Abnormal photovoltaic string detection method and system, electronic equipment and storage medium

Abstract

The invention provides an abnormal photovoltaic string detection method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical operation data of a photovoltaic string in a target area; performing transverse comparative analysis on the photovoltaic string based on the historical operation data to obtain a unit daily generated electric quantity transverse deviation rate of the photovoltaic string; performing longitudinal comparative analysis on the photovoltaic string based on the historical operation data to obtain a unit daily power generation quantity longitudinal deviation rate of the photovoltaic string; and identifying an abnormal photovoltaic string, wherein the abnormal photovoltaic string is a photovoltaic string of which the unit daily generated electric quantity transverse deviation ratio is greater than a transverse deviation threshold value and / or the unit daily generated electric quantity longitudinal deviation ratio is greater than a longitudinal deviation threshold value. According to the scheme, transverse comparative analysis and longitudinal comparative analysis are carried out on the photovoltaic string to identify the abnormal photovoltaic string, the abnormal photovoltaic string is analyzed from multiple aspects, and the detection effect of the abnormal photovoltaic string is improved.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic technology, and in particular to an abnormal photovoltaic string detection method, system, electronic equipment and storage medium. Background Art

[0002] Abnormal operation and maintenance analysis and fault location of photovoltaic strings can ensure the stable operation of photovoltaic power generation; the existing detection method for photovoltaic strings is: to conduct a horizontal comparison of photovoltaic modules in photovoltaic power stations to detect abnormal photovoltaic strings.

[0003] However, on the one hand, the existing detection methods cannot effectively analyze the abnormal failure trend of photovoltaic strings. On the other hand, when all photovoltaic strings are abnormal at the same time due to dust accumulation problems in a photovoltaic power station, the existing detection methods cannot analyze the photovoltaic strings, and the detection effect of abnormal photovoltaic strings is poor. Summary of the invention

[0004] In view of this, embodiments of the present invention provide a method, system, electronic device and storage medium for detecting abnormal photovoltaic strings to solve the problems of poor detection effect of abnormal photovoltaic strings in existing detection methods.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A first aspect of an embodiment of the present invention discloses a method for detecting abnormal photovoltaic strings, the method comprising:

[0007] Acquire historical operation data of photovoltaic strings in a target area, where the target area includes multiple photovoltaic power stations;

[0008] Performing a horizontal comparative analysis on the photovoltaic strings based on the historical operation data to obtain a horizontal deviation rate of unit daily power generation of the photovoltaic strings;

[0009] Based on the historical operation data, a longitudinal comparative analysis is performed on the photovoltaic strings to obtain a longitudinal deviation rate of unit daily power generation of the photovoltaic strings;

[0010] An abnormal photovoltaic string is identified, where the abnormal photovoltaic string is a photovoltaic string whose lateral deviation rate of the unit daily power generation is greater than a lateral deviation threshold and / or whose longitudinal deviation rate of the unit daily power generation is greater than a longitudinal deviation threshold.

[0011] Preferably, a horizontal comparative analysis is performed on the photovoltaic strings based on the historical operation data to obtain a horizontal deviation rate of unit daily power generation of the photovoltaic strings, including:

[0012] Based on the historical operation data, calculating the unit daily power generation of the photovoltaic string;

[0013] According to the unit daily power generation of the photovoltaic strings, some of the photovoltaic strings are excluded;

[0014] Calculating the consistency of the meteorological value curves at the remaining geographical locations of each of the two photovoltaic strings;

[0015] Utilizing the consistency of the meteorological numerical curve, calculating the horizontal reference unit daily power generation of the remaining photovoltaic strings;

[0016] Based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation, a horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings is calculated.

[0017] Preferably, according to the unit daily power generation of the photovoltaic strings, excluding part of the photovoltaic strings includes:

[0018] According to the unit daily power generation of the photovoltaic strings, the photovoltaic strings are sorted in descending order;

[0019] The photovoltaic strings whose unit daily power generation is within a preset ranking range are excluded.

[0020] Preferably, a longitudinal comparative analysis is performed on the photovoltaic strings based on the historical operation data to obtain a longitudinal deviation rate of unit daily power generation of the photovoltaic strings, including:

[0021] Based on the historical operation data, calculating the actual daily unit power generation of the photovoltaic string;

[0022] Using the pre-trained photovoltaic prediction model, predict the theoretical daily unit power generation of the photovoltaic string in the past X days;

[0023] Calculate the sum of the actual daily unit power generation of the photovoltaic string in the past X days to obtain the total actual unit power generation of the photovoltaic string;

[0024] Calculate the sum of the theoretical daily unit power generation of the photovoltaic string in the past X days to obtain the total theoretical unit power generation of the photovoltaic string;

[0025] The total actual unit power generation and the total theoretical unit power generation are used to calculate the unit daily power generation longitudinal deviation rate of the photovoltaic string.

