Method for diagnosing a burst of low efficiency of a photovoltaic string, storage medium, electronic device

Abstract

The application discloses a sudden inefficiency diagnosis method of a photovoltaic string, a storage medium and an electronic device. The sudden inefficiency diagnosis method of the photovoltaic string comprises the following steps: acquiring current time sequence data of N photovoltaic strings, wherein N is an integer greater than 1; and determining a sudden inefficiency photovoltaic string in the N photovoltaic strings according to the N current time sequence data. Thus, the sudden inefficiency diagnosis method of the photovoltaic string can position abnormal characteristic data by analyzing the current time sequence data of the photovoltaic string under the premise of low cost, diagnose the sudden inefficiency photovoltaic string in real time, make the photovoltaic power station more quickly and accurately perform fault alarm, improve power generation of the power station, and guide defect elimination and operation and maintenance more effectively according to the diagnosis of the sudden inefficiency problem.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, specifically to a method for diagnosing sudden inefficiencies in photovoltaic strings, a storage medium, and electronic equipment. Background Technology

[0002] In recent years, with the development of the photovoltaic industry, ensuring the normal operation of photovoltaic strings has become increasingly important. Sudden inefficiency is a common type of failure for photovoltaic strings. Sudden inefficiency refers to inefficiency caused by external forces, such as strong winds, external damage, or foreign object adhesion. Therefore, to ensure the normal operation of photovoltaic strings, a refined inefficiency diagnosis is necessary.

[0003] In related technologies, the inefficient and refined diagnosis of photovoltaic strings adopts offline analysis, such as intelligent diagnosis of IV curves and drone inspection, which has low efficiency, poor real-time performance, and high cost, and cannot effectively guide the elimination of defects in photovoltaic strings. Summary of the Invention

[0004] This invention aims to at least partially address one of the technical problems in related technologies. Therefore, the first objective of this invention is to propose a method for diagnosing sudden inefficiencies in photovoltaic (PV) strings. This method can accurately diagnose sudden inefficiencies in PV strings in real time at low cost, thus more effectively guiding defect elimination and maintenance.

[0005] A second objective of this invention is to provide a computer-readable storage medium.

[0006] The third objective of this invention is to provide an electronic device.

[0007] To achieve the above objectives, a first aspect of the present invention provides a method for diagnosing sudden inefficiency of photovoltaic strings. The method includes: acquiring current timing data of N photovoltaic strings, where N is an integer greater than 1; and determining the photovoltaic strings with sudden inefficiency among the N photovoltaic strings based on the N current timing data.

[0008] According to the photovoltaic string sudden inefficiency diagnosis method of the present invention, the current time series data of N photovoltaic strings are first acquired, where N is an integer greater than 1; based on the N current time series data, the photovoltaic strings with sudden inefficiency are identified among the N photovoltaic strings. Therefore, this photovoltaic string sudden inefficiency diagnosis method, under low cost, analyzes the current time series data of photovoltaic strings, locates abnormal characteristic data, and diagnoses the photovoltaic strings with sudden inefficiency in real time, enabling photovoltaic power plants to more quickly and accurately issue fault alarms, thereby improving power generation. Furthermore, the diagnosis of sudden inefficiency problems can more effectively guide defect elimination and maintenance.

[0009] In addition, the method for diagnosing sudden inefficiencies of photovoltaic strings according to the above embodiments of the present invention may also have the following additional technical features:

[0010] In one embodiment of the present invention, each current time series data includes current data for M time periods. The step of determining the sudden inefficient photovoltaic string among the N photovoltaic strings based on the N current time series data includes: selecting M benchmark photovoltaic strings based on the N current time series data, where M is an integer greater than 1, and the M benchmark photovoltaic strings correspond one-to-one with the M time periods; for each time period, calculating the cumulative current ratio and Pearson correlation coefficient between each photovoltaic string and the corresponding benchmark photovoltaic string based on the current data of each photovoltaic string in that time period and the current data of the corresponding benchmark photovoltaic string; and determining the sudden inefficient photovoltaic string based on the ratio and the Pearson correlation coefficient.

[0011] In one embodiment of the present invention, the step of selecting M benchmark photovoltaic strings based on N current time-series data includes: for each time period, obtaining the cumulative current of each photovoltaic string in that time period based on the current data of each photovoltaic string in that time period, and taking the photovoltaic string with the maximum cumulative current as the benchmark photovoltaic string for that time period.

