Remote data acquisition and management platform for photovoltaic power station

Abstract

The invention, which relates to the technical field of photovoltaic power station management, discloses a photovoltaic power station remote data acquisition and management platform comprising a historical generating capacity data acquisition module, a data analysis module, a generating capacity interval acquisition module, a sequence trend value acquisition module, an abnormal data marking module, a repair value acquisition module and a verification module. Data deviating from a normal range can be quickly identified through the abnormal data marking module, clues are provided for timely discovering potential faults of the power station, abnormal data can be effectively repaired through mutual cooperation of the repair value obtaining module and the verification module, data integrity is guaranteed, the quality of data collected by the photovoltaic power station is guaranteed, and the service life of the photovoltaic power station is prolonged. According to the scheme, accurate operation of the power station is guaranteed, it can be guaranteed that the repaired data is reasonable and reliable, when the generating capacity is abnormal due to temporary faults of equipment, the abnormal data can be rapidly processed, accurate data support is provided for subsequent fault diagnosis and repair, and normal operation of the power station can be rapidly recovered.

Description

Technical Field

[0001] The invention belongs to the technical field of photovoltaic power station management, and in particular is a photovoltaic power station remote data collection and management platform. Background Art

[0002] The patent with patent publication number CN108111601A discloses a photovoltaic power station data collection method, including the following steps: integrating meteorological data, location data, time information and photovoltaic power station operation data to generate a modulated wave, and superimposing it with a carrier to form a modulated signal; outputting the modulated signal to the collected device to collect data information. A photovoltaic power station data collection system is also disclosed, including a control module and a relay conversion module, the control module is connected to the relay conversion module; the control module is used to integrate meteorological data, location data, time information and photovoltaic power station operation data to generate a modulated wave, and superimposing it with a carrier to form a modulated signal; the relay conversion module is used to output the modulated signal to each collected device and collect data information of each collected device.

[0003] However, there are many problems in the current data collection and management of photovoltaic power stations. When collecting photovoltaic power generation data remotely, the traditional methods either simply ignore the abnormal data or adopt a single repair strategy, such as directly replacing it with the average value. The inherent trend and correlation of the collected data cannot be fully considered, making the repaired data unable to truly reflect the actual power generation of the power station, affecting the quality and utilization value of the remotely collected data of the photovoltaic power station. Based on this, a remote data collection and management platform for photovoltaic power stations is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a photovoltaic power station remote data collection and management platform, which solves the technical problem that when photovoltaic power generation data is remotely collected, the data after abnormal data repair cannot truly reflect the actual power generation situation of the power station.

[0005] A photovoltaic power station remote data collection and management platform, comprising: The historical power generation data acquisition module is used to obtain the historical power generation data of the photovoltaic power station within a preset time period T, where 90 days ≥ T ≥ 2 days; The data analysis module establishes multiple time series and analyzes the historical power generation data of each time series to obtain the benchmark power generation of each time series; The power generation interval acquisition module obtains the power generation interval of each time series according to the discrete values ​​of the benchmark power generation and the historical power generation of each time series; The sequence trend value acquisition module analyzes the historical power generation data of each time series and obtains the sequence trend value of each time series; The abnormal data marking module marks and removes the abnormal data in the power generation collected on the same day of each time series according to the power generation interval of each time series, and marks the retained data; The repair value acquisition module calculates the repair value corresponding to the abnormal data based on the retained data and its corresponding sequence trend value; The verification module verifies the repair value corresponding to the abnormal data and determines the new power generation data at the time series corresponding to the abnormal data according to the verification result.

[0006] As a further solution of the present invention: the specific method of establishing multiple time series is: By establishing units through time series, the twenty-four hours of a day are evenly divided into multiple identical time series Ti, where i refers to different time series, i=1, 2,..., a, a refers to the total number of time series, and i is used as the sequence label corresponding to each time series, a is a positive integer, and a satisfies a≥2.