[0026] Preferably, after identifying the abnormal photovoltaic string, the method further includes:

[0027] With the goal of maximizing the number of abnormal photovoltaic strings within a fixed range, a greedy algorithm is used to select a maintenance area;

[0028] Calculate the total maintenance cost and total maintenance benefit of abnormal photovoltaic strings in the maintenance area;

[0029] If the total maintenance benefit is greater than or equal to the total maintenance cost, a maintenance plan at least including the maintenance area is output.

[0030] A second aspect of an embodiment of the present invention discloses an abnormal photovoltaic string detection system, the system comprising:

[0031] An acquisition unit, configured to acquire historical operation data of photovoltaic strings in a target area, wherein the target area includes a plurality of photovoltaic power stations;

[0032] A horizontal analysis unit, used for performing a horizontal comparative analysis on the photovoltaic strings based on the historical operation data to obtain a horizontal deviation rate of unit daily power generation of the photovoltaic strings;

[0033] A longitudinal analysis unit, configured to perform longitudinal comparative analysis on the photovoltaic strings based on the historical operation data to obtain a longitudinal deviation rate of unit daily power generation of the photovoltaic strings;

[0034] The identification unit is used to identify abnormal photovoltaic strings, wherein the abnormal photovoltaic strings are photovoltaic strings whose lateral deviation rate of unit daily power generation is greater than a lateral deviation threshold and / or whose longitudinal deviation rate of unit daily power generation is greater than a longitudinal deviation threshold.

[0035] Preferably, the lateral analysis unit comprises:

[0036] A first calculation module, configured to calculate the unit daily power generation of the photovoltaic string based on the historical operation data;

[0037] An exclusion module, used for excluding part of the photovoltaic strings according to the unit daily power generation of the photovoltaic strings;

[0038] A second calculation module is used to calculate the consistency of the meteorological value curves at the remaining geographical locations of each two photovoltaic strings;

[0039] A third calculation module is used to calculate the horizontal reference unit daily power generation of the remaining photovoltaic strings by using the consistency of the meteorological numerical curve;

[0040] The fourth calculation module is used to calculate the horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation.

[0041] Preferably, the exclusion module is specifically used to: sort the photovoltaic strings in descending order according to their unit daily power generation; and exclude the photovoltaic strings whose unit daily power generation is within a preset ranking range.

[0042] A third aspect of an embodiment of the present invention discloses an electronic device, comprising: a processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; and the memory is used to store a program, wherein the program is used to implement the abnormal photovoltaic string detection method disclosed in the first aspect of the embodiment of the present invention.

[0043] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the abnormal photovoltaic string detection method disclosed in the first aspect of the embodiment of the present invention.

[0044] A fifth aspect of an embodiment of the present invention discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the abnormal photovoltaic string detection method disclosed in the first aspect of an embodiment of the present invention.

[0045] Based on the above-mentioned embodiment of the present invention, an abnormal photovoltaic string detection method, system, electronic device and storage medium are provided. The method is: obtaining historical operation data of photovoltaic strings in the target area; performing horizontal comparative analysis on photovoltaic strings based on historical operation data to obtain the horizontal deviation rate of unit daily power generation of photovoltaic strings; performing vertical comparative analysis on photovoltaic strings based on historical operation data to obtain the vertical deviation rate of unit daily power generation of photovoltaic strings; identifying abnormal photovoltaic strings, and abnormal photovoltaic strings are: photovoltaic strings with a horizontal deviation rate of unit daily power generation greater than a horizontal deviation threshold and / or a vertical deviation rate of unit daily power generation greater than a vertical deviation threshold. This scheme performs horizontal comparative analysis and vertical comparative analysis on photovoltaic strings to obtain the horizontal deviation rate of unit daily power generation and the vertical deviation rate of unit daily power generation of photovoltaic strings; identifying abnormal photovoltaic strings based on the horizontal deviation rate of unit daily power generation and the vertical deviation rate of unit daily power generation, analyzing abnormal photovoltaic strings from multiple aspects, and improving the detection effect of abnormal photovoltaic strings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0047] Figure 1 A flow chart of a method for detecting abnormal photovoltaic strings provided by an embodiment of the present invention;

[0048] Figure 2An example diagram of selecting a maintenance area using a greedy algorithm provided in an embodiment of the present invention;

[0049] Figure 3 A flow chart of a horizontal comparative analysis provided by an embodiment of the present invention;

[0050] Figure 4 A flowchart of a longitudinal comparative analysis provided by an embodiment of the present invention;

[0051] Figure 5 An example diagram of the principle architecture of an abnormal photovoltaic string detection method provided by an embodiment of the present invention;

[0052] Figure 6 A structural block diagram of an abnormal photovoltaic string detection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0055] With the rapid development of the photovoltaic industry, abnormal operation and maintenance analysis and fault location of photovoltaic strings have become urgent needs. The existing detection method for photovoltaic strings is to conduct a horizontal comparison of photovoltaic modules in a photovoltaic power station (or in a site) to detect abnormal photovoltaic strings.

