A method, system and storage medium for identifying inefficient photovoltaic strings

Abstract

The present application proposes a method, system and storage medium for identifying inefficient photovoltaic strings. The method includes: obtaining string data of current averages and voltage averages corresponding to a preset duration of each photovoltaic string in each photovoltaic device within a historical period; processing the obtained string data to identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and eliminating the string data corresponding to the abnormal photovoltaic strings; filtering the string data of each photovoltaic device within a first preset period from the eliminated string data, and obtaining the number of filtered photovoltaic strings in each photovoltaic device based on the filtered string data; selecting clustering objects based on the number of filtered photovoltaic strings in each photovoltaic device and then identifying inefficient photovoltaic strings in the photovoltaic device. The technical solution provided by the present invention first eliminates abnormal photovoltaic strings and then identifies inefficient photovoltaic strings, thereby improving the accuracy of identifying inefficient photovoltaic strings.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic string identification, and in particular to a method, system, and storage medium for identifying photovoltaic string inefficiencies. Background Art

[0002] With the widespread adoption of photovoltaic power plants, there is a strong demand for efficient and economical operation and maintenance. A photovoltaic power plant typically consists of a string inverter and multiple photovoltaic strings, each of which consists of multiple photovoltaic modules. Multiple photovoltaic strings are connected to the same string inverter, which converts direct current (DC) power into alternating current (AC) power for connection to the grid. Preemptive identification of abnormal photovoltaic strings is crucial for efficient and economical operation and maintenance of power plants.

[0003] At present, the identification of abnormal photovoltaic strings is to fuse the irradiance data in the environmental detector with other characteristic data. The data quality is poor, the data integrity is low, the data consistency is poor, and the data loss or fluctuation of the irradiance acquisition sensor leads to a serious reduction in the overall data integrity and accuracy of the power station, which seriously affects the abnormal identification effect of photovoltaic strings. The entire power station shares one environmental monitor, and the start and end time of power generation of different strings are not exactly the same. It is not necessarily possible to screen out the time period when all strings of the same equipment start and end power generation at the same time. At this time, due to the large discrete rate when starting and ending power generation, it is easy to cause false detection. Summary of the Invention

[0004] The present application provides a method, system and storage medium for identifying inefficient photovoltaic strings, so as to at least solve the technical problems of poor abnormality identification effect and low accuracy of photovoltaic strings in related technologies.

[0005] The first embodiment of the present application provides a method for identifying photovoltaic string inefficiencies, including:

[0006] Obtain string data of current average and voltage average corresponding to a preset duration of each photovoltaic string in each photovoltaic device within a historical period;

[0007] Processing the acquired string data, identifying abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and removing string data corresponding to the abnormal photovoltaic strings;

[0008] Filtering the string data of each photovoltaic device within a first preset time period from the eliminated string data, and obtaining the number of filtered photovoltaic strings in each photovoltaic device based on the filtered string data;

[0009] Select cluster objects based on the number of screened photovoltaic strings in each photovoltaic device to identify inefficient photovoltaic strings in the photovoltaic device;

[0010] The first preset time period is the intersection of the preset daytime period and the start time and end time when the current average of the selected photovoltaic strings is greater than the preset current threshold;

[0011] The clustering objects include: the power generation of each photovoltaic string in the photovoltaic equipment during a preset daytime period and the discrete rate of the current mean of each photovoltaic string in each photovoltaic equipment.

[0012] A second embodiment of the present application provides a photovoltaic string inefficiency identification system, comprising:

[0013] The first acquisition module is used to obtain the string data of the current average and the voltage average corresponding to the preset duration of each photovoltaic string in each photovoltaic device within a historical period;

[0014] A first identification module is configured to process the acquired string data, identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and remove string data corresponding to the abnormal photovoltaic strings;

[0015] A second acquisition module is configured to screen the string data of each photovoltaic device within a first preset time period from the eliminated string data, and acquire the number of screened photovoltaic strings in each photovoltaic device based on the screened string data;

[0016] The second identification module is used to select cluster objects based on the number of screened photovoltaic strings in each photovoltaic device and then identify inefficient photovoltaic strings in the photovoltaic device;

[0017] The first preset time period is the intersection of the preset daytime period and the start time and end time when the current average of the selected photovoltaic strings is greater than the preset current threshold;

[0018] The clustering objects include: the power generation of each photovoltaic string in the photovoltaic equipment during a preset daytime period and the discrete rate of the current mean of each photovoltaic string in each photovoltaic equipment.