[0007] As a further solution of the present invention: the specific method of obtaining the benchmark power generation of each time series is: S1: Through the benchmark power generation acquisition unit, a time series is randomly selected from each time series without replacement as the target series; S2: Obtain the daily power generation HT of the target sequence from the historical power generation of the target sequence, and mark the discrete value of the daily power generation HT as the discrete value U of the historical power generation, and analyze the discrete value U to obtain the benchmark power generation D1 corresponding to the target sequence; Step S3: repeating steps S1-S2 to obtain the reference power generation Di corresponding to each time series of the photovoltaic power station; The specific method of obtaining the benchmark power generation corresponding to the target sequence is: When the discrete value U is less than the preset value Y1, the mean value Hp of HT is used as the benchmark power generation D1 corresponding to the target sequence. When the discrete value U is greater than or equal to the preset value Y1, the values ​​of the daily power generation HT whose absolute difference with the mean value Hp is greater than the preset value Y3 are deleted in ascending order according to the numerical value corresponding to HT, and the deletion quantity c is analyzed to obtain the benchmark power generation D1 corresponding to the target sequence. The specific method for analyzing the number of deletions is: When the number of deletions c is greater than the preset value Y2, the average of the maximum and minimum values ​​in HT is used as the benchmark power generation D1 corresponding to the target sequence. When the number of deletions c is less than or equal to the preset value Y2, the average Hp of HT is used as the benchmark power generation D1 corresponding to the target sequence.

[0008] As a further solution of the present invention: the specific method of obtaining the power generation interval of each time series is: S01: Select the same time series as in step S1 as the target sequence; S02: Calculate the mean Hp of the daily power generation HT of the target sequence within the preset time T, take the sum of the mean Hp and the discrete value U of the historical power generation as the upper limit of the power generation range of the target sequence, take the difference between the mean Hp and the discrete value U as the lower limit of the power generation range of the target sequence, and then establish the power generation range Q1[Hp-U, Hp+U] of the target sequence; Step S03: Repeat steps S01-S02 to obtain the power generation interval Qi corresponding to each time series of the photovoltaic power station.

[0009] As a further solution of the present invention: the specific method of obtaining the sequence trend value of each time series is: S11: Select the same time series as in step S1 as the target sequence; S12: taking the maximum value Hmax of the daily power generation HT of the target sequence within the preset time length T as the reference value J1 of the target sequence, obtaining the ratio FT between the daily power generation HT and the reference value J1, and taking the average of the maximum and minimum values ​​in FT as the sequence trend value R1 corresponding to the target sequence; Step S13: repeat steps S11-S12 to obtain the sequence trend value Ri corresponding to each time series of the photovoltaic power station.

[0010] As a further solution of the present invention, the specific method of marking the abnormal data and the reserved data in the power generation collected on the same day in each time series is as follows: The power generation corresponding to each time series collected by the photovoltaic power station on the same day is compared one by one with the power generation interval corresponding to each time series of the photovoltaic power station. The power generation of the day within the corresponding power generation interval is retained and marked as retained data. The power generation of the day that is not within the corresponding power generation interval is marked as abnormal data and eliminated.

[0011] As a further solution of the present invention: the specific method of calculating the repair value corresponding to the abnormal data is: Obtain each retained data and mark them as Yg, mark the product of each retained data and its corresponding sequence trend value as E1, mark the sum of the sequence trend values ​​corresponding to each retained data as E2, and use the ratio between E1 and E2 and the product of the sequence trend value corresponding to the abnormal data as the repair value corresponding to the abnormal data; The repair value corresponding to the abnormal data is compared with the power generation range of the time series corresponding to the abnormal data. If the repair value is within the corresponding power generation range, the verification is successful; if the repair value is not within the corresponding power generation range, the verification fails. The repair value that passes the verification is used as the new power generation data at the corresponding time series to supplement the time series corresponding to the abnormal data. For the repair value that fails the verification, the benchmark power generation of the time series corresponding to the abnormal data is used as the new power generation data at the corresponding time series to supplement the time series corresponding to the abnormal data.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention can quickly identify data that deviates from the normal range through the abnormal data marking module, provide clues for timely discovery of potential faults in the power station, and cooperate with the repair value acquisition module and the verification module to effectively repair the abnormal data and ensure the integrity of the data, thereby ensuring the quality of the data collected by the photovoltaic power station and providing a guarantee for the accurate operation of the power station. It can also ensure that the repaired data is reasonable and reliable. When a temporary failure of the equipment causes abnormal power generation, the solution can quickly process the abnormal data, provide accurate data support for subsequent fault diagnosis and repair, and help to quickly restore the normal operation of the power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the framework structure of the present invention; Figure 2 It is a schematic diagram of the process of verifying the repair value corresponding to the abnormal data in the present invention. DETAILED DESCRIPTION