[0056] However, on the one hand, the existing detection methods cannot effectively analyze the abnormal failure trend of photovoltaic strings. On the other hand, when all photovoltaic strings in the photovoltaic power station are abnormal at the same time due to dust accumulation, the existing detection methods cannot analyze the photovoltaic strings, and the detection effect of abnormal photovoltaic strings is poor. In addition, the existing detection methods do not analyze the loss of income caused by photovoltaic string problems and the return on investment after repair.

[0057] In order to solve the above problems, this solution provides an abnormal photovoltaic string detection method, system, electronic device and storage medium, which conducts horizontal and vertical comparative analysis on photovoltaic strings to obtain the horizontal deviation rate and vertical deviation rate of unit daily power generation of photovoltaic strings; abnormal photovoltaic strings are identified according to the horizontal deviation rate and vertical deviation rate of unit daily power generation, and abnormal photovoltaic strings are analyzed from multiple aspects to improve the detection effect of abnormal photovoltaic strings. After identifying abnormal photovoltaic strings, this solution also determines whether to arrange a maintenance plan by analyzing the maintenance cost and maintenance income.

[0058] The present solution is described in detail below through various embodiments.

[0059] See also Figure 1 , shows a flow chart of an abnormal photovoltaic string detection method provided by an embodiment of the present invention, including:

[0060] Step S101: Acquire historical operation data of photovoltaic strings in a target area.

[0061] It should be noted that the target area includes multiple photovoltaic power stations (multiple sites), and the target area can be a city.

[0062] In the specific implementation of step S101, historical operation data of the photovoltaic strings in the target area is obtained, and the historical operation data includes but is not limited to: daily power generation of the photovoltaic strings and meteorological numerical curves of the geographical locations of the photovoltaic strings.

[0063] Step S102: Performing a horizontal comparative analysis on the photovoltaic strings based on the historical operation data to obtain the horizontal deviation rate of the unit daily power generation of the photovoltaic strings.

[0064] In the specific implementation of step S102, a horizontal comparison analysis is performed on the photovoltaic strings in each photovoltaic power station based on the historical operation data, so as to calculate the horizontal deviation rate of the unit daily power generation of each photovoltaic string.

[0065] It should be noted that the scope of the horizontal comparative analysis is not limited to the PV strings in a certain PV power station, but a horizontal comparative analysis of the PV strings in each PV power station; when the PV strings in a PV power station are simultaneously abnormal due to dust accumulation problems, the abnormal PV strings can also be identified through horizontal comparative analysis.

[0066] Step S103: performing longitudinal comparative analysis on the photovoltaic strings based on historical operation data to obtain the longitudinal deviation rate of the unit daily power generation of the photovoltaic strings.

[0067] In the specific implementation of step S103, a longitudinal comparative analysis is performed on the photovoltaic strings based on historical operation data, so as to calculate the longitudinal deviation rate of the unit daily power generation of the photovoltaic strings.

[0068] Step S104: Identify abnormal photovoltaic strings, where the abnormal photovoltaic strings are photovoltaic strings whose lateral deviation rate of unit daily power generation is greater than the lateral deviation threshold and / or whose longitudinal deviation rate of unit daily power generation is greater than the longitudinal deviation threshold.

[0069] In the process of specifically implementing step S104, after calculating the lateral deviation rate of unit daily power generation and the longitudinal deviation rate of unit daily power generation of the photovoltaic strings, abnormal photovoltaic strings are identified from multiple photovoltaic strings based on the lateral deviation rate of unit daily power generation and the longitudinal deviation rate of unit daily power generation, wherein the abnormal photovoltaic strings are photovoltaic strings having a lateral deviation rate of unit daily power generation greater than a lateral deviation threshold and / or a longitudinal deviation rate of unit daily power generation greater than a longitudinal deviation threshold.

[0070] That is to say, a photovoltaic string with a larger lateral deviation rate of unit daily power generation and / or a larger longitudinal deviation rate of unit daily power generation is an abnormal photovoltaic string, that is, the higher the deviation rate, the greater the probability of failure of the photovoltaic string.

[0071] For example: for a certain photovoltaic string, if the horizontal deviation rate of the unit daily power generation of the photovoltaic string is greater than 15% (horizontal deviation threshold), and / or, if the vertical deviation rate of the unit daily power generation of the photovoltaic string is greater than 30% (vertical deviation threshold), then the photovoltaic string is identified as an abnormal photovoltaic string.

[0072] It is understandable that for the abnormal PV strings identified, these abnormal PV strings need to be repaired by operation and maintenance personnel, and the repair and maintenance will bring certain labor costs and travel costs. Therefore, the investment recovery period of the maintenance needs to be considered when formulating the maintenance plan.