[0019] The computer storage medium proposed in the third embodiment of the present application, wherein the computer storage medium stores computer-executable instructions; after the computer-executable instructions are executed by the processor, the method described in the first aspect above can be implemented.

[0020] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0021] In summary, in the method, system and storage medium for identifying inefficient photovoltaic strings proposed in this application, the string data of the current mean and voltage mean corresponding to the preset duration of each photovoltaic string in each photovoltaic device in the historical period is first obtained; secondly, the obtained string data is processed to identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and the string data corresponding to the abnormal photovoltaic strings are eliminated; then, the string data contained in the first preset period of each photovoltaic device is filtered out from the eliminated string data, and the number of filtered photovoltaic strings in each photovoltaic device is obtained based on the filtered string data; finally, clustering objects are selected based on the number of filtered photovoltaic strings in each photovoltaic device to identify inefficient photovoltaic strings in the photovoltaic device. The technical solution provided by the present invention improves the accuracy of identifying inefficient photovoltaic strings by eliminating abnormal photovoltaic strings and then identifying inefficient photovoltaic strings, and has great application value.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a method for identifying photovoltaic string inefficiency according to one embodiment of the present application;

[0025] Figure 2 A comparison diagram of the current dispersion rate of photovoltaic strings in a photovoltaic device before and after data removal according to an embodiment of the present application is provided;

[0026] Figure 3 A specific flow chart of a method for identifying photovoltaic string inefficiency according to one embodiment of the present application;

[0027] Figure 4 A structural diagram of a photovoltaic string inefficiency identification system provided according to one embodiment of the present application;

[0028] Figure 5 This is a structural diagram of a second identification module provided according to one embodiment of the present application. DETAILED DESCRIPTION

[0029] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0030] In the method, system and storage medium for identifying inefficient photovoltaic strings proposed in this application, the string data of the current mean and voltage mean corresponding to the preset duration of each photovoltaic string in each photovoltaic device in a historical period is first obtained; secondly, the obtained string data is processed to identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and the string data corresponding to the abnormal photovoltaic strings are eliminated; then, the string data of each photovoltaic device included in the first preset period is filtered out from the eliminated string data, and the number of filtered photovoltaic strings in each photovoltaic device is obtained based on the filtered string data; finally, clustering objects are selected based on the number of filtered photovoltaic strings in each photovoltaic device to identify inefficient photovoltaic strings in the photovoltaic device. The technical solution provided by the present invention improves the accuracy of identifying inefficient photovoltaic strings by eliminating abnormal photovoltaic strings and then identifying inefficient photovoltaic strings, and has great application value.

[0031] The following describes, with reference to the accompanying drawings, a method, system, and storage medium for identifying photovoltaic string inefficiency according to embodiments of the present application.

[0032] Example 1

[0033] Figure 1 A flowchart of a method for identifying photovoltaic string inefficiency provided by an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method includes:

[0034] Step 1: Obtain string data of current average and voltage average corresponding to a preset duration of each photovoltaic string in each photovoltaic device within a historical period;

[0035] For example, if the historical period is 12 hours and the preset duration is 10 minutes, the historical period is divided into 72 moments, and each moment in the historical period has a corresponding current average value and voltage average value.

[0036] In the embodiment of the present disclosure, the current average is obtained by dividing the sum of the currents of a preset time by the preset time; and the voltage average is obtained by dividing the sum of the voltages of a preset time by the preset time.

[0037] Step 2: Process the acquired string data to identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and remove the string data corresponding to the abnormal photovoltaic strings;

[0038] In the embodiment of the present disclosure, the processing of the acquired string data to identify abnormal photovoltaic strings with extreme values ​​includes:

[0039] The string data of the average current and average voltage corresponding to the preset duration of each photovoltaic string in each photovoltaic device within the historical period are standardized, including the data item name and data formatting, and then the values ​​of different manufacturers are understood.