[0012] In one embodiment of the present invention, determining the sudden inefficiency photovoltaic string based on the ratio and the Pearson correlation coefficient includes: determining the abrupt change period based on the current data of each time period; determining the sudden inefficiency photovoltaic string based on the cumulative current ratio of the m time periods before and the n time periods after the abrupt change period and the Pearson correlation coefficient, wherein m is a positive integer, n is an integer greater than m, and m+n+1 is less than or equal to M.

[0013] In one embodiment of the present invention, determining the sudden inefficient photovoltaic string based on the cumulative current ratio of the m-periods before and the n-periods after the abrupt change and the Pearson correlation coefficient includes: determining an initial inefficient string based on the cumulative current ratio of the m-periods before and the n-periods after the abrupt change; and determining the sudden inefficient photovoltaic string based on the Pearson correlation coefficient of the initial inefficient string in the m-periods before and the n-periods after.

[0014] In one embodiment of the present invention, determining the initial inefficient string based on the cumulative current ratio of the m periods before and the n periods after the abrupt change includes: determining whether all photovoltaic strings in the m periods before the abrupt change are normal strings based on the cumulative current ratio of the m periods before the abrupt change; if so, determining whether there is an abrupt change process based on the cumulative current ratio of the m periods before and the n periods after the abrupt change; if so, determining the initial inefficient string based on the cumulative current ratio of the n periods after the abrupt change.

[0015] In one embodiment of the present invention, determining the sudden inefficient photovoltaic string based on the Pearson correlation coefficient of the initial inefficient string in the first m time periods and the last n time periods includes: obtaining photovoltaic strings in the initial inefficient string that are similar before and after the sudden change based on the Pearson correlation coefficient of the initial inefficient string in the first m time periods and the last n time periods, and denoting them as similar inefficient strings; determining whether the similar inefficient strings are inefficient throughout the entire time period based on the Pearson correlation coefficient of the similar inefficient strings in the last n time periods; if so, determining whether there are cloudy or rainy periods in the last n time periods based on the current data of the n benchmark strings in the last n time periods; if so, determining that the similar inefficient strings are the sudden inefficient strings; otherwise, performing time-by-time tracking analysis on the similar inefficient strings, and determining that the similar inefficient strings are the sudden inefficient strings when there are cloudy or rainy periods and the strings are inefficient throughout the entire time period.

[0016] In one embodiment of the present invention, determining whether all photovoltaic strings in the first m periods are normal strings based on the cumulative current ratio of the first m periods before the sudden change period includes: if the cumulative current ratio of the first m periods before the sudden change period is greater than the current magnitude threshold, then all photovoltaic strings in the first m periods are normal strings.

[0017] In one embodiment of the present invention, determining whether a sudden change process exists based on the cumulative current ratio of the first m time periods and the last n time periods after the sudden change period includes: if the difference between the cumulative current ratio of the first m time periods and the cumulative current ratio of the last n time periods is greater than the inefficient sudden change amplitude threshold, then it is determined that a sudden change process exists.

[0018] In one embodiment of the present invention, determining the initial inefficient string based on the cumulative current ratio of the last n time periods includes: if the absolute value of the difference between each pair of cumulative current ratios of the last n time periods is less than the inefficiency floating threshold, then the corresponding inefficient string is determined as the initial inefficient string.

[0019] In one embodiment of the present invention, the step of obtaining the photovoltaic strings with similarity before and after the mutation based on the Pearson correlation coefficients of the initial inefficient strings in the first m time periods and the last n time periods includes: if the difference between the Pearson correlation coefficient of the last n time periods and the Pearson correlation coefficient of the first m time periods is greater than the Pearson similarity floating threshold, then it is determined that the corresponding photovoltaic strings have similarity before and after the mutation.

[0020] In one embodiment of the present invention, determining whether the similar inefficient string is inefficient throughout the entire time period based on the Pearson correlation coefficient of the similar inefficient string in the subsequent n time periods includes: if the Pearson correlation coefficient of the subsequent n time periods is greater than the Pearson similarity threshold, then the similar inefficient string is determined to be inefficient throughout the entire time period.

[0021] In one embodiment of the present invention, determining whether there is a rainy period in the following n time periods based on the current data of the n benchmark strings in the following n time periods includes: if there is current data in the current data of the n benchmark strings in the following n time periods that is less than the peak current threshold of the benchmark strings, then it is determined that there is a rainy period.

[0022] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for diagnosing sudden inefficiencies in photovoltaic strings.

[0023] According to an embodiment of the present invention, when a computer program thereon is executed by a processor, it first acquires the current timing data of N photovoltaic strings, where N is an integer greater than 1; and then identifies the photovoltaic strings experiencing sudden inefficiency based on the N current timing data. Thus, this method for diagnosing sudden inefficiency of photovoltaic strings, under low cost, analyzes the current timing data of photovoltaic strings, locates abnormal characteristic data, and diagnoses the photovoltaic strings experiencing sudden inefficiency in real time. This enables photovoltaic power plants to issue fault alarms more quickly and accurately, thereby improving power generation. Furthermore, the diagnosis of sudden inefficiency problems can more effectively guide defect elimination and maintenance.