[0073] In the embodiment of the present invention, after all abnormal photovoltaic strings are identified, a maintenance area is selected using a greedy algorithm with the goal of maximizing the number of abnormal photovoltaic strings within a fixed range; the total maintenance cost and total maintenance benefit of the abnormal photovoltaic strings in the maintenance area are calculated; if the total maintenance benefit is greater than or equal to the total maintenance cost, a maintenance plan including the maintenance area is output;

[0074] On the contrary, if the total maintenance benefit is less than the total maintenance cost, no maintenance plan will be output (i.e., no maintenance plan will be arranged).

[0075] Specifically, when calculating the total maintenance cost and total maintenance benefit, the travel cost of the operation and maintenance personnel within a fixed range is defined to remain unchanged, so the labor cost is proportional to the number of abnormal PV strings repaired. Therefore, the total maintenance cost of abnormal PV strings is: total maintenance cost = average travel cost + number of abnormal PV strings repaired * average maintenance cost.

[0076] like Figure 2 As shown in the example diagram of selecting the maintenance area using the greedy algorithm, it can be seen that the greedy algorithm is used to select the maintenance area with the goal of maximizing the number of abnormal PV strings to be repaired within a fixed range; then the profit after the abnormal PV strings are repaired is calculated (this profit is usually calculated over 3 years), the profit after the abnormal PV strings are repaired = (horizontal reference unit daily power generation - actual power generation) * photovoltaic power generation price * number of days; wherein, the actual power generation refers to the actual power generation after the abnormal PV strings are repaired; the calculation method of the horizontal reference unit daily power generation after the abnormal PV strings are repaired will be described in detail in the subsequent embodiment of "horizontal comparative analysis".

[0077] Total maintenance revenue = the sum of the revenue after repair of each abnormal PV string.

[0078] If the total maintenance benefit is greater than or equal to the total maintenance cost, a maintenance plan is arranged; otherwise, no maintenance plan is arranged.

[0079] In an embodiment of the present invention, a horizontal comparative analysis and a vertical comparative analysis are performed on photovoltaic strings to obtain a horizontal deviation rate of unit daily power generation and a vertical deviation rate of unit daily power generation of the photovoltaic strings; abnormal photovoltaic strings are identified based on the horizontal deviation rate of unit daily power generation and the vertical deviation rate of unit daily power generation, and the abnormal photovoltaic strings are analyzed from multiple aspects to improve the detection effect of abnormal photovoltaic strings.

[0080] For the above-mentioned embodiment of the present invention Figure 1 For the horizontal comparison analysis involved in step S102, see Figure 3 , shows a flow chart of the horizontal comparison analysis provided by an embodiment of the present invention, including the following steps:

[0081] Step S301: Calculate the unit daily power generation of the photovoltaic strings based on historical operation data.

[0082] In the specific implementation of step S301, based on the historical operation data, the unit daily power generation of each photovoltaic string in the target area is calculated by formula (1).

[0083] U i =E i / C i (1)

[0084] In formula (1), Ui is the unit daily power generation of photovoltaic string i, E i is the daily power generation of photovoltaic string i, C i is the installed capacity of PV string i.

[0085] Step S302: exclude some photovoltaic strings according to the unit daily power generation of the photovoltaic strings.

[0086] In the specific implementation of step S302 , the photovoltaic strings are sorted in descending order (from high to low) according to their unit daily power generation; and photovoltaic strings whose unit daily power generation is within a preset ranking range are excluded (or filtered).

[0087] It should be noted that after the PV strings are sorted according to the unit daily power generation, the PV strings whose unit daily power generation is within the preset ranking range may have faults, so it is necessary to exclude the PV strings whose unit daily power generation is within the preset ranking range, and then perform subsequent steps S303-S305 on the remaining PV strings (whose unit daily power generation is not within the preset ranking range), so that the calculation of the horizontal reference unit daily power generation can be more accurate.

[0088] For example: Each photovoltaic string is divided into units of daily power generation U i The PV strings ranked in the top 95% (95%-100%) and the bottom 15% (0-15%) are sorted from high to low, and the PV strings ranked in the top 95% (95%-100%) and the bottom 15% (0-15%) are excluded, where "95%-100%" and "0-15%" are the preset ranking ranges; and the remaining (or not excluded) PV strings are processed in subsequent steps S303-S305.

[0089] Step S303: Calculate the consistency of the meteorological value curves at the geographical locations of each of the remaining two photovoltaic strings.

[0090] In the specific implementation of step S303, after excluding some photovoltaic strings, for the remaining photovoltaic strings, the consistency of the meteorological numerical curves at the geographical locations of every two remaining photovoltaic strings is calculated, that is, the consistency of the meteorological numerical curves at the geographical locations of the two remaining photovoltaic strings is calculated.

[0091] For example: assuming that the remaining PV strings are PV string A, PV string B and PV string C, calculate the consistency of the meteorological numerical curves at the geographical locations of PV string A and PV string B, calculate the consistency of the meteorological numerical curves at the geographical locations of PV string A and PV string C, and calculate the consistency of the meteorological numerical curves at the geographical locations of PV string B and PV string C.