[0014] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] Example 1: Please refer to Figure 1 ,This application provides a photovoltaic power station remote data collection and management platform, including; The historical power generation data acquisition module is used to acquire the historical power generation data of the photovoltaic power station within a preset time period T; The value range of the preset time length T is 90 days ≥ T ≥ 2 days. In this embodiment, the specific value of the preset time length T is 30 days from the moment the data is acquired. It should be noted that the data on the day the data is acquired is not included. This module is responsible for obtaining the historical power generation data of the photovoltaic power station within the preset time T. By collecting long-term historical data, it provides rich samples for subsequent data analysis.

[0016] The data analysis module divides the twenty-four hours of a day into multiple time series for analyzing the historical power generation data of the photovoltaic power station in different time series. According to the analysis results, the benchmark power generation corresponding to each time series of the photovoltaic power station is obtained. The specific method is as follows: The time series establishment unit is used to divide the twenty-four hours of a day into multiple time series Ti, where i refers to different time series, i=1, 2, ..., a, a refers to the total number of time series, and i is used as the sequence number corresponding to each time series, a is a positive integer, and a satisfies a≥2; It should be noted that the time intervals between multiple time series Ti can be the same time interval or different time intervals. In this embodiment, the time intervals between multiple time series Ti are the same. In this embodiment, the time interval between each time series is one hour, that is, the number of time series in this embodiment is 24. This division method is helpful for fine analysis of power generation data characteristics in different time periods; The benchmark power generation acquisition unit is used to analyze the historical power generation data corresponding to each time series, and obtain the benchmark power generation corresponding to each time series of the photovoltaic power station according to the analysis results. The specific method is as follows: S1: Randomly select a time series from each time series without replacement as the target series; S2: Obtain the historical power generation of the target sequence within the preset time length T, and mark the daily power generation of the target sequence within the preset time length T as HT; The daily power generation HT of the target sequence within the preset time T is analyzed, and the benchmark power generation corresponding to the target sequence is generated according to the analysis results. The specific method is as follows: By formula, Where Hp is the mean value of HT, Hj is any one of HT, T≥j≥1, obtain the discrete value U of the historical power generation of the target sequence within the preset time length T, and analyze the discrete value U. According to the analysis result of the discrete value U, the benchmark power generation D1 corresponding to the target sequence is obtained. The specific method is: When the discrete value U is less than the preset value Y1, the mean Hp of HT is used as the benchmark power generation D1 corresponding to the target sequence. When the discrete value U is greater than or equal to the preset value Y1, it means that the discrete degree of the daily power generation HT of the target sequence within the preset time T is large. According to the numerical value corresponding to HT, the values ​​of the daily power generation HT with large deviations from the mean Hp are deleted in order from small to large, and the number of deleted values ​​c is recorded. At the same time, the discrete value U is recalculated after each deletion until the discrete value U satisfies the preset value Y1. When the deleted When the number c is greater than the preset value Y2, the average of the maximum and minimum values ​​in HT is used as the benchmark power generation D1 corresponding to the target sequence, that is, the benchmark power generation D1 corresponding to the target sequence is calculated by (Hmax+Hmin) / 2=D1, where Hmax is the maximum value in HT and Hmin is the minimum value in HT. When the number c deleted is less than or equal to the preset value Y2, the average value Hp of HT is used as the benchmark power generation D1 corresponding to the target sequence, where the specific values ​​of Y1 and Y2 are set by relevant personnel according to specific application scenarios and requirements; The specific method for judging the value of the daily power generation HT that deviates greatly from the mean Hp is as follows: if the absolute value of the difference between the daily power generation HT and the mean Hp is greater than the preset value Y3, it is judged as the value of the deviation from the mean Hp; otherwise, no processing is performed, that is, the daily power generation HT that satisfies |HT-Hp|>Y3 is judged as the value that deviates greatly from the mean Hp, wherein the specific value of the preset value Y3 is set by relevant personnel according to specific application scenarios and requirements; Step S3: Repeat steps S1-S2 to obtain the benchmark power generation Di corresponding to each time series of the photovoltaic power station. In this way, the benchmark power generation of each time series can be determined more accurately, reflecting the normal power generation level of the power station in different time periods.