[0024] To achieve the above objectives, a third aspect of the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the above-described method for diagnosing sudden inefficiencies in photovoltaic strings.

[0025] According to an embodiment of the present invention, when the computer program on the electronic device is executed by the processor, it first acquires the current timing data of N photovoltaic strings, where N is an integer greater than 1; and determines the photovoltaic strings with sudden inefficiency among the N photovoltaic strings based on the N current timing data. Thus, this method for diagnosing sudden inefficiency of photovoltaic strings, under low cost, analyzes the current timing data of photovoltaic strings, locates abnormal characteristic data, and diagnoses the photovoltaic strings with sudden inefficiency in real time. This enables photovoltaic power plants to more quickly and accurately issue fault alarms, thereby improving power generation. Furthermore, the diagnosis of sudden inefficiency problems can more effectively guide defect elimination and maintenance.

[0026] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0027] Figure 1 This is a flowchart of a method for diagnosing sudden inefficiencies in photovoltaic strings according to an embodiment of the present invention;

[0028] Figure 2 This is a flowchart of a method for diagnosing sudden inefficiencies in photovoltaic strings according to another embodiment of the present invention;

[0029] Figure 3 This is a flowchart of a sudden inefficiency diagnosis method for photovoltaic strings according to another embodiment of the present invention;

[0030] Figure 4 This is a flowchart of a sudden inefficiency diagnosis method for photovoltaic strings according to another embodiment of the present invention;

[0031] Figure 5 This is a flowchart illustrating an example of a photovoltaic string sudden inefficiency diagnosis method according to the present invention.

[0032] Figure 6 This is a flowchart illustrating another example of a method for diagnosing sudden inefficiencies in photovoltaic strings according to the present invention. Detailed Implementation

[0033] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0034] The following describes, with reference to the accompanying drawings, a method for diagnosing sudden inefficiencies in photovoltaic strings, a storage medium, and an electronic device according to embodiments of the present invention.

[0035] Figure 1 This is a flowchart of a method for diagnosing sudden inefficiencies in photovoltaic strings according to an embodiment of the present invention.

[0036] like Figure 1 As shown, the method for diagnosing sudden inefficiencies in photovoltaic strings according to an embodiment of the present invention includes the following steps:

[0037] S101, obtain the current timing data of N photovoltaic strings, where N is an integer greater than 1.

[0038] In some embodiments of the present invention, each current time series data includes current data for M time periods, where M is an integer greater than 1. It should be noted that the value of M must be no less than a time threshold. As an example, this time threshold can be set to a daily unit. For example, a time threshold of 5 can be set, in which case each current time series data can include current data from 5 days, thus obtaining current data for each photovoltaic string from 8:00 AM to 5:00 PM for 5 consecutive days.

[0039] Specifically, current data for all branches of a single device (inverter, combiner box, etc.) is acquired over M time periods.

[0040] Furthermore, after acquiring the current data of all branches in M ​​time periods, the acquired current time series data needs to be preprocessed, including filtering out communication dead values, interruptions, and over-limit values. The aforementioned over-limit values ​​refer to the collected current being greater than the rated current value. Specific processing methods may include filtering strings with all zero values, filtering strings with constant values ​​for a continuous preset time (such as half an hour), filtering strings with over-limit values, and filtering unconnected strings, thereby obtaining the current time series data of N photovoltaic strings.

[0041] In addition, the current time series data of the above N photovoltaic strings need to meet the requirement that the number of current sampling points in each time period is greater than the sampling threshold. As an example, a 5-minute resolution can be set, with a total of 90 sampling points per day, and a sampling threshold of 83 can be set. After sampling 90 sampling points per day, the data obtained after preprocessing the sampling results of the 90 sampling points will include at least 83 sampling point data, that is, a maximum of half an hour of missing data is allowed.

[0042] S102, determine the bursty inefficient photovoltaic string among the N photovoltaic strings based on N current time series data.

[0043] In some embodiments of the present invention, sudden inefficiency is different from gradual failures such as component aging and vegetation obstruction. Sudden inefficiency often occurs abruptly at a certain point in time, directly forming inefficiency. Subsequently, the degree of inefficiency is relatively stable in the short term and conforms to the situation of inefficiency throughout the entire time period. This makes sudden inefficiency characterized by abruptness, inefficiency throughout the entire time period, stability, and continuity.