[0040] Obtaining a first range of photovoltaic string current and a first range of photovoltaic string voltage within the historical period based on a current quantile threshold and a voltage fraction threshold of the photovoltaic string within the historical period;

[0041] Obtaining a second range of photovoltaic string current and a second range of photovoltaic string voltage within the historical period based on the short-circuit current and open-circuit voltage parameters of the photovoltaic string within the historical period;

[0042] The intersection of the first range and the second range of the photovoltaic string current is taken as the normal range of the photovoltaic string current;

[0043] Taking the intersection of the first range and the second range of the photovoltaic string voltage as the normal range of the photovoltaic string voltage;

[0044] The photovoltaic strings corresponding to the string data of the current average and voltage average corresponding to the preset time length of each photovoltaic string of the photovoltaic station in the historical period that does not fall within the normal current range and the normal voltage range are identified as abnormal photovoltaic strings with extreme values.

[0045] For example, the process of obtaining a first range of photovoltaic string current and a first range of photovoltaic string voltage within a historical period includes:

[0046] The PV string current and voltage data timing diagrams for the recent historical period are respectively prepared, and the initial quantile is set to 0.95. Values ​​exceeding this value are considered abnormal values. The quantile threshold is adjusted based on the amount of abnormal data in the timing diagram and the fault record to determine whether it is abnormal data. The quantile used in this embodiment is 0.99, and the first range of the PV string current and the first range of the voltage in the historical period are obtained.

[0047] For example, the process of obtaining the second range of photovoltaic string current and the second range of photovoltaic string voltage within a historical period includes:

[0048] The theoretical maximum values ​​of the PV string current and voltage are determined respectively, where the maximum current value of the PV string is 1.5 times the string short-circuit current, and the maximum voltage is 1.3 times the open-circuit voltage. Zero is taken as the theoretical minimum values ​​of the PV string current and voltage, and a second range of the PV string current and voltage within the historical period are obtained.

[0049] In the embodiment of the present disclosure, the processing of the acquired string data to identify abnormal photovoltaic strings with constant values ​​includes:

[0050] Eliminate and identify abnormal PV strings with extreme values;

[0051] Obtain the standard deviation of the current mean corresponding to each photovoltaic string in the photovoltaic station after removing the abnormal photovoltaic strings with extreme values;

[0052] If the standard deviation of the current mean corresponding to the photovoltaic string is less than the current mean standard deviation threshold, the photovoltaic string is identified as an abnormal photovoltaic string with a constant, wherein the current mean standard deviation threshold can be set to 0.15.

[0053] In the embodiment of the present disclosure, the processing of the acquired string data to identify abnormal photovoltaic strings generating power at night includes:

[0054] Eliminate and identify abnormal PV strings with extreme values ​​and constants;

[0055] Obtain the current average value in the preset daytime period and the current average value in the preset nighttime period corresponding to each photovoltaic string after excluding abnormal photovoltaic strings with extreme values ​​and constants in the photovoltaic station;

[0056] If the current average value in the preset daytime period is smaller than the current average value in the preset nighttime period, the photovoltaic string is identified as an abnormal photovoltaic string generating power at night.

[0057] In the embodiment of the present disclosure, the period from 5:00 to 20:00 in a day is defined as the daytime period, and the rest of the period in a day is defined as the nighttime period.

[0058] Step 3: Filtering the string data of each photovoltaic device within the first preset time period from the eliminated string data, and obtaining the number of filtered photovoltaic strings in each photovoltaic device based on the filtered string data;

[0059] It should be noted that: the first preset time period is the intersection of the preset daytime period and the start time and end time when the current average of the screened photovoltaic strings is greater than the preset current threshold;

[0060] In the embodiment of the present disclosure, the preset current threshold may be 0.5A.