[0017] The power generation interval acquisition module is used to analyze and obtain the power generation interval corresponding to each time series of the photovoltaic power station according to the discrete values ​​of the historical power generation corresponding to each time series of the photovoltaic power station and the benchmark power generation. The specific method is as follows: S01: Select the same time series as in step S1 from each time series without replacement as the target series; S02: Calculate the mean Hp of the daily power generation HT of the target sequence within the preset time T, take the sum of the mean Hp and the discrete value U of the historical power generation as the upper limit of the power generation range of the target sequence, take the difference between the mean Hp and the discrete value U as the lower limit of the power generation range of the target sequence, and then establish the power generation range Q1[Hp-U, Hp+U] of the target sequence; Step S03: repeating steps S01-S02 to obtain the power generation intervals Qi corresponding to the photovoltaic power station at each time series, and binding each power generation interval to its corresponding time series one by one, thereby generating a power generation reference table; By determining the power generation interval for each time series, the generated power generation reference table provides a standard for subsequent judgment of whether the data is abnormal.

[0018] The abnormal data marking module is used to compare and analyze the power generation corresponding to each time series collected by the photovoltaic power station on the day with the power generation interval corresponding to each time series of the photovoltaic power station, mark the abnormal data in the power generation on the day according to the analysis results, and remove the abnormal data. The specific method is as follows: The power generation corresponding to each time series collected by the photovoltaic power station on the day is compared with the power generation interval corresponding to each time series of the photovoltaic power station one by one, and it is judged whether the power generation on the day is within the corresponding power generation interval. The power generation on the day within the corresponding power generation interval is retained and marked as retained data, and the power generation on the day that is not within the corresponding power generation interval is marked as abnormal data and removed; The power generation of each time series collected by the photovoltaic power station on the same day is compared with the corresponding power generation interval in the power generation reference table. The power generation within the corresponding interval is retained as data, and the power generation outside the interval is marked as abnormal data and eliminated. This can quickly identify and remove data that obviously deviates from the normal range. This operation effectively purifies the data and improves the reliability and availability of the data. After removing the abnormal data, the subsequent data analysis and processing results are more accurate, avoiding erroneous judgments and decisions caused by abnormal data, and ensuring that the power station operation decision is based on a reliable data foundation to ensure the reliability of the data.