[0044] Among them, sudden change refers to a sudden change at a certain point in time; all-time inefficiency means that the inefficiency formed after the sudden change is all-time, and the current data of that time period is similar to that of the benchmark photovoltaic string; stability and continuity mean that the inefficiency formed after the sudden change is stable, that is, the degree of inefficiency does not fluctuate greatly and is continuous, and it is generally difficult to recover on its own without treatment.

[0045] Furthermore, when external obstacles such as mountains or trees block the signal throughout the day, even if the period is sunny, it will still result in inefficiency. On cloudy or rainy days, there will be no significant difference compared to normal sequences. However, for sudden inefficiency, the period will be inefficient regardless of whether it is sunny or cloudy. Therefore, if for a given period, the preceding period is cloudy or rainy, and the subsequent periods are sunny, even if there is actual obstruction from mountains or trees, it will be mistakenly identified as sudden inefficiency. To address this, we can use the presence of cloudy or rainy days to distinguish between external obstacle obstruction and sudden inefficiency. For example, we can determine if there are cloudy or rainy days in the three periods following the sudden change in timing. If so, it is considered sudden inefficiency. If not, we can analyze each period sequentially. If subsequent periods are cloudy or rainy and inefficient throughout the day, it is also considered sudden inefficiency.

[0046] Therefore, based on N current time-series data, the photovoltaic strings experiencing sudden inefficiencies can be identified from among the N photovoltaic strings. (See also...) Figure 2 ,include:

[0047] S201: Select M benchmark photovoltaic strings based on N current time series data, where M is an integer greater than 1, and the M benchmark photovoltaic strings correspond one-to-one with the M time periods.

[0048] Specifically, for each time period, the cumulative current of each photovoltaic string in that time period is obtained based on the current data of each photovoltaic string in that time period, and the photovoltaic string corresponding to the maximum cumulative current is taken as the benchmark photovoltaic string for that time period.

[0049] Taking the first time period as an example, the cumulative current of the N photovoltaic strings in the first time period is obtained based on the current data of the N photovoltaic strings in the first time period. The maximum value among the N cumulative currents is then taken, and the photovoltaic string corresponding to the maximum cumulative current is taken as the benchmark photovoltaic string a1 for the first time period. Similarly, M benchmark photovoltaic strings corresponding to M time periods can be obtained, which can be represented as a1, a2, ..., a M .

[0050] S202, for each time period, based on the current data of each photovoltaic string in that time period and the current data of the corresponding benchmark photovoltaic string, calculate the cumulative current ratio and Pearson correlation coefficient of each photovoltaic string and the corresponding benchmark photovoltaic string.

[0051] Taking the first time period as an example, the cumulative current ratio and Pearson correlation coefficient of each photovoltaic string with the corresponding benchmark photovoltaic string in the first time period are calculated, which can be denoted as ratio1 and corr1, respectively. Similarly, the cumulative current ratio and Pearson correlation coefficient of each photovoltaic string with the corresponding benchmark photovoltaic string in M ​​time periods can be obtained, which can be represented as ratio1, ratio2, ..., ratio1. Mand corr1, corr2, ..., corr M .

[0052] S203, based on the ratio and Pearson correlation coefficient, determines the sudden inefficiency of photovoltaic strings.

[0053] In some embodiments of the present invention, see Figure 3 The sudden inefficiency of photovoltaic strings can be determined based on the ratio and Pearson correlation coefficient, and may include:

[0054] S301 determines the abrupt change period based on the current data for each time period.

[0055] Specifically, in the current data of M time periods, the abrupt change period is determined, that is, the change occurs at a certain point in time and the change process is abrupt. The time period in which the point in time is located is the abrupt change period.

[0056] S302, the sudden inefficiency photovoltaic string is determined based on the cumulative current ratio of the m-period before and n-period after the sudden change period and the Pearson correlation, where m is a positive integer, n is an integer greater than m, and m+n+1 is less than or equal to M.

[0057] In some embodiments of the present invention, determining the sudden inefficiency photovoltaic string based on the ratio of the cumulative current during the m-periods before and the n-periods after the abrupt change, and the Pearson correlation, may include:

[0058] S401 determines the initial inefficient string based on the ratio of the cumulative current in the m-periods before and the n-periods after the abrupt change.

[0059] Specifically, step S401 may include:

[0060] A1. Determine whether all photovoltaic strings in the first m periods are normal strings based on the cumulative current ratio of the periods before the sudden change.