[0092] In some embodiments, the consistency of the meteorological value curves at the geographical locations of the two photovoltaic strings is calculated by formula (2).

[0093] (2)

[0094] In formula 2, k mn is the consistency of the meteorological value curves of the geographical locations of PV strings m and PV strings n, q m (t) is the meteorological value at the geographical location of the photovoltaic string m at time t, q n (t) is the meteorological value at the geographical location of PV string n at time t, and T is the number of daily time intervals.

[0095] Step S304: using the consistency of the meteorological numerical curve, calculate the horizontal reference unit daily power generation of the remaining photovoltaic strings.

[0096] In the specific implementation of step S304, after calculating the consistency of the meteorological value curves of the geographical locations of each of the remaining two photovoltaic strings, the horizontal reference unit daily power generation of the remaining photovoltaic strings is calculated using the consistency of the calculated meteorological value curves.

[0097] Specifically, the horizontal reference unit daily power generation of the remaining PV strings is calculated using formula (3).

[0098] (3)

[0099] In formula (3), H m is the horizontal reference unit daily power generation of photovoltaic string m, k mi is the consistency of the meteorological value curves of the geographical locations of PV string m and PV string i, U i is the unit daily power generation of PV string i, and N is the total number of remaining PV strings.

[0100] Step S305: Calculate the horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation.

[0101] In the process of specifically implementing step S305, after calculating the unit daily power generation of each remaining photovoltaic string and the horizontal reference unit daily power generation, the horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings is calculated based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation.

[0102] Specifically, the lateral deviation rate of unit daily power generation of the remaining PV strings is calculated using formula (4).

[0103] D m =|H m -E m | / E m (4)

[0104] In formula (4), D m is the horizontal deviation rate of unit daily power generation of the remaining PV strings m, H m is the horizontal reference unit daily power generation of the remaining PV string m, E m is the unit daily power generation of the remaining PV strings m.

[0105] For a certain remaining PV string, the greater the lateral deviation rate of the unit daily power generation of the PV string, the greater the probability of failure of the PV string; when the lateral deviation rate of the unit daily power generation of the PV string is greater than the lateral deviation threshold, the PV string can be identified as an abnormal PV string.

[0106] The above embodiments of the present invention Figure 3 It is a detailed description of horizontal comparative analysis.

[0107] For the above-mentioned embodiment of the present invention Figure 1 For the longitudinal comparative analysis involved in step S103, see Figure 4 , shows a flow chart of the longitudinal comparative analysis provided by an embodiment of the present invention, including the following steps:

[0108] Step S401: Calculate the actual daily unit power generation of the photovoltaic strings based on historical operation data.

[0109] In the specific implementation of step S401, for each photovoltaic string, the daily unit power generation of the photovoltaic string in the past Y days is calculated, so as to obtain the actual daily unit power generation U of the photovoltaic string. d , where d=1, 2,…Y.

[0110] For example: Calculate the daily unit power generation of PV string m in the past 180 days (Y=180), and thus obtain the actual daily unit power generation of PV string m.

[0111] Specifically, the actual daily unit power generation of the PV string is calculated using formula (5).

[0112] U d =E d / C (5)

[0113] In formula (5), U d is the actual daily unit power generation of the PV string on day d, E d is the power generation of the PV string on the dth day, and C is the installed capacity of the PV string.

[0114] Step S402: using the pre-trained photovoltaic prediction model, predict the theoretical daily unit power generation of the photovoltaic string in the past X days.

[0115] In the specific implementation of step S402, the photovoltaic prediction model obtained by pre-training is used to predict the daily unit power generation of the photovoltaic string in the past X days (equivalent to the theoretical daily power generation per unit), and the theoretical daily unit power generation of the photovoltaic string in the past X days is obtained. The predicted theoretical daily unit power generation of the photovoltaic string on the dth day is recorded as F d .

[0116] For example: Use the photovoltaic prediction model to predict the theoretical daily unit power generation of photovoltaic strings in the past 30 days (X=30).

[0117] It should be noted that the photovoltaic prediction model is trained in the following way: based on the daily unit power generation of photovoltaic strings and historical meteorological data, the photovoltaic prediction model is constructed and trained using artificial intelligence algorithms such as neural networks or decision trees, and then the photovoltaic prediction model is used to predict the theoretical daily unit power generation of photovoltaic strings in the past X days based on historical meteorological data.

[0118] For example: after calculating the actual daily unit power generation of PV strings in the past 180 days (Y=180), based on the actual daily unit power generation of PV strings in the past 180 days to the past 30 days (X=30) and historical meteorological data, a PV prediction model is constructed and trained using artificial intelligence algorithms such as neural networks or decision trees; based on historical meteorological data, the PV prediction model is used to predict the theoretical daily unit power generation of PV strings in the past 30 days.