[0061] For example, Figure 2 This is a comparison chart of the current discrete rate of photovoltaic strings in a photovoltaic device before and after data removal, such as Figure 2 As shown, after the data corresponding to the abnormal photovoltaic strings are eliminated, the discrete rate of the photovoltaic string current in the photovoltaic device becomes smaller, which lays a foundation for the accuracy of the subsequent identification of inefficient photovoltaic strings.

[0062] Step 4: Select cluster objects based on the number of screened PV strings in each PV device to identify inefficient PV strings in the PV device;

[0063] In the embodiment of the present disclosure, the method of selecting cluster objects based on the number of screened photovoltaic strings in each photovoltaic device and then identifying inefficient photovoltaic strings in the photovoltaic device includes:

[0064] Determine whether the number of screened photovoltaic strings in each photovoltaic device is greater than a preset daily power clustering threshold;

[0065] If the number of screened photovoltaic strings in the photovoltaic device is greater than a preset daily power clustering threshold, the power generation of each photovoltaic string in the photovoltaic device during a preset daytime period is calculated, and the power generation of each photovoltaic string during the preset daytime period is clustered to identify inefficient photovoltaic strings in the photovoltaic device;

[0066] If the number of screened photovoltaic strings in the photovoltaic device is less than or equal to a preset daily power clustering threshold, the current discrete rate of the photovoltaic strings of each photovoltaic device at each same time on different days is obtained, and the current discrete rate at each time is clustered to identify inefficient photovoltaic strings in the photovoltaic device.

[0067] The power generation W of the mth photovoltaic string in the photovoltaic device during the preset daytime period is calculated as follows: m :

[0068]

[0069] Where U t m is the average voltage of the mth photovoltaic string in the photovoltaic device at time t, I t m is the average current of the mth photovoltaic string in the photovoltaic device at time t, n is the total number of time in the preset daytime period, P t m is the power of the mth photovoltaic string in the photovoltaic device at time t, Δt is the preset duration, and Q is a duration coefficient pre-set based on the preset duration.

[0070] For example, when the preset duration is equal to 10 minutes, the duration coefficient is set to one-sixth.

[0071] In the embodiment of the present disclosure, the clustering objects include: the power generation of each photovoltaic string in the photovoltaic device during a preset daytime period and the discrete rate of the current mean of each photovoltaic string in each photovoltaic device.

[0072] For example, Figure 3As shown, first, the string data of the average current and voltage corresponding to the preset duration of each photovoltaic string in each photovoltaic device in the historical period is obtained, including: obtaining the data of the photovoltaic strings in each photovoltaic device provided by different manufacturers in the photovoltaic power station, understanding the names of the measurement points of different manufacturers, that is, understanding and analyzing the data to filter out the photovoltaic string current and voltage, and then standardizing the data, unifying the format of missing data, and adjusting the data structure to obtain the string data of the average current and voltage corresponding to the preset duration of each photovoltaic string in each photovoltaic device in the historical period. Secondly, the abnormal photovoltaic strings are eliminated and the number of photovoltaic strings in each photovoltaic device and the power generation of the photovoltaic strings during the daytime period are calculated, and the daytime power generation corresponding to the photovoltaic strings in a photovoltaic device are placed into a set. Then, it is determined whether the number of screened photovoltaic strings in each device is greater than 5; if it is greater than 5, the daily power generation data in the corresponding set is clustered. First, the Bayesian Information Criterion (BIC) is used as a clustering indicator. A BIC is calculated for each number of clusters, and the cluster number with the smallest BIC is selected. If the number of clusters is greater than 1, the silhouette coefficient (S) is used as a clustering indicator to determine the number of clusters, and the cluster number with the largest silhouette coefficient is selected as the optimal cluster number. If the number of strings in the minimum cluster center is less than the number of strings in the non-minimum cluster center and the relative error between the minimum cluster center and other cluster centers is greater than a certain percentage, the strings in the minimum cluster center are considered to be inefficient strings, where the percentage is set to 15% in the embodiment of the present disclosure.