[0061] Specifically, if the cumulative current ratios for the m periods preceding the abrupt change are all greater than the current magnitude threshold, then the photovoltaic strings for the first m periods are all considered normal strings. As an example, for each photovoltaic string, we can determine whether its cumulative current ratio for the first m periods is greater than the current magnitude threshold; if so, the corresponding photovoltaic string for the first m periods is considered a normal string.

[0062] It should be noted that the aforementioned current threshold is a limit set on the ratio of the cumulative current of each photovoltaic string in the first m time periods to that of the corresponding benchmark photovoltaic string. This is an inefficiency threshold used to determine whether a photovoltaic string is a normal string, and can be denoted as ratio_value. threshold .

[0063] A2. If so, then determine whether there is a sudden change process based on the ratio of the cumulative current in the first m time period and the last n time period after the sudden change period.

[0064] Specifically, if the photovoltaic string in the current m-period is a normal string, and the difference between the cumulative current ratio of the previous m-periods and the cumulative current ratio of the next n-periods is greater than the threshold for inefficiency mutation amplitude, then a mutation process is determined to exist.

[0065] It should be noted that the aforementioned inefficient abrupt change threshold sets a limit on the difference between the cumulative current ratio of the first m time periods and the last n time periods. This limit is used to measure the decrease in current between the first m time periods and the last n time periods during the abrupt change period, in order to determine whether an abrupt change process exists. This can be denoted as ratio_change. threshold .

[0066] A3. If so, the initial inefficient string is determined based on the cumulative current ratio of the last n time periods.

[0067] Specifically, when a mutation process is determined, if the absolute value of the difference between each pair of cumulative current ratios in the subsequent n time periods is less than the inefficient floating threshold, then the corresponding inefficient string is determined as the initial inefficient string, and an inefficient string with mutation capability and stable inefficiency after mutation is generated.

[0068] It should be noted that the aforementioned inefficient floating threshold can be denoted as ratio_swim threshold The inefficiency fluctuation threshold sets a limit on the fluctuation of inefficiency between the last n segments in order to determine whether the inefficiency is stable after the mutation.

[0069] S402, the burst inefficient photovoltaic string is determined based on the Pearson correlation coefficient of the initial inefficient string in the first m time period and the last n time period.

[0070] Specifically, step S402 may include:

[0071] B1. Based on the Pearson correlation coefficients of the initial inefficient strings in the first m time periods and the last n time periods, the photovoltaic strings that are similar before and after the mutation in the initial inefficient strings are obtained and denoted as similar inefficient strings.

[0072] Specifically, if the difference between the Pearson correlation coefficient in the last n time periods and the Pearson correlation coefficient in the first m time periods is greater than the Pearson similarity floating threshold, then the corresponding photovoltaic string is determined to have similarity before and after the mutation.

[0073] It should be noted that the Pearson similarity fluctuation threshold mentioned above is a limit set on the fluctuation of Pearson similarity between the first m segments and the last n segments, in order to determine the photovoltaic strings with similarity before and after the mutation in the initially inefficient strings, which can be denoted as similar_change. threshold .

[0074] B2. Based on the Pearson correlation coefficient of similar inefficient sequences in the last n time periods, determine whether similar inefficient sequences are inefficient throughout the entire time period.

[0075] Specifically, if the Pearson correlation coefficient of the similar inefficient string over the next n time periods is greater than the Pearson similarity threshold, then the similar inefficient string is determined to be similar to the corresponding benchmark string, that is, the similar inefficient string is inefficient throughout the entire time period.

[0076] It should be noted that the Pearson similarity threshold mentioned above is the lower limit of the Pearson similarity for the last n segments, which can be denoted as similar_value. threshold .

[0077] B3. If so, then determine whether there are rainy periods in the next n time periods based on the current data of the n benchmark strings in the next n time periods.

[0078] Specifically, when similar inefficient strings are inefficient throughout the entire time period, if there are current data in the peak current data of the n benchmark strings in the next n time periods that are less than the peak current threshold of the benchmark strings, then it is determined that there is a rainy period.

[0079] It should be noted that the above-mentioned benchmark string peak current threshold refers to the benchmark string peak current I. max Setting restrictions can be denoted as I. threshold .

[0080] B4. If it exists, then the similar inefficient string is determined to be a sudden inefficient string. Otherwise, the similar inefficient string is tracked and analyzed on a time-by-time basis. If there is a rainy period and the string is inefficient throughout the entire period, the similar inefficient string is determined to be a sudden inefficient string.

