

[0050] The present invention provides a method for repairing the quality of power output curve data, in which the power output curve data of a target photovoltaic power station is collected; the data to be repaired with problems is determined in the power output curve data; if the data to be repaired is multi-day data, a proportional repair method is used to repair the data to be repaired; if the data to be repaired is single-day data, a linear interpolation method is used to repair the data to be repaired. According to the data missing situation, single-day data or multi-day data, or a combination of the two, is selected for repair, thereby improving the accuracy of the power output curve data repair of the target photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic flow chart of a method for repairing power output curve data quality provided by the present invention;

[0052] Figure 2 An architectural diagram of a power output curve data quality repair system provided by the present invention;

[0053] Figure 3A daily total meter code curve diagram of a photovoltaic power station unit in Example 3 of the present invention;

[0054] Figure 4 A curve diagram of the daily total meter code of the unit after repair by the proportional repair method in Example 3 of the present invention;

[0055] Figure 5 The total meter code curve diagram of the unit in Example 3 of the present invention;

[0056] Figure 6 The total table code curve diagram of the unit after linear interpolation in Example 3 of the present invention;

[0057] Figure 7 A schematic diagram of the operation of an electronic device provided in the present invention application. DETAILED DESCRIPTION

[0058] The specific implementation methods of the present invention are further described in detail below with reference to the accompanying drawings.

[0059] Embodiment 1:

[0060] like Figure 1 As shown, the present invention provides a method for repairing power output curve data quality, comprising:

[0061] Step 1: Collect the power output curve data of the target photovoltaic power station;

[0062] Step 2: determining problematic data to be repaired in the power output curve data;

[0063] Step 3: If the data to be repaired is multi-day data, the proportional repair method is used to repair the data to be repaired;

[0064] Step 4: If the data to be repaired is single-day data, the data to be repaired is repaired using a linear interpolation method.

[0065] For example, in the above step 1, the power output curve data of the target photovoltaic power station is collected by a big data analysis method;

[0066] In a possible implementation manner, after collecting the power output curve data of the target photovoltaic power station, the following may also be included:

[0067] Based on the power output curve data, the power output curve data is cleaned.

[0068] The power output curve data of the target photovoltaic power station collected in step 1 may contain abnormal data. This situation can be solved by data cleaning. These abnormal data mainly include duplicate data, erroneous data, missing data, etc. If these problem data are not processed and the abnormal data are directly entered into the data repair stage, it will have a serious impact on the repair result. Therefore, it is necessary to "clean" the power output curve data collected in step 1. The purpose is to detect the abnormal data in the power output curve data set manually or automatically, and correct or merge or delete these abnormal data, so as to improve the data quality, provide a basis for the subsequent step 2, and facilitate the determination of the problematic data to be repaired;

[0069] In the above, the power output curve data of the target photovoltaic power station is derived from the original meter code of the target photovoltaic power station.

[0070] When determining the source of the power output curve data of the target photovoltaic power station, it is considered that since the power generation of each target photovoltaic power station is calculated by multiplying the original meter code data by the multiplication factor, the abnormality of the original meter code data will definitely cause the abnormality of the power. If the power data is repaired directly, there are many problems with the power data itself, and the repair process is more complicated. Compared with the power data, the original meter code data has smaller fluctuations and is easier to repair. Therefore, the original meter code data is selected as the power output curve data of the target photovoltaic power station.

[0071] For example, in the above step 2, since the output of the target photovoltaic power station will fluctuate and intermittently with the changes in solar radiation intensity and temperature, the power output will fluctuate and intermittently with the changes in the capacity and parameters of the unit. Various changes in factors will lead to a large number of problems in the collected power output curve data of the target photovoltaic power station, so it is necessary to determine the characteristics of the problem data and formulate standards for determining the data to be repaired accordingly.

[0072] For example, in the above step 3, if the data to be repaired is multi-day data, repairing the data to be repaired using a proportional repair method may include:

[0073] Based on the data to be repaired being multi-day data, determining a data missing value interval of the data to be repaired, the number of days between the data missing value intervals, and a previous period value of the missing data in the data to be repaired;

[0074] Based on the data missing value interval, the interval days, and the previous period value of the missing data, the missing data in the data missing value interval is calculated using a proportional repair method;

[0075] Based on the calculation result, the missing data in the data missing value interval is repaired.