[0119] Step S403: Calculate the sum of the actual daily unit power generation of the photovoltaic strings in the past X days to obtain the total actual unit power generation of the photovoltaic strings.

[0120] In the specific implementation of step S403, for each photovoltaic string, the actual daily unit power generation U of the photovoltaic string in the past X days is calculated. d The total actual unit power generation U of the PV string is obtained by adding the sum of d , where d=1, 2,…X.

[0121] For example: Calculate the sum of the actual daily unit power generation of the PV string in the past 30 days to obtain the total actual unit power generation of the PV string.

[0122] Step S404: Calculate the sum of the theoretical daily unit power generation of the photovoltaic strings in the past X days to obtain the total theoretical unit power generation of the photovoltaic strings.

[0123] In the specific implementation of step S404, for each photovoltaic string, the theoretical daily unit power generation F of the photovoltaic string in the past X days is calculated. dThe total theoretical unit power generation F of the photovoltaic string is obtained by summing up the total theoretical unit power generation F of the photovoltaic string, that is, F=∑F d , where d=1, 2,…X.

[0124] For example: calculate the sum of the theoretical daily unit power generation of the PV string in the past 30 days to obtain the total theoretical unit power generation of the PV string.

[0125] Step S405: Calculate the vertical deviation rate of the unit daily power generation of the photovoltaic strings by using the total actual unit power generation and the total theoretical unit power generation.

[0126] In the specific implementation of step S405, after the total actual unit power generation U and the total theoretical unit power generation F of the photovoltaic string are calculated, the unit daily power generation longitudinal deviation rate of the photovoltaic string is calculated by formula (6).

[0127] Z = |UF| / U (6)

[0128] In formula (6), Z is the longitudinal deviation rate of the unit daily power generation of the PV string in the past X days.

[0129] For a certain photovoltaic string, the greater the longitudinal deviation rate of the unit daily power generation of the photovoltaic string, the greater the probability of failure of the photovoltaic string; when the longitudinal deviation rate of the unit daily power generation of the photovoltaic string is greater than the longitudinal deviation threshold, the photovoltaic string can be identified as an abnormal photovoltaic string.

[0130] The above embodiments of the present invention Figure 4 It is a detailed description of longitudinal comparative analysis.

[0131] In combination with the above embodiments of the present invention Figures 1 to 4 content, from Figure 5 As shown in the schematic diagram of the principle architecture of an abnormal photovoltaic string detection method, the scheme is generally divided into three parts: photovoltaic horizontal comparison, photovoltaic vertical comparison and maintenance cost analysis;

[0132] For the photovoltaic horizontal comparison part, the power generation data of a photovoltaic string is compared horizontally with other photovoltaic strings to locate the abnormal photovoltaic string;

[0133] For the photovoltaic vertical comparison, the abnormal photovoltaic strings can be located by vertically comparing the historical power generation data;

[0134] For the maintenance cost analysis, we calculate and analyze whether the revenue from the maintenance of abnormal PV strings can cover the maintenance costs, and then determine whether to arrange a maintenance plan to carry out maintenance of the PV strings based on the calculation and analysis results.

[0135] Based on the description of the above embodiments, this solution has the following beneficial effects:

[0136] 1. Analyze whether there is any abnormality in the power generation of PV strings through horizontal comparison. The scope of horizontal comparison covers the PV strings of various PV power stations, and is no longer limited to a single PV power station, avoiding the situation that "a certain PV power station has batch abnormal problems and cannot be identified". In addition, excluding some PV strings can make the calculation of the horizontal reference unit daily power generation more accurate.

[0137] 2. Analyze whether there is any abnormality in the power generation of the PV strings through longitudinal comparison. The longitudinal comparison is for a single PV string, and the power generation trend of the single PV string is analyzed. The PV strings with abnormal power generation trend attenuation are identified as abnormal PV strings.

[0138] 3. Based on the return on investment of operation and maintenance, determine whether abnormal PV strings need maintenance, avoid the problem of excessively high operation and maintenance costs due to frequent maintenance, and avoid the problem of loss of PV power generation income due to long-term non-maintenance.

[0139] Corresponding to the abnormal photovoltaic string detection method provided in the above embodiment of the present invention, see Figure 6 , the embodiment of the present invention also provides a structural block diagram of an abnormal photovoltaic string detection system, the abnormal photovoltaic string detection system includes: an acquisition unit 100, a horizontal analysis unit 200, a vertical analysis unit 300 and an identification unit 400;

[0140] The acquisition unit 100 is used to acquire historical operation data of photovoltaic strings in a target area, where the target area includes a plurality of photovoltaic power stations.

[0141] The horizontal analysis unit 200 is used to perform horizontal comparative analysis on the photovoltaic strings based on historical operation data to obtain the horizontal deviation rate of the unit daily power generation of the photovoltaic strings.