[0019] Embodiment 2: As the embodiment 2 of the present invention, when the present application is specifically implemented, compared with the embodiment 1, the technical solution of this embodiment is different from that of the embodiment 1 only in that this embodiment further includes a sequence trend value acquisition module; The sequence trend value acquisition module analyzes the historical power generation data of the photovoltaic power station corresponding to each time series every day within the preset time length T, and then obtains the sequence trend value corresponding to each time series of the photovoltaic power station. The specific method is as follows: S11: Select the same time series as in step S1 from each time series without replacement as the target series; S12: Determine the reference value J1 of the target sequence from the daily power generation HT of the target sequence within the preset time T, specifically in the following manner: The maximum value Hmax of the daily power generation HT of the target sequence within the preset time T is obtained and used as the reference value J1 of the target sequence; Obtain the ratio FT between the daily power generation HT and the benchmark value J1, and take the average of the maximum and minimum values ​​in FT as the sequence trend value R1 corresponding to the target sequence, that is, by (Fmax+Fmin) / 2=R1, calculate the sequence trend value R1 corresponding to the target sequence, where Fmax is the maximum value in FT and Fmin is the minimum value in FT; Obtain the ratio FT between the daily power generation HT of the target sequence within the preset time length T and the reference value J1, and perform normalization on the daily power generation HT of the target sequence within the preset time length T, so that all daily power generation HT values ​​are compressed into the [0,1] interval, which is convenient for analyzing the relative fluctuation of the daily power generation of the target sequence within the preset time length T; Step S13: repeat steps S11-S12 to obtain the sequence trend value Ri corresponding to each time series of the photovoltaic power station; By taking the maximum value Hmax as the benchmark value J1, calculating the ratio FT of daily power generation HT and J1, and normalizing HT to the interval [0,1], and finally calculating the sequence trend value, it can reflect the relative fluctuation of power generation in each time series, capture the changing trend of the data, help predict the change of power generation of the power station, make arrangements for power dispatch and equipment maintenance in advance, and improve the foresight and initiative of power station operation.

[0020] Embodiment 3: As the embodiment 3 of the present invention, when the present application is specifically implemented, compared with the embodiments 1 and 2, the technical solution of this embodiment is to combine the solutions of the above-mentioned embodiments 1 and 2 for implementation, and the difference between the technical solution of this embodiment and the embodiments 1 and 2 is that this embodiment also includes a repair value acquisition module; The repair value acquisition module is used to perform compensation calculation on the abnormal data after removing the abnormal data, according to the sequence trend value corresponding to the retained data and its time series, and then obtain the repair value corresponding to the abnormal data. The specific method is as follows: Obtain each retained data and mark them as Yg, mark the product of each retained data and its corresponding sequence trend value as E1, mark the sum of the sequence trend values ​​corresponding to each retained data as E2, and take the product of the ratio between E1 and E2 and the sequence trend value corresponding to the abnormal data as the repair value X1 corresponding to the abnormal data; It should be noted that the calculation method of the repair value revolves around data trends and correlations. From the perspective of data trends, the calculation of the sequence trend value is based on the ratio of the daily power generation HT of the target sequence within the preset duration T to the baseline value J1, which reflects the relative fluctuation of the data. For example, in different seasons, the duration and intensity of light are different, and the power generation trend of the photovoltaic power station is also different. The sequence trend value can capture this seasonal change trend. When calculating the repair value, the product E1 of the retained data Yg and the sequence trend value, and the ratio of E1 to the sum of the sequence trend values ​​corresponding to all retained data E2 are multiplied by the sequence trend value corresponding to the abnormal data to obtain the repair value. This process takes into account the contribution of different retained data to the overall trend. For example, in a time series, the power generation is higher on some days, and its sequence trend value is larger. When calculating the repair value, the impact of these data will be more significant, making the repair value more in line with the trend change of the sequence. When calculating the repair value, the relative relationship between the retained data is taken into account. In the same time series, different retained data contribute differently to the overall trend. This calculation method assigns weights according to the relative importance of the retained data, so as to calculate the repair value more reasonably. For example, in a time series, there are several retained data with larger trend values, which means that they are more representative in the series. When calculating, the weights of these data will be increased accordingly, so that the repair value can better reflect the actual situation of the time series; Using the retained data and its corresponding sequence trend value, the repair value of the abnormal data is obtained through a specific calculation method and added to the corresponding time series of the abnormal data. This repair method comprehensively considers the size of the retained data and the trend characteristics of each time series, so that the repair value is more in line with the inherent laws of the data, and restores the integrity and accuracy of the data to the greatest extent, providing complete data support for subsequent data analysis.