[0076] In a possible implementation, the missing data in the missing data interval is calculated using a proportional repair method based on the missing data interval, the interval days, and the previous period value of the missing data, satisfying the following calculation formula:

[0077]

[0078] In the above formula, x t is the missing data in multiple days’ data, x t-1 is the previous period data value of the missing data, x t-1+n is the data value of the next period after the missing data, n is the number of days, and t is the number of days; i is the proportion of missing data in multiple days of data, and its value is an integer from 1 to n.

[0079] The proportional repair method is suitable for multi-day data with a lot of missing data. Multi-day data can form a data missing interval. After the proportional repair method is used to repair the data, the data before the data missing value interval and after the data missing value interval show an increasing trend, which is in line with the trend of data development, so the repaired data is more accurate.

[0080] For example, in the above step 4, if the data to be repaired is single-day data, repairing the data to be repaired by using a linear interpolation method may include:

[0081] Based on the fact that the data to be repaired is single-day data, taking the average of the data before and after the missing data in the data to be repaired, and using the average as the missing data to interpolate the position where the missing data is located;

[0082] The average of the preceding and following data of the missing data in the data to be repaired satisfies the following calculation formula:

[0083]

[0084] Among them, x t’ is the mean of the data before and after the missing data, x t-1’ is the previous period value of the missing data, x t+1 is the value of the next period for missing data.

[0085] The linear interpolation method uses the mean of the previous and next data to interpolate and repair the intermediate data. The interpolated data curve shows a spiral upward trend. The interpolated data curve is consistent with the actual situation. Since a single data is calculated each time, it is suitable for missing interpolation of single-day data.

[0086] In step 3 and step 4, according to the actual situation of data missing, a proportional repair method or a linear interpolation method is selected for repair, which improves the accuracy of repairing the historical output data of the target photovoltaic power station.

[0087] To sum up, the method of the present invention is mainly to study the trend of historical output data of the target photovoltaic power station, and quickly collect the power output curve data of the target photovoltaic power station through the big data analysis method. Since the power output curve data of the target photovoltaic power station is often minute-level data, the power output curve data of the target photovoltaic power station is large in volume. After the method of the present invention is used to quickly judge abnormal data in the massive power output curve data of the target photovoltaic power station, the data to be repaired with problems is cleaned and confirmed, and data repair standards are formulated. After that, the data to be repaired with problems is repaired, thereby improving the accuracy of the power output curve data repair of the target photovoltaic power station.

[0088] Embodiment 2:

[0089] like Figure 2 As shown, the present invention provides a power output curve data quality repair system, comprising:

[0090] A collection module, used to collect power output curve data of the target photovoltaic power station;

[0091] A module for determining data to be repaired, used for determining data to be repaired that has problems in the power output curve data;

[0092] A proportion repair method repair module, used to repair the data to be repaired by using a proportion repair method if the data to be repaired is multi-day data;

[0093] The linear interpolation repair module is used to repair the data to be repaired by using the linear interpolation method if the data to be repaired is single-day data.

[0094] Furthermore, the proportion repair method repair module includes:

[0095] A data determination submodule, for determining, based on the data to be repaired being multi-day data, a data missing value interval of the data to be repaired, the number of days between the data missing value intervals, and a previous period value of missing data in the data to be repaired;

[0096] A data calculation submodule, configured to calculate the missing data in the data missing value interval by using a proportional repair method based on the data missing value interval, the interval days, and the previous period value of the missing data;

[0097] The data repair submodule is used to repair the missing data in the data missing value interval based on the calculation result.

[0098] Furthermore, the data calculation submodule calculates the missing data in the data missing value interval using a proportional repair method based on the data missing value interval, the interval days, and the previous period value of the missing data, satisfying the following calculation formula:

[0099]

[0100] In the above formula, x t is the missing data in multiple days’ data, x t-1 is the previous period data value of the missing data, x t-1+n is the data value of the next period after the missing data, n is the number of days, and t is the number of days; i is the proportion of missing data in multiple days of data, and its value is an integer from 1 to n.