[0142] The longitudinal analysis unit 300 is used to perform longitudinal comparative analysis on the photovoltaic strings based on historical operation data to obtain the longitudinal deviation rate of the unit daily power generation of the photovoltaic strings.

[0143] The identification unit 400 is used to identify abnormal photovoltaic strings, which are photovoltaic strings with a horizontal deviation rate of unit daily power generation greater than a horizontal deviation threshold and / or a vertical deviation rate of unit daily power generation greater than a vertical deviation threshold.

[0144] In an embodiment of the present invention, a horizontal comparative analysis and a vertical comparative analysis are performed on photovoltaic strings to obtain a horizontal deviation rate of unit daily power generation and a vertical deviation rate of unit daily power generation of the photovoltaic strings; abnormal photovoltaic strings are identified based on the horizontal deviation rate of unit daily power generation and the vertical deviation rate of unit daily power generation, and the abnormal photovoltaic strings are analyzed from multiple aspects to improve the detection effect of abnormal photovoltaic strings.

[0145] Preferably, combined Figure 6 As shown in the figure, the horizontal analysis unit 200 includes a first calculation module, an exclusion module, a second calculation module, a third calculation module and a fourth calculation module. The execution principle of each module is as follows:

[0146] The first calculation module is used to calculate the unit daily power generation of the photovoltaic string based on historical operation data.

[0147] The exclusion module is used to exclude some photovoltaic strings according to the unit daily power generation of the photovoltaic strings.

[0148] In a specific implementation, the exclusion module is specifically used to: sort the photovoltaic strings in descending order according to their unit daily power generation; and exclude photovoltaic strings whose unit daily power generation is within a preset ranking range.

[0149] The second calculation module is used to calculate the consistency of the meteorological value curves at the geographical locations of each of the remaining two photovoltaic strings.

[0150] The third calculation module is used to calculate the horizontal reference unit daily power generation of the remaining photovoltaic strings by utilizing the consistency of the meteorological numerical curve.

[0151] The fourth calculation module is used to calculate the horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation.

[0152] Preferably, combined Figure 6 As shown in the figure, the longitudinal analysis unit 300 includes a first calculation module, a prediction module, a second calculation module, a third calculation module and a fourth calculation module. The execution principle of each module is as follows:

[0153] The first calculation module is used to calculate the actual daily unit power generation of the photovoltaic string based on historical operation data.

[0154] A prediction module is used to predict the theoretical daily unit power generation of photovoltaic strings in the past X days using a pre-trained photovoltaic prediction model;

[0155] The second calculation module is used to calculate the sum of the actual daily unit power generation of the photovoltaic strings in the past X days to obtain the total actual unit power generation of the photovoltaic strings.

[0156] The third calculation module is used to calculate the sum of theoretical daily unit power generation of the photovoltaic strings in the past X days to obtain the total theoretical unit power generation of the photovoltaic strings.

[0157] The fourth calculation module is used to calculate the longitudinal deviation rate of the unit daily power generation of the photovoltaic strings by using the total actual unit power generation and the total theoretical unit power generation.

[0158] Preferably, combined Figure 6 The abnormal photovoltaic string detection system further includes:

[0159] The selection unit is used to select a maintenance area using a greedy algorithm with the goal of maximizing the number of abnormal photovoltaic strings within a fixed range.

[0160] The calculation unit is used to calculate the total maintenance cost and total maintenance benefit of abnormal photovoltaic strings in the maintenance area.

[0161] The output unit is used for outputting a maintenance plan that at least includes the maintenance area if the total maintenance benefit is greater than or equal to the total maintenance cost.

[0162] Preferably, an embodiment of the present invention further provides an electronic device, comprising: a processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; and the memory is used to store a program, wherein the program is used to implement the abnormal photovoltaic string detection method provided in the above method embodiment.

[0163] Preferably, an embodiment of the present invention further provides a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are used to execute the abnormal photovoltaic string detection method provided by the above method embodiment.

[0164] Preferably, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the abnormal photovoltaic string detection method provided in the above method embodiment.

[0165] In summary, the embodiments of the present invention provide a method, system, electronic device and storage medium for detecting abnormal photovoltaic strings, which perform horizontal comparative analysis and vertical comparative analysis on photovoltaic strings to obtain the horizontal deviation rate of unit daily power generation and the vertical deviation rate of unit daily power generation of the photovoltaic strings; abnormal photovoltaic strings are identified according to the horizontal deviation rate of unit daily power generation and the vertical deviation rate of unit daily power generation, and abnormal photovoltaic strings are analyzed from multiple aspects to improve the detection effect of abnormal photovoltaic strings.