[0021] Embodiment 4: As the fourth embodiment of the present invention, please refer to Figure 2 , when the present application is implemented, compared with Embodiment 1, Embodiment 2 and Embodiment 3, the difference between this embodiment and Embodiment 1, Embodiment 2 and Embodiment 3 is that this embodiment also includes a verification module; The verification module verifies the repair value X1 corresponding to the abnormal data. The repair value that passes the verification is used as the new power generation data at the corresponding time series to supplement the abnormal data at the corresponding time series. For the repair value that fails the verification, the benchmark power generation of the time series corresponding to the abnormal data is used as the new power generation data at the corresponding time series to supplement the abnormal data at the corresponding time series, so that the collected data of the photovoltaic power station on that day is complete. The specific verification processing method is: Compare the repair value corresponding to the abnormal data with the power generation range of the time series corresponding to the abnormal data. If the repair value is within the corresponding power generation range, the verification is passed; if the repair value is not within the corresponding power generation range, the verification fails. The repaired value is compared with the power generation range of the corresponding time series. The repaired value that passes the verification is used as the new power generation data, and the unverified value is used as the benchmark power generation as the new data. This verification mechanism further ensures the rationality and accuracy of the repaired data. By comparing with the power generation range, it can be checked whether the repaired value is within a reasonable range to avoid secondary pollution of the data caused by unreasonable repair values, thus ensuring the quality of the data collected by the photovoltaic power station and providing guarantee for the accurate operation of the power station. If the repair value is within the interval, it means that it is consistent with the fluctuation of historical data and has a high degree of credibility; if it is not within the interval, there may be a problem and further processing is required. This verification mechanism provides a guarantee for the reliability of the repair value, ensuring that the repair value finally added to the data is more in line with the actual situation.

[0022] Embodiment 5: As the embodiment 5 of the present invention, when this application is specifically implemented, compared with Embodiment 1, Embodiment 2, Embodiment 3 and Embodiment 4, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned Embodiment 1, Embodiment 2, Embodiment 3 and Embodiment 4.

[0023] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0024] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A photovoltaic power station remote data collection and management platform, characterized in that: include; The historical power generation data acquisition module is used to obtain the historical power generation data of the photovoltaic power station within a preset time period T, where 90 days ≥ T ≥ 2 days; The data analysis module establishes multiple time series and analyzes the historical power generation data of each time series to obtain the benchmark power generation of each time series; The power generation interval acquisition module obtains the power generation interval of each time series according to the discrete values ​​of the benchmark power generation and the historical power generation of each time series; The sequence trend value acquisition module analyzes the historical power generation data of each time series and obtains the sequence trend value of each time series; The abnormal data marking module marks and removes the abnormal data in the power generation collected on the same day of each time series according to the power generation interval of each time series, and marks the retained data; The repair value acquisition module calculates the repair value corresponding to the abnormal data based on the retained data and its corresponding sequence trend value; The verification module verifies the repair value corresponding to the abnormal data and determines the new power generation data at the time series corresponding to the abnormal data according to the verification result.

2. A photovoltaic power station remote data collection and management platform according to claim 1, characterized in that: The specific way to establish multiple time series is: By establishing units through time series, the twenty-four hours of a day are evenly divided into multiple identical time series Ti, where i refers to different time series, i=1, 2, ..., a, a refers to the total number of time series, and i is used as the sequence label corresponding to each time series, a is a positive integer, and a satisfies a≥2.

3. A photovoltaic power station remote data collection and management platform according to claim 2, characterized in that: The specific method of obtaining the benchmark power generation of each time series is: S1: Through the benchmark power generation acquisition unit, a time series is randomly selected from each time series without replacement as the target series; S2: Obtain the daily power generation HT of the target sequence from the historical power generation of the target sequence, and mark the discrete value of the daily power generation HT as the discrete value U of the historical power generation, and analyze the discrete value U to obtain the benchmark power generation D1 corresponding to the target sequence; Step S3: Repeat steps S1-S2 to obtain the reference power generation Di corresponding to each time series of the photovoltaic power station.