[0081] To better understand step S302 above, as an example, M is set to 5, with the 5 time periods corresponding to the period from 8:00 AM to 5:00 PM in the past 5 days. The abrupt change period corresponds to the 2nd day, the first m periods of the abrupt change period correspond to the previous day, and the last n periods correspond to the last 3 days. The cumulative current ratio and Pearson correlation coefficient of each photovoltaic string with the corresponding benchmark photovoltaic string in each of the 5 time periods are represented as ratio1, ratio2, ratio3, ratio4, ratio5 and corr1, corr2, corr3, corr4, corr5, respectively. (Refer to...) Figure 5 Specifically, it includes the following steps:

[0082] S501, determine whether the photovoltaic strings in the period preceding the abrupt change are normal strings. If ratio1 > ratio_value threshold If the photovoltaic strings in the previous period are determined to be normal strings, proceed to step S502.

[0083] S502, determine if a mutation process exists. If the following conditions are met:

[0084] ratio1-ratio3>atio_changethreshold ,

[0085] ratio1-ratio4>atio_change threshold ,

[0086] ratio1-ratio5>atio_change threshold ,

[0087] If the current value decreases in every period from the first period to the last three periods, it is determined that there is a sudden change process, and the process proceeds to step S503.

[0088] S503, determine whether the inefficiency after mutation is stable. If it meets the following conditions:

[0089] abs(ratio3-ratio4) <ratio_swim threshold ,

[0090] abs(ratio3-ratio5) <atio_swim threshold ,

[0091] abs(ratio4-ratio5) <ratio_swim threshold ,

[0092] If the absolute value of the difference between each pair of cumulative current ratios in the last three time periods is less than the inefficient floating threshold, then the corresponding inefficient string is determined to be an initial inefficient string with a mutation and stable inefficiency after the mutation, and proceed to step S504.

[0093] S504, determine whether the initially inefficient strings are similar to the photovoltaic strings before and after the mutation. Since the similarity of photovoltaic strings will not change due to the mutation inefficiency, if the following conditions are met:

[0094] corr3-corr1>similar_change threshold ,

[0095] corr4-corr1>similar_change threshold ,

[0096] corr5-corr1>similar_change threshold ,

[0097] If the difference between the Pearson correlation coefficients of the last 3 time periods and the first time period is greater than the Pearson similarity floating threshold, then the corresponding photovoltaic strings are determined to be similar before and after the mutation, i.e., similar inefficient strings, and proceed to step S505.

[0098] S505, determine whether similar inefficient strings are inefficient throughout the entire time period. If satisfied:

[0099] corr3>similar_value threshold ,

[0100] corr4>similar_value threshold ,

[0101] corr5>similar_value threshold ,

[0102] If the Pearson correlation coefficients for the last three time periods are all greater than the Pearson similarity threshold, then the similar inefficient strings are determined to be inefficient throughout the entire time period, and proceed to step S506.

[0103] S506, determine whether there are any rainy periods in the last three time periods, that is, determine whether there are any peak current data of the three benchmark strings in the last three time periods that are less than the peak current threshold I of the benchmark string. threshold Current data, if I exists max threshold If a rainy period is found in the last three time periods, the similar inefficient string is identified as a sudden inefficient string and the process proceeds to step S508; otherwise, a similar inefficient string with sudden change and inefficiency throughout the time period is identified, stored, and the process proceeds to step S507.

[0104] S507: Obtain similar inefficient strings that are mutable and inefficient throughout the day, and perform time-by-time tracking analysis. If there are rainy periods in subsequent periods and the strings are inefficient throughout the entire period, proceed to step S508.

[0105] S508 outputs bursty inefficient strings.

[0106] Based on the above example, refer to Figure 6 The present invention describes a method for diagnosing sudden inefficiencies in photovoltaic strings, which specifically includes the following steps:

[0107] S601, acquire sample data, taking a single device as the unit, acquire the 5-minute resolution current time series data of the photovoltaic strings of all branches for the past 5 days corresponding to 5 time periods.

[0108] S602, perform data preprocessing on the above data. For details, please refer to step S101, which will not be elaborated here.

[0109] S603 determines the relevant thresholds for sudden inefficiencies based on data statistical methods, specifically including: current magnitude threshold ratio_value threshold Inefficient mutation amplitude threshold ratio_change threshold ​Inefficient floating threshold ratio_swim threshold Pearson similarity threshold similar_change threshold Pearson similarity threshold (similar_value) threshold Benchmark string peak current threshold I threshold .

[0110] S604. Based on the threshold for sudden inefficiency and the current timing data of the photovoltaic string, perform sudden inefficiency diagnosis to identify the string with sudden inefficiency. The specific diagnosis method can be referred to step S203, which will not be elaborated here.

[0111] S605 outputs the diagnostic results and stores the burst of inefficient strings.