[0166] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0167] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0168] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting abnormal photovoltaic strings, characterized in that: The method comprises: Acquire historical operation data of photovoltaic strings in a target area, where the target area includes multiple photovoltaic power stations; Performing a horizontal comparative analysis on the photovoltaic strings based on the historical operation data to obtain a horizontal deviation rate of unit daily power generation of the photovoltaic strings; Based on the historical operation data, a longitudinal comparative analysis is performed on the photovoltaic strings to obtain a longitudinal deviation rate of unit daily power generation of the photovoltaic strings; An abnormal photovoltaic string is identified, where the abnormal photovoltaic string is a photovoltaic string whose lateral deviation rate of the unit daily power generation is greater than a lateral deviation threshold and / or whose longitudinal deviation rate of the unit daily power generation is greater than a longitudinal deviation threshold.

2. The method according to claim 1, characterized in that A horizontal comparative analysis is performed on the photovoltaic strings based on the historical operation data to obtain a horizontal deviation rate of unit daily power generation of the photovoltaic strings, including: Based on the historical operation data, calculating the unit daily power generation of the photovoltaic string; According to the unit daily power generation of the photovoltaic strings, some of the photovoltaic strings are excluded; Calculating the consistency of the meteorological value curves at the remaining geographical locations of each of the two photovoltaic strings; Utilizing the consistency of the meteorological numerical curve, calculating the horizontal reference unit daily power generation of the remaining photovoltaic strings; Based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation, a horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings is calculated.

3. The method according to claim 2, characterized in that According to the unit daily power generation of the photovoltaic strings, some of the photovoltaic strings are excluded, including: According to the unit daily power generation of the photovoltaic strings, the photovoltaic strings are sorted in descending order; The photovoltaic strings whose unit daily power generation is within a preset ranking range are excluded.

4. The method according to claim 1, characterized in that Based on the historical operation data, a longitudinal comparative analysis is performed on the photovoltaic strings to obtain a longitudinal deviation rate of unit daily power generation of the photovoltaic strings, including: Based on the historical operation data, calculating the actual daily unit power generation of the photovoltaic string; Using the pre-trained photovoltaic prediction model, predict the theoretical daily unit power generation of the photovoltaic string in the past X days; Calculate the sum of the actual daily unit power generation of the photovoltaic string in the past X days to obtain the total actual unit power generation of the photovoltaic string; Calculate the sum of the theoretical daily unit power generation of the photovoltaic string in the past X days to obtain the total theoretical unit power generation of the photovoltaic string; The total actual unit power generation and the total theoretical unit power generation are used to calculate the unit daily power generation longitudinal deviation rate of the photovoltaic string.

5. The method according to any one of claims 1 to 4, characterized in that: After identifying abnormal PV strings, the following also applies: With the goal of maximizing the number of abnormal photovoltaic strings within a fixed range, a greedy algorithm is used to select a maintenance area; Calculate the total maintenance cost and total maintenance benefit of abnormal photovoltaic strings in the maintenance area; If the total maintenance benefit is greater than or equal to the total maintenance cost, a maintenance plan at least including the maintenance area is output.

6. An abnormal photovoltaic string detection system, characterized in that: The system comprises: An acquisition unit, configured to acquire historical operation data of photovoltaic strings in a target area, wherein the target area includes a plurality of photovoltaic power stations; A horizontal analysis unit, used for performing a horizontal comparative analysis on the photovoltaic strings based on the historical operation data to obtain a horizontal deviation rate of unit daily power generation of the photovoltaic strings; A longitudinal analysis unit, configured to perform longitudinal comparative analysis on the photovoltaic strings based on the historical operation data to obtain a longitudinal deviation rate of unit daily power generation of the photovoltaic strings; The identification unit is used to identify abnormal photovoltaic strings, wherein the abnormal photovoltaic strings are photovoltaic strings whose lateral deviation rate of unit daily power generation is greater than a lateral deviation threshold and / or whose longitudinal deviation rate of unit daily power generation is greater than a longitudinal deviation threshold.

7. The system according to claim 6, characterized in that The horizontal analysis unit comprises: A first calculation module, configured to calculate the unit daily power generation of the photovoltaic string based on the historical operation data; An exclusion module, used for excluding part of the photovoltaic strings according to the unit daily power generation of the photovoltaic strings; A second calculation module is used to calculate the consistency of the meteorological value curves at the remaining geographical locations of each two photovoltaic strings; A third calculation module is used to calculate the horizontal reference unit daily power generation of the remaining photovoltaic strings by using the consistency of the meteorological numerical curve; The fourth calculation module is used to calculate the horizontal deviation rate of the unit daily power generation of the remaining photovoltaic strings based on the unit daily power generation of the remaining photovoltaic strings and the horizontal reference unit daily power generation.

8. The system according to claim 7, characterized in that The exclusion module is specifically used to: sort the photovoltaic strings in descending order according to the unit daily power generation of the photovoltaic strings; and exclude the photovoltaic strings whose unit daily power generation is within a preset ranking range.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; The memory is used to store a program, and the program is used to implement the abnormal photovoltaic string detection method as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the abnormal photovoltaic string detection method according to any one of claims 1 to 5.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the abnormal photovoltaic string detection method as described in any one of claims 1 to 5 is implemented.

Images