[0073] Otherwise, the filtered data is used to calculate the string current discrete rate (CV) for each photovoltaic device at the same time on different dates, and the discrete rate at each moment is clustered. The clustering method is the same. First, the Bayesian information measure is used to determine whether to cluster into one class or multiple classes. Then, the final number of clusters is removed based on the silhouette coefficient. The class with a larger discrete rate is the abnormal class, recorded as set C. If there is a device belonging to set C on the detection date, it is considered that the device has an abnormal string, and the string with the highest efficiency is the photovoltaic string with the smallest daily power consumption.

[0074] Based on the above clustering, inefficient PV strings are identified.

[0075] Among them, BIC is to select a model that best fits the existing data from the perspective of fitting, taking into account the number of samples. When the number of samples is too large, it can effectively prevent the model complexity from being too high due to excessive model accuracy. The smaller the BIC, the better;

[0076] The value of the silhouette coefficient S is between [-1,1]. The larger the value, the closer the samples of the same type are to each other, and the farther the samples of different types are from each other, the better the clustering effect.

[0077] Specifically, the calculation formulas for the two clustering indices (BIC and S) and the dispersion rate (CV) mentioned above are as follows:

[0078] BIC=-2lnL+kln(h)

[0079]

[0080]

[0081] Where L is the likelihood function, K is the number of parameters of the clustering model, h is the number of daily power generation in the daily power generation set corresponding to the photovoltaic strings in the photovoltaic device, S(i) is the silhouette coefficient of the i-th daily power generation sample in the daily power generation set corresponding to the photovoltaic strings in the photovoltaic device, a(i) is the average Euclidean distance between the i-th daily power generation sample in the daily power generation set corresponding to the photovoltaic strings in the photovoltaic device and other daily power generation samples in the same cluster, b(i) is the minimum value of the average Euclidean distance between the i-th daily power generation sample in the daily power generation set corresponding to the photovoltaic strings in the photovoltaic device and daily power generation samples in other clusters; S is the average silhouette coefficient of all daily power generation samples in the daily power generation set corresponding to the photovoltaic strings in the photovoltaic device, CV is the average discrete rate of the average current of the photovoltaic strings in the photovoltaic device within the preset daytime period, and n is the total number of moments within the preset daytime period. j∈[1~n],CV j is the discrete rate of the current mean value of all photovoltaic strings in the photovoltaic equipment at the jth moment in the preset daytime period, σ j is the standard deviation of the current values ​​of all photovoltaic strings of the photovoltaic equipment at the jth moment in the preset daytime period, μ j is the average current of all photovoltaic strings of the photovoltaic device at the jth moment in the preset daytime period.

[0082] In summary, in the method for identifying inefficient photovoltaic strings proposed in this application, the string data of the current mean and voltage mean corresponding to the preset duration of each photovoltaic string in each photovoltaic device within the historical period is first obtained; secondly, the obtained string data is processed to identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and the string data corresponding to the abnormal photovoltaic strings are eliminated; then, the string data contained in the first preset period of each photovoltaic device is filtered out from the eliminated string data, and the number of filtered photovoltaic strings in each photovoltaic device is obtained based on the filtered string data; finally, clustering objects are selected based on the number of filtered photovoltaic strings in each photovoltaic device to identify inefficient photovoltaic strings in the photovoltaic device. The technical solution provided by the present invention improves the accuracy of identifying inefficient photovoltaic strings by eliminating abnormal photovoltaic strings and then identifying inefficient photovoltaic strings, and has great application value.

[0083] Example 2

[0084] Figure 4This is a structural diagram of a photovoltaic string inefficiency identification system provided by an embodiment of the present disclosure, such as Figure 4 As shown, the system includes:

[0085] The first acquisition module is used to obtain the string data of the current average and the voltage average corresponding to the preset duration of each photovoltaic string in each photovoltaic device within a historical period;

[0086] A first identification module is configured to process the acquired string data, identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and remove string data corresponding to the abnormal photovoltaic strings;

[0087] A second acquisition module is configured to screen the string data of each photovoltaic device within a first preset time period from the eliminated string data, and acquire the number of screened photovoltaic strings in each photovoltaic device based on the screened string data;

[0088] The second identification module is used to select cluster objects based on the number of screened photovoltaic strings in each photovoltaic device and then identify inefficient photovoltaic strings in the photovoltaic device;

[0089] The first preset time period is the intersection of the preset daytime period and the start time and end time when the current average of the selected photovoltaic strings is greater than the preset current threshold;

[0090] The clustering objects include: the power generation of each photovoltaic string in the photovoltaic equipment during a preset daytime period and the discrete rate of the current mean of each photovoltaic string in each photovoltaic equipment.