4. A photovoltaic power station remote data collection and management platform according to claim 3, characterized in that: The specific method of obtaining the benchmark power generation corresponding to the target sequence is: When the discrete value U is less than the preset value Y1, the mean Hp of HT is used as the benchmark power generation D1 corresponding to the target sequence. When the discrete value U is greater than or equal to the preset value Y1, the values ​​of the daily power generation HT whose absolute difference with the mean Hp is greater than the preset value Y3 are deleted in order from small to large according to the numerical value corresponding to HT, and the deletion quantity c is analyzed to obtain the benchmark power generation D1 corresponding to the target sequence.

5. A photovoltaic power station remote data collection and management platform according to claim 4, characterized in that: The specific method for analyzing the number of deletions is: When the number of deletions c is greater than the preset value Y2, the average of the maximum and minimum values ​​in HT is used as the benchmark power generation D1 corresponding to the target sequence. When the number of deletions c is less than or equal to the preset value Y2, the average Hp of HT is used as the benchmark power generation D1 corresponding to the target sequence.

6. A photovoltaic power station remote data collection and management platform according to claim 3, characterized in that: The specific method of obtaining the power generation interval of each time series is as follows; S01: Select the same time series as in step S1 as the target sequence; S02: Calculate the mean Hp of the daily power generation HT of the target sequence within the preset time T, take the sum of the mean Hp and the discrete value U of the historical power generation as the upper limit of the power generation range of the target sequence, take the difference between the mean Hp and the discrete value U as the lower limit of the power generation range of the target sequence, and then establish the power generation range Q1[Hp-U, Hp+U] of the target sequence; Step S03: Repeat steps S01-S02 to obtain the power generation interval Qi corresponding to each time series of the photovoltaic power station.

7. A photovoltaic power station remote data collection and management platform according to claim 6, characterized in that: The specific method of obtaining the sequence trend value of each time series is: S11: Select the same time series as in step S1 as the target sequence; S12: taking the maximum value Hmax of the daily power generation HT of the target sequence within the preset time length T as the reference value J1 of the target sequence, obtaining the ratio FT between the daily power generation HT and the reference value J1, and taking the average of the maximum and minimum values ​​in FT as the sequence trend value R1 corresponding to the target sequence; Step S13: repeat steps S11-S12 to obtain the sequence trend value Ri corresponding to each time series of the photovoltaic power station.

8. A photovoltaic power station remote data collection and management platform according to claim 7, characterized in that: The specific method of marking the abnormal data and reserved data in the power generation collected on the same day of each time series is as follows: The power generation corresponding to each time series collected by the photovoltaic power station on the same day is compared one by one with the power generation interval corresponding to each time series of the photovoltaic power station. The power generation of the day within the corresponding power generation interval is retained and marked as retained data. The power generation of the day that is not within the corresponding power generation interval is marked as abnormal data and eliminated.

9. A photovoltaic power station remote data collection and management platform according to claim 8, characterized in that: The specific method of calculating the repair value corresponding to the abnormal data is: Obtain each retained data and mark them as Yg, mark the product of each retained data and its corresponding sequence trend value as E1, mark the sum of the sequence trend values ​​corresponding to each retained data as E2, and take the product of the ratio between E1 and E2 and the sequence trend value corresponding to the abnormal data as the repair value corresponding to the abnormal data.

10. A photovoltaic power station remote data collection and management platform according to claim 9, characterized in that: The specific method of verifying the repair value corresponding to the abnormal data is as follows: The repair value corresponding to the abnormal data is compared with the power generation range of the time series corresponding to the abnormal data. If the repair value is within the corresponding power generation range, the verification is successful; if the repair value is not within the corresponding power generation range, the verification fails. The repair value that passes the verification is used as the new power generation data at the corresponding time series to supplement the time series corresponding to the abnormal data. For the repair value that fails the verification, the benchmark power generation of the time series corresponding to the abnormal data is used as the new power generation data at the corresponding time series to supplement the time series corresponding to the abnormal data.

Images