[0101] Furthermore, the linear interpolation repair module includes:

[0102] A data interpolation submodule is used for taking the average of the data before and after the missing data in the data to be repaired based on the fact that the data to be repaired is a single day's data, and using the average as the missing data to interpolate the position where the missing data is located;

[0103] The data interpolation submodule takes the average of the preceding and following data of the missing data in the data to be repaired, and satisfies the following calculation formula:

[0104]

[0105] Among them, x t’ is the mean of the data before and after the missing data, x t-1’ is the previous period value of the missing data, x t+1 is the value of the next period for missing data.

[0106] Furthermore, the system further comprises:

[0107] A cleaning module is used to clean the power output curve data based on the power output curve data.

[0108] Furthermore, the power output curve data of the target photovoltaic power station is derived from the original table code of the target photovoltaic power station.

[0109] Embodiment 3:

[0110] The embodiment of the present invention provides a specific embodiment of a method for repairing power output curve data quality, as follows:

[0111] First, determine the source of the power output curve data of the target photovoltaic power station: because the power generation of each power plant is calculated by multiplying the meter code by the multiplication factor, the abnormal meter code will definitely cause abnormal power. However, if the power data is repaired directly, there are many problems with the power data itself, and the repair process is more complicated. Compared with the power data, the meter code data has smaller fluctuations and is easier to repair. Therefore, the present invention selects the original meter code data as the power output curve data of the target photovoltaic power station for repair;

[0112] Secondly, the power output curve data of the target photovoltaic power station is collected, and then the data quality is "cleaned". The problematic data in the power output curve data set of the target photovoltaic power station is detected manually or automatically, and these data are corrected or merged or deleted to improve the data quality and complete the preliminary processing of the power output curve data of the target photovoltaic power station.

[0113] Finally, for the case of missing data for multiple days, method 1 is used to repair the data, and for the case of missing data for a single day, method 2 is used to repair the data.

[0114] Method 1: Proportional repair method

[0115] In view of the missing power output curve data of the target photovoltaic power station, the proportional repair method can be used to fill it. The calculation formula is as follows:

[0116]

[0117] In the above formula, x t is the missing data in multiple days’ data, x t-1 is the previous period data value of the missing data, x t-1+n is the data value of the next period after the missing data, n is the number of days, and t is the number of days; i is the proportion of missing data in multiple days of data, and its value is an integer from 1 to n.

[0118] Here we take the daily total meter code data of a photovoltaic power station as an example. Figure 3 It can be seen that the unit had a meter replacement on December 23, 2020, and the meter code value dropped from 9989.62 of the old meter to 2.46 of the new meter code. And the meter code value of the unit was 0 on April 28, 2021 and April 30, 2021, and it needs to be corrected. A specific analysis of the meter code values ​​before and after the 0 value interval found that the meter code value before the 0 value interval was 1140.46, and the meter code value after the interval was 1140.69. The values ​​before and after are not equal, so the proportional repair method is used here to correct it.

[0119] After the daily total meter code of the unit is repaired to 0 according to the proportional repair method, the meter code curve of the unit is obtained, as shown in Figure 4As shown, it can be seen that the meter code values ​​of the unit before and after the meter replacement show an increasing trend, which is consistent with the actual situation.

[0120] Method 2: Linear interpolation

[0121] Select the total meter code curve of a photovoltaic power station at a time point every 15 minutes from June 1 to July 22, 2022, such as Figure 5 As shown, it can be clearly seen that the table code of the unit is missing at 16:00 on June 28, 2022 and 18:00 on July 22. Analyzing the specific situation of the values ​​before and after the missing values, it can be seen that the values ​​before and after the missing values ​​are not equal, so the linear interpolation method can be selected here to use the mean of the values ​​before and after the missing values ​​to fill the missing values, that is:

[0122]

[0123] Among them, x t’ is the mean of the data before and after the missing data, x t-1’ is the previous period value of the missing data, x t+1 is the value of the next period of missing data. The changes of data after interpolation are as follows Figure 6 shown.

[0124] The missing values ​​of the total table code of the station unit are filled by linear interpolation method. Figure 6 It can be seen that the total table code of the unit after interpolation shows a spiral upward trend.