[0091] In the embodiment of the present disclosure, the processing of the acquired string data to identify abnormal photovoltaic strings with extreme values ​​includes:

[0092] Standardize the string data of the current average and voltage average corresponding to the preset duration of each photovoltaic string in each photovoltaic device within the historical period;

[0093] Obtaining a first range of photovoltaic string current and a first range of photovoltaic string voltage within the historical period based on a current quantile threshold and a voltage fraction threshold of the photovoltaic string within the historical period;

[0094] Obtaining a second range of photovoltaic string current and a second range of photovoltaic string voltage within the historical period based on the short-circuit current and open-circuit voltage parameters of the photovoltaic string within the historical period;

[0095] The intersection of the first range and the second range of the photovoltaic string current is taken as the normal range of the photovoltaic string current;

[0096] Taking the intersection of the first range and the second range of the photovoltaic string voltage as the normal range of the photovoltaic string voltage;

[0097] The photovoltaic strings corresponding to the string data of the current average and voltage average corresponding to the preset time length of each photovoltaic string of the photovoltaic station in the historical period that does not fall within the normal current range and the normal voltage range are identified as abnormal photovoltaic strings with extreme values.

[0098] In the embodiment of the present disclosure, the step of processing the acquired string data to identify abnormal photovoltaic strings with constant values ​​includes:

[0099] Eliminate and identify abnormal PV strings with extreme values;

[0100] Obtain the standard deviation of the current mean corresponding to each photovoltaic string in the photovoltaic station after removing the abnormal photovoltaic strings with extreme values;

[0101] If the standard deviation of the current mean corresponding to the photovoltaic string is less than the current mean standard deviation threshold, the photovoltaic string is identified as an abnormal photovoltaic string with a constant.

[0102] In the embodiment of the present disclosure, the processing of the acquired string data to identify abnormal photovoltaic strings generating power at night includes:

[0103] Eliminate and identify abnormal PV strings with extreme values ​​and constants;

[0104] Obtain the current average value in the preset daytime period and the current average value in the preset nighttime period corresponding to each photovoltaic string after excluding abnormal photovoltaic strings with extreme values ​​and constants in the photovoltaic station;

[0105] If the current average value in the preset daytime period is smaller than the current average value in the preset nighttime period, the photovoltaic string is identified as an abnormal photovoltaic string generating power at night.

[0106] In the embodiment of the present disclosure, Figure 5 As shown, the second identification module includes:

[0107] The first judgment unit is used to judge whether the number of photovoltaic strings screened in each photovoltaic device is greater than a preset daily power clustering threshold;

[0108] If the number of screened photovoltaic strings in the photovoltaic device is greater than a preset daily power clustering threshold, the power generation of each photovoltaic string in the photovoltaic device during a preset daytime period is calculated, and the power generation of each photovoltaic string during the preset daytime period is clustered to identify inefficient photovoltaic strings in the photovoltaic device.

[0109] If the number of screened photovoltaic strings in the photovoltaic device is less than or equal to a preset daily power clustering threshold, the current discrete rate of the photovoltaic strings of each photovoltaic device at each same time on different days is obtained, and the current discrete rate at each time is clustered to identify inefficient photovoltaic strings in the photovoltaic device.

[0110] In summary, the photovoltaic string inefficiency identification system proposed in this application includes: a first identification module for processing the acquired string data, identifying abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and eliminating the string data corresponding to the abnormal photovoltaic strings; a second acquisition module for screening the string data of each photovoltaic device contained in the first preset time period in the eliminated string data, and obtaining the number of screened photovoltaic strings in each photovoltaic device based on the screened string data; a second identification module for selecting clustering objects based on the number of screened photovoltaic strings in each photovoltaic device and then identifying inefficient photovoltaic strings in the photovoltaic device. The technical solution provided by the present invention improves the accuracy of photovoltaic string inefficiency identification by eliminating abnormal photovoltaic strings and then identifying photovoltaic string inefficiencies, and has great application value.