[0112] S606, based on the diagnostic results, performs fault recovery and re-alarm. Fault recovery can utilize the closed-loop work order processing results to update the sudden inefficiency state to a normal state, or it can perform self-recovery. For example, it can subsequently track the sudden inefficiency string in time periods. If the ratio of the cumulative current of the subsequent three consecutive time periods to the cumulative current of the corresponding benchmark photovoltaic string is greater than the current magnitude threshold ratio_value, then... threshold If so, update the sudden inefficient state to the normal state.

[0113] In summary, the photovoltaic string sudden inefficiency diagnosis method of this invention first acquires the current time-series data of N photovoltaic strings, where N is an integer greater than 1; based on the N current time-series data, it identifies the photovoltaic strings with sudden inefficiency among the N photovoltaic strings. Therefore, this photovoltaic string sudden inefficiency diagnosis method, without increasing the workload of maintenance personnel or requiring the installation of any additional sensors at low cost, analyzes the current time-series data of photovoltaic strings to locate abnormal characteristic data and diagnoses the photovoltaic strings with sudden inefficiency in real time. This enables photovoltaic power plants to issue fault alarms more quickly and accurately, thereby improving power generation. Furthermore, the diagnosis of sudden inefficiency problems can more effectively guide defect elimination and maintenance.

[0114] Furthermore, the present invention proposes a computer-readable storage medium.

[0115] In this embodiment of the invention, a computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for diagnosing sudden inefficiencies in photovoltaic strings.

[0116] The computer-readable storage medium of this invention, when executed by a processor, first acquires the current timing data of N photovoltaic strings, where N is an integer greater than 1; based on the N current timing data, it identifies the photovoltaic strings experiencing sudden inefficiency. Therefore, this method for diagnosing sudden inefficiency of photovoltaic strings, without increasing the workload of maintenance personnel or requiring the installation of any additional sensors at low cost, analyzes the current timing data of the photovoltaic strings to locate abnormal characteristic data and diagnoses the photovoltaic strings experiencing sudden inefficiency in real time. This enables photovoltaic power plants to issue fault alarms more quickly and accurately, thereby improving power generation. Furthermore, the diagnosis of sudden inefficiency problems can more effectively guide defect elimination and maintenance.

[0117] Furthermore, the present invention proposes an electronic device.

[0118] In this embodiment of the invention, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements a method for diagnosing sudden inefficiencies in photovoltaic strings.

[0119] In the electronic device of this invention, when the computer program on it is executed by the processor, it first acquires the current timing data of N photovoltaic strings, where N is an integer greater than 1; based on the N current timing data, it identifies the photovoltaic strings experiencing sudden inefficiency. Therefore, this method for diagnosing sudden inefficiency of photovoltaic strings, without increasing the workload of maintenance personnel or requiring the installation of any additional sensors at low cost, analyzes the current timing data of the photovoltaic strings to locate abnormal characteristic data and diagnoses the photovoltaic strings experiencing sudden inefficiency in real time. This enables photovoltaic power plants to issue fault alarms more quickly and accurately, thereby improving power generation. Furthermore, the diagnosis of sudden inefficiency problems can more effectively guide defect elimination and maintenance.

[0120] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein can be considered as a ordered list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0121] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0122] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0123] In the description of this specification, the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and should not be construed as limiting the present invention.

[0124] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0125] In this specification, unless otherwise stated, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly defined. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0126] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0127] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for diagnosing sudden inefficiencies in photovoltaic strings, characterized in that, The method includes: Obtain the current timing data of N photovoltaic strings, where N is an integer greater than 1; Based on the N current timing data, identify the N photovoltaic strings that experience sudden inefficiency. Each current time series data includes current data for M time periods. The step of determining the N photovoltaic strings experiencing sudden inefficiency based on the N current time series data includes: Based on the N current time series data, M benchmark photovoltaic strings are selected, where M is an integer greater than 1, and the M benchmark photovoltaic strings correspond one-to-one with the M time periods; For each time period, based on the current data of each photovoltaic string and the current data of the corresponding benchmark photovoltaic string, the cumulative current ratio and Pearson correlation coefficient of each photovoltaic string and the corresponding benchmark photovoltaic string are calculated respectively. The sudden inefficiency of the photovoltaic string is determined based on the ratio and the Pearson correlation coefficient, including: The abrupt change period is determined based on the current data for each of the aforementioned time periods; The sudden inefficiency photovoltaic string is determined based on the cumulative current ratio of the m-period period before and the n-period period after the sudden change, and the Pearson correlation, where m is a positive integer, n is an integer greater than m, and m+n+1 is less than or equal to M.