[0125] It can be seen from this implementation that after preliminary processing of the power output curve data of the target photovoltaic power station, method 1 or method 2 is selected for repair according to actual needs, which can quickly and accurately repair the data that needs to be repaired in the power output curve data of the target photovoltaic power station.

[0126] Embodiment 4:

[0127] like Figure 7 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0128] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to implement the steps of a power output curve data quality repair method in the above-mentioned embodiment.

[0129] Embodiment 5:

[0130] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a power output curve data quality repair method in the above embodiment.

[0131] Those skilled in the art will appreciate that the embodiments of the present invention application can be provided as methods, systems, or computer program products. Therefore, the present invention application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present invention application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0132] The present invention application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention application rather than to limit its protection scope. Although the present invention application is described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present invention application, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the protection scope of the claims to be approved.

Claims

1. A method for repairing the quality of power output curve data, characterized in that: include: Collect power output curve data of the target photovoltaic power station; Determining problematic data to be repaired in the power output curve data; If the data to be repaired is data for multiple days, the data to be repaired is repaired using a proportional repair method; If the data to be repaired is single-day data, a linear interpolation method is used to repair the data to be repaired.

2. The method according to claim 1, characterized in that If the data to be repaired is data of multiple days, a proportional repair method is used to repair the data to be repaired, including: Based on the data to be repaired being multi-day data, determining a data missing value interval of the data to be repaired, the number of days between the data missing value intervals, and a previous period value of the missing data in the data to be repaired; Based on the data missing value interval, the interval days, and the previous period value of the missing data, the missing data in the data missing value interval is calculated using a proportional repair method; Based on the calculation result, the missing data in the data missing value interval is repaired.

3. The method according to claim 2, characterized in that The missing data in the missing data interval is calculated based on the missing data interval, the interval days, and the previous period value of the missing data, using the proportional repair method to satisfy the following calculation formula: In the above formula, x t is the missing data in multiple days’ data, x t-1 is the previous period data value of the missing data, x t-1+n is the value of the next period of missing data, n is the number of days between missing data, t is the number of days; i is the proportion of missing data in multiple days of data, and its value is an integer from 1 to n.

4. The method according to claim 1, characterized in that: If the data to be repaired is single-day data, the data to be repaired is repaired using a linear interpolation method, including: Based on the fact that the data to be repaired is single-day data, taking the average of the data before and after the missing data in the data to be repaired, and using the average as the missing data to interpolate the position where the missing data is located; The average of the preceding and following data of the missing data in the data to be repaired satisfies the following calculation formula: Among them, x t’ is the mean of the data before and after the missing data, x t-1’ is the previous period value of the missing data, x t+1 is the value of the next period for missing data.

5. The method according to claim 1, characterized in that After collecting the power output curve data of the target photovoltaic power station, the method includes: Based on the power output curve data, the power output curve data is cleaned.

6. The method according to claim 1, characterized in that The power output curve data of the target photovoltaic power station is derived from the original meter code of the target photovoltaic power station.

7. A power output curve data quality repair system, characterized in that: include: A collection module, used to collect power output curve data of the target photovoltaic power station; A module for determining data to be repaired, used for determining data to be repaired that has problems in the power output curve data; A proportion repair method repair module, used to repair the data to be repaired by using a proportion repair method if the data to be repaired is multi-day data; The linear interpolation repair module is used to repair the data to be repaired by using the linear interpolation method if the data to be repaired is single-day data.

8. The system according to claim 7, characterized in that The proportional repair method repair module includes: A data determination submodule, for determining, based on the data to be repaired being multi-day data, a data missing value interval of the data to be repaired, the number of days between the data missing value intervals, and a previous period value of missing data in the data to be repaired; A data calculation submodule, for calculating the missing data in the data missing value interval by using a proportional repair method based on the data missing value interval, the interval days, and the previous period value of the missing data; The data repair submodule is used to repair the missing data in the data missing value interval based on the calculation result.

9. An electronic device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, a power output curve data quality repair method as described in any one of claims 1 to 6 is implemented.

10. A readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, a power output curve data quality repair method as described in any one of claims 1 to 6 is implemented.

Images