[0111] Example 3

[0112] In order to implement the above embodiments, the present disclosure also proposes a computer storage medium.

[0113] The computer storage medium provided in the embodiment of the present disclosure stores an executable program; after the executable program is executed by the processor, it can achieve the following Figures 1 to 3 or Figures 4 and 5 Any of the methods shown.

[0114] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0115] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0116] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for identifying photovoltaic string inefficiency, characterized in that: The method comprises: Obtain string data of current average and voltage average corresponding to a preset duration of each photovoltaic string in each photovoltaic device within a historical period; Processing the acquired string data, identifying abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and removing string data corresponding to the abnormal photovoltaic strings; Filtering the string data of each photovoltaic device within a first preset time period from the eliminated string data, and obtaining the number of filtered photovoltaic strings in each photovoltaic device based on the filtered string data; Select cluster objects based on the number of screened photovoltaic strings in each photovoltaic device to identify inefficient photovoltaic strings in the photovoltaic device; The first preset time period is the intersection of the preset daytime period and the start time and end time when the current average of the selected photovoltaic strings is greater than the preset current threshold; The clustering objects include: the power generation of each photovoltaic string in the photovoltaic equipment during a preset daytime period and the discrete rate of the current mean of each photovoltaic string in each photovoltaic equipment; The selecting of cluster objects based on the number of screened photovoltaic strings in each photovoltaic device and then identifying inefficient photovoltaic strings in the photovoltaic device includes: Determine whether the number of screened photovoltaic strings in each photovoltaic device is greater than a preset daily power clustering threshold; If the number of screened photovoltaic strings in the photovoltaic device is greater than a preset daily power clustering threshold, the power generation of each photovoltaic string in the photovoltaic device during a preset daytime period is calculated, and the power generation of each photovoltaic string during the preset daytime period is clustered to identify inefficient photovoltaic strings in the photovoltaic device; If the number of screened photovoltaic strings in the photovoltaic device is less than or equal to a preset daily power clustering threshold, the current discrete rate of the photovoltaic strings of each photovoltaic device at each same time on different days is obtained, and the current discrete rate at each time is clustered to identify inefficient photovoltaic strings in the photovoltaic device.

2. The method according to claim 1, wherein The processing of the acquired string data to identify abnormal photovoltaic strings with extreme values ​​includes: Standardize the string data of the current average and voltage average corresponding to the preset duration of each photovoltaic string in each photovoltaic device within the historical period; Obtaining a first range of photovoltaic string current and a first range of photovoltaic string voltage within the historical period based on a current quantile threshold and a voltage fraction threshold of the photovoltaic string within the historical period; Obtaining a second range of photovoltaic string current and a second range of photovoltaic string voltage within the historical period based on the short-circuit current and open-circuit voltage parameters of the photovoltaic string within the historical period; The intersection of the first range and the second range of the photovoltaic string current is taken as the normal range of the photovoltaic string current; Taking the intersection of the first range and the second range of the photovoltaic string voltage as the normal range of the photovoltaic string voltage; The photovoltaic strings corresponding to the string data of the current average and voltage average corresponding to the preset time length of each photovoltaic string of the photovoltaic station in the historical period that does not fall within the normal current range and the normal voltage range are identified as abnormal photovoltaic strings with extreme values.

3. The method according to claim 1, wherein The step of processing the acquired string data to identify abnormal photovoltaic strings with constant values ​​includes: Eliminate and identify abnormal PV strings with extreme values; Obtain the standard deviation of the current mean corresponding to each photovoltaic string in the photovoltaic station after removing the abnormal photovoltaic strings with extreme values; If the standard deviation of the current mean corresponding to the photovoltaic string is less than the current mean standard deviation threshold, the photovoltaic string is identified as an abnormal photovoltaic string with a constant.