2. The method according to claim 1, characterized in that, The step of selecting M benchmark photovoltaic strings based on N current timing data includes: For each time period, the cumulative current of each photovoltaic string in that time period is obtained based on the current data of each photovoltaic string in that time period, and the photovoltaic string with the maximum cumulative current is taken as the benchmark photovoltaic string for that time period.

3. The method according to claim 2, characterized in that, The determination of the sudden inefficiency photovoltaic string based on the cumulative current ratio of the m-periods before and n-periods after the abrupt change and the Pearson correlation includes: The initial inefficient string is determined based on the cumulative current ratio of the m-periods before and the n-periods after the abrupt change. The sudden inefficient photovoltaic string is determined based on the Pearson correlation coefficient of the initial inefficient string during the first m time period and the last n time period.

4. The method according to claim 3, characterized in that, The determination of the initial inefficient string based on the cumulative current ratio of the m time periods before and the n time periods after the abrupt change includes: The cumulative current ratio of the m periods before the abrupt change period is used to determine whether all photovoltaic strings in the m periods before the abrupt change period are normal strings. If so, then the existence of a sudden change process is determined based on the ratio of the cumulative current in the first m time periods and the n time periods after the sudden change period; If so, the initial inefficient string is determined based on the cumulative current ratio of the last n time periods.

5. The method according to claim 3, characterized in that, The step of determining the sudden inefficient photovoltaic string based on the Pearson correlation coefficient of the initial inefficient string in the first m time periods and the last n time periods includes: Based on the Pearson correlation coefficients of the initial inefficient strings in the first m time periods and the last n time periods, photovoltaic strings that are similar before and after the mutation are obtained from the initial inefficient strings and are denoted as similar inefficient strings. Based on the Pearson correlation coefficient of the similar inefficient strings in the last n time periods, it is determined whether the similar inefficient strings are inefficient throughout the entire time period; If so, then determine whether there are rainy periods in the last n time periods based on the current data of the n benchmark strings in the last n time periods; If such a string exists, it is determined that the similar inefficient string is the sudden inefficient photovoltaic string; otherwise, the similar inefficient string is tracked and analyzed on a time-by-time basis, and if there are subsequent cloudy or rainy periods and the string is inefficient throughout the entire period, the similar inefficient string is determined to be the sudden inefficient photovoltaic string.

6. The method according to claim 4, characterized in that, The step of determining whether all photovoltaic strings in the previous m periods are normal strings based on the cumulative current ratio of the previous m periods before the sudden change period includes: If the cumulative current ratio of the m periods before the sudden change period is greater than the current magnitude threshold, then the photovoltaic strings in the m periods before the sudden change period are all normal strings.

7. The method according to claim 4, characterized in that, The step of determining whether a sudden change process exists based on the ratio of the cumulative current in the first m time periods to the cumulative current in the n time periods after the sudden change period includes: If the difference between the cumulative current ratio of the first m time periods and the cumulative current ratio of the last n time periods is greater than the inefficient mutation amplitude threshold, then a mutation process is determined to exist.

8. The method according to claim 4, characterized in that, Determining the initial inefficient string based on the cumulative current ratio over the next n time periods includes: If the absolute value of the difference between each pair of cumulative current ratios in the subsequent n time periods is less than the inefficient floating threshold, then the corresponding inefficient string is determined as the initial inefficient string.

9. The method according to claim 5, characterized in that, The step of obtaining photovoltaic strings with similarities before and after abrupt changes based on the Pearson correlation coefficients of the initial inefficient strings in the first m time periods and the last n time periods includes: If the difference between the Pearson correlation coefficient of the latter n time period and the Pearson correlation coefficient of the former m time period is greater than the Pearson similarity floating threshold, then the corresponding photovoltaic string is determined to have similarity before and after the mutation.

10. The method according to claim 5, characterized in that, The step of determining whether the similar inefficient strings are inefficient throughout the entire time period based on the Pearson correlation coefficient of the similar inefficient strings in the subsequent n time periods includes: If the Pearson correlation coefficients for the last n time periods are all greater than the Pearson similarity threshold, then the similar inefficient strings are determined to be inefficient throughout the entire time period.

11. The method according to claim 5, characterized in that, The step of determining whether there are rainy periods in the following n time periods based on the current data of the n benchmark strings in the following n time periods includes: If any of the current data in the n benchmark strings during the subsequent n time periods contains current data that is less than the peak current threshold of the benchmark string, then it is determined that there is a rainy period.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for diagnosing sudden inefficiencies of photovoltaic strings as described in any one of claims 1-11.

13. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, it implements the method for diagnosing sudden inefficiencies of photovoltaic strings as described in any one of claims 1-11.

Images