4. The method according to claim 1, wherein The processing of the acquired string data to identify abnormal photovoltaic strings generating power at night includes: Eliminate and identify abnormal PV strings with extreme values ​​and constants; Obtain the current average value in the preset daytime period and the current average value in the preset nighttime period corresponding to each photovoltaic string after excluding abnormal photovoltaic strings with extreme values ​​and constants in the photovoltaic station; If the current average value in the preset daytime period is smaller than the current average value in the preset nighttime period, the photovoltaic string is identified as an abnormal photovoltaic string generating power at night.

5. The method according to claim 1, wherein The step of calculating the power generation of each photovoltaic string in the photovoltaic device during a preset daytime period includes: The power generation of the mth photovoltaic string in the photovoltaic device during the preset daytime period is calculated as follows: : Where, is the average voltage of the mth photovoltaic string in the photovoltaic device at time t, is the average current value of the mth photovoltaic string in the photovoltaic device at time t, n is the total number of moments in the preset daytime period, It is a duration coefficient pre-set based on the preset duration.

6. A photovoltaic string inefficiency identification system, characterized in that: The system comprises: The first acquisition module is used to obtain the string data of the current average and the voltage average corresponding to the preset duration of each photovoltaic string in each photovoltaic device within a historical period; A first identification module is configured to process the acquired string data, identify abnormal photovoltaic strings with extreme values / constants / nighttime power generation, and remove string data corresponding to the abnormal photovoltaic strings; A second acquisition module is configured to screen the string data of each photovoltaic device within a first preset time period from the eliminated string data, and acquire the number of screened photovoltaic strings in each photovoltaic device based on the screened string data; The second identification module is used to select cluster objects based on the number of screened photovoltaic strings in each photovoltaic device and then identify inefficient photovoltaic strings in the photovoltaic device; The first preset time period is the intersection of the preset daytime period and the start time and end time when the current average of the selected photovoltaic strings is greater than the preset current threshold; The clustering objects include: the power generation of each photovoltaic string in the photovoltaic equipment during a preset daytime period and the discrete rate of the current mean of each photovoltaic string in each photovoltaic equipment; The second identification module includes: The first judgment unit is used to judge whether the number of photovoltaic strings screened in each photovoltaic device is greater than a preset daily power clustering threshold; If the number of screened photovoltaic strings in the photovoltaic device is greater than a preset daily power clustering threshold, the power generation of each photovoltaic string in the photovoltaic device during a preset daytime period is calculated, and the power generation of each photovoltaic string during the preset daytime period is clustered to identify inefficient photovoltaic strings in the photovoltaic device. If the number of screened photovoltaic strings in the photovoltaic device is less than or equal to a preset daily power clustering threshold, the current discrete rate of the photovoltaic strings of each photovoltaic device at each same time on different days is obtained, and the current discrete rate at each time is clustered to identify inefficient photovoltaic strings in the photovoltaic device.

7. The system according to claim 6, wherein: The processing of the acquired string data to identify abnormal photovoltaic strings with extreme values ​​includes: Standardize the string data of the current average and voltage average corresponding to the preset duration of each photovoltaic string in each photovoltaic device within the historical period; Obtaining a first range of photovoltaic string current and a first range of photovoltaic string voltage within the historical period based on a current quantile threshold and a voltage fraction threshold of the photovoltaic string within the historical period; Obtaining a second range of photovoltaic string current and a second range of photovoltaic string voltage within the historical period based on the short-circuit current and open-circuit voltage parameters of the photovoltaic string within the historical period; The intersection of the first range and the second range of the photovoltaic string current is taken as the normal range of the photovoltaic string current; Taking the intersection of the first range and the second range of the photovoltaic string voltage as the normal range of the photovoltaic string voltage; The photovoltaic strings corresponding to the string data of the current average and voltage average corresponding to the preset time length of each photovoltaic string of the photovoltaic station in the historical period that does not fall within the normal current range and the normal voltage range are identified as abnormal photovoltaic strings with extreme values.

8. A computer storage medium, wherein: The computer storage medium stores computer-executable instructions; after the computer-executable instructions are executed by the processor, the method according to any one of claims 1 to 5 can be implemented.

Images